Merge pull request #7307 from open-webui/dev

0.4.5

.dockerignore

@@ -16,4 +16,5 @@ _old
 uploads
 .ipynb_checkpoints
 **/*.db
-_test
+_test
+backend/data/*

.github/ISSUE_TEMPLATE/bug_report.md

@@ -8,9 +8,19 @@ assignees: ''
 
 # Bug Report
 
-**Important: Before submitting a bug report, please check whether a similar issue or feature request has already been posted in the Issues or Discussions section. It's likely we're already tracking it. In case of uncertainty, initiate a discussion post first. This helps us all to efficiently focus on improving the project.**
+## Important Notes
 
-**Let's collaborate respectfully. If you bring negativity, please understand our capacity to engage may be limited. If you're open to learning and communicating constructively, we're more than happy to assist you. Remember, Open WebUI is a volunteer-driven project maintained by a single maintainer, supported by our amazing contributors who also manage full-time jobs. We respect your time; please respect ours. If you have an issue, We highly encourage you to submit a pull request or to fork the project. We actively work to prevent contributor burnout to preserve the quality and continuity of Open WebUI.**
+- **Before submitting a bug report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.
+
+- **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.
+
+- **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
+
+- **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
+
+Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!
+
+---
 
 ## Installation Method
 

.github/ISSUE_TEMPLATE/feature_request.md

@@ -8,9 +8,19 @@ assignees: ''
 
 # Feature Request
 
-**Important: Before submitting a feature request, please check whether a similar issue or feature request has already been posted in the Issues or Discussions section. It's likely we're already tracking it. In case of uncertainty, initiate a discussion post first. This helps us all to efficiently focus on improving the project.**
+## Important Notes
 
-**Let's collaborate respectfully. If you bring negativity, please understand our capacity to engage may be limited. If you're open to learning and communicating constructively, we're more than happy to assist you. Remember, Open WebUI is a volunteer-driven project maintained by a single maintainer, supported by our amazing contributors who also manage full-time jobs. We respect your time; please respect ours. If you have an issue, We highly encourage you to submit a pull request or to fork the project. We actively work to prevent contributor burnout to preserve the quality and continuity of Open WebUI.**
+- **Before submitting a report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.
+
+- **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.
+
+- **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
+
+- **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
+
+Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!
+
+---
 
 **Is your feature request related to a problem? Please describe.**
 A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

.github/workflows/deploy-to-hf-spaces.yml

@@ -28,6 +28,8 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
+        with:
+          lfs: true
 
       - name: Remove git history
         run: rm -rf .git
@@ -52,7 +54,9 @@ jobs:
       - name: Set up Git and push to Space
         run: |
           git init --initial-branch=main
+          git lfs install
           git lfs track "*.ttf"
+          git lfs track "*.jpg"
           rm demo.gif
           git add .
           git commit -m "GitHub deploy: ${{ github.sha }}"

CHANGELOG.md

@@ -5,6 +5,191 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.5] - 2024-11-26
+
+### Added
+
+- **🎨 Model Order/Defaults Reintroduced**: Brought back the ability to set model order and default models, now configurable via Admin Settings > Models > Configure (Gear Icon).
+
+### Fixed
+
+- **🔍 Query Generation Issue**: Resolved an error in web search query generation, enhancing search accuracy and ensuring smoother search workflows.
+- **📏 Textarea Auto Height Bug**: Fixed a layout issue where textarea input height was shifting unpredictably, particularly when editing system prompts.
+- **🔑 Ollama Authentication**: Corrected an issue with Ollama’s authorization headers, guaranteeing reliable authentication across all endpoints.
+- **⚙️ Missing Min_P Save**: Resolved an issue where the 'min_p' parameter was not being saved in configurations.
+- **🛠️ Tools Description**: Fixed a key issue that omitted tool descriptions in tools payload.
+
+## [0.4.4] - 2024-11-22
+
+### Added
+
+- **🌐 Translation Updates**: Refreshed Catalan, Brazilian Portuguese, German, and Ukrainian translations, further enhancing the platform's accessibility and improving the experience for international users.
+
+### Fixed
+
+- **📱 Mobile Controls Visibility**: Resolved an issue where the controls button was not displaying on the new chats page for mobile users, ensuring smoother navigation and functionality on smaller screens.
+- **📷 LDAP Profile Image Issue**: Fixed an LDAP integration bug related to profile images, ensuring seamless authentication and a reliable login experience for users.
+- **⏳ RAG Query Generation Issue**: Addressed a significant problem where RAG query generation occurred unnecessarily without attached files, drastically improving speed and reducing delays during chat completions.
+
+### Changed
+
+- **⚙️ Legacy Event Emitter Support**: Reintroduced compatibility with legacy "citation" types for event emitters in tools and functions, providing smoother workflows and broader tool support for users.
+
+## [0.4.3] - 2024-11-21
+
+### Added
+
+- **📚 Inline Citations for RAG Results**: Get seamless inline citations for Retrieval-Augmented Generation (RAG) responses using the default RAG prompt. Note: This feature only supports newly uploaded files, improving traceability and providing source clarity.
+- **🎨 Better Rich Text Input Support**: Enjoy smoother and more reliable rich text formatting for chats, enhancing communication quality.
+- **⚡ Faster Model Retrieval**: Implemented caching optimizations for faster model loading, providing a noticeable speed boost across workflows. Further improvements are on the way!
+
+### Fixed
+
+- **🔗 Pipelines Feature Restored**: Resolved a critical issue that previously prevented Pipelines from functioning, ensuring seamless workflows.
+- **✏️ Missing Suffix Field in Ollama Form**: Added the missing "suffix" field to the Ollama generate form, enhancing customization options.
+
+### Changed
+
+- **🗂️ Renamed "Citations" to "Sources"**: Improved clarity and consistency by renaming the "citations" field to "sources" in messages.
+
+## [0.4.2] - 2024-11-20
+
+### Fixed
+
+- **📁 Knowledge Files Visibility Issue**: Resolved the bug preventing individual files in knowledge collections from displaying when referenced with '#'.
+- **🔗 OpenAI Endpoint Prefix**: Fixed the issue where certain OpenAI connections that deviate from the official API spec weren’t working correctly with prefixes.
+- **⚔️ Arena Model Access Control**: Corrected an issue where arena model access control settings were not being saved.
+- **🔧 Usage Capability Selector**: Fixed the broken usage capabilities selector in the model editor.
+
+## [0.4.1] - 2024-11-19
+
+### Added
+
+- **📊 Enhanced Feedback System**: Introduced a detailed 1-10 rating scale for feedback alongside thumbs up/down, preparing for more precise model fine-tuning and improving feedback quality.
+- **ℹ️ Tool Descriptions on Hover**: Easily access tool descriptions by hovering over the message input, providing a smoother workflow with more context when utilizing tools.
+
+### Fixed
+
+- **🗑️ Graceful Handling of Deleted Users**: Resolved an issue where deleted users caused workspace items (models, knowledge, prompts, tools) to fail, ensuring reliable workspace loading.
+- **🔑 API Key Creation**: Fixed an issue preventing users from creating new API keys, restoring secure and seamless API management.
+- **🔗 HTTPS Proxy Fix**: Corrected HTTPS proxy issues affecting the '/api/v1/models/' endpoint, ensuring smoother, uninterrupted model management.
+
+## [0.4.0] - 2024-11-19
+
+### Added
+
+- **👥 User Groups**: You can now create and manage user groups, making user organization seamless.
+- **🔐 Group-Based Access Control**: Set granular access to models, knowledge, prompts, and tools based on user groups, allowing for more controlled and secure environments.
+- **🛠️ Group-Based User Permissions**: Easily manage workspace permissions. Grant users the ability to upload files, delete, edit, or create temporary chats, as well as define their ability to create models, knowledge, prompts, and tools.
+- **🔑 LDAP Support**: Newly introduced LDAP authentication adds robust security and scalability to user management.
+- **🌐 Enhanced OpenAI-Compatible Connections**: Added prefix ID support to avoid model ID clashes, with explicit model ID support for APIs lacking '/models' endpoint support, ensuring smooth operation with custom setups.
+- **🔐 Ollama API Key Support**: Now manage credentials for Ollama when set behind proxies, including the option to utilize prefix ID for proper distinction across multiple Ollama instances.
+- **🔄 Connection Enable/Disable Toggle**: Easily enable or disable individual OpenAI and Ollama connections as needed.
+- **🎨 Redesigned Model Workspace**: Freshly redesigned to improve usability for managing models across users and groups.
+- **🎨 Redesigned Prompt Workspace**: A fresh UI to conveniently organize and manage prompts.
+- **🧩 Sorted Functions Workspace**: Functions are now automatically categorized by type (Action, Filter, Pipe), streamlining management.
+- **💻 Redesigned Collaborative Workspace**: Enhanced support for multiple users contributing to models, knowledge, prompts, or tools, improving collaboration.
+- **🔧 Auto-Selected Tools in Model Editor**: Tools enabled through the model editor are now automatically selected, whereas previously it only gave users the option to enable the tool, reducing manual steps and enhancing efficiency.
+- **🔔 Web Search & Tools Indicator**: A clear indication now shows when web search or tools are active, reducing confusion.
+- **🔑 Toggle API Key Auth**: Tighten security by easily enabling or disabling API key authentication option for Open WebUI.
+- **🗂️ Agentic Retrieval**: Improve RAG accuracy via smart pre-processing of chat history to determine the best queries before retrieval.
+- **📁 Large Text as File Option**: Optionally convert large pasted text into a file upload, keeping the chat interface cleaner.
+- **🗂️ Toggle Citations for Models**: Ability to disable citations has been introduced in the model editor.
+- **🔍 User Settings Search**: Quickly search for settings fields, improving ease of use and navigation.
+- **🗣️ Experimental SpeechT5 TTS**: Local SpeechT5 support added for improved text-to-speech capabilities.
+- **🔄 Unified Reset for Models**: A one-click option has been introduced to reset and remove all models from the Admin Settings.
+- **🛠️ Initial Setup Wizard**: The setup process now explicitly informs users that they are creating an admin account during the first-time setup, ensuring clarity. Previously, users encountered the login page right away without this distinction.
+- **🌐 Enhanced Translations**: Several language translations, including Ukrainian, Norwegian, and Brazilian Portuguese, were refined for better localization.
+
+### Fixed
+
+- **🎥 YouTube Video Attachments**: Fixed issues preventing proper loading and attachment of YouTube videos as files.
+- **🔄 Shared Chat Update**: Corrected issues where shared chats were not updating, improving collaboration consistency.
+- **🔍 DuckDuckGo Rate Limit Fix**: Addressed issues with DuckDuckGo search integration, enhancing search stability and performance when operating within rate limits.
+- **🧾 Citations Relevance Fix**: Adjusted the relevance percentage calculation for citations, so that Open WebUI properly reflect the accuracy of a retrieved document in RAG, ensuring users get clearer insights into sources.
+- **🔑 Jina Search API Key Requirement**: Added the option to input an API key for Jina Search, ensuring smooth functionality as keys are now mandatory.
+
+### Changed
+
+- **🛠️ Functions Moved to Admin Panel**: As Functions operate as advanced plugins, they are now accessible from the Admin Panel instead of the workspace.
+- **🛠️ Manage Ollama Connections**: The "Models" section in Admin Settings has been relocated to Admin Settings > "Connections" > Ollama Connections. You can now manage Ollama instances via a dedicated "Manage Ollama" modal from "Connections", streamlining the setup and configuration of Ollama models.
+- **📊 Base Models in Admin Settings**: Admins can now find all base models, both connections or functions, in the "Models" Admin setting. Global model accessibility can be enabled or disabled here. Models are private by default, requiring explicit permission assignment for user access.
+- **📌 Sticky Model Selection for New Chats**: The model chosen from a previous chat now persists when creating a new chat. If you click "New Chat" again from the new chat page, it will revert to your default model.
+- **🎨 Design Refactoring**: Overall design refinements across the platform have been made, providing a more cohesive and polished user experience.
+
+### Removed
+
+- **📂 Model List Reordering**: Temporarily removed and will be reintroduced in upcoming user group settings improvements.
+- **⚙️ Default Model Setting**: Removed the ability to set a default model for users, will be reintroduced with user group settings in the future.
+
+## [0.3.35] - 2024-10-26
+
+### Added
+
+- **🌐 Translation Update**: Added translation labels in the SearchInput and CreateCollection components and updated Brazilian Portuguese translation (pt-BR)
+- **📁 Robust File Handling**: Enhanced file input handling for chat. If the content extraction fails or is empty, users will now receive a clear warning, preventing silent failures and ensuring you always know what's happening with your uploads.
+- **🌍 New Language Support**: Introduced Hungarian translations and updated French translations, expanding the platform's language accessibility for a more global user base.
+
+### Fixed
+
+- **📚 Knowledge Base Loading Issue**: Resolved a critical bug where the Knowledge Base was not loading, ensuring smooth access to your stored documents and improving information retrieval in RAG-enhanced workflows.
+- **🛠️ Tool Parameters Issue**: Fixed an error where tools were not functioning correctly when required parameters were missing, ensuring reliable tool performance and more efficient task completions.
+- **🔗 Merged Response Loss in Multi-Model Chats**: Addressed an issue where responses in multi-model chat workflows were being deleted after follow-up queries, improving consistency and ensuring smoother interactions across models.
+
+## [0.3.34] - 2024-10-26
+
+### Added
+
+- **🔧 Feedback Export Enhancements**: Feedback history data can now be exported to JSON, allowing for seamless integration in RLHF processing and further analysis.
+- **🗂️ Embedding Model Lazy Loading**: Search functionality for leaderboard reranking is now more efficient, as embedding models are lazy-loaded only when needed, optimizing performance.
+- **🎨 Rich Text Input Toggle**: Users can now switch back to legacy textarea input for chat if they prefer simpler text input, though rich text is still the default until deprecation.
+- **🛠️ Improved Tool Calling Mechanism**: Enhanced method for parsing and calling tools, improving the reliability and robustness of tool function calls.
+- **🌐 Globalization Enhancements**: Updates to internationalization (i18n) support, further refining multi-language compatibility and accuracy.
+
+### Fixed
+
+- **🖥️ Folder Rename Fix for Firefox**: Addressed a persistent issue where users could not rename folders by pressing enter in Firefox, now ensuring seamless folder management across browsers.
+- **🔠 Tiktoken Model Text Splitter Issue**: Resolved an issue where the tiktoken text splitter wasn’t working in Docker installations, restoring full functionality for tokenized text editing.
+- **💼 S3 File Upload Issue**: Fixed a problem affecting S3 file uploads, ensuring smooth operations for those who store files on cloud storage.
+- **🔒 Strict-Transport-Security Crash**: Resolved a crash when setting the Strict-Transport-Security (HSTS) header, improving stability and security enhancements.
+- **🚫 OIDC Boolean Access Fix**: Addressed an issue with boolean values not being accessed correctly during OIDC logins, ensuring login reliability.
+- **⚙️ Rich Text Paste Behavior**: Refined paste behavior in rich text input to make it smoother and more intuitive when pasting various content types.
+- **🔨 Model Exclusion for Arena Fix**: Corrected the filter function that was not properly excluding models from the arena, improving model management.
+- **🏷️ "Tags Generation Prompt" Fix**: Addressed an issue preventing custom "tags generation prompts" from registering properly, ensuring custom prompt work seamlessly.
+
+## [0.3.33] - 2024-10-24
+
+### Added
+
+- **🏆 Evaluation Leaderboard**: Easily track your performance through a new leaderboard system where your ratings contribute to a real-time ranking based on the Elo system. Sibling responses (regenerations, many model chats) are required for your ratings to count in the leaderboard. Additionally, you can opt-in to share your feedback history and be part of the community-wide leaderboard. Expect further improvements as we refine the algorithm—help us build the best community leaderboard!
+- **⚔️ Arena Model Evaluation**: Enable blind A/B testing of models directly from Admin Settings > Evaluation for a true side-by-side comparison. Ideal for pinpointing the best model for your needs.
+- **🎯 Topic-Based Leaderboard**: Discover more accurate rankings with experimental topic-based reranking, which adjusts leaderboard standings based on tag similarity in feedback. Get more relevant insights based on specific topics!
+- **📁 Folders Support for Chats**: Organize your chats better by grouping them into folders. Drag and drop chats between folders and export them seamlessly for easy sharing or analysis.
+- **📤 Easy Chat Import via Drag & Drop**: Save time by simply dragging and dropping chat exports (JSON) directly onto the sidebar to import them into your workspace—streamlined, efficient, and intuitive!
+- **📚 Enhanced Knowledge Collection**: Now, you can reference individual files from a knowledge collection—ideal for more precise Retrieval-Augmented Generations (RAG) queries and document analysis.
+- **🏷️ Enhanced Tagging System**: Tags now take up less space! Utilize the new 'tag:' query system to manage, search, and organize your conversations more effectively without cluttering the interface.
+- **🧠 Auto-Tagging for Chats**: Your conversations are now automatically tagged for improved organization, mirroring the efficiency of auto-generated titles.
+- **🔍 Backend Chat Query System**: Chat filtering has become more efficient, now handled through the backend\*\* instead of your browser, improving search performance and accuracy.
+- **🎮 Revamped Playground**: Experience a refreshed and optimized Playground for smoother testing, tweaks, and experimentation of your models and tools.
+- **🧩 Token-Based Text Splitter**: Introducing token-based text splitting (tiktoken), giving you more precise control over how text is processed. Previously, only character-based splitting was available.
+- **🔢 Ollama Batch Embeddings**: Leverage new batch embedding support for improved efficiency and performance with Ollama embedding models.
+- **🔍 Enhanced Add Text Content Modal**: Enjoy a cleaner, more intuitive workflow for adding and curating knowledge content with an upgraded input modal from our Knowledge workspace.
+- **🖋️ Rich Text Input for Chats**: Make your chat inputs more dynamic with support for rich text formatting. Your conversations just got a lot more polished and professional.
+- **⚡ Faster Whisper Model Configurability**: Customize your local faster whisper model directly from the WebUI.
+- **☁️ Experimental S3 Support**: Enable stateless WebUI instances with S3 support, greatly enhancing scalability and balancing heavy workloads.
+- **🔕 Disable Update Toast**: Now you can streamline your workspace even further—choose to disable update notifications for a more focused experience.
+- **🌟 RAG Citation Relevance Percentage**: Easily assess citation accuracy with the addition of relevance percentages in RAG results.
+- **⚙️ Mermaid Copy Button**: Mermaid diagrams now come with a handy copy button, simplifying the extraction and use of diagram contents directly in your workflow.
+- **🎨 UI Redesign**: Major interface redesign that will make navigation smoother, keep your focus where it matters, and ensure a modern look.
+
+### Fixed
+
+- **🎙️ Voice Note Mic Stopping Issue**: Fixed the issue where the microphone stayed active after ending a voice note recording, ensuring your audio workflow runs smoothly.
+
+### Removed
+
+- **👋 Goodbye Sidebar Tags**: Sidebar tag clutter is gone. We’ve shifted tag buttons to more effective query-based tag filtering for a sleeker, more agile interface.
+
 ## [0.3.32] - 2024-10-06
 
 ### Added

CODE_OF_CONDUCT.md

@@ -2,76 +2,98 @@
 
 ## Our Pledge
 
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
+As members, contributors, and leaders of this community, we pledge to make participation in our open-source project a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
 
-We pledge to act and interact in ways that contribute to an open, welcoming, diverse, inclusive, and healthy community.
+We are committed to creating and maintaining an open, respectful, and professional environment where positive contributions and meaningful discussions can flourish. By participating in this project, you agree to uphold these values and align your behavior to the standards outlined in this Code of Conduct.
+
+## Why These Standards Are Important
+
+Open-source projects rely on a community of volunteers dedicating their time, expertise, and effort toward a shared goal. These projects are inherently collaborative but also fragile, as the success of the project depends on the goodwill, energy, and productivity of those involved.
+
+Maintaining a positive and respectful environment is essential to safeguarding the integrity of this project and protecting contributors' efforts. Behavior that disrupts this atmosphere—whether through hostility, entitlement, or unprofessional conduct—can severely harm the morale and productivity of the community. **Strict enforcement of these standards ensures a safe and supportive space for meaningful collaboration.**
+
+This is a community where **respect and professionalism are mandatory.** Violations of these standards will result in **zero tolerance** and immediate enforcement to prevent disruption and ensure the well-being of all participants.
 
 ## Our Standards
 
-Examples of behavior that contribute to a positive environment for our community include:
+Examples of behavior that contribute to a positive and professional community include:
 
-- Demonstrating empathy and kindness toward other people
-- Being respectful of differing opinions, viewpoints, and experiences
-- Giving and gracefully accepting constructive feedback
-- Accepting responsibility and apologizing to those affected by our mistakes, and learning from the experience
-- Focusing on what is best not just for us as individuals, but for the overall community
+- **Respecting others.** Be considerate, listen actively, and engage with empathy toward others' viewpoints and experiences.
+- **Constructive feedback.** Provide actionable, thoughtful, and respectful feedback that helps improve the project and encourages collaboration. Avoid unproductive negativity or hypercriticism.
+- **Recognizing volunteer contributions.** Appreciate that contributors dedicate their free time and resources selflessly. Approach them with gratitude and patience.
+- **Focusing on shared goals.** Collaborate in ways that prioritize the health, success, and sustainability of the community over individual agendas.
 
 Examples of unacceptable behavior include:
 
-- The use of sexualized language or imagery, and sexual attention or advances of any kind
-- Trolling, insulting or derogatory comments, and personal or political attacks
-- Public or private harassment
-- Publishing others' private information, such as a physical or email address, without their explicit permission
-- **Spamming of any kind**
-- Aggressive sales tactics targeting our community members are strictly prohibited. You can mention your product if it's relevant to the discussion, but under no circumstances should you push it forcefully
-- Other conduct which could reasonably be considered inappropriate in a professional setting
+- The use of discriminatory, demeaning, or sexualized language or behavior.
+- Personal attacks, derogatory comments, trolling, or inflammatory political or ideological arguments.
+- Harassment, intimidation, or any behavior intended to create a hostile, uncomfortable, or unsafe environment.
+- Publishing others' private information (e.g., physical or email addresses) without explicit permission.
+- **Entitlement, demand, or aggression toward contributors.** Volunteers are under no obligation to provide immediate or personalized support. Rude or dismissive behavior will not be tolerated.
+- **Unproductive or destructive behavior.** This includes venting frustration as hostility ("tantrums"), hypercriticism, attention-seeking negativity, or anything that distracts from the project's goals.
+- **Spamming and promotional exploitation.** Sharing irrelevant product promotions or self-promotion in the community is not allowed unless it directly contributes value to the discussion.
+
+### Feedback and Community Engagement
+
+- **Constructive feedback is encouraged, but hostile or entitled behavior will result in immediate action.** If you disagree with elements of the project, we encourage you to offer meaningful improvements or fork the project if necessary. Healthy discussions and technical disagreements are welcome only when handled with professionalism.
+- **Respect contributors' time and efforts.** No one is entitled to personalized or on-demand assistance. This is a community built on collaboration and shared effort; demanding or demeaning behavior undermines that trust and will not be allowed.
+
+### Zero Tolerance: No Warnings, Immediate Action
+
+This community operates under a **zero-tolerance policy.** Any behavior deemed unacceptable under this Code of Conduct will result in **immediate enforcement, without prior warning.**
+
+We employ this approach to ensure that unproductive or disruptive behavior does not escalate further or cause unnecessary harm to other contributors. The standards are clear, and violations of any kind—whether mild or severe—will be addressed decisively to protect the community.
 
 ## Enforcement Responsibilities
 
-Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
+Community leaders are responsible for upholding and enforcing these standards. They are empowered to take **immediate and appropriate action** to address any behaviors they deem unacceptable under this Code of Conduct. These actions are taken with the goal of protecting the community and preserving its safe, positive, and productive environment.
 
 ## Scope
 
-This Code of Conduct applies within all community spaces and also applies when an individual is officially representing the community in public spaces. Examples of representing our community include using an official e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event.
+This Code of Conduct applies to all community spaces, including forums, repositories, social media accounts, and in-person events. It also applies when an individual represents the community in public settings, such as conferences or official communications.
 
-## Enforcement
+Additionally, any behavior outside of these defined spaces that negatively impacts the community or its members may fall within the scope of this Code of Conduct.
 
-Instances of abusive, harassing, spamming, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at hello@openwebui.com. All complaints will be reviewed and investigated promptly and fairly.
+## Reporting Violations
 
-All community leaders are obligated to respect the privacy and security of the reporter of any incident.
+Instances of unacceptable behavior can be reported to the leadership team at **hello@openwebui.com**. Reports will be handled promptly, confidentially, and with consideration for the safety and well-being of the reporter.
+
+All community leaders are required to uphold confidentiality and impartiality when addressing reports of violations.
 
 ## Enforcement Guidelines
 
-Community leaders will follow these Community Impact Guidelines in determining the consequences for any action they deem in violation of this Code of Conduct:
+### Ban
 
-### 1. Temporary Ban
+**Community Impact**: Community leaders will issue a ban to any participant whose behavior is deemed unacceptable according to this Code of Conduct. Bans are enforced immediately and without prior notice.
 
-**Community Impact**: Any violation of community standards, including but not limited to inappropriate language, unprofessional behavior, harassment, or spamming.
+A ban may be temporary or permanent, depending on the severity of the violation. This includes—but is not limited to—behavior such as:
 
-**Consequence**: A temporary ban from any sort of interaction or public communication with the community for a specified period of time. No public or private interaction with the people involved, including unsolicited interaction with those enforcing the Code of Conduct, is allowed during this period. Violating these terms may lead to a permanent ban.
+- Harassment or abusive behavior toward contributors.
+- Persistent negativity or hostility that disrupts the collaborative environment.
+- Disrespectful, demanding, or aggressive interactions with others.
+- Attempts to cause harm or sabotage the community.
 
-### 2. Permanent Ban
+**Consequence**: A banned individual is immediately removed from access to all community spaces, communication channels, and events. Community leaders reserve the right to enforce either a time-limited suspension or a permanent ban based on the specific circumstances of the violation.
 
-**Community Impact**: Repeated or severe violations of community standards, including sustained inappropriate behavior, harassment of an individual, or aggression toward or disparagement of classes of individuals.
+This approach ensures that disruptive behaviors are addressed swiftly and decisively in order to maintain the integrity and productivity of the community.
 
-**Consequence**: A permanent ban from any sort of public interaction within the community.
+## Why Zero Tolerance Is Necessary
+
+Open-source projects thrive on collaboration, goodwill, and mutual respect. Toxic behaviors—such as entitlement, hostility, or persistent negativity—threaten not just individual contributors but the health of the project as a whole. Allowing such behaviors to persist robs contributors of their time, energy, and enthusiasm for the work they do.
+
+By enforcing a zero-tolerance policy, we ensure that the community remains a safe, welcoming space for all participants. These measures are not about harshness—they are about protecting contributors and fostering a productive environment where innovation can thrive.
+
+Our expectations are clear, and our enforcement reflects our commitment to this project's long-term success.
 
 ## Attribution
 
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 2.0, available at  
 https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
 
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
+Community Impact Guidelines were inspired by [Mozilla's code of conduct enforcement ladder](https://github.com/mozilla/diversity).
 
 [homepage]: https://www.contributor-covenant.org
 
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
+For answers to common questions about this code of conduct, see the FAQ at  
+https://www.contributor-covenant.org/faq. Translations are available at  
 https://www.contributor-covenant.org/translations.

Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1
 # Initialize device type args
-# use build args in the docker build commmand with --build-arg="BUILDARG=true"
+# use build args in the docker build command with --build-arg="BUILDARG=true"
 ARG USE_CUDA=false
 ARG USE_OLLAMA=false
 # Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
@@ -11,6 +11,10 @@ ARG USE_CUDA_VER=cu121
 # IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
 ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
 ARG USE_RERANKING_MODEL=""
+
+# Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
+ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
+
 ARG BUILD_HASH=dev-build
 # Override at your own risk - non-root configurations are untested
 ARG UID=0
@@ -72,6 +76,10 @@ ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
     RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
     SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
 
+## Tiktoken model settings ##
+ENV TIKTOKEN_ENCODING_NAME="cl100k_base" \
+    TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken"
+
 ## Hugging Face download cache ##
 ENV HF_HOME="/app/backend/data/cache/embedding/models"
 
@@ -131,11 +139,13 @@ RUN pip3 install uv && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     else \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     fi; \
     chown -R $UID:$GID /app/backend/data/
 

README.md

@@ -21,7 +21,7 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 🤝 **Ollama/OpenAI API Integration**: Effortlessly integrate OpenAI-compatible APIs for versatile conversations alongside Ollama models. Customize the OpenAI API URL to link with **LMStudio, GroqCloud, Mistral, OpenRouter, and more**.
 
-- 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
+- 🛡️ **Granular Permissions and User Groups**: By allowing administrators to create detailed user roles and permissions, we ensure a secure user environment. This granularity not only enhances security but also allows for customized user experiences, fostering a sense of ownership and responsibility amongst users.
 
 - 📱 **Responsive Design**: Enjoy a seamless experience across Desktop PC, Laptop, and Mobile devices.
 
@@ -37,7 +37,7 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 📚 **Local RAG Integration**: Dive into the future of chat interactions with groundbreaking Retrieval Augmented Generation (RAG) support. This feature seamlessly integrates document interactions into your chat experience. You can load documents directly into the chat or add files to your document library, effortlessly accessing them using the `#` command before a query.
 
-- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, `serper`, `Serply`, `DuckDuckGo`, `TavilySearch` and `SearchApi` and inject the results directly into your chat experience.
+- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, `serper`, `Serply`, `DuckDuckGo`, `TavilySearch`, `SearchApi` and `Bing` and inject the results directly into your chat experience.
 
 - 🌐 **Web Browsing Capability**: Seamlessly integrate websites into your chat experience using the `#` command followed by a URL. This feature allows you to incorporate web content directly into your conversations, enhancing the richness and depth of your interactions.
 
@@ -49,6 +49,8 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
 
+- 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
+
 - 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates, fixes, and new features.
 
 Want to learn more about Open WebUI's features? Check out our [Open WebUI documentation](https://docs.openwebui.com/features) for a comprehensive overview!
@@ -187,18 +189,6 @@ docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui --a
 
 Discover upcoming features on our roadmap in the [Open WebUI Documentation](https://docs.openwebui.com/roadmap/).
 
-## Supporters ✨
-
-A big shoutout to our amazing supporters who's helping to make this project possible! 🙏
-
-### Platinum Sponsors 🤍
-
-- We're looking for Sponsors!
-
-### Acknowledgments
-
-Special thanks to [Prof. Lawrence Kim](https://www.lhkim.com/) and [Prof. Nick Vincent](https://www.nickmvincent.com/) for their invaluable support and guidance in shaping this project into a research endeavor. Grateful for your mentorship throughout the journey! 🙌
-
 ## License 📜
 
 This project is licensed under the [MIT License](LICENSE) - see the [LICENSE](LICENSE) file for details. 📄

TROUBLESHOOTING.md

@@ -18,7 +18,7 @@ If you're experiencing connection issues, it’s often due to the WebUI docker c
 docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
 ```
 
-### Error on Slow Reponses for Ollama
+### Error on Slow Responses for Ollama
 
 Open WebUI has a default timeout of 5 minutes for Ollama to finish generating the response. If needed, this can be adjusted via the environment variable AIOHTTP_CLIENT_TIMEOUT, which sets the timeout in seconds.
 

backend/open_webui/apps/audio/main.py

@@ -8,6 +8,8 @@ from pathlib import Path
 from pydub import AudioSegment
 from pydub.silence import split_on_silence
 
+import aiohttp
+import aiofiles
 import requests
 from open_webui.config import (
     AUDIO_STT_ENGINE,
@@ -32,7 +34,13 @@ from open_webui.config import (
 )
 
 from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS, DEVICE_TYPE
+from open_webui.env import (
+    ENV,
+    SRC_LOG_LEVELS,
+    DEVICE_TYPE,
+    ENABLE_FORWARD_USER_INFO_HEADERS,
+)
+
 from fastapi import Depends, FastAPI, File, HTTPException, Request, UploadFile, status
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import FileResponse
@@ -47,7 +55,12 @@ MAX_FILE_SIZE = MAX_FILE_SIZE_MB * 1024 * 1024  # Convert MB to bytes
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["AUDIO"])
 
-app = FastAPI()
+app = FastAPI(
+    docs_url="/docs" if ENV == "dev" else None,
+    openapi_url="/openapi.json" if ENV == "dev" else None,
+    redoc_url=None,
+)
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=CORS_ALLOW_ORIGIN,
@@ -63,6 +76,9 @@ app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
 app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
 app.state.config.STT_MODEL = AUDIO_STT_MODEL
 
+app.state.config.WHISPER_MODEL = WHISPER_MODEL
+app.state.faster_whisper_model = None
+
 app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
 app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
 app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
@@ -71,6 +87,10 @@ app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
 app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
 app.state.config.TTS_SPLIT_ON = AUDIO_TTS_SPLIT_ON
 
+
+app.state.speech_synthesiser = None
+app.state.speech_speaker_embeddings_dataset = None
+
 app.state.config.TTS_AZURE_SPEECH_REGION = AUDIO_TTS_AZURE_SPEECH_REGION
 app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT
 
@@ -82,6 +102,31 @@ SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
 SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
+def set_faster_whisper_model(model: str, auto_update: bool = False):
+    if model and app.state.config.STT_ENGINE == "":
+        from faster_whisper import WhisperModel
+
+        faster_whisper_kwargs = {
+            "model_size_or_path": model,
+            "device": whisper_device_type,
+            "compute_type": "int8",
+            "download_root": WHISPER_MODEL_DIR,
+            "local_files_only": not auto_update,
+        }
+
+        try:
+            app.state.faster_whisper_model = WhisperModel(**faster_whisper_kwargs)
+        except Exception:
+            log.warning(
+                "WhisperModel initialization failed, attempting download with local_files_only=False"
+            )
+            faster_whisper_kwargs["local_files_only"] = False
+            app.state.faster_whisper_model = WhisperModel(**faster_whisper_kwargs)
+
+    else:
+        app.state.faster_whisper_model = None
+
+
 class TTSConfigForm(BaseModel):
     OPENAI_API_BASE_URL: str
     OPENAI_API_KEY: str
@@ -99,6 +144,7 @@ class STTConfigForm(BaseModel):
     OPENAI_API_KEY: str
     ENGINE: str
     MODEL: str
+    WHISPER_MODEL: str
 
 
 class AudioConfigUpdateForm(BaseModel):
@@ -152,6 +198,7 @@ async def get_audio_config(user=Depends(get_admin_user)):
             "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
             "ENGINE": app.state.config.STT_ENGINE,
             "MODEL": app.state.config.STT_MODEL,
+            "WHISPER_MODEL": app.state.config.WHISPER_MODEL,
         },
     }
 
@@ -176,6 +223,8 @@ async def update_audio_config(
     app.state.config.STT_OPENAI_API_KEY = form_data.stt.OPENAI_API_KEY
     app.state.config.STT_ENGINE = form_data.stt.ENGINE
     app.state.config.STT_MODEL = form_data.stt.MODEL
+    app.state.config.WHISPER_MODEL = form_data.stt.WHISPER_MODEL
+    set_faster_whisper_model(form_data.stt.WHISPER_MODEL, WHISPER_MODEL_AUTO_UPDATE)
 
     return {
         "tts": {
@@ -194,10 +243,26 @@ async def update_audio_config(
             "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
             "ENGINE": app.state.config.STT_ENGINE,
             "MODEL": app.state.config.STT_MODEL,
+            "WHISPER_MODEL": app.state.config.WHISPER_MODEL,
         },
     }
 
 
+def load_speech_pipeline():
+    from transformers import pipeline
+    from datasets import load_dataset
+
+    if app.state.speech_synthesiser is None:
+        app.state.speech_synthesiser = pipeline(
+            "text-to-speech", "microsoft/speecht5_tts"
+        )
+
+    if app.state.speech_speaker_embeddings_dataset is None:
+        app.state.speech_speaker_embeddings_dataset = load_dataset(
+            "Matthijs/cmu-arctic-xvectors", split="validation"
+        )
+
+
 @app.post("/speech")
 async def speech(request: Request, user=Depends(get_verified_user)):
     body = await request.body()
@@ -215,6 +280,12 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         headers["Authorization"] = f"Bearer {app.state.config.TTS_OPENAI_API_KEY}"
         headers["Content-Type"] = "application/json"
 
+        if ENABLE_FORWARD_USER_INFO_HEADERS:
+            headers["X-OpenWebUI-User-Name"] = user.name
+            headers["X-OpenWebUI-User-Id"] = user.id
+            headers["X-OpenWebUI-User-Email"] = user.email
+            headers["X-OpenWebUI-User-Role"] = user.role
+
         try:
             body = body.decode("utf-8")
             body = json.loads(body)
@@ -223,46 +294,39 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         except Exception:
             pass
 
-        r = None
         try:
-            r = requests.post(
-                url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
-                data=body,
-                headers=headers,
-                stream=True,
-            )
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
+                    data=body,
+                    headers=headers,
+                ) as r:
+                    r.raise_for_status()
+                    async with aiofiles.open(file_path, "wb") as f:
+                        await f.write(await r.read())
 
-            r.raise_for_status()
+                    async with aiofiles.open(file_body_path, "w") as f:
+                        await f.write(json.dumps(json.loads(body.decode("utf-8"))))
 
-            # Save the streaming content to a file
-            with open(file_path, "wb") as f:
-                for chunk in r.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            with open(file_body_path, "w") as f:
-                json.dump(json.loads(body.decode("utf-8")), f)
-
-            # Return the saved file
             return FileResponse(file_path)
 
         except Exception as e:
             log.exception(e)
             error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
+            try:
+                if r.status != 200:
+                    res = await r.json()
                     if "error" in res:
                         error_detail = f"External: {res['error']['message']}"
-                except Exception:
-                    error_detail = f"External: {e}"
+            except Exception:
+                error_detail = f"External: {e}"
 
             raise HTTPException(
-                status_code=r.status_code if r != None else 500,
+                status_code=getattr(r, "status", 500),
                 detail=error_detail,
             )
 
     elif app.state.config.TTS_ENGINE == "elevenlabs":
-        payload = None
         try:
             payload = json.loads(body.decode("utf-8"))
         except Exception as e:
@@ -270,7 +334,6 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             raise HTTPException(status_code=400, detail="Invalid JSON payload")
 
         voice_id = payload.get("voice", "")
-
         if voice_id not in get_available_voices():
             raise HTTPException(
                 status_code=400,
@@ -278,13 +341,11 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             )
 
         url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
-
         headers = {
             "Accept": "audio/mpeg",
             "Content-Type": "application/json",
             "xi-api-key": app.state.config.TTS_API_KEY,
         }
-
         data = {
             "text": payload["input"],
             "model_id": app.state.config.TTS_MODEL,
@@ -292,39 +353,34 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         }
 
         try:
-            r = requests.post(url, json=data, headers=headers)
+            async with aiohttp.ClientSession() as session:
+                async with session.post(url, json=data, headers=headers) as r:
+                    r.raise_for_status()
+                    async with aiofiles.open(file_path, "wb") as f:
+                        await f.write(await r.read())
 
-            r.raise_for_status()
+                    async with aiofiles.open(file_body_path, "w") as f:
+                        await f.write(json.dumps(json.loads(body.decode("utf-8"))))
 
-            # Save the streaming content to a file
-            with open(file_path, "wb") as f:
-                for chunk in r.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            with open(file_body_path, "w") as f:
-                json.dump(json.loads(body.decode("utf-8")), f)
-
-            # Return the saved file
             return FileResponse(file_path)
 
         except Exception as e:
             log.exception(e)
             error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
+            try:
+                if r.status != 200:
+                    res = await r.json()
                     if "error" in res:
                         error_detail = f"External: {res['error']['message']}"
-                except Exception:
-                    error_detail = f"External: {e}"
+            except Exception:
+                error_detail = f"External: {e}"
 
             raise HTTPException(
-                status_code=r.status_code if r != None else 500,
+                status_code=getattr(r, "status", 500),
                 detail=error_detail,
             )
 
     elif app.state.config.TTS_ENGINE == "azure":
-        payload = None
         try:
             payload = json.loads(body.decode("utf-8"))
         except Exception as e:
@@ -347,17 +403,57 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                 <voice name="{language}">{payload["input"]}</voice>
             </speak>"""
 
-        response = requests.post(url, headers=headers, data=data)
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.post(url, headers=headers, data=data) as response:
+                    if response.status == 200:
+                        async with aiofiles.open(file_path, "wb") as f:
+                            await f.write(await response.read())
+                        return FileResponse(file_path)
+                    else:
+                        error_msg = f"Error synthesizing speech - {response.reason}"
+                        log.error(error_msg)
+                        raise HTTPException(status_code=500, detail=error_msg)
+        except Exception as e:
+            log.exception(e)
+            raise HTTPException(status_code=500, detail=str(e))
+    elif app.state.config.TTS_ENGINE == "transformers":
+        payload = None
+        try:
+            payload = json.loads(body.decode("utf-8"))
+        except Exception as e:
+            log.exception(e)
+            raise HTTPException(status_code=400, detail="Invalid JSON payload")
 
-        if response.status_code == 200:
-            with open(file_path, "wb") as f:
-                f.write(response.content)
-            return FileResponse(file_path)
-        else:
-            log.error(f"Error synthesizing speech - {response.reason}")
-            raise HTTPException(
-                status_code=500, detail=f"Error synthesizing speech - {response.reason}"
+        import torch
+        import soundfile as sf
+
+        load_speech_pipeline()
+
+        embeddings_dataset = app.state.speech_speaker_embeddings_dataset
+
+        speaker_index = 6799
+        try:
+            speaker_index = embeddings_dataset["filename"].index(
+                app.state.config.TTS_MODEL
             )
+        except Exception:
+            pass
+
+        speaker_embedding = torch.tensor(
+            embeddings_dataset[speaker_index]["xvector"]
+        ).unsqueeze(0)
+
+        speech = app.state.speech_synthesiser(
+            payload["input"],
+            forward_params={"speaker_embeddings": speaker_embedding},
+        )
+
+        sf.write(file_path, speech["audio"], samplerate=speech["sampling_rate"])
+        with open(file_body_path, "w") as f:
+            json.dump(json.loads(body.decode("utf-8")), f)
+
+        return FileResponse(file_path)
 
 
 def transcribe(file_path):
@@ -367,27 +463,10 @@ def transcribe(file_path):
     id = filename.split(".")[0]
 
     if app.state.config.STT_ENGINE == "":
-        from faster_whisper import WhisperModel
-
-        whisper_kwargs = {
-            "model_size_or_path": WHISPER_MODEL,
-            "device": whisper_device_type,
-            "compute_type": "int8",
-            "download_root": WHISPER_MODEL_DIR,
-            "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
-        }
-
-        log.debug(f"whisper_kwargs: {whisper_kwargs}")
-
-        try:
-            model = WhisperModel(**whisper_kwargs)
-        except Exception:
-            log.warning(
-                "WhisperModel initialization failed, attempting download with local_files_only=False"
-            )
-            whisper_kwargs["local_files_only"] = False
-            model = WhisperModel(**whisper_kwargs)
+        if app.state.faster_whisper_model is None:
+            set_faster_whisper_model(app.state.config.WHISPER_MODEL)
 
+        model = app.state.faster_whisper_model
         segments, info = model.transcribe(file_path, beam_size=5)
         log.info(
             "Detected language '%s' with probability %f"
@@ -395,7 +474,6 @@ def transcribe(file_path):
         )
 
         transcript = "".join([segment.text for segment in list(segments)])
-
         data = {"text": transcript.strip()}
 
         # save the transcript to a json file
@@ -403,7 +481,7 @@ def transcribe(file_path):
         with open(transcript_file, "w") as f:
             json.dump(data, f)
 
-        print(data)
+        log.debug(data)
         return data
     elif app.state.config.STT_ENGINE == "openai":
         if is_mp4_audio(file_path):
@@ -417,7 +495,7 @@ def transcribe(file_path):
         files = {"file": (filename, open(file_path, "rb"))}
         data = {"model": app.state.config.STT_MODEL}
 
-        print(files, data)
+        log.debug(files, data)
 
         r = None
         try:
@@ -450,7 +528,7 @@ def transcribe(file_path):
                 except Exception:
                     error_detail = f"External: {e}"
 
-            raise error_detail
+            raise Exception(error_detail)
 
 
 @app.post("/transcriptions")
@@ -507,7 +585,8 @@ def transcription(
             else:
                 data = transcribe(file_path)
 
-            return data
+            file_path = file_path.split("/")[-1]
+            return {**data, "filename": file_path}
         except Exception as e:
             log.exception(e)
             raise HTTPException(

backend/open_webui/apps/images/main.py

@@ -35,7 +35,8 @@ from open_webui.config import (
     AppConfig,
 )
 from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.env import ENV, SRC_LOG_LEVELS, ENABLE_FORWARD_USER_INFO_HEADERS
+
 from fastapi import Depends, FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
@@ -47,7 +48,12 @@ log.setLevel(SRC_LOG_LEVELS["IMAGES"])
 IMAGE_CACHE_DIR = Path(CACHE_DIR).joinpath("./image/generations/")
 IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
-app = FastAPI()
+app = FastAPI(
+    docs_url="/docs" if ENV == "dev" else None,
+    openapi_url="/openapi.json" if ENV == "dev" else None,
+    redoc_url=None,
+)
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=CORS_ALLOW_ORIGIN,
@@ -456,6 +462,12 @@ async def image_generations(
             headers["Authorization"] = f"Bearer {app.state.config.OPENAI_API_KEY}"
             headers["Content-Type"] = "application/json"
 
+            if ENABLE_FORWARD_USER_INFO_HEADERS:
+                headers["X-OpenWebUI-User-Name"] = user.name
+                headers["X-OpenWebUI-User-Id"] = user.id
+                headers["X-OpenWebUI-User-Email"] = user.email
+                headers["X-OpenWebUI-User-Role"] = user.role
+
             data = {
                 "model": (
                     app.state.config.MODEL

backend/open_webui/apps/images/utils/comfyui.py

@@ -125,22 +125,34 @@ async def comfyui_generate_image(
                     workflow[node_id]["inputs"][node.key] = model
             elif node.type == "prompt":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["text"] = payload.prompt
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "text"
+                    ] = payload.prompt
             elif node.type == "negative_prompt":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["text"] = payload.negative_prompt
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "text"
+                    ] = payload.negative_prompt
             elif node.type == "width":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["width"] = payload.width
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "width"
+                    ] = payload.width
             elif node.type == "height":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["height"] = payload.height
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "height"
+                    ] = payload.height
             elif node.type == "n":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["batch_size"] = payload.n
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "batch_size"
+                    ] = payload.n
             elif node.type == "steps":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["steps"] = payload.steps
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "steps"
+                    ] = payload.steps
             elif node.type == "seed":
                 seed = (
                     payload.seed

backend/open_webui/apps/openai/main.py

@@ -6,22 +6,28 @@ from pathlib import Path
 from typing import Literal, Optional, overload
 
 import aiohttp
+from aiocache import cached
 import requests
+
+
 from open_webui.apps.webui.models.models import Models
 from open_webui.config import (
     CACHE_DIR,
     CORS_ALLOW_ORIGIN,
-    ENABLE_MODEL_FILTER,
     ENABLE_OPENAI_API,
-    MODEL_FILTER_LIST,
     OPENAI_API_BASE_URLS,
     OPENAI_API_KEYS,
+    OPENAI_API_CONFIGS,
     AppConfig,
 )
-from open_webui.env import AIOHTTP_CLIENT_TIMEOUT
+from open_webui.env import (
+    AIOHTTP_CLIENT_TIMEOUT,
+    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
+    ENABLE_FORWARD_USER_INFO_HEADERS,
+)
 
 from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.env import ENV, SRC_LOG_LEVELS
 from fastapi import Depends, FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import FileResponse, StreamingResponse
@@ -34,11 +40,20 @@ from open_webui.utils.payload import (
 )
 
 from open_webui.utils.utils import get_admin_user, get_verified_user
+from open_webui.utils.access_control import has_access
+
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["OPENAI"])
 
-app = FastAPI()
+
+app = FastAPI(
+    docs_url="/docs" if ENV == "dev" else None,
+    openapi_url="/openapi.json" if ENV == "dev" else None,
+    redoc_url=None,
+)
+
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=CORS_ALLOW_ORIGIN,
@@ -49,69 +64,66 @@ app.add_middleware(
 
 app.state.config = AppConfig()
 
-app.state.config.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
-app.state.config.MODEL_FILTER_LIST = MODEL_FILTER_LIST
-
 app.state.config.ENABLE_OPENAI_API = ENABLE_OPENAI_API
 app.state.config.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
 app.state.config.OPENAI_API_KEYS = OPENAI_API_KEYS
-
-app.state.MODELS = {}
-
-
-@app.middleware("http")
-async def check_url(request: Request, call_next):
-    if len(app.state.MODELS) == 0:
-        await get_all_models()
-
-    response = await call_next(request)
-    return response
+app.state.config.OPENAI_API_CONFIGS = OPENAI_API_CONFIGS
 
 
 @app.get("/config")
 async def get_config(user=Depends(get_admin_user)):
-    return {"ENABLE_OPENAI_API": app.state.config.ENABLE_OPENAI_API}
+    return {
+        "ENABLE_OPENAI_API": app.state.config.ENABLE_OPENAI_API,
+        "OPENAI_API_BASE_URLS": app.state.config.OPENAI_API_BASE_URLS,
+        "OPENAI_API_KEYS": app.state.config.OPENAI_API_KEYS,
+        "OPENAI_API_CONFIGS": app.state.config.OPENAI_API_CONFIGS,
+    }
 
 
 class OpenAIConfigForm(BaseModel):
-    enable_openai_api: Optional[bool] = None
+    ENABLE_OPENAI_API: Optional[bool] = None
+    OPENAI_API_BASE_URLS: list[str]
+    OPENAI_API_KEYS: list[str]
+    OPENAI_API_CONFIGS: dict
 
 
 @app.post("/config/update")
 async def update_config(form_data: OpenAIConfigForm, user=Depends(get_admin_user)):
-    app.state.config.ENABLE_OPENAI_API = form_data.enable_openai_api
-    return {"ENABLE_OPENAI_API": app.state.config.ENABLE_OPENAI_API}
+    app.state.config.ENABLE_OPENAI_API = form_data.ENABLE_OPENAI_API
 
+    app.state.config.OPENAI_API_BASE_URLS = form_data.OPENAI_API_BASE_URLS
+    app.state.config.OPENAI_API_KEYS = form_data.OPENAI_API_KEYS
 
-class UrlsUpdateForm(BaseModel):
-    urls: list[str]
+    # Check if API KEYS length is same than API URLS length
+    if len(app.state.config.OPENAI_API_KEYS) != len(
+        app.state.config.OPENAI_API_BASE_URLS
+    ):
+        if len(app.state.config.OPENAI_API_KEYS) > len(
+            app.state.config.OPENAI_API_BASE_URLS
+        ):
+            app.state.config.OPENAI_API_KEYS = app.state.config.OPENAI_API_KEYS[
+                : len(app.state.config.OPENAI_API_BASE_URLS)
+            ]
+        else:
+            app.state.config.OPENAI_API_KEYS += [""] * (
+                len(app.state.config.OPENAI_API_BASE_URLS)
+                - len(app.state.config.OPENAI_API_KEYS)
+            )
 
+    app.state.config.OPENAI_API_CONFIGS = form_data.OPENAI_API_CONFIGS
 
-class KeysUpdateForm(BaseModel):
-    keys: list[str]
+    # Remove any extra configs
+    config_urls = app.state.config.OPENAI_API_CONFIGS.keys()
+    for idx, url in enumerate(app.state.config.OPENAI_API_BASE_URLS):
+        if url not in config_urls:
+            app.state.config.OPENAI_API_CONFIGS.pop(url, None)
 
-
-@app.get("/urls")
-async def get_openai_urls(user=Depends(get_admin_user)):
-    return {"OPENAI_API_BASE_URLS": app.state.config.OPENAI_API_BASE_URLS}
-
-
-@app.post("/urls/update")
-async def update_openai_urls(form_data: UrlsUpdateForm, user=Depends(get_admin_user)):
-    await get_all_models()
-    app.state.config.OPENAI_API_BASE_URLS = form_data.urls
-    return {"OPENAI_API_BASE_URLS": app.state.config.OPENAI_API_BASE_URLS}
-
-
-@app.get("/keys")
-async def get_openai_keys(user=Depends(get_admin_user)):
-    return {"OPENAI_API_KEYS": app.state.config.OPENAI_API_KEYS}
-
-
-@app.post("/keys/update")
-async def update_openai_key(form_data: KeysUpdateForm, user=Depends(get_admin_user)):
-    app.state.config.OPENAI_API_KEYS = form_data.keys
-    return {"OPENAI_API_KEYS": app.state.config.OPENAI_API_KEYS}
+    return {
+        "ENABLE_OPENAI_API": app.state.config.ENABLE_OPENAI_API,
+        "OPENAI_API_BASE_URLS": app.state.config.OPENAI_API_BASE_URLS,
+        "OPENAI_API_KEYS": app.state.config.OPENAI_API_KEYS,
+        "OPENAI_API_CONFIGS": app.state.config.OPENAI_API_CONFIGS,
+    }
 
 
 @app.post("/audio/speech")
@@ -137,6 +149,11 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         if "openrouter.ai" in app.state.config.OPENAI_API_BASE_URLS[idx]:
             headers["HTTP-Referer"] = "https://openwebui.com/"
             headers["X-Title"] = "Open WebUI"
+        if ENABLE_FORWARD_USER_INFO_HEADERS:
+            headers["X-OpenWebUI-User-Name"] = user.name
+            headers["X-OpenWebUI-User-Id"] = user.id
+            headers["X-OpenWebUI-User-Email"] = user.email
+            headers["X-OpenWebUI-User-Role"] = user.role
         r = None
         try:
             r = requests.post(
@@ -178,10 +195,10 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
 
 
-async def fetch_url(url, key):
-    timeout = aiohttp.ClientTimeout(total=3)
+async def aiohttp_get(url, key=None):
+    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
     try:
-        headers = {"Authorization": f"Bearer {key}"}
+        headers = {"Authorization": f"Bearer {key}"} if key else {}
         async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
             async with session.get(url, headers=headers) as response:
                 return await response.json()
@@ -236,14 +253,8 @@ def merge_models_lists(model_lists):
     return merged_list
 
 
-def is_openai_api_disabled():
-    api_keys = app.state.config.OPENAI_API_KEYS
-    no_keys = len(api_keys) == 1 and api_keys[0] == ""
-    return no_keys or not app.state.config.ENABLE_OPENAI_API
-
-
-async def get_all_models_raw() -> list:
-    if is_openai_api_disabled():
+async def get_all_models_responses() -> list:
+    if not app.state.config.ENABLE_OPENAI_API:
         return []
 
     # Check if API KEYS length is same than API URLS length
@@ -259,33 +270,72 @@ async def get_all_models_raw() -> list:
         else:
             app.state.config.OPENAI_API_KEYS += [""] * (num_urls - num_keys)
 
-    tasks = [
-        fetch_url(f"{url}/models", app.state.config.OPENAI_API_KEYS[idx])
-        for idx, url in enumerate(app.state.config.OPENAI_API_BASE_URLS)
-    ]
+    tasks = []
+    for idx, url in enumerate(app.state.config.OPENAI_API_BASE_URLS):
+        if url not in app.state.config.OPENAI_API_CONFIGS:
+            tasks.append(
+                aiohttp_get(f"{url}/models", app.state.config.OPENAI_API_KEYS[idx])
+            )
+        else:
+            api_config = app.state.config.OPENAI_API_CONFIGS.get(url, {})
+
+            enable = api_config.get("enable", True)
+            model_ids = api_config.get("model_ids", [])
+
+            if enable:
+                if len(model_ids) == 0:
+                    tasks.append(
+                        aiohttp_get(
+                            f"{url}/models", app.state.config.OPENAI_API_KEYS[idx]
+                        )
+                    )
+                else:
+                    model_list = {
+                        "object": "list",
+                        "data": [
+                            {
+                                "id": model_id,
+                                "name": model_id,
+                                "owned_by": "openai",
+                                "openai": {"id": model_id},
+                                "urlIdx": idx,
+                            }
+                            for model_id in model_ids
+                        ],
+                    }
+
+                    tasks.append(asyncio.ensure_future(asyncio.sleep(0, model_list)))
+            else:
+                tasks.append(asyncio.ensure_future(asyncio.sleep(0, None)))
 
     responses = await asyncio.gather(*tasks)
+
+    for idx, response in enumerate(responses):
+        if response:
+            url = app.state.config.OPENAI_API_BASE_URLS[idx]
+            api_config = app.state.config.OPENAI_API_CONFIGS.get(url, {})
+
+            prefix_id = api_config.get("prefix_id", None)
+
+            if prefix_id:
+                for model in (
+                    response if isinstance(response, list) else response.get("data", [])
+                ):
+                    model["id"] = f"{prefix_id}.{model['id']}"
+
     log.debug(f"get_all_models:responses() {responses}")
 
     return responses
 
 
-@overload
-async def get_all_models(raw: Literal[True]) -> list: ...
-
-
-@overload
-async def get_all_models(raw: Literal[False] = False) -> dict[str, list]: ...
-
-
-async def get_all_models(raw=False) -> dict[str, list] | list:
+@cached(ttl=3)
+async def get_all_models() -> dict[str, list]:
     log.info("get_all_models()")
-    if is_openai_api_disabled():
-        return [] if raw else {"data": []}
 
-    responses = await get_all_models_raw()
-    if raw:
-        return responses
+    if not app.state.config.ENABLE_OPENAI_API:
+        return {"data": []}
+
+    responses = await get_all_models_responses()
 
     def extract_data(response):
         if response and "data" in response:
@@ -295,9 +345,7 @@ async def get_all_models(raw=False) -> dict[str, list] | list:
         return None
 
     models = {"data": merge_models_lists(map(extract_data, responses))}
-
     log.debug(f"models: {models}")
-    app.state.MODELS = {model["id"]: model for model in models["data"]}
 
     return models
 
@@ -305,18 +353,12 @@ async def get_all_models(raw=False) -> dict[str, list] | list:
 @app.get("/models")
 @app.get("/models/{url_idx}")
 async def get_models(url_idx: Optional[int] = None, user=Depends(get_verified_user)):
+    models = {
+        "data": [],
+    }
+
     if url_idx is None:
         models = await get_all_models()
-        if app.state.config.ENABLE_MODEL_FILTER:
-            if user.role == "user":
-                models["data"] = list(
-                    filter(
-                        lambda model: model["id"] in app.state.config.MODEL_FILTER_LIST,
-                        models["data"],
-                    )
-                )
-                return models
-        return models
     else:
         url = app.state.config.OPENAI_API_BASE_URLS[url_idx]
         key = app.state.config.OPENAI_API_KEYS[url_idx]
@@ -325,56 +367,126 @@ async def get_models(url_idx: Optional[int] = None, user=Depends(get_verified_us
         headers["Authorization"] = f"Bearer {key}"
         headers["Content-Type"] = "application/json"
 
+        if ENABLE_FORWARD_USER_INFO_HEADERS:
+            headers["X-OpenWebUI-User-Name"] = user.name
+            headers["X-OpenWebUI-User-Id"] = user.id
+            headers["X-OpenWebUI-User-Email"] = user.email
+            headers["X-OpenWebUI-User-Role"] = user.role
+
         r = None
 
-        try:
-            r = requests.request(method="GET", url=f"{url}/models", headers=headers)
-            r.raise_for_status()
+        timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
+        async with aiohttp.ClientSession(timeout=timeout) as session:
+            try:
+                async with session.get(f"{url}/models", headers=headers) as r:
+                    if r.status != 200:
+                        # Extract response error details if available
+                        error_detail = f"HTTP Error: {r.status}"
+                        res = await r.json()
+                        if "error" in res:
+                            error_detail = f"External Error: {res['error']}"
+                        raise Exception(error_detail)
 
-            response_data = r.json()
+                    response_data = await r.json()
 
-            if "api.openai.com" in url:
-                # Filter the response data
-                response_data["data"] = [
-                    model
-                    for model in response_data["data"]
-                    if not any(
-                        name in model["id"]
-                        for name in [
-                            "babbage",
-                            "dall-e",
-                            "davinci",
-                            "embedding",
-                            "tts",
-                            "whisper",
+                    # Check if we're calling OpenAI API based on the URL
+                    if "api.openai.com" in url:
+                        # Filter models according to the specified conditions
+                        response_data["data"] = [
+                            model
+                            for model in response_data.get("data", [])
+                            if not any(
+                                name in model["id"]
+                                for name in [
+                                    "babbage",
+                                    "dall-e",
+                                    "davinci",
+                                    "embedding",
+                                    "tts",
+                                    "whisper",
+                                ]
+                            )
                         ]
-                    )
-                ]
 
-            return response_data
-        except Exception as e:
-            log.exception(e)
-            error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
+                    models = response_data
+            except aiohttp.ClientError as e:
+                # ClientError covers all aiohttp requests issues
+                log.exception(f"Client error: {str(e)}")
+                # Handle aiohttp-specific connection issues, timeout etc.
+                raise HTTPException(
+                    status_code=500, detail="Open WebUI: Server Connection Error"
+                )
+            except Exception as e:
+                log.exception(f"Unexpected error: {e}")
+                # Generic error handler in case parsing JSON or other steps fail
+                error_detail = f"Unexpected error: {str(e)}"
+                raise HTTPException(status_code=500, detail=error_detail)
+
+    if user.role == "user":
+        # Filter models based on user access control
+        filtered_models = []
+        for model in models.get("data", []):
+            model_info = Models.get_model_by_id(model["id"])
+            if model_info:
+                if user.id == model_info.user_id or has_access(
+                    user.id, type="read", access_control=model_info.access_control
+                ):
+                    filtered_models.append(model)
+        models["data"] = filtered_models
+
+    return models
+
+
+class ConnectionVerificationForm(BaseModel):
+    url: str
+    key: str
+
+
+@app.post("/verify")
+async def verify_connection(
+    form_data: ConnectionVerificationForm, user=Depends(get_admin_user)
+):
+    url = form_data.url
+    key = form_data.key
+
+    headers = {}
+    headers["Authorization"] = f"Bearer {key}"
+    headers["Content-Type"] = "application/json"
+
+    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
+    async with aiohttp.ClientSession(timeout=timeout) as session:
+        try:
+            async with session.get(f"{url}/models", headers=headers) as r:
+                if r.status != 200:
+                    # Extract response error details if available
+                    error_detail = f"HTTP Error: {r.status}"
+                    res = await r.json()
                     if "error" in res:
-                        error_detail = f"External: {res['error']}"
-                except Exception:
-                    error_detail = f"External: {e}"
+                        error_detail = f"External Error: {res['error']}"
+                    raise Exception(error_detail)
 
+                response_data = await r.json()
+                return response_data
+
+        except aiohttp.ClientError as e:
+            # ClientError covers all aiohttp requests issues
+            log.exception(f"Client error: {str(e)}")
+            # Handle aiohttp-specific connection issues, timeout etc.
             raise HTTPException(
-                status_code=r.status_code if r else 500,
-                detail=error_detail,
+                status_code=500, detail="Open WebUI: Server Connection Error"
             )
+        except Exception as e:
+            log.exception(f"Unexpected error: {e}")
+            # Generic error handler in case parsing JSON or other steps fail
+            error_detail = f"Unexpected error: {str(e)}"
+            raise HTTPException(status_code=500, detail=error_detail)
 
 
 @app.post("/chat/completions")
-@app.post("/chat/completions/{url_idx}")
 async def generate_chat_completion(
     form_data: dict,
-    url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
+    bypass_filter: Optional[bool] = False,
 ):
     idx = 0
     payload = {**form_data}
@@ -385,6 +497,7 @@ async def generate_chat_completion(
     model_id = form_data.get("model")
     model_info = Models.get_model_by_id(model_id)
 
+    # Check model info and override the payload
     if model_info:
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
@@ -393,9 +506,52 @@ async def generate_chat_completion(
         payload = apply_model_params_to_body_openai(params, payload)
         payload = apply_model_system_prompt_to_body(params, payload, user)
 
-    model = app.state.MODELS[payload.get("model")]
-    idx = model["urlIdx"]
+        # Check if user has access to the model
+        if not bypass_filter and user.role == "user":
+            if not (
+                user.id == model_info.user_id
+                or has_access(
+                    user.id, type="read", access_control=model_info.access_control
+                )
+            ):
+                raise HTTPException(
+                    status_code=403,
+                    detail="Model not found",
+                )
+    elif not bypass_filter:
+        if user.role != "admin":
+            raise HTTPException(
+                status_code=403,
+                detail="Model not found",
+            )
 
+    # Attemp to get urlIdx from the model
+    models = await get_all_models()
+
+    # Find the model from the list
+    model = next(
+        (model for model in models["data"] if model["id"] == payload.get("model")),
+        None,
+    )
+
+    if model:
+        idx = model["urlIdx"]
+    else:
+        raise HTTPException(
+            status_code=404,
+            detail="Model not found",
+        )
+
+    # Get the API config for the model
+    api_config = app.state.config.OPENAI_API_CONFIGS.get(
+        app.state.config.OPENAI_API_BASE_URLS[idx], {}
+    )
+    prefix_id = api_config.get("prefix_id", None)
+
+    if prefix_id:
+        payload["model"] = payload["model"].replace(f"{prefix_id}.", "")
+
+    # Add user info to the payload if the model is a pipeline
     if "pipeline" in model and model.get("pipeline"):
         payload["user"] = {
             "name": user.name,
@@ -406,8 +562,9 @@ async def generate_chat_completion(
 
     url = app.state.config.OPENAI_API_BASE_URLS[idx]
     key = app.state.config.OPENAI_API_KEYS[idx]
-    is_o1 = payload["model"].lower().startswith("o1-")
 
+    # Fix: O1 does not support the "max_tokens" parameter, Modify "max_tokens" to "max_completion_tokens"
+    is_o1 = payload["model"].lower().startswith("o1-")
     # Change max_completion_tokens to max_tokens (Backward compatible)
     if "api.openai.com" not in url and not is_o1:
         if "max_completion_tokens" in payload:
@@ -428,14 +585,17 @@ async def generate_chat_completion(
     # Convert the modified body back to JSON
     payload = json.dumps(payload)
 
-    log.debug(payload)
-
     headers = {}
     headers["Authorization"] = f"Bearer {key}"
     headers["Content-Type"] = "application/json"
     if "openrouter.ai" in app.state.config.OPENAI_API_BASE_URLS[idx]:
         headers["HTTP-Referer"] = "https://openwebui.com/"
         headers["X-Title"] = "Open WebUI"
+    if ENABLE_FORWARD_USER_INFO_HEADERS:
+        headers["X-OpenWebUI-User-Name"] = user.name
+        headers["X-OpenWebUI-User-Id"] = user.id
+        headers["X-OpenWebUI-User-Email"] = user.email
+        headers["X-OpenWebUI-User-Role"] = user.role
 
     r = None
     session = None
@@ -504,6 +664,11 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
     headers = {}
     headers["Authorization"] = f"Bearer {key}"
     headers["Content-Type"] = "application/json"
+    if ENABLE_FORWARD_USER_INFO_HEADERS:
+        headers["X-OpenWebUI-User-Name"] = user.name
+        headers["X-OpenWebUI-User-Id"] = user.id
+        headers["X-OpenWebUI-User-Email"] = user.email
+        headers["X-OpenWebUI-User-Role"] = user.role
 
     r = None
     session = None

backend/open_webui/apps/retrieval/loaders/main.py

@@ -159,7 +159,7 @@ class Loader:
             elif file_ext in ["htm", "html"]:
                 loader = BSHTMLLoader(file_path, open_encoding="unicode_escape")
             elif file_ext == "md":
-                loader = UnstructuredMarkdownLoader(file_path)
+                loader = TextLoader(file_path, autodetect_encoding=True)
             elif file_content_type == "application/epub+zip":
                 loader = UnstructuredEPubLoader(file_path)
             elif (

backend/open_webui/apps/retrieval/loaders/youtube.py

@@ -0,0 +1,98 @@
+from typing import Any, Dict, Generator, List, Optional, Sequence, Union
+from urllib.parse import parse_qs, urlparse
+from langchain_core.documents import Document
+
+
+ALLOWED_SCHEMES = {"http", "https"}
+ALLOWED_NETLOCS = {
+    "youtu.be",
+    "m.youtube.com",
+    "youtube.com",
+    "www.youtube.com",
+    "www.youtube-nocookie.com",
+    "vid.plus",
+}
+
+
+def _parse_video_id(url: str) -> Optional[str]:
+    """Parse a YouTube URL and return the video ID if valid, otherwise None."""
+    parsed_url = urlparse(url)
+
+    if parsed_url.scheme not in ALLOWED_SCHEMES:
+        return None
+
+    if parsed_url.netloc not in ALLOWED_NETLOCS:
+        return None
+
+    path = parsed_url.path
+
+    if path.endswith("/watch"):
+        query = parsed_url.query
+        parsed_query = parse_qs(query)
+        if "v" in parsed_query:
+            ids = parsed_query["v"]
+            video_id = ids if isinstance(ids, str) else ids[0]
+        else:
+            return None
+    else:
+        path = parsed_url.path.lstrip("/")
+        video_id = path.split("/")[-1]
+
+    if len(video_id) != 11:  # Video IDs are 11 characters long
+        return None
+
+    return video_id
+
+
+class YoutubeLoader:
+    """Load `YouTube` video transcripts."""
+
+    def __init__(
+        self,
+        video_id: str,
+        language: Union[str, Sequence[str]] = "en",
+    ):
+        """Initialize with YouTube video ID."""
+        _video_id = _parse_video_id(video_id)
+        self.video_id = _video_id if _video_id is not None else video_id
+        self._metadata = {"source": video_id}
+        self.language = language
+        if isinstance(language, str):
+            self.language = [language]
+        else:
+            self.language = language
+
+    def load(self) -> List[Document]:
+        """Load YouTube transcripts into `Document` objects."""
+        try:
+            from youtube_transcript_api import (
+                NoTranscriptFound,
+                TranscriptsDisabled,
+                YouTubeTranscriptApi,
+            )
+        except ImportError:
+            raise ImportError(
+                'Could not import "youtube_transcript_api" Python package. '
+                "Please install it with `pip install youtube-transcript-api`."
+            )
+
+        try:
+            transcript_list = YouTubeTranscriptApi.list_transcripts(self.video_id)
+        except Exception as e:
+            print(e)
+            return []
+
+        try:
+            transcript = transcript_list.find_transcript(self.language)
+        except NoTranscriptFound:
+            transcript = transcript_list.find_transcript(["en"])
+
+        transcript_pieces: List[Dict[str, Any]] = transcript.fetch()
+
+        transcript = " ".join(
+            map(
+                lambda transcript_piece: transcript_piece["text"].strip(" "),
+                transcript_pieces,
+            )
+        )
+        return [Document(page_content=transcript, metadata=self._metadata)]

backend/open_webui/apps/retrieval/main.py

@@ -14,16 +14,22 @@ from typing import Iterator, Optional, Sequence, Union
 from fastapi import Depends, FastAPI, File, Form, HTTPException, UploadFile, status
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
+import tiktoken
 
+
+from open_webui.storage.provider import Storage
+from open_webui.apps.webui.models.knowledge import Knowledges
 from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
 
 # Document loaders
 from open_webui.apps.retrieval.loaders.main import Loader
+from open_webui.apps.retrieval.loaders.youtube import YoutubeLoader
 
 # Web search engines
 from open_webui.apps.retrieval.web.main import SearchResult
 from open_webui.apps.retrieval.web.utils import get_web_loader
 from open_webui.apps.retrieval.web.brave import search_brave
+from open_webui.apps.retrieval.web.mojeek import search_mojeek
 from open_webui.apps.retrieval.web.duckduckgo import search_duckduckgo
 from open_webui.apps.retrieval.web.google_pse import search_google_pse
 from open_webui.apps.retrieval.web.jina_search import search_jina
@@ -33,6 +39,7 @@ from open_webui.apps.retrieval.web.serper import search_serper
 from open_webui.apps.retrieval.web.serply import search_serply
 from open_webui.apps.retrieval.web.serpstack import search_serpstack
 from open_webui.apps.retrieval.web.tavily import search_tavily
+from open_webui.apps.retrieval.web.bing import search_bing
 
 
 from open_webui.apps.retrieval.utils import (
@@ -47,6 +54,9 @@ from open_webui.apps.retrieval.utils import (
 from open_webui.apps.webui.models.files import Files
 from open_webui.config import (
     BRAVE_SEARCH_API_KEY,
+    MOJEEK_SEARCH_API_KEY,
+    TIKTOKEN_ENCODING_NAME,
+    RAG_TEXT_SPLITTER,
     CHUNK_OVERLAP,
     CHUNK_SIZE,
     CONTENT_EXTRACTION_ENGINE,
@@ -63,11 +73,13 @@ from open_webui.config import (
     RAG_EMBEDDING_MODEL,
     RAG_EMBEDDING_MODEL_AUTO_UPDATE,
     RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-    RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+    RAG_EMBEDDING_BATCH_SIZE,
     RAG_FILE_MAX_COUNT,
     RAG_FILE_MAX_SIZE,
     RAG_OPENAI_API_BASE_URL,
     RAG_OPENAI_API_KEY,
+    RAG_OLLAMA_BASE_URL,
+    RAG_OLLAMA_API_KEY,
     RAG_RELEVANCE_THRESHOLD,
     RAG_RERANKING_MODEL,
     RAG_RERANKING_MODEL_AUTO_UPDATE,
@@ -79,6 +91,7 @@ from open_webui.config import (
     RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
     RAG_WEB_SEARCH_ENGINE,
     RAG_WEB_SEARCH_RESULT_COUNT,
+    JINA_API_KEY,
     SEARCHAPI_API_KEY,
     SEARCHAPI_ENGINE,
     SEARXNG_QUERY_URL,
@@ -87,13 +100,20 @@ from open_webui.config import (
     SERPSTACK_API_KEY,
     SERPSTACK_HTTPS,
     TAVILY_API_KEY,
+    BING_SEARCH_V7_ENDPOINT,
+    BING_SEARCH_V7_SUBSCRIPTION_KEY,
     TIKA_SERVER_URL,
     UPLOAD_DIR,
     YOUTUBE_LOADER_LANGUAGE,
+    DEFAULT_LOCALE,
     AppConfig,
 )
 from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS, DEVICE_TYPE, DOCKER
+from open_webui.env import (
+    SRC_LOG_LEVELS,
+    DEVICE_TYPE,
+    DOCKER,
+)
 from open_webui.utils.misc import (
     calculate_sha256,
     calculate_sha256_string,
@@ -102,17 +122,18 @@ from open_webui.utils.misc import (
 )
 from open_webui.utils.utils import get_admin_user, get_verified_user
 
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.document_loaders import (
-    YoutubeLoader,
-)
+from langchain.text_splitter import RecursiveCharacterTextSplitter, TokenTextSplitter
 from langchain_core.documents import Document
 
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
-app = FastAPI()
+app = FastAPI(
+    docs_url="/docs" if ENV == "dev" else None,
+    openapi_url="/openapi.json" if ENV == "dev" else None,
+    redoc_url=None,
+)
 
 app.state.config = AppConfig()
 
@@ -129,18 +150,24 @@ app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION = (
 app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
 app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
 
+app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
+app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME
+
 app.state.config.CHUNK_SIZE = CHUNK_SIZE
 app.state.config.CHUNK_OVERLAP = CHUNK_OVERLAP
 
 app.state.config.RAG_EMBEDDING_ENGINE = RAG_EMBEDDING_ENGINE
 app.state.config.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
-app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE = RAG_EMBEDDING_OPENAI_BATCH_SIZE
+app.state.config.RAG_EMBEDDING_BATCH_SIZE = RAG_EMBEDDING_BATCH_SIZE
 app.state.config.RAG_RERANKING_MODEL = RAG_RERANKING_MODEL
 app.state.config.RAG_TEMPLATE = RAG_TEMPLATE
 
 app.state.config.OPENAI_API_BASE_URL = RAG_OPENAI_API_BASE_URL
 app.state.config.OPENAI_API_KEY = RAG_OPENAI_API_KEY
 
+app.state.config.OLLAMA_BASE_URL = RAG_OLLAMA_BASE_URL
+app.state.config.OLLAMA_API_KEY = RAG_OLLAMA_API_KEY
+
 app.state.config.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
 
 app.state.config.YOUTUBE_LOADER_LANGUAGE = YOUTUBE_LOADER_LANGUAGE
@@ -155,6 +182,7 @@ app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
 app.state.config.GOOGLE_PSE_API_KEY = GOOGLE_PSE_API_KEY
 app.state.config.GOOGLE_PSE_ENGINE_ID = GOOGLE_PSE_ENGINE_ID
 app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY
+app.state.config.MOJEEK_SEARCH_API_KEY = MOJEEK_SEARCH_API_KEY
 app.state.config.SERPSTACK_API_KEY = SERPSTACK_API_KEY
 app.state.config.SERPSTACK_HTTPS = SERPSTACK_HTTPS
 app.state.config.SERPER_API_KEY = SERPER_API_KEY
@@ -162,6 +190,10 @@ app.state.config.SERPLY_API_KEY = SERPLY_API_KEY
 app.state.config.TAVILY_API_KEY = TAVILY_API_KEY
 app.state.config.SEARCHAPI_API_KEY = SEARCHAPI_API_KEY
 app.state.config.SEARCHAPI_ENGINE = SEARCHAPI_ENGINE
+app.state.config.JINA_API_KEY = JINA_API_KEY
+app.state.config.BING_SEARCH_V7_ENDPOINT = BING_SEARCH_V7_ENDPOINT
+app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY = BING_SEARCH_V7_SUBSCRIPTION_KEY
+
 app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = RAG_WEB_SEARCH_RESULT_COUNT
 app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = RAG_WEB_SEARCH_CONCURRENT_REQUESTS
 
@@ -171,13 +203,17 @@ def update_embedding_model(
     auto_update: bool = False,
 ):
     if embedding_model and app.state.config.RAG_EMBEDDING_ENGINE == "":
-        import sentence_transformers
+        from sentence_transformers import SentenceTransformer
 
-        app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
-            get_model_path(embedding_model, auto_update),
-            device=DEVICE_TYPE,
-            trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
-        )
+        try:
+            app.state.sentence_transformer_ef = SentenceTransformer(
+                get_model_path(embedding_model, auto_update),
+                device=DEVICE_TYPE,
+                trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
+            )
+        except Exception as e:
+            log.debug(f"Error loading SentenceTransformer: {e}")
+            app.state.sentence_transformer_ef = None
     else:
         app.state.sentence_transformer_ef = None
 
@@ -231,9 +267,17 @@ app.state.EMBEDDING_FUNCTION = get_embedding_function(
     app.state.config.RAG_EMBEDDING_ENGINE,
     app.state.config.RAG_EMBEDDING_MODEL,
     app.state.sentence_transformer_ef,
-    app.state.config.OPENAI_API_KEY,
-    app.state.config.OPENAI_API_BASE_URL,
-    app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+    (
+        app.state.config.OPENAI_API_BASE_URL
+        if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
+        else app.state.config.OLLAMA_BASE_URL
+    ),
+    (
+        app.state.config.OPENAI_API_KEY
+        if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
+        else app.state.config.OLLAMA_API_KEY
+    ),
+    app.state.config.RAG_EMBEDDING_BATCH_SIZE,
 )
 
 app.add_middleware(
@@ -267,7 +311,7 @@ async def get_status():
         "embedding_engine": app.state.config.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.config.RAG_EMBEDDING_MODEL,
         "reranking_model": app.state.config.RAG_RERANKING_MODEL,
-        "openai_batch_size": app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+        "embedding_batch_size": app.state.config.RAG_EMBEDDING_BATCH_SIZE,
     }
 
 
@@ -277,10 +321,14 @@ async def get_embedding_config(user=Depends(get_admin_user)):
         "status": True,
         "embedding_engine": app.state.config.RAG_EMBEDDING_ENGINE,
         "embedding_model": app.state.config.RAG_EMBEDDING_MODEL,
+        "embedding_batch_size": app.state.config.RAG_EMBEDDING_BATCH_SIZE,
         "openai_config": {
             "url": app.state.config.OPENAI_API_BASE_URL,
             "key": app.state.config.OPENAI_API_KEY,
-            "batch_size": app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+        },
+        "ollama_config": {
+            "url": app.state.config.OLLAMA_BASE_URL,
+            "key": app.state.config.OLLAMA_API_KEY,
         },
     }
 
@@ -296,13 +344,19 @@ async def get_reraanking_config(user=Depends(get_admin_user)):
 class OpenAIConfigForm(BaseModel):
     url: str
     key: str
-    batch_size: Optional[int] = None
+
+
+class OllamaConfigForm(BaseModel):
+    url: str
+    key: str
 
 
 class EmbeddingModelUpdateForm(BaseModel):
     openai_config: Optional[OpenAIConfigForm] = None
+    ollama_config: Optional[OllamaConfigForm] = None
     embedding_engine: str
     embedding_model: str
+    embedding_batch_size: Optional[int] = 1
 
 
 @app.post("/embedding/update")
@@ -320,11 +374,12 @@ async def update_embedding_config(
             if form_data.openai_config is not None:
                 app.state.config.OPENAI_API_BASE_URL = form_data.openai_config.url
                 app.state.config.OPENAI_API_KEY = form_data.openai_config.key
-                app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE = (
-                    form_data.openai_config.batch_size
-                    if form_data.openai_config.batch_size
-                    else 1
-                )
+
+            if form_data.ollama_config is not None:
+                app.state.config.OLLAMA_BASE_URL = form_data.ollama_config.url
+                app.state.config.OLLAMA_API_KEY = form_data.ollama_config.key
+
+            app.state.config.RAG_EMBEDDING_BATCH_SIZE = form_data.embedding_batch_size
 
         update_embedding_model(app.state.config.RAG_EMBEDDING_MODEL)
 
@@ -332,19 +387,31 @@ async def update_embedding_config(
             app.state.config.RAG_EMBEDDING_ENGINE,
             app.state.config.RAG_EMBEDDING_MODEL,
             app.state.sentence_transformer_ef,
-            app.state.config.OPENAI_API_KEY,
-            app.state.config.OPENAI_API_BASE_URL,
-            app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+            (
+                app.state.config.OPENAI_API_BASE_URL
+                if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
+                else app.state.config.OLLAMA_BASE_URL
+            ),
+            (
+                app.state.config.OPENAI_API_KEY
+                if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
+                else app.state.config.OLLAMA_API_KEY
+            ),
+            app.state.config.RAG_EMBEDDING_BATCH_SIZE,
         )
 
         return {
             "status": True,
             "embedding_engine": app.state.config.RAG_EMBEDDING_ENGINE,
             "embedding_model": app.state.config.RAG_EMBEDDING_MODEL,
+            "embedding_batch_size": app.state.config.RAG_EMBEDDING_BATCH_SIZE,
             "openai_config": {
                 "url": app.state.config.OPENAI_API_BASE_URL,
                 "key": app.state.config.OPENAI_API_KEY,
-                "batch_size": app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+            },
+            "ollama_config": {
+                "url": app.state.config.OLLAMA_BASE_URL,
+                "key": app.state.config.OLLAMA_API_KEY,
             },
         }
     except Exception as e:
@@ -388,24 +455,25 @@ async def get_rag_config(user=Depends(get_admin_user)):
     return {
         "status": True,
         "pdf_extract_images": app.state.config.PDF_EXTRACT_IMAGES,
-        "file": {
-            "max_size": app.state.config.FILE_MAX_SIZE,
-            "max_count": app.state.config.FILE_MAX_COUNT,
-        },
         "content_extraction": {
             "engine": app.state.config.CONTENT_EXTRACTION_ENGINE,
             "tika_server_url": app.state.config.TIKA_SERVER_URL,
         },
         "chunk": {
+            "text_splitter": app.state.config.TEXT_SPLITTER,
             "chunk_size": app.state.config.CHUNK_SIZE,
             "chunk_overlap": app.state.config.CHUNK_OVERLAP,
         },
+        "file": {
+            "max_size": app.state.config.FILE_MAX_SIZE,
+            "max_count": app.state.config.FILE_MAX_COUNT,
+        },
         "youtube": {
             "language": app.state.config.YOUTUBE_LOADER_LANGUAGE,
             "translation": app.state.YOUTUBE_LOADER_TRANSLATION,
         },
         "web": {
-            "ssl_verification": app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
+            "web_loader_ssl_verification": app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
             "search": {
                 "enabled": app.state.config.ENABLE_RAG_WEB_SEARCH,
                 "engine": app.state.config.RAG_WEB_SEARCH_ENGINE,
@@ -413,6 +481,7 @@ async def get_rag_config(user=Depends(get_admin_user)):
                 "google_pse_api_key": app.state.config.GOOGLE_PSE_API_KEY,
                 "google_pse_engine_id": app.state.config.GOOGLE_PSE_ENGINE_ID,
                 "brave_search_api_key": app.state.config.BRAVE_SEARCH_API_KEY,
+                "mojeek_search_api_key": app.state.config.MOJEEK_SEARCH_API_KEY,
                 "serpstack_api_key": app.state.config.SERPSTACK_API_KEY,
                 "serpstack_https": app.state.config.SERPSTACK_HTTPS,
                 "serper_api_key": app.state.config.SERPER_API_KEY,
@@ -420,6 +489,9 @@ async def get_rag_config(user=Depends(get_admin_user)):
                 "tavily_api_key": app.state.config.TAVILY_API_KEY,
                 "searchapi_api_key": app.state.config.SEARCHAPI_API_KEY,
                 "seaarchapi_engine": app.state.config.SEARCHAPI_ENGINE,
+                "jina_api_key": app.state.config.JINA_API_KEY,
+                "bing_search_v7_endpoint": app.state.config.BING_SEARCH_V7_ENDPOINT,
+                "bing_search_v7_subscription_key": app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
                 "result_count": app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
                 "concurrent_requests": app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
             },
@@ -438,6 +510,7 @@ class ContentExtractionConfig(BaseModel):
 
 
 class ChunkParamUpdateForm(BaseModel):
+    text_splitter: Optional[str] = None
     chunk_size: int
     chunk_overlap: int
 
@@ -454,6 +527,7 @@ class WebSearchConfig(BaseModel):
     google_pse_api_key: Optional[str] = None
     google_pse_engine_id: Optional[str] = None
     brave_search_api_key: Optional[str] = None
+    mojeek_search_api_key: Optional[str] = None
     serpstack_api_key: Optional[str] = None
     serpstack_https: Optional[bool] = None
     serper_api_key: Optional[str] = None
@@ -461,6 +535,9 @@ class WebSearchConfig(BaseModel):
     tavily_api_key: Optional[str] = None
     searchapi_api_key: Optional[str] = None
     searchapi_engine: Optional[str] = None
+    jina_api_key: Optional[str] = None
+    bing_search_v7_endpoint: Optional[str] = None
+    bing_search_v7_subscription_key: Optional[str] = None
     result_count: Optional[int] = None
     concurrent_requests: Optional[int] = None
 
@@ -497,6 +574,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
         app.state.config.TIKA_SERVER_URL = form_data.content_extraction.tika_server_url
 
     if form_data.chunk is not None:
+        app.state.config.TEXT_SPLITTER = form_data.chunk.text_splitter
         app.state.config.CHUNK_SIZE = form_data.chunk.chunk_size
         app.state.config.CHUNK_OVERLAP = form_data.chunk.chunk_overlap
 
@@ -506,6 +584,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
 
     if form_data.web is not None:
         app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION = (
+            # Note: When UI "Bypass SSL verification for Websites"=True then ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION=False
             form_data.web.web_loader_ssl_verification
         )
 
@@ -519,6 +598,9 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
         app.state.config.BRAVE_SEARCH_API_KEY = (
             form_data.web.search.brave_search_api_key
         )
+        app.state.config.MOJEEK_SEARCH_API_KEY = (
+            form_data.web.search.mojeek_search_api_key
+        )
         app.state.config.SERPSTACK_API_KEY = form_data.web.search.serpstack_api_key
         app.state.config.SERPSTACK_HTTPS = form_data.web.search.serpstack_https
         app.state.config.SERPER_API_KEY = form_data.web.search.serper_api_key
@@ -526,6 +608,15 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
         app.state.config.TAVILY_API_KEY = form_data.web.search.tavily_api_key
         app.state.config.SEARCHAPI_API_KEY = form_data.web.search.searchapi_api_key
         app.state.config.SEARCHAPI_ENGINE = form_data.web.search.searchapi_engine
+
+        app.state.config.JINA_API_KEY = form_data.web.search.jina_api_key
+        app.state.config.BING_SEARCH_V7_ENDPOINT = (
+            form_data.web.search.bing_search_v7_endpoint
+        )
+        app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY = (
+            form_data.web.search.bing_search_v7_subscription_key
+        )
+
         app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = form_data.web.search.result_count
         app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = (
             form_data.web.search.concurrent_requests
@@ -543,6 +634,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
             "tika_server_url": app.state.config.TIKA_SERVER_URL,
         },
         "chunk": {
+            "text_splitter": app.state.config.TEXT_SPLITTER,
             "chunk_size": app.state.config.CHUNK_SIZE,
             "chunk_overlap": app.state.config.CHUNK_OVERLAP,
         },
@@ -551,7 +643,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
             "translation": app.state.YOUTUBE_LOADER_TRANSLATION,
         },
         "web": {
-            "ssl_verification": app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
+            "web_loader_ssl_verification": app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
             "search": {
                 "enabled": app.state.config.ENABLE_RAG_WEB_SEARCH,
                 "engine": app.state.config.RAG_WEB_SEARCH_ENGINE,
@@ -559,6 +651,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
                 "google_pse_api_key": app.state.config.GOOGLE_PSE_API_KEY,
                 "google_pse_engine_id": app.state.config.GOOGLE_PSE_ENGINE_ID,
                 "brave_search_api_key": app.state.config.BRAVE_SEARCH_API_KEY,
+                "mojeek_search_api_key": app.state.config.MOJEEK_SEARCH_API_KEY,
                 "serpstack_api_key": app.state.config.SERPSTACK_API_KEY,
                 "serpstack_https": app.state.config.SERPSTACK_HTTPS,
                 "serper_api_key": app.state.config.SERPER_API_KEY,
@@ -566,6 +659,9 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
                 "serachapi_api_key": app.state.config.SEARCHAPI_API_KEY,
                 "searchapi_engine": app.state.config.SEARCHAPI_ENGINE,
                 "tavily_api_key": app.state.config.TAVILY_API_KEY,
+                "jina_api_key": app.state.config.JINA_API_KEY,
+                "bing_search_v7_endpoint": app.state.config.BING_SEARCH_V7_ENDPOINT,
+                "bing_search_v7_subscription_key": app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
                 "result_count": app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
                 "concurrent_requests": app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
             },
@@ -603,11 +699,10 @@ class QuerySettingsForm(BaseModel):
 async def update_query_settings(
     form_data: QuerySettingsForm, user=Depends(get_admin_user)
 ):
-    app.state.config.RAG_TEMPLATE = (
-        form_data.template if form_data.template != "" else DEFAULT_RAG_TEMPLATE
-    )
+    app.state.config.RAG_TEMPLATE = form_data.template
     app.state.config.TOP_K = form_data.k if form_data.k else 4
     app.state.config.RELEVANCE_THRESHOLD = form_data.r if form_data.r else 0.0
+
     app.state.config.ENABLE_RAG_HYBRID_SEARCH = (
         form_data.hybrid if form_data.hybrid else False
     )
@@ -628,6 +723,23 @@ async def update_query_settings(
 ####################################
 
 
+def _get_docs_info(docs: list[Document]) -> str:
+    docs_info = set()
+
+    # Trying to select relevant metadata identifying the document.
+    for doc in docs:
+        metadata = getattr(doc, "metadata", {})
+        doc_name = metadata.get("name", "")
+        if not doc_name:
+            doc_name = metadata.get("title", "")
+        if not doc_name:
+            doc_name = metadata.get("source", "")
+        if doc_name:
+            docs_info.add(doc_name)
+
+    return ", ".join(docs_info)
+
+
 def save_docs_to_vector_db(
     docs,
     collection_name,
@@ -636,7 +748,9 @@ def save_docs_to_vector_db(
     split: bool = True,
     add: bool = False,
 ) -> bool:
-    log.info(f"save_docs_to_vector_db {docs} {collection_name}")
+    log.info(
+        f"save_docs_to_vector_db: document {_get_docs_info(docs)} {collection_name}"
+    )
 
     # Check if entries with the same hash (metadata.hash) already exist
     if metadata and "hash" in metadata:
@@ -645,25 +759,53 @@ def save_docs_to_vector_db(
             filter={"hash": metadata["hash"]},
         )
 
-        if result:
+        if result is not None:
             existing_doc_ids = result.ids[0]
             if existing_doc_ids:
                 log.info(f"Document with hash {metadata['hash']} already exists")
                 raise ValueError(ERROR_MESSAGES.DUPLICATE_CONTENT)
 
     if split:
-        text_splitter = RecursiveCharacterTextSplitter(
-            chunk_size=app.state.config.CHUNK_SIZE,
-            chunk_overlap=app.state.config.CHUNK_OVERLAP,
-            add_start_index=True,
-        )
+        if app.state.config.TEXT_SPLITTER in ["", "character"]:
+            text_splitter = RecursiveCharacterTextSplitter(
+                chunk_size=app.state.config.CHUNK_SIZE,
+                chunk_overlap=app.state.config.CHUNK_OVERLAP,
+                add_start_index=True,
+            )
+        elif app.state.config.TEXT_SPLITTER == "token":
+            log.info(
+                f"Using token text splitter: {app.state.config.TIKTOKEN_ENCODING_NAME}"
+            )
+
+            tiktoken.get_encoding(str(app.state.config.TIKTOKEN_ENCODING_NAME))
+            text_splitter = TokenTextSplitter(
+                encoding_name=str(app.state.config.TIKTOKEN_ENCODING_NAME),
+                chunk_size=app.state.config.CHUNK_SIZE,
+                chunk_overlap=app.state.config.CHUNK_OVERLAP,
+                add_start_index=True,
+            )
+        else:
+            raise ValueError(ERROR_MESSAGES.DEFAULT("Invalid text splitter"))
+
         docs = text_splitter.split_documents(docs)
 
     if len(docs) == 0:
         raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
 
     texts = [doc.page_content for doc in docs]
-    metadatas = [{**doc.metadata, **(metadata if metadata else {})} for doc in docs]
+    metadatas = [
+        {
+            **doc.metadata,
+            **(metadata if metadata else {}),
+            "embedding_config": json.dumps(
+                {
+                    "engine": app.state.config.RAG_EMBEDDING_ENGINE,
+                    "model": app.state.config.RAG_EMBEDDING_MODEL,
+                }
+            ),
+        }
+        for doc in docs
+    ]
 
     # ChromaDB does not like datetime formats
     # for meta-data so convert them to string.
@@ -679,8 +821,10 @@ def save_docs_to_vector_db(
             if overwrite:
                 VECTOR_DB_CLIENT.delete_collection(collection_name=collection_name)
                 log.info(f"deleting existing collection {collection_name}")
-
-            if add is False:
+            elif add is False:
+                log.info(
+                    f"collection {collection_name} already exists, overwrite is False and add is False"
+                )
                 return True
 
         log.info(f"adding to collection {collection_name}")
@@ -688,9 +832,17 @@ def save_docs_to_vector_db(
             app.state.config.RAG_EMBEDDING_ENGINE,
             app.state.config.RAG_EMBEDDING_MODEL,
             app.state.sentence_transformer_ef,
-            app.state.config.OPENAI_API_KEY,
-            app.state.config.OPENAI_API_BASE_URL,
-            app.state.config.RAG_EMBEDDING_OPENAI_BATCH_SIZE,
+            (
+                app.state.config.OPENAI_API_BASE_URL
+                if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
+                else app.state.config.OLLAMA_BASE_URL
+            ),
+            (
+                app.state.config.OPENAI_API_KEY
+                if app.state.config.RAG_EMBEDDING_ENGINE == "openai"
+                else app.state.config.OLLAMA_API_KEY
+            ),
+            app.state.config.RAG_EMBEDDING_BATCH_SIZE,
         )
 
         embeddings = embedding_function(
@@ -741,19 +893,17 @@ def process_file(
             # Update the content in the file
             # Usage: /files/{file_id}/data/content/update
 
-            VECTOR_DB_CLIENT.delete(
-                collection_name=f"file-{file.id}",
-                filter={"file_id": file.id},
-            )
+            VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
 
             docs = [
                 Document(
                     page_content=form_data.content,
                     metadata={
-                        "name": file.meta.get("name", file.filename),
+                        **file.meta,
+                        "name": file.filename,
                         "created_by": file.user_id,
                         "file_id": file.id,
-                        **file.meta,
+                        "source": file.filename,
                     },
                 )
             ]
@@ -767,7 +917,7 @@ def process_file(
                 collection_name=f"file-{file.id}", filter={"file_id": file.id}
             )
 
-            if len(result.ids[0]) > 0:
+            if result is not None and len(result.ids[0]) > 0:
                 docs = [
                     Document(
                         page_content=result.documents[0][idx],
@@ -780,10 +930,11 @@ def process_file(
                     Document(
                         page_content=file.data.get("content", ""),
                         metadata={
-                            "name": file.meta.get("name", file.filename),
+                            **file.meta,
+                            "name": file.filename,
                             "created_by": file.user_id,
                             "file_id": file.id,
-                            **file.meta,
+                            "source": file.filename,
                         },
                     )
                 ]
@@ -792,31 +943,44 @@ def process_file(
         else:
             # Process the file and save the content
             # Usage: /files/
-
-            file_path = file.meta.get("path", None)
+            file_path = file.path
             if file_path:
+                file_path = Storage.get_file(file_path)
                 loader = Loader(
                     engine=app.state.config.CONTENT_EXTRACTION_ENGINE,
                     TIKA_SERVER_URL=app.state.config.TIKA_SERVER_URL,
                     PDF_EXTRACT_IMAGES=app.state.config.PDF_EXTRACT_IMAGES,
                 )
-
                 docs = loader.load(
                     file.filename, file.meta.get("content_type"), file_path
                 )
+
+                docs = [
+                    Document(
+                        page_content=doc.page_content,
+                        metadata={
+                            **doc.metadata,
+                            "name": file.filename,
+                            "created_by": file.user_id,
+                            "file_id": file.id,
+                            "source": file.filename,
+                        },
+                    )
+                    for doc in docs
+                ]
             else:
                 docs = [
                     Document(
                         page_content=file.data.get("content", ""),
                         metadata={
+                            **file.meta,
                             "name": file.filename,
                             "created_by": file.user_id,
                             "file_id": file.id,
-                            **file.meta,
+                            "source": file.filename,
                         },
                     )
                 ]
-
             text_content = " ".join([doc.page_content for doc in docs])
 
         log.debug(f"text_content: {text_content}")
@@ -834,7 +998,7 @@ def process_file(
                 collection_name=collection_name,
                 metadata={
                     "file_id": file.id,
-                    "name": file.meta.get("name", file.filename),
+                    "name": file.filename,
                     "hash": hash,
                 },
                 add=(True if form_data.collection_name else False),
@@ -851,7 +1015,7 @@ def process_file(
                 return {
                     "status": True,
                     "collection_name": collection_name,
-                    "filename": file.meta.get("name", file.filename),
+                    "filename": file.filename,
                     "content": text_content,
                 }
         except Exception as e:
@@ -916,12 +1080,10 @@ def process_youtube_video(form_data: ProcessUrlForm, user=Depends(get_verified_u
         if not collection_name:
             collection_name = calculate_sha256_string(form_data.url)[:63]
 
-        loader = YoutubeLoader.from_youtube_url(
-            form_data.url,
-            add_video_info=True,
-            language=app.state.config.YOUTUBE_LOADER_LANGUAGE,
-            translation=app.state.YOUTUBE_LOADER_TRANSLATION,
+        loader = YoutubeLoader(
+            form_data.url, language=app.state.config.YOUTUBE_LOADER_LANGUAGE
         )
+
         docs = loader.load()
         content = " ".join([doc.page_content for doc in docs])
         log.debug(f"text_content: {content}")
@@ -992,6 +1154,7 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
     - SEARXNG_QUERY_URL
     - GOOGLE_PSE_API_KEY + GOOGLE_PSE_ENGINE_ID
     - BRAVE_SEARCH_API_KEY
+    - MOJEEK_SEARCH_API_KEY
     - SERPSTACK_API_KEY
     - SERPER_API_KEY
     - SERPLY_API_KEY
@@ -1038,6 +1201,16 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
             )
         else:
             raise Exception("No BRAVE_SEARCH_API_KEY found in environment variables")
+    elif engine == "mojeek":
+        if app.state.config.MOJEEK_SEARCH_API_KEY:
+            return search_mojeek(
+                app.state.config.MOJEEK_SEARCH_API_KEY,
+                query,
+                app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+                app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
+            )
+        else:
+            raise Exception("No MOJEEK_SEARCH_API_KEY found in environment variables")
     elif engine == "serpstack":
         if app.state.config.SERPSTACK_API_KEY:
             return search_serpstack(
@@ -1096,7 +1269,20 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
         else:
             raise Exception("No SEARCHAPI_API_KEY found in environment variables")
     elif engine == "jina":
-        return search_jina(query, app.state.config.RAG_WEB_SEARCH_RESULT_COUNT)
+        return search_jina(
+            app.state.config.JINA_API_KEY,
+            query,
+            app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+        )
+    elif engine == "bing":
+        return search_bing(
+            app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
+            app.state.config.BING_SEARCH_V7_ENDPOINT,
+            str(DEFAULT_LOCALE),
+            query,
+            app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+            app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
+        )
     else:
         raise Exception("No search engine API key found in environment variables")
 
@@ -1126,8 +1312,12 @@ def process_web_search(form_data: SearchForm, user=Depends(get_verified_user)):
 
         urls = [result.link for result in web_results]
 
-        loader = get_web_loader(urls)
-        docs = loader.load()
+        loader = get_web_loader(
+            urls,
+            verify_ssl=app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
+            requests_per_second=app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
+        )
+        docs = loader.aload()
 
         save_docs_to_vector_db(docs, collection_name, overwrite=True)
 
@@ -1259,6 +1449,7 @@ def delete_entries_from_collection(form_data: DeleteForm, user=Depends(get_admin
 @app.post("/reset/db")
 def reset_vector_db(user=Depends(get_admin_user)):
     VECTOR_DB_CLIENT.reset()
+    Knowledges.delete_all_knowledge()
 
 
 @app.post("/reset/uploads")
@@ -1281,28 +1472,6 @@ def reset_upload_dir(user=Depends(get_admin_user)) -> bool:
             print(f"The directory {folder} does not exist")
     except Exception as e:
         print(f"Failed to process the directory {folder}. Reason: {e}")
-
-    return True
-
-
-@app.post("/reset")
-def reset(user=Depends(get_admin_user)) -> bool:
-    folder = f"{UPLOAD_DIR}"
-    for filename in os.listdir(folder):
-        file_path = os.path.join(folder, filename)
-        try:
-            if os.path.isfile(file_path) or os.path.islink(file_path):
-                os.unlink(file_path)
-            elif os.path.isdir(file_path):
-                shutil.rmtree(file_path)
-        except Exception as e:
-            log.error("Failed to delete %s. Reason: %s" % (file_path, e))
-
-    try:
-        VECTOR_DB_CLIENT.reset()
-    except Exception as e:
-        log.exception(e)
-
     return True
 
 

backend/open_webui/apps/retrieval/utils.py

@@ -3,6 +3,7 @@ import os
 import uuid
 from typing import Optional, Union
 
+import asyncio
 import requests
 
 from huggingface_hub import snapshot_download
@@ -10,17 +11,11 @@ from langchain.retrievers import ContextualCompressionRetriever, EnsembleRetriev
 from langchain_community.retrievers import BM25Retriever
 from langchain_core.documents import Document
 
-
-from open_webui.apps.ollama.main import (
-    GenerateEmbeddingsForm,
-    generate_ollama_embeddings,
-)
 from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
 from open_webui.utils.misc import get_last_user_message
 
 from open_webui.env import SRC_LOG_LEVELS
 
-
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
@@ -75,7 +70,7 @@ def query_doc(
             limit=k,
         )
 
-        log.info(f"query_doc:result {result}")
+        log.info(f"query_doc:result {result.ids} {result.metadatas}")
         return result
     except Exception as e:
         print(e)
@@ -126,7 +121,10 @@ def query_doc_with_hybrid_search(
             "metadatas": [[d.metadata for d in result]],
         }
 
-        log.info(f"query_doc_with_hybrid_search:result {result}")
+        log.info(
+            "query_doc_with_hybrid_search:result "
+            + f'{result["metadatas"]} {result["distances"]}'
+        )
         return result
     except Exception as e:
         raise e
@@ -177,34 +175,34 @@ def merge_and_sort_query_results(
 
 def query_collection(
     collection_names: list[str],
-    query: str,
+    queries: list[str],
     embedding_function,
     k: int,
 ) -> dict:
-
     results = []
-    query_embedding = embedding_function(query)
-
-    for collection_name in collection_names:
-        if collection_name:
-            try:
-                result = query_doc(
-                    collection_name=collection_name,
-                    k=k,
-                    query_embedding=query_embedding,
-                )
-                results.append(result.model_dump())
-            except Exception as e:
-                log.exception(f"Error when querying the collection: {e}")
-        else:
-            pass
+    for query in queries:
+        query_embedding = embedding_function(query)
+        for collection_name in collection_names:
+            if collection_name:
+                try:
+                    result = query_doc(
+                        collection_name=collection_name,
+                        k=k,
+                        query_embedding=query_embedding,
+                    )
+                    if result is not None:
+                        results.append(result.model_dump())
+                except Exception as e:
+                    log.exception(f"Error when querying the collection: {e}")
+            else:
+                pass
 
     return merge_and_sort_query_results(results, k=k)
 
 
 def query_collection_with_hybrid_search(
     collection_names: list[str],
-    query: str,
+    queries: list[str],
     embedding_function,
     k: int,
     reranking_function,
@@ -214,15 +212,16 @@ def query_collection_with_hybrid_search(
     error = False
     for collection_name in collection_names:
         try:
-            result = query_doc_with_hybrid_search(
-                collection_name=collection_name,
-                query=query,
-                embedding_function=embedding_function,
-                k=k,
-                reranking_function=reranking_function,
-                r=r,
-            )
-            results.append(result)
+            for query in queries:
+                result = query_doc_with_hybrid_search(
+                    collection_name=collection_name,
+                    query=query,
+                    embedding_function=embedding_function,
+                    k=k,
+                    reranking_function=reranking_function,
+                    r=r,
+                )
+                results.append(result)
         except Exception as e:
             log.exception(
                 "Error when querying the collection with " f"hybrid_search: {e}"
@@ -237,82 +236,47 @@ def query_collection_with_hybrid_search(
     return merge_and_sort_query_results(results, k=k, reverse=True)
 
 
-def rag_template(template: str, context: str, query: str):
-    count = template.count("[context]")
-    assert "[context]" in template, "RAG template does not contain '[context]'"
-
-    if "<context>" in context and "</context>" in context:
-        log.debug(
-            "WARNING: Potential prompt injection attack: the RAG "
-            "context contains '<context>' and '</context>'. This might be "
-            "nothing, or the user might be trying to hack something."
-        )
-
-    if "[query]" in context:
-        query_placeholder = f"[query-{str(uuid.uuid4())}]"
-        template = template.replace("[query]", query_placeholder)
-        template = template.replace("[context]", context)
-        template = template.replace(query_placeholder, query)
-    else:
-        template = template.replace("[context]", context)
-        template = template.replace("[query]", query)
-    return template
-
-
 def get_embedding_function(
     embedding_engine,
     embedding_model,
     embedding_function,
-    openai_key,
-    openai_url,
-    batch_size,
+    url,
+    key,
+    embedding_batch_size,
 ):
     if embedding_engine == "":
         return lambda query: embedding_function.encode(query).tolist()
     elif embedding_engine in ["ollama", "openai"]:
-        if embedding_engine == "ollama":
-            func = lambda query: generate_ollama_embeddings(
-                GenerateEmbeddingsForm(
-                    **{
-                        "model": embedding_model,
-                        "prompt": query,
-                    }
-                )
-            )
-        elif embedding_engine == "openai":
-            func = lambda query: generate_openai_embeddings(
-                model=embedding_model,
-                text=query,
-                key=openai_key,
-                url=openai_url,
-            )
+        func = lambda query: generate_embeddings(
+            engine=embedding_engine,
+            model=embedding_model,
+            text=query,
+            url=url,
+            key=key,
+        )
 
-        def generate_multiple(query, f):
+        def generate_multiple(query, func):
             if isinstance(query, list):
-                if embedding_engine == "openai":
-                    embeddings = []
-                    for i in range(0, len(query), batch_size):
-                        embeddings.extend(f(query[i : i + batch_size]))
-                    return embeddings
-                else:
-                    return [f(q) for q in query]
+                embeddings = []
+                for i in range(0, len(query), embedding_batch_size):
+                    embeddings.extend(func(query[i : i + embedding_batch_size]))
+                return embeddings
             else:
-                return f(query)
+                return func(query)
 
         return lambda query: generate_multiple(query, func)
 
 
-def get_rag_context(
+def get_sources_from_files(
     files,
-    messages,
+    queries,
     embedding_function,
     k,
     reranking_function,
     r,
     hybrid_search,
 ):
-    log.debug(f"files: {files} {messages} {embedding_function} {reranking_function}")
-    query = get_last_user_message(messages)
+    log.debug(f"files: {files} {queries} {embedding_function} {reranking_function}")
 
     extracted_collections = []
     relevant_contexts = []
@@ -354,7 +318,7 @@ def get_rag_context(
                         try:
                             context = query_collection_with_hybrid_search(
                                 collection_names=collection_names,
-                                query=query,
+                                queries=queries,
                                 embedding_function=embedding_function,
                                 k=k,
                                 reranking_function=reranking_function,
@@ -369,7 +333,7 @@ def get_rag_context(
                     if (not hybrid_search) or (context is None):
                         context = query_collection(
                             collection_names=collection_names,
-                            query=query,
+                            queries=queries,
                             embedding_function=embedding_function,
                             k=k,
                         )
@@ -379,31 +343,28 @@ def get_rag_context(
             extracted_collections.extend(collection_names)
 
         if context:
+            if "data" in file:
+                del file["data"]
             relevant_contexts.append({**context, "file": file})
 
-    contexts = []
-    citations = []
+    sources = []
     for context in relevant_contexts:
         try:
             if "documents" in context:
-                contexts.append(
-                    "\n\n".join(
-                        [text for text in context["documents"][0] if text is not None]
-                    )
-                )
-
                 if "metadatas" in context:
-                    citations.append(
-                        {
-                            "source": context["file"],
-                            "document": context["documents"][0],
-                            "metadata": context["metadatas"][0],
-                        }
-                    )
+                    source = {
+                        "source": context["file"],
+                        "document": context["documents"][0],
+                        "metadata": context["metadatas"][0],
+                    }
+                    if "distances" in context and context["distances"]:
+                        source["distances"] = context["distances"][0]
+
+                    sources.append(source)
         except Exception as e:
             log.exception(e)
 
-    return contexts, citations
+    return sources
 
 
 def get_model_path(model: str, update_model: bool = False):
@@ -444,22 +405,8 @@ def get_model_path(model: str, update_model: bool = False):
         return model
 
 
-def generate_openai_embeddings(
-    model: str,
-    text: Union[str, list[str]],
-    key: str,
-    url: str = "https://api.openai.com/v1",
-):
-    if isinstance(text, list):
-        embeddings = generate_openai_batch_embeddings(model, text, key, url)
-    else:
-        embeddings = generate_openai_batch_embeddings(model, [text], key, url)
-
-    return embeddings[0] if isinstance(text, str) else embeddings
-
-
 def generate_openai_batch_embeddings(
-    model: str, texts: list[str], key: str, url: str = "https://api.openai.com/v1"
+    model: str, texts: list[str], url: str = "https://api.openai.com/v1", key: str = ""
 ) -> Optional[list[list[float]]]:
     try:
         r = requests.post(
@@ -481,6 +428,53 @@ def generate_openai_batch_embeddings(
         return None
 
 
+def generate_ollama_batch_embeddings(
+    model: str, texts: list[str], url: str, key: str
+) -> Optional[list[list[float]]]:
+    try:
+        r = requests.post(
+            f"{url}/api/embed",
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {key}",
+            },
+            json={"input": texts, "model": model},
+        )
+        r.raise_for_status()
+        data = r.json()
+
+        if "embeddings" in data:
+            return data["embeddings"]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        print(e)
+        return None
+
+
+def generate_embeddings(engine: str, model: str, text: Union[str, list[str]], **kwargs):
+    url = kwargs.get("url", "")
+    key = kwargs.get("key", "")
+
+    if engine == "ollama":
+        if isinstance(text, list):
+            embeddings = generate_ollama_batch_embeddings(
+                **{"model": model, "texts": text, "url": url, "key": key}
+            )
+        else:
+            embeddings = generate_ollama_batch_embeddings(
+                **{"model": model, "texts": [text], "url": url, "key": key}
+            )
+        return embeddings[0] if isinstance(text, str) else embeddings
+    elif engine == "openai":
+        if isinstance(text, list):
+            embeddings = generate_openai_batch_embeddings(model, text, url, key)
+        else:
+            embeddings = generate_openai_batch_embeddings(model, [text], url, key)
+
+        return embeddings[0] if isinstance(text, str) else embeddings
+
+
 import operator
 from typing import Optional, Sequence
 

backend/open_webui/apps/retrieval/vector/connector.py

@@ -4,6 +4,18 @@ if VECTOR_DB == "milvus":
     from open_webui.apps.retrieval.vector.dbs.milvus import MilvusClient
 
     VECTOR_DB_CLIENT = MilvusClient()
+elif VECTOR_DB == "qdrant":
+    from open_webui.apps.retrieval.vector.dbs.qdrant import QdrantClient
+
+    VECTOR_DB_CLIENT = QdrantClient()
+elif VECTOR_DB == "opensearch":
+    from open_webui.apps.retrieval.vector.dbs.opensearch import OpenSearchClient
+
+    VECTOR_DB_CLIENT = OpenSearchClient()
+elif VECTOR_DB == "pgvector":
+    from open_webui.apps.retrieval.vector.dbs.pgvector import PgvectorClient
+
+    VECTOR_DB_CLIENT = PgvectorClient()
 else:
     from open_webui.apps.retrieval.vector.dbs.chroma import ChromaClient
 

backend/open_webui/apps/retrieval/vector/dbs/chroma.py

@@ -13,11 +13,24 @@ from open_webui.config import (
     CHROMA_HTTP_SSL,
     CHROMA_TENANT,
     CHROMA_DATABASE,
+    CHROMA_CLIENT_AUTH_PROVIDER,
+    CHROMA_CLIENT_AUTH_CREDENTIALS,
 )
 
 
 class ChromaClient:
     def __init__(self):
+        settings_dict = {
+            "allow_reset": True,
+            "anonymized_telemetry": False,
+        }
+        if CHROMA_CLIENT_AUTH_PROVIDER is not None:
+            settings_dict["chroma_client_auth_provider"] = CHROMA_CLIENT_AUTH_PROVIDER
+        if CHROMA_CLIENT_AUTH_CREDENTIALS is not None:
+            settings_dict["chroma_client_auth_credentials"] = (
+                CHROMA_CLIENT_AUTH_CREDENTIALS
+            )
+
         if CHROMA_HTTP_HOST != "":
             self.client = chromadb.HttpClient(
                 host=CHROMA_HTTP_HOST,
@@ -26,12 +39,12 @@ class ChromaClient:
                 ssl=CHROMA_HTTP_SSL,
                 tenant=CHROMA_TENANT,
                 database=CHROMA_DATABASE,
-                settings=Settings(allow_reset=True, anonymized_telemetry=False),
+                settings=Settings(**settings_dict),
             )
         else:
             self.client = chromadb.PersistentClient(
                 path=CHROMA_DATA_PATH,
-                settings=Settings(allow_reset=True, anonymized_telemetry=False),
+                settings=Settings(**settings_dict),
                 tenant=CHROMA_TENANT,
                 database=CHROMA_DATABASE,
             )
@@ -109,7 +122,9 @@ class ChromaClient:
 
     def insert(self, collection_name: str, items: list[VectorItem]):
         # Insert the items into the collection, if the collection does not exist, it will be created.
-        collection = self.client.get_or_create_collection(name=collection_name)
+        collection = self.client.get_or_create_collection(
+            name=collection_name, metadata={"hnsw:space": "cosine"}
+        )
 
         ids = [item["id"] for item in items]
         documents = [item["text"] for item in items]
@@ -127,7 +142,9 @@ class ChromaClient:
 
     def upsert(self, collection_name: str, items: list[VectorItem]):
         # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
-        collection = self.client.get_or_create_collection(name=collection_name)
+        collection = self.client.get_or_create_collection(
+            name=collection_name, metadata={"hnsw:space": "cosine"}
+        )
 
         ids = [item["id"] for item in items]
         documents = [item["text"] for item in items]

backend/open_webui/apps/retrieval/vector/dbs/opensearch.py

@@ -0,0 +1,178 @@
+from opensearchpy import OpenSearch
+from typing import Optional
+
+from open_webui.apps.retrieval.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.config import (
+    OPENSEARCH_URI,
+    OPENSEARCH_SSL,
+    OPENSEARCH_CERT_VERIFY,
+    OPENSEARCH_USERNAME,
+    OPENSEARCH_PASSWORD,
+)
+
+
+class OpenSearchClient:
+    def __init__(self):
+        self.index_prefix = "open_webui"
+        self.client = OpenSearch(
+            hosts=[OPENSEARCH_URI],
+            use_ssl=OPENSEARCH_SSL,
+            verify_certs=OPENSEARCH_CERT_VERIFY,
+            http_auth=(OPENSEARCH_USERNAME, OPENSEARCH_PASSWORD),
+        )
+
+    def _result_to_get_result(self, result) -> GetResult:
+        ids = []
+        documents = []
+        metadatas = []
+
+        for hit in result["hits"]["hits"]:
+            ids.append(hit["_id"])
+            documents.append(hit["_source"].get("text"))
+            metadatas.append(hit["_source"].get("metadata"))
+
+        return GetResult(ids=ids, documents=documents, metadatas=metadatas)
+
+    def _result_to_search_result(self, result) -> SearchResult:
+        ids = []
+        distances = []
+        documents = []
+        metadatas = []
+
+        for hit in result["hits"]["hits"]:
+            ids.append(hit["_id"])
+            distances.append(hit["_score"])
+            documents.append(hit["_source"].get("text"))
+            metadatas.append(hit["_source"].get("metadata"))
+
+        return SearchResult(
+            ids=ids, distances=distances, documents=documents, metadatas=metadatas
+        )
+
+    def _create_index(self, index_name: str, dimension: int):
+        body = {
+            "mappings": {
+                "properties": {
+                    "id": {"type": "keyword"},
+                    "vector": {
+                        "type": "dense_vector",
+                        "dims": dimension,  # Adjust based on your vector dimensions
+                        "index": true,
+                        "similarity": "faiss",
+                        "method": {
+                            "name": "hnsw",
+                            "space_type": "ip",  # Use inner product to approximate cosine similarity
+                            "engine": "faiss",
+                            "ef_construction": 128,
+                            "m": 16,
+                        },
+                    },
+                    "text": {"type": "text"},
+                    "metadata": {"type": "object"},
+                }
+            }
+        }
+        self.client.indices.create(index=f"{self.index_prefix}_{index_name}", body=body)
+
+    def _create_batches(self, items: list[VectorItem], batch_size=100):
+        for i in range(0, len(items), batch_size):
+            yield items[i : i + batch_size]
+
+    def has_collection(self, index_name: str) -> bool:
+        # has_collection here means has index.
+        # We are simply adapting to the norms of the other DBs.
+        return self.client.indices.exists(index=f"{self.index_prefix}_{index_name}")
+
+    def delete_colleciton(self, index_name: str):
+        # delete_collection here means delete index.
+        # We are simply adapting to the norms of the other DBs.
+        self.client.indices.delete(index=f"{self.index_prefix}_{index_name}")
+
+    def search(
+        self, index_name: str, vectors: list[list[float]], limit: int
+    ) -> Optional[SearchResult]:
+        query = {
+            "size": limit,
+            "_source": ["text", "metadata"],
+            "query": {
+                "script_score": {
+                    "query": {"match_all": {}},
+                    "script": {
+                        "source": "cosineSimilarity(params.vector, 'vector') + 1.0",
+                        "params": {
+                            "vector": vectors[0]
+                        },  # Assuming single query vector
+                    },
+                }
+            },
+        }
+
+        result = self.client.search(
+            index=f"{self.index_prefix}_{index_name}", body=query
+        )
+
+        return self._result_to_search_result(result)
+
+    def get_or_create_index(self, index_name: str, dimension: int):
+        if not self.has_index(index_name):
+            self._create_index(index_name, dimension)
+
+    def get(self, index_name: str) -> Optional[GetResult]:
+        query = {"query": {"match_all": {}}, "_source": ["text", "metadata"]}
+
+        result = self.client.search(
+            index=f"{self.index_prefix}_{index_name}", body=query
+        )
+        return self._result_to_get_result(result)
+
+    def insert(self, index_name: str, items: list[VectorItem]):
+        if not self.has_index(index_name):
+            self._create_index(index_name, dimension=len(items[0]["vector"]))
+
+        for batch in self._create_batches(items):
+            actions = [
+                {
+                    "index": {
+                        "_id": item["id"],
+                        "_source": {
+                            "vector": item["vector"],
+                            "text": item["text"],
+                            "metadata": item["metadata"],
+                        },
+                    }
+                }
+                for item in batch
+            ]
+            self.client.bulk(actions)
+
+    def upsert(self, index_name: str, items: list[VectorItem]):
+        if not self.has_index(index_name):
+            self._create_index(index_name, dimension=len(items[0]["vector"]))
+
+        for batch in self._create_batches(items):
+            actions = [
+                {
+                    "index": {
+                        "_id": item["id"],
+                        "_source": {
+                            "vector": item["vector"],
+                            "text": item["text"],
+                            "metadata": item["metadata"],
+                        },
+                    }
+                }
+                for item in batch
+            ]
+            self.client.bulk(actions)
+
+    def delete(self, index_name: str, ids: list[str]):
+        actions = [
+            {"delete": {"_index": f"{self.index_prefix}_{index_name}", "_id": id}}
+            for id in ids
+        ]
+        self.client.bulk(body=actions)
+
+    def reset(self):
+        indices = self.client.indices.get(index=f"{self.index_prefix}_*")
+        for index in indices:
+            self.client.indices.delete(index=index)

backend/open_webui/apps/retrieval/vector/dbs/pgvector.py

@@ -0,0 +1,354 @@
+from typing import Optional, List, Dict, Any
+from sqlalchemy import (
+    cast,
+    column,
+    create_engine,
+    Column,
+    Integer,
+    select,
+    text,
+    Text,
+    values,
+)
+from sqlalchemy.sql import true
+from sqlalchemy.pool import NullPool
+
+from sqlalchemy.orm import declarative_base, scoped_session, sessionmaker
+from sqlalchemy.dialects.postgresql import JSONB, array
+from pgvector.sqlalchemy import Vector
+from sqlalchemy.ext.mutable import MutableDict
+
+from open_webui.apps.retrieval.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.config import PGVECTOR_DB_URL
+
+VECTOR_LENGTH = 1536
+Base = declarative_base()
+
+
+class DocumentChunk(Base):
+    __tablename__ = "document_chunk"
+
+    id = Column(Text, primary_key=True)
+    vector = Column(Vector(dim=VECTOR_LENGTH), nullable=True)
+    collection_name = Column(Text, nullable=False)
+    text = Column(Text, nullable=True)
+    vmetadata = Column(MutableDict.as_mutable(JSONB), nullable=True)
+
+
+class PgvectorClient:
+    def __init__(self) -> None:
+
+        # if no pgvector uri, use the existing database connection
+        if not PGVECTOR_DB_URL:
+            from open_webui.apps.webui.internal.db import Session
+
+            self.session = Session
+        else:
+            engine = create_engine(
+                PGVECTOR_DB_URL, pool_pre_ping=True, poolclass=NullPool
+            )
+            SessionLocal = sessionmaker(
+                autocommit=False, autoflush=False, bind=engine, expire_on_commit=False
+            )
+            self.session = scoped_session(SessionLocal)
+
+        try:
+            # Ensure the pgvector extension is available
+            self.session.execute(text("CREATE EXTENSION IF NOT EXISTS vector;"))
+
+            # Create the tables if they do not exist
+            # Base.metadata.create_all requires a bind (engine or connection)
+            # Get the connection from the session
+            connection = self.session.connection()
+            Base.metadata.create_all(bind=connection)
+
+            # Create an index on the vector column if it doesn't exist
+            self.session.execute(
+                text(
+                    "CREATE INDEX IF NOT EXISTS idx_document_chunk_vector "
+                    "ON document_chunk USING ivfflat (vector vector_cosine_ops) WITH (lists = 100);"
+                )
+            )
+            self.session.execute(
+                text(
+                    "CREATE INDEX IF NOT EXISTS idx_document_chunk_collection_name "
+                    "ON document_chunk (collection_name);"
+                )
+            )
+            self.session.commit()
+            print("Initialization complete.")
+        except Exception as e:
+            self.session.rollback()
+            print(f"Error during initialization: {e}")
+            raise
+
+    def adjust_vector_length(self, vector: List[float]) -> List[float]:
+        # Adjust vector to have length VECTOR_LENGTH
+        current_length = len(vector)
+        if current_length < VECTOR_LENGTH:
+            # Pad the vector with zeros
+            vector += [0.0] * (VECTOR_LENGTH - current_length)
+        elif current_length > VECTOR_LENGTH:
+            raise Exception(
+                f"Vector length {current_length} not supported. Max length must be <= {VECTOR_LENGTH}"
+            )
+        return vector
+
+    def insert(self, collection_name: str, items: List[VectorItem]) -> None:
+        try:
+            new_items = []
+            for item in items:
+                vector = self.adjust_vector_length(item["vector"])
+                new_chunk = DocumentChunk(
+                    id=item["id"],
+                    vector=vector,
+                    collection_name=collection_name,
+                    text=item["text"],
+                    vmetadata=item["metadata"],
+                )
+                new_items.append(new_chunk)
+            self.session.bulk_save_objects(new_items)
+            self.session.commit()
+            print(
+                f"Inserted {len(new_items)} items into collection '{collection_name}'."
+            )
+        except Exception as e:
+            self.session.rollback()
+            print(f"Error during insert: {e}")
+            raise
+
+    def upsert(self, collection_name: str, items: List[VectorItem]) -> None:
+        try:
+            for item in items:
+                vector = self.adjust_vector_length(item["vector"])
+                existing = (
+                    self.session.query(DocumentChunk)
+                    .filter(DocumentChunk.id == item["id"])
+                    .first()
+                )
+                if existing:
+                    existing.vector = vector
+                    existing.text = item["text"]
+                    existing.vmetadata = item["metadata"]
+                    existing.collection_name = (
+                        collection_name  # Update collection_name if necessary
+                    )
+                else:
+                    new_chunk = DocumentChunk(
+                        id=item["id"],
+                        vector=vector,
+                        collection_name=collection_name,
+                        text=item["text"],
+                        vmetadata=item["metadata"],
+                    )
+                    self.session.add(new_chunk)
+            self.session.commit()
+            print(f"Upserted {len(items)} items into collection '{collection_name}'.")
+        except Exception as e:
+            self.session.rollback()
+            print(f"Error during upsert: {e}")
+            raise
+
+    def search(
+        self,
+        collection_name: str,
+        vectors: List[List[float]],
+        limit: Optional[int] = None,
+    ) -> Optional[SearchResult]:
+        try:
+            if not vectors:
+                return None
+
+            # Adjust query vectors to VECTOR_LENGTH
+            vectors = [self.adjust_vector_length(vector) for vector in vectors]
+            num_queries = len(vectors)
+
+            def vector_expr(vector):
+                return cast(array(vector), Vector(VECTOR_LENGTH))
+
+            # Create the values for query vectors
+            qid_col = column("qid", Integer)
+            q_vector_col = column("q_vector", Vector(VECTOR_LENGTH))
+            query_vectors = (
+                values(qid_col, q_vector_col)
+                .data(
+                    [(idx, vector_expr(vector)) for idx, vector in enumerate(vectors)]
+                )
+                .alias("query_vectors")
+            )
+
+            # Build the lateral subquery for each query vector
+            subq = (
+                select(
+                    DocumentChunk.id,
+                    DocumentChunk.text,
+                    DocumentChunk.vmetadata,
+                    (
+                        DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector)
+                    ).label("distance"),
+                )
+                .where(DocumentChunk.collection_name == collection_name)
+                .order_by(
+                    (DocumentChunk.vector.cosine_distance(query_vectors.c.q_vector))
+                )
+            )
+            if limit is not None:
+                subq = subq.limit(limit)
+            subq = subq.lateral("result")
+
+            # Build the main query by joining query_vectors and the lateral subquery
+            stmt = (
+                select(
+                    query_vectors.c.qid,
+                    subq.c.id,
+                    subq.c.text,
+                    subq.c.vmetadata,
+                    subq.c.distance,
+                )
+                .select_from(query_vectors)
+                .join(subq, true())
+                .order_by(query_vectors.c.qid, subq.c.distance)
+            )
+
+            result_proxy = self.session.execute(stmt)
+            results = result_proxy.all()
+
+            ids = [[] for _ in range(num_queries)]
+            distances = [[] for _ in range(num_queries)]
+            documents = [[] for _ in range(num_queries)]
+            metadatas = [[] for _ in range(num_queries)]
+
+            if not results:
+                return SearchResult(
+                    ids=ids,
+                    distances=distances,
+                    documents=documents,
+                    metadatas=metadatas,
+                )
+
+            for row in results:
+                qid = int(row.qid)
+                ids[qid].append(row.id)
+                distances[qid].append(row.distance)
+                documents[qid].append(row.text)
+                metadatas[qid].append(row.vmetadata)
+
+            return SearchResult(
+                ids=ids, distances=distances, documents=documents, metadatas=metadatas
+            )
+        except Exception as e:
+            print(f"Error during search: {e}")
+            return None
+
+    def query(
+        self, collection_name: str, filter: Dict[str, Any], limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        try:
+            query = self.session.query(DocumentChunk).filter(
+                DocumentChunk.collection_name == collection_name
+            )
+
+            for key, value in filter.items():
+                query = query.filter(DocumentChunk.vmetadata[key].astext == str(value))
+
+            if limit is not None:
+                query = query.limit(limit)
+
+            results = query.all()
+
+            if not results:
+                return None
+
+            ids = [[result.id for result in results]]
+            documents = [[result.text for result in results]]
+            metadatas = [[result.vmetadata for result in results]]
+
+            return GetResult(
+                ids=ids,
+                documents=documents,
+                metadatas=metadatas,
+            )
+        except Exception as e:
+            print(f"Error during query: {e}")
+            return None
+
+    def get(
+        self, collection_name: str, limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        try:
+            query = self.session.query(DocumentChunk).filter(
+                DocumentChunk.collection_name == collection_name
+            )
+            if limit is not None:
+                query = query.limit(limit)
+
+            results = query.all()
+
+            if not results:
+                return None
+
+            ids = [[result.id for result in results]]
+            documents = [[result.text for result in results]]
+            metadatas = [[result.vmetadata for result in results]]
+
+            return GetResult(ids=ids, documents=documents, metadatas=metadatas)
+        except Exception as e:
+            print(f"Error during get: {e}")
+            return None
+
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[List[str]] = None,
+        filter: Optional[Dict[str, Any]] = None,
+    ) -> None:
+        try:
+            query = self.session.query(DocumentChunk).filter(
+                DocumentChunk.collection_name == collection_name
+            )
+            if ids:
+                query = query.filter(DocumentChunk.id.in_(ids))
+            if filter:
+                for key, value in filter.items():
+                    query = query.filter(
+                        DocumentChunk.vmetadata[key].astext == str(value)
+                    )
+            deleted = query.delete(synchronize_session=False)
+            self.session.commit()
+            print(f"Deleted {deleted} items from collection '{collection_name}'.")
+        except Exception as e:
+            self.session.rollback()
+            print(f"Error during delete: {e}")
+            raise
+
+    def reset(self) -> None:
+        try:
+            deleted = self.session.query(DocumentChunk).delete()
+            self.session.commit()
+            print(
+                f"Reset complete. Deleted {deleted} items from 'document_chunk' table."
+            )
+        except Exception as e:
+            self.session.rollback()
+            print(f"Error during reset: {e}")
+            raise
+
+    def close(self) -> None:
+        pass
+
+    def has_collection(self, collection_name: str) -> bool:
+        try:
+            exists = (
+                self.session.query(DocumentChunk)
+                .filter(DocumentChunk.collection_name == collection_name)
+                .first()
+                is not None
+            )
+            return exists
+        except Exception as e:
+            print(f"Error checking collection existence: {e}")
+            return False
+
+    def delete_collection(self, collection_name: str) -> None:
+        self.delete(collection_name)
+        print(f"Collection '{collection_name}' deleted.")

backend/open_webui/apps/retrieval/vector/dbs/qdrant.py

@@ -0,0 +1,184 @@
+from typing import Optional
+
+from qdrant_client import QdrantClient as Qclient
+from qdrant_client.http.models import PointStruct
+from qdrant_client.models import models
+
+from open_webui.apps.retrieval.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.config import QDRANT_URI, QDRANT_API_KEY
+
+NO_LIMIT = 999999999
+
+
+class QdrantClient:
+    def __init__(self):
+        self.collection_prefix = "open-webui"
+        self.QDRANT_URI = QDRANT_URI
+        self.QDRANT_API_KEY = QDRANT_API_KEY
+        self.client = (
+            Qclient(url=self.QDRANT_URI, api_key=self.QDRANT_API_KEY)
+            if self.QDRANT_URI
+            else None
+        )
+
+    def _result_to_get_result(self, points) -> GetResult:
+        ids = []
+        documents = []
+        metadatas = []
+
+        for point in points:
+            payload = point.payload
+            ids.append(point.id)
+            documents.append(payload["text"])
+            metadatas.append(payload["metadata"])
+
+        return GetResult(
+            **{
+                "ids": [ids],
+                "documents": [documents],
+                "metadatas": [metadatas],
+            }
+        )
+
+    def _create_collection(self, collection_name: str, dimension: int):
+        collection_name_with_prefix = f"{self.collection_prefix}_{collection_name}"
+        self.client.create_collection(
+            collection_name=collection_name_with_prefix,
+            vectors_config=models.VectorParams(
+                size=dimension, distance=models.Distance.COSINE
+            ),
+        )
+
+        print(f"collection {collection_name_with_prefix} successfully created!")
+
+    def _create_collection_if_not_exists(self, collection_name, dimension):
+        if not self.has_collection(collection_name=collection_name):
+            self._create_collection(
+                collection_name=collection_name, dimension=dimension
+            )
+
+    def _create_points(self, items: list[VectorItem]):
+        return [
+            PointStruct(
+                id=item["id"],
+                vector=item["vector"],
+                payload={"text": item["text"], "metadata": item["metadata"]},
+            )
+            for item in items
+        ]
+
+    def has_collection(self, collection_name: str) -> bool:
+        return self.client.collection_exists(
+            f"{self.collection_prefix}_{collection_name}"
+        )
+
+    def delete_collection(self, collection_name: str):
+        return self.client.delete_collection(
+            collection_name=f"{self.collection_prefix}_{collection_name}"
+        )
+
+    def search(
+        self, collection_name: str, vectors: list[list[float | int]], limit: int
+    ) -> Optional[SearchResult]:
+        # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
+        if limit is None:
+            limit = NO_LIMIT  # otherwise qdrant would set limit to 10!
+
+        query_response = self.client.query_points(
+            collection_name=f"{self.collection_prefix}_{collection_name}",
+            query=vectors[0],
+            limit=limit,
+        )
+        get_result = self._result_to_get_result(query_response.points)
+        return SearchResult(
+            ids=get_result.ids,
+            documents=get_result.documents,
+            metadatas=get_result.metadatas,
+            distances=[[point.score for point in query_response.points]],
+        )
+
+    def query(self, collection_name: str, filter: dict, limit: Optional[int] = None):
+        # Construct the filter string for querying
+        if not self.has_collection(collection_name):
+            return None
+        try:
+            if limit is None:
+                limit = NO_LIMIT  # otherwise qdrant would set limit to 10!
+
+            field_conditions = []
+            for key, value in filter.items():
+                field_conditions.append(
+                    models.FieldCondition(
+                        key=f"metadata.{key}", match=models.MatchValue(value=value)
+                    )
+                )
+
+            points = self.client.query_points(
+                collection_name=f"{self.collection_prefix}_{collection_name}",
+                query_filter=models.Filter(should=field_conditions),
+                limit=limit,
+            )
+            return self._result_to_get_result(points.points)
+        except Exception as e:
+            print(e)
+            return None
+
+    def get(self, collection_name: str) -> Optional[GetResult]:
+        # Get all the items in the collection.
+        points = self.client.query_points(
+            collection_name=f"{self.collection_prefix}_{collection_name}",
+            limit=NO_LIMIT,  # otherwise qdrant would set limit to 10!
+        )
+        return self._result_to_get_result(points.points)
+
+    def insert(self, collection_name: str, items: list[VectorItem]):
+        # Insert the items into the collection, if the collection does not exist, it will be created.
+        self._create_collection_if_not_exists(collection_name, len(items[0]["vector"]))
+        points = self._create_points(items)
+        self.client.upload_points(f"{self.collection_prefix}_{collection_name}", points)
+
+    def upsert(self, collection_name: str, items: list[VectorItem]):
+        # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
+        self._create_collection_if_not_exists(collection_name, len(items[0]["vector"]))
+        points = self._create_points(items)
+        return self.client.upsert(f"{self.collection_prefix}_{collection_name}", points)
+
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[list[str]] = None,
+        filter: Optional[dict] = None,
+    ):
+        # Delete the items from the collection based on the ids.
+        field_conditions = []
+
+        if ids:
+            for id_value in ids:
+                field_conditions.append(
+                    models.FieldCondition(
+                        key="metadata.id",
+                        match=models.MatchValue(value=id_value),
+                    ),
+                ),
+        elif filter:
+            for key, value in filter.items():
+                field_conditions.append(
+                    models.FieldCondition(
+                        key=f"metadata.{key}",
+                        match=models.MatchValue(value=value),
+                    ),
+                ),
+
+        return self.client.delete(
+            collection_name=f"{self.collection_prefix}_{collection_name}",
+            points_selector=models.FilterSelector(
+                filter=models.Filter(must=field_conditions)
+            ),
+        )
+
+    def reset(self):
+        # Resets the database. This will delete all collections and item entries.
+        collection_names = self.client.get_collections().collections
+        for collection_name in collection_names:
+            if collection_name.name.startswith(self.collection_prefix):
+                self.client.delete_collection(collection_name=collection_name.name)

backend/open_webui/apps/retrieval/web/bing.py

@@ -0,0 +1,73 @@
+import logging
+import os
+from pprint import pprint
+from typing import Optional
+import requests
+from open_webui.apps.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.env import SRC_LOG_LEVELS
+import argparse
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+"""
+Documentation: https://docs.microsoft.com/en-us/bing/search-apis/bing-web-search/overview
+"""
+
+
+def search_bing(
+    subscription_key: str,
+    endpoint: str,
+    locale: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    mkt = locale
+    params = {"q": query, "mkt": mkt, "answerCount": count}
+    headers = {"Ocp-Apim-Subscription-Key": subscription_key}
+
+    try:
+        response = requests.get(endpoint, headers=headers, params=params)
+        response.raise_for_status()
+        json_response = response.json()
+        results = json_response.get("webPages", {}).get("value", [])
+        if filter_list:
+            results = get_filtered_results(results, filter_list)
+        return [
+            SearchResult(
+                link=result["url"],
+                title=result.get("name"),
+                snippet=result.get("snippet"),
+            )
+            for result in results
+        ]
+    except Exception as ex:
+        log.error(f"Error: {ex}")
+        raise ex
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Search Bing from the command line.")
+    parser.add_argument(
+        "query",
+        type=str,
+        default="Top 10 international news today",
+        help="The search query.",
+    )
+    parser.add_argument(
+        "--count", type=int, default=10, help="Number of search results to return."
+    )
+    parser.add_argument(
+        "--filter", nargs="*", help="List of filters to apply to the search results."
+    )
+    parser.add_argument(
+        "--locale",
+        type=str,
+        default="en-US",
+        help="The locale to use for the search, maps to market in api",
+    )
+
+    args = parser.parse_args()
+
+    results = search_bing(args.locale, args.query, args.count, args.filter)
+    pprint(results)

backend/open_webui/apps/retrieval/web/jina_search.py

@@ -9,7 +9,7 @@ log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
-def search_jina(query: str, count: int) -> list[SearchResult]:
+def search_jina(api_key: str, query: str, count: int) -> list[SearchResult]:
     """
     Search using Jina's Search API and return the results as a list of SearchResult objects.
     Args:
@@ -20,9 +20,7 @@ def search_jina(query: str, count: int) -> list[SearchResult]:
         list[SearchResult]: A list of search results
     """
     jina_search_endpoint = "https://s.jina.ai/"
-    headers = {
-        "Accept": "application/json",
-    }
+    headers = {"Accept": "application/json", "Authorization": f"Bearer {api_key}"}
     url = str(URL(jina_search_endpoint + query))
     response = requests.get(url, headers=headers)
     response.raise_for_status()

backend/open_webui/apps/retrieval/web/mojeek.py

@@ -0,0 +1,40 @@
+import logging
+from typing import Optional
+
+import requests
+from open_webui.apps.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def search_mojeek(
+    api_key: str, query: str, count: int, filter_list: Optional[list[str]] = None
+) -> list[SearchResult]:
+    """Search using Mojeek's Search API and return the results as a list of SearchResult objects.
+
+    Args:
+        api_key (str): A Mojeek Search API key
+        query (str): The query to search for
+    """
+    url = "https://api.mojeek.com/search"
+    headers = {
+        "Accept": "application/json",
+    }
+    params = {"q": query, "api_key": api_key, "fmt": "json", "t": count}
+
+    response = requests.get(url, headers=headers, params=params)
+    response.raise_for_status()
+    json_response = response.json()
+    results = json_response.get("response", {}).get("results", [])
+    print(results)
+    if filter_list:
+        results = get_filtered_results(results, filter_list)
+
+    return [
+        SearchResult(
+            link=result["url"], title=result.get("title"), snippet=result.get("desc")
+        )
+        for result in results
+    ]

backend/open_webui/apps/retrieval/web/testdata/bing.json

@@ -0,0 +1,58 @@
+{
+	"_type": "SearchResponse",
+	"queryContext": {
+		"originalQuery": "Top 10 international results"
+	},
+	"webPages": {
+		"webSearchUrl": "https://www.bing.com/search?q=Top+10+international+results",
+		"totalEstimatedMatches": 687,
+		"value": [
+			{
+				"id": "https://api.bing.microsoft.com/api/v7/#WebPages.0",
+				"name": "2024 Mexican Grand Prix - F1 results and latest standings ... - PlanetF1",
+				"url": "https://www.planetf1.com/news/f1-results-2024-mexican-grand-prix-race-standings",
+				"datePublished": "2024-10-27T00:00:00.0000000",
+				"datePublishedFreshnessText": "1 day ago",
+				"isFamilyFriendly": true,
+				"displayUrl": "https://www.planetf1.com/news/f1-results-2024-mexican-grand-prix-race-standings",
+				"snippet": "Nico Hulkenberg and Pierre Gasly completed the top 10. A full report of the Mexican Grand Prix is available at the bottom of this article. F1 results – 2024 Mexican Grand Prix",
+				"dateLastCrawled": "2024-10-28T07:15:00.0000000Z",
+				"cachedPageUrl": "https://cc.bingj.com/cache.aspx?q=Top+10+international+results&d=916492551782&mkt=en-US&setlang=en-US&w=zBsfaAPyF2tUrHFHr_vFFdUm8sng4g34",
+				"language": "en",
+				"isNavigational": false,
+				"noCache": false
+			},
+			{
+				"id": "https://api.bing.microsoft.com/api/v7/#WebPages.1",
+				"name": "F1 Results Today: HUGE Verstappen penalties cause major title change",
+				"url": "https://www.gpfans.com/en/f1-news/1033512/f1-results-today-mexican-grand-prix-huge-max-verstappen-penalties-cause-major-title-change/",
+				"datePublished": "2024-10-27T00:00:00.0000000",
+				"datePublishedFreshnessText": "1 day ago",
+				"isFamilyFriendly": true,
+				"displayUrl": "https://www.gpfans.com/en/f1-news/1033512/f1-results-today-mexican-grand-prix-huge-max...",
+				"snippet": "Elsewhere, Mercedes duo Lewis Hamilton and George Russell came home in P4 and P5 respectively. Meanwhile, the surprise package of the day were Haas, with both Kevin Magnussen and Nico Hulkenberg finishing inside the points.. READ MORE: RB star issues apology after red flag CRASH at Mexican GP Mexican Grand Prix 2024 results. 1. Carlos Sainz [Ferrari] 2. Lando Norris [McLaren] - +4.705",
+				"dateLastCrawled": "2024-10-28T06:06:00.0000000Z",
+				"cachedPageUrl": "https://cc.bingj.com/cache.aspx?q=Top+10+international+results&d=2840656522642&mkt=en-US&setlang=en-US&w=-Tbkwxnq52jZCvG7l3CtgcwT1vwAjIUD",
+				"language": "en",
+				"isNavigational": false,
+				"noCache": false
+			},
+			{
+				"id": "https://api.bing.microsoft.com/api/v7/#WebPages.2",
+				"name": "International Power Rankings: England flying, Kangaroos cruising, Fiji rise",
+				"url": "https://www.loverugbyleague.com/post/international-power-rankings-england-flying-kangaroos-cruising-fiji-rise",
+				"datePublished": "2024-10-28T00:00:00.0000000",
+				"datePublishedFreshnessText": "7 hours ago",
+				"isFamilyFriendly": true,
+				"displayUrl": "https://www.loverugbyleague.com/post/international-power-rankings-england-flying...",
+				"snippet": "LRL RECOMMENDS: England player ratings from first Test against Samoa as omnificent George Williams scores perfect 10. 2. Australia (Men) – SAME. The Kangaroos remain 2nd in our Power Rankings after their 22-10 win against New Zealand in Christchurch on Sunday. As was the case in their win against Tonga last week, Mal Meninga’s side weren ...",
+				"dateLastCrawled": "2024-10-28T07:09:00.0000000Z",
+				"cachedPageUrl": "https://cc.bingj.com/cache.aspx?q=Top+10+international+results&d=1535008462672&mkt=en-US&setlang=en-US&w=82ujhH4Kp0iuhCS7wh1xLUFYUeetaVVm",
+				"language": "en",
+				"isNavigational": false,
+				"noCache": false
+			}
+		],
+		"someResultsRemoved": true
+	}
+}

backend/open_webui/apps/socket/main.py

@@ -1,3 +1,5 @@
+# TODO: move socket to webui app
+
 import asyncio
 import socketio
 import logging

backend/open_webui/apps/webui/main.py

@@ -1,6 +1,7 @@
 import inspect
 import json
 import logging
+import time
 from typing import AsyncGenerator, Generator, Iterator
 
 from open_webui.apps.socket.main import get_event_call, get_event_emitter
@@ -9,13 +10,16 @@ from open_webui.apps.webui.models.models import Models
 from open_webui.apps.webui.routers import (
     auths,
     chats,
+    folders,
     configs,
+    groups,
     files,
     functions,
     memories,
     models,
     knowledge,
     prompts,
+    evaluations,
     tools,
     users,
     utils,
@@ -27,22 +31,45 @@ from open_webui.config import (
     DEFAULT_MODELS,
     DEFAULT_PROMPT_SUGGESTIONS,
     DEFAULT_USER_ROLE,
+    MODEL_ORDER_LIST,
     ENABLE_COMMUNITY_SHARING,
     ENABLE_LOGIN_FORM,
     ENABLE_MESSAGE_RATING,
     ENABLE_SIGNUP,
+    ENABLE_API_KEY,
+    ENABLE_EVALUATION_ARENA_MODELS,
+    EVALUATION_ARENA_MODELS,
+    DEFAULT_ARENA_MODEL,
     JWT_EXPIRES_IN,
+    ENABLE_OAUTH_ROLE_MANAGEMENT,
+    OAUTH_ROLES_CLAIM,
     OAUTH_EMAIL_CLAIM,
     OAUTH_PICTURE_CLAIM,
     OAUTH_USERNAME_CLAIM,
+    OAUTH_ALLOWED_ROLES,
+    OAUTH_ADMIN_ROLES,
     SHOW_ADMIN_DETAILS,
     USER_PERMISSIONS,
     WEBHOOK_URL,
     WEBUI_AUTH,
     WEBUI_BANNERS,
+    ENABLE_LDAP,
+    LDAP_SERVER_LABEL,
+    LDAP_SERVER_HOST,
+    LDAP_SERVER_PORT,
+    LDAP_ATTRIBUTE_FOR_USERNAME,
+    LDAP_SEARCH_FILTERS,
+    LDAP_SEARCH_BASE,
+    LDAP_APP_DN,
+    LDAP_APP_PASSWORD,
+    LDAP_USE_TLS,
+    LDAP_CA_CERT_FILE,
+    LDAP_CIPHERS,
     AppConfig,
 )
 from open_webui.env import (
+    ENV,
+    SRC_LOG_LEVELS,
     WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
     WEBUI_AUTH_TRUSTED_NAME_HEADER,
 )
@@ -62,14 +89,21 @@ from open_webui.utils.payload import (
 
 from open_webui.utils.tools import get_tools
 
-app = FastAPI()
+app = FastAPI(
+    docs_url="/docs" if ENV == "dev" else None,
+    openapi_url="/openapi.json" if ENV == "dev" else None,
+    redoc_url=None,
+)
 
 log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 app.state.config = AppConfig()
 
 app.state.config.ENABLE_SIGNUP = ENABLE_SIGNUP
 app.state.config.ENABLE_LOGIN_FORM = ENABLE_LOGIN_FORM
+app.state.config.ENABLE_API_KEY = ENABLE_API_KEY
+
 app.state.config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
 app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 app.state.AUTH_TRUSTED_NAME_HEADER = WEBUI_AUTH_TRUSTED_NAME_HEADER
@@ -82,18 +116,41 @@ app.state.config.ADMIN_EMAIL = ADMIN_EMAIL
 app.state.config.DEFAULT_MODELS = DEFAULT_MODELS
 app.state.config.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
 app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
+
+
 app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
 app.state.config.BANNERS = WEBUI_BANNERS
+app.state.config.MODEL_ORDER_LIST = MODEL_ORDER_LIST
 
 app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
 app.state.config.ENABLE_MESSAGE_RATING = ENABLE_MESSAGE_RATING
 
+app.state.config.ENABLE_EVALUATION_ARENA_MODELS = ENABLE_EVALUATION_ARENA_MODELS
+app.state.config.EVALUATION_ARENA_MODELS = EVALUATION_ARENA_MODELS
+
 app.state.config.OAUTH_USERNAME_CLAIM = OAUTH_USERNAME_CLAIM
 app.state.config.OAUTH_PICTURE_CLAIM = OAUTH_PICTURE_CLAIM
 app.state.config.OAUTH_EMAIL_CLAIM = OAUTH_EMAIL_CLAIM
 
-app.state.MODELS = {}
+app.state.config.ENABLE_OAUTH_ROLE_MANAGEMENT = ENABLE_OAUTH_ROLE_MANAGEMENT
+app.state.config.OAUTH_ROLES_CLAIM = OAUTH_ROLES_CLAIM
+app.state.config.OAUTH_ALLOWED_ROLES = OAUTH_ALLOWED_ROLES
+app.state.config.OAUTH_ADMIN_ROLES = OAUTH_ADMIN_ROLES
+
+app.state.config.ENABLE_LDAP = ENABLE_LDAP
+app.state.config.LDAP_SERVER_LABEL = LDAP_SERVER_LABEL
+app.state.config.LDAP_SERVER_HOST = LDAP_SERVER_HOST
+app.state.config.LDAP_SERVER_PORT = LDAP_SERVER_PORT
+app.state.config.LDAP_ATTRIBUTE_FOR_USERNAME = LDAP_ATTRIBUTE_FOR_USERNAME
+app.state.config.LDAP_APP_DN = LDAP_APP_DN
+app.state.config.LDAP_APP_PASSWORD = LDAP_APP_PASSWORD
+app.state.config.LDAP_SEARCH_BASE = LDAP_SEARCH_BASE
+app.state.config.LDAP_SEARCH_FILTERS = LDAP_SEARCH_FILTERS
+app.state.config.LDAP_USE_TLS = LDAP_USE_TLS
+app.state.config.LDAP_CA_CERT_FILE = LDAP_CA_CERT_FILE
+app.state.config.LDAP_CIPHERS = LDAP_CIPHERS
+
 app.state.TOOLS = {}
 app.state.FUNCTIONS = {}
 
@@ -107,19 +164,26 @@ app.add_middleware(
 
 
 app.include_router(configs.router, prefix="/configs", tags=["configs"])
+
 app.include_router(auths.router, prefix="/auths", tags=["auths"])
 app.include_router(users.router, prefix="/users", tags=["users"])
+
 app.include_router(chats.router, prefix="/chats", tags=["chats"])
 
 app.include_router(models.router, prefix="/models", tags=["models"])
 app.include_router(knowledge.router, prefix="/knowledge", tags=["knowledge"])
 app.include_router(prompts.router, prefix="/prompts", tags=["prompts"])
-
-app.include_router(files.router, prefix="/files", tags=["files"])
 app.include_router(tools.router, prefix="/tools", tags=["tools"])
-app.include_router(functions.router, prefix="/functions", tags=["functions"])
 
 app.include_router(memories.router, prefix="/memories", tags=["memories"])
+app.include_router(folders.router, prefix="/folders", tags=["folders"])
+
+app.include_router(groups.router, prefix="/groups", tags=["groups"])
+app.include_router(files.router, prefix="/files", tags=["files"])
+app.include_router(functions.router, prefix="/functions", tags=["functions"])
+app.include_router(evaluations.router, prefix="/evaluations", tags=["evaluations"])
+
+
 app.include_router(utils.router, prefix="/utils", tags=["utils"])
 
 
@@ -133,6 +197,47 @@ async def get_status():
     }
 
 
+async def get_all_models():
+    models = []
+    pipe_models = await get_pipe_models()
+    models = models + pipe_models
+
+    if app.state.config.ENABLE_EVALUATION_ARENA_MODELS:
+        arena_models = []
+        if len(app.state.config.EVALUATION_ARENA_MODELS) > 0:
+            arena_models = [
+                {
+                    "id": model["id"],
+                    "name": model["name"],
+                    "info": {
+                        "meta": model["meta"],
+                    },
+                    "object": "model",
+                    "created": int(time.time()),
+                    "owned_by": "arena",
+                    "arena": True,
+                }
+                for model in app.state.config.EVALUATION_ARENA_MODELS
+            ]
+        else:
+            # Add default arena model
+            arena_models = [
+                {
+                    "id": DEFAULT_ARENA_MODEL["id"],
+                    "name": DEFAULT_ARENA_MODEL["name"],
+                    "info": {
+                        "meta": DEFAULT_ARENA_MODEL["meta"],
+                    },
+                    "object": "model",
+                    "created": int(time.time()),
+                    "owned_by": "arena",
+                    "arena": True,
+                }
+            ]
+        models = models + arena_models
+    return models
+
+
 def get_function_module(pipe_id: str):
     # Check if function is already loaded
     if pipe_id not in app.state.FUNCTIONS:
@@ -169,7 +274,9 @@ async def get_pipe_models():
                 log.exception(e)
                 sub_pipes = []
 
-            print(sub_pipes)
+            log.debug(
+                f"get_pipe_models: function '{pipe.id}' is a manifold of {sub_pipes}"
+            )
 
             for p in sub_pipes:
                 sub_pipe_id = f'{pipe.id}.{p["id"]}'
@@ -179,6 +286,7 @@ async def get_pipe_models():
                     sub_pipe_name = f"{function_module.name}{sub_pipe_name}"
 
                 pipe_flag = {"type": pipe.type}
+
                 pipe_models.append(
                     {
                         "id": sub_pipe_id,
@@ -192,6 +300,10 @@ async def get_pipe_models():
         else:
             pipe_flag = {"type": "pipe"}
 
+            log.debug(
+                f"get_pipe_models: function '{pipe.id}' is a single pipe {{ 'id': {pipe.id}, 'name': {pipe.name} }}"
+            )
+
             pipe_models.append(
                 {
                     "id": pipe.id,
@@ -245,7 +357,7 @@ def get_pipe_id(form_data: dict) -> str:
     pipe_id = form_data["model"]
     if "." in pipe_id:
         pipe_id, _ = pipe_id.split(".", 1)
-    print(pipe_id)
+
     return pipe_id
 
 
@@ -272,7 +384,7 @@ def get_function_params(function_module, form_data, user, extra_params=None):
     return params
 
 
-async def generate_function_chat_completion(form_data, user):
+async def generate_function_chat_completion(form_data, user, models: dict = {}):
     model_id = form_data.get("model")
     model_info = Models.get_model_by_id(model_id)
 
@@ -308,6 +420,7 @@ async def generate_function_chat_completion(form_data, user):
             "name": user.name,
             "role": user.role,
         },
+        "__metadata__": metadata,
     }
     extra_params["__tools__"] = get_tools(
         app,
@@ -315,7 +428,7 @@ async def generate_function_chat_completion(form_data, user):
         user,
         {
             **extra_params,
-            "__model__": app.state.MODELS[form_data["model"]],
+            "__model__": models.get(form_data["model"], None),
             "__messages__": form_data["messages"],
             "__files__": files,
         },
@@ -335,7 +448,7 @@ async def generate_function_chat_completion(form_data, user):
     pipe = function_module.pipe
     params = get_function_params(function_module, form_data, user, extra_params)
 
-    if form_data["stream"]:
+    if form_data.get("stream", False):
 
         async def stream_content():
             try:
@@ -351,7 +464,7 @@ async def generate_function_chat_completion(form_data, user):
                     return
 
             except Exception as e:
-                print(f"Error: {e}")
+                log.error(f"Error: {e}")
                 yield f"data: {json.dumps({'error': {'detail':str(e)}})}\n\n"
                 return
 
@@ -381,7 +494,7 @@ async def generate_function_chat_completion(form_data, user):
             res = await execute_pipe(pipe, params)
 
         except Exception as e:
-            print(f"Error: {e}")
+            log.error(f"Error: {e}")
             return {"error": {"detail": str(e)}}
 
         if isinstance(res, StreamingResponse) or isinstance(res, dict):

backend/open_webui/apps/webui/models/auths.py

@@ -64,6 +64,11 @@ class SigninForm(BaseModel):
     password: str
 
 
+class LdapForm(BaseModel):
+    user: str
+    password: str
+
+
 class ProfileImageUrlForm(BaseModel):
     profile_image_url: str
 

backend/open_webui/apps/webui/models/chats.py

@@ -4,8 +4,13 @@ import uuid
 from typing import Optional
 
 from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.apps.webui.models.tags import TagModel, Tag, Tags
+
+
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Boolean, Column, String, Text
+from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
+from sqlalchemy import or_, func, select, and_, text
+from sqlalchemy.sql import exists
 
 ####################
 # Chat DB Schema
@@ -18,13 +23,17 @@ class Chat(Base):
     id = Column(String, primary_key=True)
     user_id = Column(String)
     title = Column(Text)
-    chat = Column(Text)  # Save Chat JSON as Text
+    chat = Column(JSON)
 
     created_at = Column(BigInteger)
     updated_at = Column(BigInteger)
 
     share_id = Column(Text, unique=True, nullable=True)
     archived = Column(Boolean, default=False)
+    pinned = Column(Boolean, default=False, nullable=True)
+
+    meta = Column(JSON, server_default="{}")
+    folder_id = Column(Text, nullable=True)
 
 
 class ChatModel(BaseModel):
@@ -33,13 +42,17 @@ class ChatModel(BaseModel):
     id: str
     user_id: str
     title: str
-    chat: str
+    chat: dict
 
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
     share_id: Optional[str] = None
     archived: bool = False
+    pinned: Optional[bool] = False
+
+    meta: dict = {}
+    folder_id: Optional[str] = None
 
 
 ####################
@@ -51,6 +64,17 @@ class ChatForm(BaseModel):
     chat: dict
 
 
+class ChatImportForm(ChatForm):
+    meta: Optional[dict] = {}
+    pinned: Optional[bool] = False
+    folder_id: Optional[str] = None
+
+
+class ChatTitleMessagesForm(BaseModel):
+    title: str
+    messages: list[dict]
+
+
 class ChatTitleForm(BaseModel):
     title: str
 
@@ -64,6 +88,9 @@ class ChatResponse(BaseModel):
     created_at: int  # timestamp in epoch
     share_id: Optional[str] = None  # id of the chat to be shared
     archived: bool
+    pinned: Optional[bool] = False
+    meta: dict = {}
+    folder_id: Optional[str] = None
 
 
 class ChatTitleIdResponse(BaseModel):
@@ -86,7 +113,36 @@ class ChatTable:
                         if "title" in form_data.chat
                         else "New Chat"
                     ),
-                    "chat": json.dumps(form_data.chat),
+                    "chat": form_data.chat,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            result = Chat(**chat.model_dump())
+            db.add(result)
+            db.commit()
+            db.refresh(result)
+            return ChatModel.model_validate(result) if result else None
+
+    def import_chat(
+        self, user_id: str, form_data: ChatImportForm
+    ) -> Optional[ChatModel]:
+        with get_db() as db:
+            id = str(uuid.uuid4())
+            chat = ChatModel(
+                **{
+                    "id": id,
+                    "user_id": user_id,
+                    "title": (
+                        form_data.chat["title"]
+                        if "title" in form_data.chat
+                        else "New Chat"
+                    ),
+                    "chat": form_data.chat,
+                    "meta": form_data.meta,
+                    "pinned": form_data.pinned,
+                    "folder_id": form_data.folder_id,
                     "created_at": int(time.time()),
                     "updated_at": int(time.time()),
                 }
@@ -101,14 +157,14 @@ class ChatTable:
     def update_chat_by_id(self, id: str, chat: dict) -> Optional[ChatModel]:
         try:
             with get_db() as db:
-                chat_obj = db.get(Chat, id)
-                chat_obj.chat = json.dumps(chat)
-                chat_obj.title = chat["title"] if "title" in chat else "New Chat"
-                chat_obj.updated_at = int(time.time())
+                chat_item = db.get(Chat, id)
+                chat_item.chat = chat
+                chat_item.title = chat["title"] if "title" in chat else "New Chat"
+                chat_item.updated_at = int(time.time())
                 db.commit()
-                db.refresh(chat_obj)
+                db.refresh(chat_item)
 
-                return ChatModel.model_validate(chat_obj)
+                return ChatModel.model_validate(chat_item)
         except Exception:
             return None
 
@@ -147,15 +203,22 @@ class ChatTable:
     def update_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
         try:
             with get_db() as db:
-                print("update_shared_chat_by_id")
                 chat = db.get(Chat, chat_id)
-                print(chat)
-                chat.title = chat.title
-                chat.chat = chat.chat
-                db.commit()
-                db.refresh(chat)
+                shared_chat = (
+                    db.query(Chat).filter_by(user_id=f"shared-{chat_id}").first()
+                )
 
-                return self.get_chat_by_id(chat.share_id)
+                if shared_chat is None:
+                    return self.insert_shared_chat_by_chat_id(chat_id)
+
+                shared_chat.title = chat.title
+                shared_chat.chat = chat.chat
+
+                shared_chat.updated_at = int(time.time())
+                db.commit()
+                db.refresh(shared_chat)
+
+                return ChatModel.model_validate(shared_chat)
         except Exception:
             return None
 
@@ -182,11 +245,24 @@ class ChatTable:
         except Exception:
             return None
 
+    def toggle_chat_pinned_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.pinned = not chat.pinned
+                chat.updated_at = int(time.time())
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
     def toggle_chat_archive_by_id(self, id: str) -> Optional[ChatModel]:
         try:
             with get_db() as db:
                 chat = db.get(Chat, id)
                 chat.archived = not chat.archived
+                chat.updated_at = int(time.time())
                 db.commit()
                 db.refresh(chat)
                 return ChatModel.model_validate(chat)
@@ -223,14 +299,18 @@ class ChatTable:
         limit: int = 50,
     ) -> list[ChatModel]:
         with get_db() as db:
-            query = db.query(Chat).filter_by(user_id=user_id)
+            query = db.query(Chat).filter_by(user_id=user_id).filter_by(folder_id=None)
             if not include_archived:
                 query = query.filter_by(archived=False)
-            all_chats = (
-                query.order_by(Chat.updated_at.desc())
-                # .limit(limit).offset(skip)
-                .all()
-            )
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            all_chats = query.all()
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
     def get_chat_title_id_list_by_user_id(
@@ -241,7 +321,9 @@ class ChatTable:
         limit: Optional[int] = None,
     ) -> list[ChatTitleIdResponse]:
         with get_db() as db:
-            query = db.query(Chat).filter_by(user_id=user_id)
+            query = db.query(Chat).filter_by(user_id=user_id).filter_by(folder_id=None)
+            query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
+
             if not include_archived:
                 query = query.filter_by(archived=False)
 
@@ -249,10 +331,10 @@ class ChatTable:
                 Chat.id, Chat.title, Chat.updated_at, Chat.created_at
             )
 
-            if limit:
-                query = query.limit(limit)
             if skip:
                 query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
 
             all_chats = query.all()
 
@@ -328,6 +410,15 @@ class ChatTable:
             )
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
+    def get_pinned_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                .filter_by(user_id=user_id, pinned=True, archived=False)
+                .order_by(Chat.updated_at.desc())
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
     def get_archived_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
         with get_db() as db:
             all_chats = (
@@ -337,6 +428,329 @@ class ChatTable:
             )
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
+    def get_chats_by_user_id_and_search_text(
+        self,
+        user_id: str,
+        search_text: str,
+        include_archived: bool = False,
+        skip: int = 0,
+        limit: int = 60,
+    ) -> list[ChatModel]:
+        """
+        Filters chats based on a search query using Python, allowing pagination using skip and limit.
+        """
+        search_text = search_text.lower().strip()
+
+        if not search_text:
+            return self.get_chat_list_by_user_id(user_id, include_archived, skip, limit)
+
+        search_text_words = search_text.split(" ")
+
+        # search_text might contain 'tag:tag_name' format so we need to extract the tag_name, split the search_text and remove the tags
+        tag_ids = [
+            word.replace("tag:", "").replace(" ", "_").lower()
+            for word in search_text_words
+            if word.startswith("tag:")
+        ]
+
+        search_text_words = [
+            word for word in search_text_words if not word.startswith("tag:")
+        ]
+
+        search_text = " ".join(search_text_words)
+
+        with get_db() as db:
+            query = db.query(Chat).filter(Chat.user_id == user_id)
+
+            if not include_archived:
+                query = query.filter(Chat.archived == False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            # Check if the database dialect is either 'sqlite' or 'postgresql'
+            dialect_name = db.bind.dialect.name
+            if dialect_name == "sqlite":
+                # SQLite case: using JSON1 extension for JSON searching
+                query = query.filter(
+                    (
+                        Chat.title.ilike(
+                            f"%{search_text}%"
+                        )  # Case-insensitive search in title
+                        | text(
+                            """
+                            EXISTS (
+                                SELECT 1 
+                                FROM json_each(Chat.chat, '$.messages') AS message 
+                                WHERE LOWER(message.value->>'content') LIKE '%' || :search_text || '%'
+                            )
+                            """
+                        )
+                    ).params(search_text=search_text)
+                )
+
+                # Check if there are any tags to filter, it should have all the tags
+                if "none" in tag_ids:
+                    query = query.filter(
+                        text(
+                            """
+                            NOT EXISTS (
+                                SELECT 1
+                                FROM json_each(Chat.meta, '$.tags') AS tag
+                            )
+                            """
+                        )
+                    )
+                elif tag_ids:
+                    query = query.filter(
+                        and_(
+                            *[
+                                text(
+                                    f"""
+                                    EXISTS (
+                                        SELECT 1
+                                        FROM json_each(Chat.meta, '$.tags') AS tag
+                                        WHERE tag.value = :tag_id_{tag_idx}
+                                    )
+                                    """
+                                ).params(**{f"tag_id_{tag_idx}": tag_id})
+                                for tag_idx, tag_id in enumerate(tag_ids)
+                            ]
+                        )
+                    )
+
+            elif dialect_name == "postgresql":
+                # PostgreSQL relies on proper JSON query for search
+                query = query.filter(
+                    (
+                        Chat.title.ilike(
+                            f"%{search_text}%"
+                        )  # Case-insensitive search in title
+                        | text(
+                            """
+                            EXISTS (
+                                SELECT 1
+                                FROM json_array_elements(Chat.chat->'messages') AS message
+                                WHERE LOWER(message->>'content') LIKE '%' || :search_text || '%'
+                            )
+                            """
+                        )
+                    ).params(search_text=search_text)
+                )
+
+                # Check if there are any tags to filter, it should have all the tags
+                if "none" in tag_ids:
+                    query = query.filter(
+                        text(
+                            """
+                            NOT EXISTS (
+                                SELECT 1
+                                FROM json_array_elements_text(Chat.meta->'tags') AS tag
+                            )
+                            """
+                        )
+                    )
+                elif tag_ids:
+                    query = query.filter(
+                        and_(
+                            *[
+                                text(
+                                    f"""
+                                    EXISTS (
+                                        SELECT 1
+                                        FROM json_array_elements_text(Chat.meta->'tags') AS tag
+                                        WHERE tag = :tag_id_{tag_idx}
+                                    )
+                                    """
+                                ).params(**{f"tag_id_{tag_idx}": tag_id})
+                                for tag_idx, tag_id in enumerate(tag_ids)
+                            ]
+                        )
+                    )
+            else:
+                raise NotImplementedError(
+                    f"Unsupported dialect: {db.bind.dialect.name}"
+                )
+
+            # Perform pagination at the SQL level
+            all_chats = query.offset(skip).limit(limit).all()
+
+            print(len(all_chats))
+
+            # Validate and return chats
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chats_by_folder_id_and_user_id(
+        self, folder_id: str, user_id: str
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(folder_id=folder_id, user_id=user_id)
+            query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
+            query = query.filter_by(archived=False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            all_chats = query.all()
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chats_by_folder_ids_and_user_id(
+        self, folder_ids: list[str], user_id: str
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter(
+                Chat.folder_id.in_(folder_ids), Chat.user_id == user_id
+            )
+            query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
+            query = query.filter_by(archived=False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            all_chats = query.all()
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def update_chat_folder_id_by_id_and_user_id(
+        self, id: str, user_id: str, folder_id: str
+    ) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.folder_id = folder_id
+                chat.updated_at = int(time.time())
+                chat.pinned = False
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def get_chat_tags_by_id_and_user_id(self, id: str, user_id: str) -> list[TagModel]:
+        with get_db() as db:
+            chat = db.get(Chat, id)
+            tags = chat.meta.get("tags", [])
+            return [Tags.get_tag_by_name_and_user_id(tag, user_id) for tag in tags]
+
+    def get_chat_list_by_user_id_and_tag_name(
+        self, user_id: str, tag_name: str, skip: int = 0, limit: int = 50
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(user_id=user_id)
+            tag_id = tag_name.replace(" ", "_").lower()
+
+            print(db.bind.dialect.name)
+            if db.bind.dialect.name == "sqlite":
+                # SQLite JSON1 querying for tags within the meta JSON field
+                query = query.filter(
+                    text(
+                        f"EXISTS (SELECT 1 FROM json_each(Chat.meta, '$.tags') WHERE json_each.value = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+            elif db.bind.dialect.name == "postgresql":
+                # PostgreSQL JSON query for tags within the meta JSON field (for `json` type)
+                query = query.filter(
+                    text(
+                        "EXISTS (SELECT 1 FROM json_array_elements_text(Chat.meta->'tags') elem WHERE elem = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+            else:
+                raise NotImplementedError(
+                    f"Unsupported dialect: {db.bind.dialect.name}"
+                )
+
+            all_chats = query.all()
+            print("all_chats", all_chats)
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def add_chat_tag_by_id_and_user_id_and_tag_name(
+        self, id: str, user_id: str, tag_name: str
+    ) -> Optional[ChatModel]:
+        tag = Tags.get_tag_by_name_and_user_id(tag_name, user_id)
+        if tag is None:
+            tag = Tags.insert_new_tag(tag_name, user_id)
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+
+                tag_id = tag.id
+                if tag_id not in chat.meta.get("tags", []):
+                    chat.meta = {
+                        **chat.meta,
+                        "tags": list(set(chat.meta.get("tags", []) + [tag_id])),
+                    }
+
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def count_chats_by_tag_name_and_user_id(self, tag_name: str, user_id: str) -> int:
+        with get_db() as db:  # Assuming `get_db()` returns a session object
+            query = db.query(Chat).filter_by(user_id=user_id, archived=False)
+
+            # Normalize the tag_name for consistency
+            tag_id = tag_name.replace(" ", "_").lower()
+
+            if db.bind.dialect.name == "sqlite":
+                # SQLite JSON1 support for querying the tags inside the `meta` JSON field
+                query = query.filter(
+                    text(
+                        f"EXISTS (SELECT 1 FROM json_each(Chat.meta, '$.tags') WHERE json_each.value = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+
+            elif db.bind.dialect.name == "postgresql":
+                # PostgreSQL JSONB support for querying the tags inside the `meta` JSON field
+                query = query.filter(
+                    text(
+                        "EXISTS (SELECT 1 FROM json_array_elements_text(Chat.meta->'tags') elem WHERE elem = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+
+            else:
+                raise NotImplementedError(
+                    f"Unsupported dialect: {db.bind.dialect.name}"
+                )
+
+            # Get the count of matching records
+            count = query.count()
+
+            # Debugging output for inspection
+            print(f"Count of chats for tag '{tag_name}':", count)
+
+            return count
+
+    def delete_tag_by_id_and_user_id_and_tag_name(
+        self, id: str, user_id: str, tag_name: str
+    ) -> bool:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                tags = chat.meta.get("tags", [])
+                tag_id = tag_name.replace(" ", "_").lower()
+
+                tags = [tag for tag in tags if tag != tag_id]
+                chat.meta = {
+                    **chat.meta,
+                    "tags": list(set(tags)),
+                }
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def delete_all_tags_by_id_and_user_id(self, id: str, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.meta = {
+                    **chat.meta,
+                    "tags": [],
+                }
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
     def delete_chat_by_id(self, id: str) -> bool:
         try:
             with get_db() as db:
@@ -369,6 +783,18 @@ class ChatTable:
         except Exception:
             return False
 
+    def delete_chats_by_user_id_and_folder_id(
+        self, user_id: str, folder_id: str
+    ) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(user_id=user_id, folder_id=folder_id).delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
     def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
         try:
             with get_db() as db:

backend/open_webui/apps/webui/models/documents.py

@@ -1,157 +0,0 @@
-import json
-import logging
-import time
-from typing import Optional
-
-from open_webui.apps.webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
-from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
-####################
-# Documents DB Schema
-####################
-
-
-class Document(Base):
-    __tablename__ = "document"
-
-    collection_name = Column(String, primary_key=True)
-    name = Column(String, unique=True)
-    title = Column(Text)
-    filename = Column(Text)
-    content = Column(Text, nullable=True)
-    user_id = Column(String)
-    timestamp = Column(BigInteger)
-
-
-class DocumentModel(BaseModel):
-    model_config = ConfigDict(from_attributes=True)
-
-    collection_name: str
-    name: str
-    title: str
-    filename: str
-    content: Optional[str] = None
-    user_id: str
-    timestamp: int  # timestamp in epoch
-
-
-####################
-# Forms
-####################
-
-
-class DocumentResponse(BaseModel):
-    collection_name: str
-    name: str
-    title: str
-    filename: str
-    content: Optional[dict] = None
-    user_id: str
-    timestamp: int  # timestamp in epoch
-
-
-class DocumentUpdateForm(BaseModel):
-    name: str
-    title: str
-
-
-class DocumentForm(DocumentUpdateForm):
-    collection_name: str
-    filename: str
-    content: Optional[str] = None
-
-
-class DocumentsTable:
-    def insert_new_doc(
-        self, user_id: str, form_data: DocumentForm
-    ) -> Optional[DocumentModel]:
-        with get_db() as db:
-            document = DocumentModel(
-                **{
-                    **form_data.model_dump(),
-                    "user_id": user_id,
-                    "timestamp": int(time.time()),
-                }
-            )
-
-            try:
-                result = Document(**document.model_dump())
-                db.add(result)
-                db.commit()
-                db.refresh(result)
-                if result:
-                    return DocumentModel.model_validate(result)
-                else:
-                    return None
-            except Exception:
-                return None
-
-    def get_doc_by_name(self, name: str) -> Optional[DocumentModel]:
-        try:
-            with get_db() as db:
-                document = db.query(Document).filter_by(name=name).first()
-                return DocumentModel.model_validate(document) if document else None
-        except Exception:
-            return None
-
-    def get_docs(self) -> list[DocumentModel]:
-        with get_db() as db:
-            return [
-                DocumentModel.model_validate(doc) for doc in db.query(Document).all()
-            ]
-
-    def update_doc_by_name(
-        self, name: str, form_data: DocumentUpdateForm
-    ) -> Optional[DocumentModel]:
-        try:
-            with get_db() as db:
-                db.query(Document).filter_by(name=name).update(
-                    {
-                        "title": form_data.title,
-                        "name": form_data.name,
-                        "timestamp": int(time.time()),
-                    }
-                )
-                db.commit()
-                return self.get_doc_by_name(form_data.name)
-        except Exception as e:
-            log.exception(e)
-            return None
-
-    def update_doc_content_by_name(
-        self, name: str, updated: dict
-    ) -> Optional[DocumentModel]:
-        try:
-            doc = self.get_doc_by_name(name)
-            doc_content = json.loads(doc.content if doc.content else "{}")
-            doc_content = {**doc_content, **updated}
-
-            with get_db() as db:
-                db.query(Document).filter_by(name=name).update(
-                    {
-                        "content": json.dumps(doc_content),
-                        "timestamp": int(time.time()),
-                    }
-                )
-                db.commit()
-                return self.get_doc_by_name(name)
-        except Exception as e:
-            log.exception(e)
-            return None
-
-    def delete_doc_by_name(self, name: str) -> bool:
-        try:
-            with get_db() as db:
-                db.query(Document).filter_by(name=name).delete()
-                db.commit()
-                return True
-        except Exception:
-            return False
-
-
-Documents = DocumentsTable()

backend/open_webui/apps/webui/models/feedbacks.py

@@ -0,0 +1,254 @@
+import logging
+import time
+import uuid
+from typing import Optional
+
+from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.apps.webui.models.chats import Chats
+
+from open_webui.env import SRC_LOG_LEVELS
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+
+####################
+# Feedback DB Schema
+####################
+
+
+class Feedback(Base):
+    __tablename__ = "feedback"
+    id = Column(Text, primary_key=True)
+    user_id = Column(Text)
+    version = Column(BigInteger, default=0)
+    type = Column(Text)
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+    snapshot = Column(JSON, nullable=True)
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class FeedbackModel(BaseModel):
+    id: str
+    user_id: str
+    version: int
+    type: str
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+    snapshot: Optional[dict] = None
+    created_at: int
+    updated_at: int
+
+    model_config = ConfigDict(from_attributes=True)
+
+
+####################
+# Forms
+####################
+
+
+class FeedbackResponse(BaseModel):
+    id: str
+    user_id: str
+    version: int
+    type: str
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+    created_at: int
+    updated_at: int
+
+
+class RatingData(BaseModel):
+    rating: Optional[str | int] = None
+    model_id: Optional[str] = None
+    sibling_model_ids: Optional[list[str]] = None
+    reason: Optional[str] = None
+    comment: Optional[str] = None
+    model_config = ConfigDict(extra="allow", protected_namespaces=())
+
+
+class MetaData(BaseModel):
+    arena: Optional[bool] = None
+    chat_id: Optional[str] = None
+    message_id: Optional[str] = None
+    tags: Optional[list[str]] = None
+    model_config = ConfigDict(extra="allow")
+
+
+class SnapshotData(BaseModel):
+    chat: Optional[dict] = None
+    model_config = ConfigDict(extra="allow")
+
+
+class FeedbackForm(BaseModel):
+    type: str
+    data: Optional[RatingData] = None
+    meta: Optional[dict] = None
+    snapshot: Optional[SnapshotData] = None
+    model_config = ConfigDict(extra="allow")
+
+
+class FeedbackTable:
+    def insert_new_feedback(
+        self, user_id: str, form_data: FeedbackForm
+    ) -> Optional[FeedbackModel]:
+        with get_db() as db:
+            id = str(uuid.uuid4())
+            feedback = FeedbackModel(
+                **{
+                    "id": id,
+                    "user_id": user_id,
+                    "version": 0,
+                    **form_data.model_dump(),
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+            try:
+                result = Feedback(**feedback.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return FeedbackModel.model_validate(result)
+                else:
+                    return None
+            except Exception as e:
+                print(e)
+                return None
+
+    def get_feedback_by_id(self, id: str) -> Optional[FeedbackModel]:
+        try:
+            with get_db() as db:
+                feedback = db.query(Feedback).filter_by(id=id).first()
+                if not feedback:
+                    return None
+                return FeedbackModel.model_validate(feedback)
+        except Exception:
+            return None
+
+    def get_feedback_by_id_and_user_id(
+        self, id: str, user_id: str
+    ) -> Optional[FeedbackModel]:
+        try:
+            with get_db() as db:
+                feedback = db.query(Feedback).filter_by(id=id, user_id=user_id).first()
+                if not feedback:
+                    return None
+                return FeedbackModel.model_validate(feedback)
+        except Exception:
+            return None
+
+    def get_all_feedbacks(self) -> list[FeedbackModel]:
+        with get_db() as db:
+            return [
+                FeedbackModel.model_validate(feedback)
+                for feedback in db.query(Feedback)
+                .order_by(Feedback.updated_at.desc())
+                .all()
+            ]
+
+    def get_feedbacks_by_type(self, type: str) -> list[FeedbackModel]:
+        with get_db() as db:
+            return [
+                FeedbackModel.model_validate(feedback)
+                for feedback in db.query(Feedback)
+                .filter_by(type=type)
+                .order_by(Feedback.updated_at.desc())
+                .all()
+            ]
+
+    def get_feedbacks_by_user_id(self, user_id: str) -> list[FeedbackModel]:
+        with get_db() as db:
+            return [
+                FeedbackModel.model_validate(feedback)
+                for feedback in db.query(Feedback)
+                .filter_by(user_id=user_id)
+                .order_by(Feedback.updated_at.desc())
+                .all()
+            ]
+
+    def update_feedback_by_id(
+        self, id: str, form_data: FeedbackForm
+    ) -> Optional[FeedbackModel]:
+        with get_db() as db:
+            feedback = db.query(Feedback).filter_by(id=id).first()
+            if not feedback:
+                return None
+
+            if form_data.data:
+                feedback.data = form_data.data.model_dump()
+            if form_data.meta:
+                feedback.meta = form_data.meta
+            if form_data.snapshot:
+                feedback.snapshot = form_data.snapshot.model_dump()
+
+            feedback.updated_at = int(time.time())
+
+            db.commit()
+            return FeedbackModel.model_validate(feedback)
+
+    def update_feedback_by_id_and_user_id(
+        self, id: str, user_id: str, form_data: FeedbackForm
+    ) -> Optional[FeedbackModel]:
+        with get_db() as db:
+            feedback = db.query(Feedback).filter_by(id=id, user_id=user_id).first()
+            if not feedback:
+                return None
+
+            if form_data.data:
+                feedback.data = form_data.data.model_dump()
+            if form_data.meta:
+                feedback.meta = form_data.meta
+            if form_data.snapshot:
+                feedback.snapshot = form_data.snapshot.model_dump()
+
+            feedback.updated_at = int(time.time())
+
+            db.commit()
+            return FeedbackModel.model_validate(feedback)
+
+    def delete_feedback_by_id(self, id: str) -> bool:
+        with get_db() as db:
+            feedback = db.query(Feedback).filter_by(id=id).first()
+            if not feedback:
+                return False
+            db.delete(feedback)
+            db.commit()
+            return True
+
+    def delete_feedback_by_id_and_user_id(self, id: str, user_id: str) -> bool:
+        with get_db() as db:
+            feedback = db.query(Feedback).filter_by(id=id, user_id=user_id).first()
+            if not feedback:
+                return False
+            db.delete(feedback)
+            db.commit()
+            return True
+
+    def delete_feedbacks_by_user_id(self, user_id: str) -> bool:
+        with get_db() as db:
+            feedbacks = db.query(Feedback).filter_by(user_id=user_id).all()
+            if not feedbacks:
+                return False
+            for feedback in feedbacks:
+                db.delete(feedback)
+            db.commit()
+            return True
+
+    def delete_all_feedbacks(self) -> bool:
+        with get_db() as db:
+            feedbacks = db.query(Feedback).all()
+            if not feedbacks:
+                return False
+            for feedback in feedbacks:
+                db.delete(feedback)
+            db.commit()
+            return True
+
+
+Feedbacks = FeedbackTable()

backend/open_webui/apps/webui/models/files.py

@@ -17,14 +17,15 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
 class File(Base):
     __tablename__ = "file"
-
     id = Column(String, primary_key=True)
     user_id = Column(String)
     hash = Column(Text, nullable=True)
 
     filename = Column(Text)
+    path = Column(Text, nullable=True)
+
     data = Column(JSON, nullable=True)
-    meta = Column(JSONField)
+    meta = Column(JSON, nullable=True)
 
     created_at = Column(BigInteger)
     updated_at = Column(BigInteger)
@@ -38,11 +39,13 @@ class FileModel(BaseModel):
     hash: Optional[str] = None
 
     filename: str
-    data: Optional[dict] = None
-    meta: dict
+    path: Optional[str] = None
 
-    created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+    created_at: Optional[int]  # timestamp in epoch
+    updated_at: Optional[int]  # timestamp in epoch
 
 
 ####################
@@ -50,6 +53,14 @@ class FileModel(BaseModel):
 ####################
 
 
+class FileMeta(BaseModel):
+    name: Optional[str] = None
+    content_type: Optional[str] = None
+    size: Optional[int] = None
+
+    model_config = ConfigDict(extra="allow")
+
+
 class FileModelResponse(BaseModel):
     id: str
     user_id: str
@@ -57,16 +68,26 @@ class FileModelResponse(BaseModel):
 
     filename: str
     data: Optional[dict] = None
-    meta: dict
+    meta: FileMeta
 
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
+    model_config = ConfigDict(extra="allow")
+
+
+class FileMetadataResponse(BaseModel):
+    id: str
+    meta: dict
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
 
 class FileForm(BaseModel):
     id: str
     hash: Optional[str] = None
     filename: str
+    path: str
     data: dict = {}
     meta: dict = {}
 
@@ -104,6 +125,19 @@ class FilesTable:
             except Exception:
                 return None
 
+    def get_file_metadata_by_id(self, id: str) -> Optional[FileMetadataResponse]:
+        with get_db() as db:
+            try:
+                file = db.get(File, id)
+                return FileMetadataResponse(
+                    id=file.id,
+                    meta=file.meta,
+                    created_at=file.created_at,
+                    updated_at=file.updated_at,
+                )
+            except Exception:
+                return None
+
     def get_files(self) -> list[FileModel]:
         with get_db() as db:
             return [FileModel.model_validate(file) for file in db.query(File).all()]
@@ -118,6 +152,21 @@ class FilesTable:
                 .all()
             ]
 
+    def get_file_metadatas_by_ids(self, ids: list[str]) -> list[FileMetadataResponse]:
+        with get_db() as db:
+            return [
+                FileMetadataResponse(
+                    id=file.id,
+                    meta=file.meta,
+                    created_at=file.created_at,
+                    updated_at=file.updated_at,
+                )
+                for file in db.query(File)
+                .filter(File.id.in_(ids))
+                .order_by(File.updated_at.desc())
+                .all()
+            ]
+
     def get_files_by_user_id(self, user_id: str) -> list[FileModel]:
         with get_db() as db:
             return [

backend/open_webui/apps/webui/models/folders.py

@@ -0,0 +1,271 @@
+import logging
+import time
+import uuid
+from typing import Optional
+
+from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.apps.webui.models.chats import Chats
+
+from open_webui.env import SRC_LOG_LEVELS
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+
+####################
+# Folder DB Schema
+####################
+
+
+class Folder(Base):
+    __tablename__ = "folder"
+    id = Column(Text, primary_key=True)
+    parent_id = Column(Text, nullable=True)
+    user_id = Column(Text)
+    name = Column(Text)
+    items = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+    is_expanded = Column(Boolean, default=False)
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class FolderModel(BaseModel):
+    id: str
+    parent_id: Optional[str] = None
+    user_id: str
+    name: str
+    items: Optional[dict] = None
+    meta: Optional[dict] = None
+    is_expanded: bool = False
+    created_at: int
+    updated_at: int
+
+    model_config = ConfigDict(from_attributes=True)
+
+
+####################
+# Forms
+####################
+
+
+class FolderForm(BaseModel):
+    name: str
+    model_config = ConfigDict(extra="allow")
+
+
+class FolderTable:
+    def insert_new_folder(
+        self, user_id: str, name: str, parent_id: Optional[str] = None
+    ) -> Optional[FolderModel]:
+        with get_db() as db:
+            id = str(uuid.uuid4())
+            folder = FolderModel(
+                **{
+                    "id": id,
+                    "user_id": user_id,
+                    "name": name,
+                    "parent_id": parent_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+            try:
+                result = Folder(**folder.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return FolderModel.model_validate(result)
+                else:
+                    return None
+            except Exception as e:
+                print(e)
+                return None
+
+    def get_folder_by_id_and_user_id(
+        self, id: str, user_id: str
+    ) -> Optional[FolderModel]:
+        try:
+            with get_db() as db:
+                folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
+
+                if not folder:
+                    return None
+
+                return FolderModel.model_validate(folder)
+        except Exception:
+            return None
+
+    def get_children_folders_by_id_and_user_id(
+        self, id: str, user_id: str
+    ) -> Optional[FolderModel]:
+        try:
+            with get_db() as db:
+                folders = []
+
+                def get_children(folder):
+                    children = self.get_folders_by_parent_id_and_user_id(
+                        folder.id, user_id
+                    )
+                    for child in children:
+                        get_children(child)
+                        folders.append(child)
+
+                folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
+                if not folder:
+                    return None
+
+                get_children(folder)
+                return folders
+        except Exception:
+            return None
+
+    def get_folders_by_user_id(self, user_id: str) -> list[FolderModel]:
+        with get_db() as db:
+            return [
+                FolderModel.model_validate(folder)
+                for folder in db.query(Folder).filter_by(user_id=user_id).all()
+            ]
+
+    def get_folder_by_parent_id_and_user_id_and_name(
+        self, parent_id: Optional[str], user_id: str, name: str
+    ) -> Optional[FolderModel]:
+        try:
+            with get_db() as db:
+                # Check if folder exists
+                folder = (
+                    db.query(Folder)
+                    .filter_by(parent_id=parent_id, user_id=user_id)
+                    .filter(Folder.name.ilike(name))
+                    .first()
+                )
+
+                if not folder:
+                    return None
+
+                return FolderModel.model_validate(folder)
+        except Exception as e:
+            log.error(f"get_folder_by_parent_id_and_user_id_and_name: {e}")
+            return None
+
+    def get_folders_by_parent_id_and_user_id(
+        self, parent_id: Optional[str], user_id: str
+    ) -> list[FolderModel]:
+        with get_db() as db:
+            return [
+                FolderModel.model_validate(folder)
+                for folder in db.query(Folder)
+                .filter_by(parent_id=parent_id, user_id=user_id)
+                .all()
+            ]
+
+    def update_folder_parent_id_by_id_and_user_id(
+        self,
+        id: str,
+        user_id: str,
+        parent_id: str,
+    ) -> Optional[FolderModel]:
+        try:
+            with get_db() as db:
+                folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
+
+                if not folder:
+                    return None
+
+                folder.parent_id = parent_id
+                folder.updated_at = int(time.time())
+
+                db.commit()
+
+                return FolderModel.model_validate(folder)
+        except Exception as e:
+            log.error(f"update_folder: {e}")
+            return
+
+    def update_folder_name_by_id_and_user_id(
+        self, id: str, user_id: str, name: str
+    ) -> Optional[FolderModel]:
+        try:
+            with get_db() as db:
+                folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
+
+                if not folder:
+                    return None
+
+                existing_folder = (
+                    db.query(Folder)
+                    .filter_by(name=name, parent_id=folder.parent_id, user_id=user_id)
+                    .first()
+                )
+
+                if existing_folder:
+                    return None
+
+                folder.name = name
+                folder.updated_at = int(time.time())
+
+                db.commit()
+
+                return FolderModel.model_validate(folder)
+        except Exception as e:
+            log.error(f"update_folder: {e}")
+            return
+
+    def update_folder_is_expanded_by_id_and_user_id(
+        self, id: str, user_id: str, is_expanded: bool
+    ) -> Optional[FolderModel]:
+        try:
+            with get_db() as db:
+                folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
+
+                if not folder:
+                    return None
+
+                folder.is_expanded = is_expanded
+                folder.updated_at = int(time.time())
+
+                db.commit()
+
+                return FolderModel.model_validate(folder)
+        except Exception as e:
+            log.error(f"update_folder: {e}")
+            return
+
+    def delete_folder_by_id_and_user_id(self, id: str, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                folder = db.query(Folder).filter_by(id=id, user_id=user_id).first()
+                if not folder:
+                    return False
+
+                # Delete all chats in the folder
+                Chats.delete_chats_by_user_id_and_folder_id(user_id, folder.id)
+
+                # Delete all children folders
+                def delete_children(folder):
+                    folder_children = self.get_folders_by_parent_id_and_user_id(
+                        folder.id, user_id
+                    )
+                    for folder_child in folder_children:
+                        Chats.delete_chats_by_user_id_and_folder_id(
+                            user_id, folder_child.id
+                        )
+                        delete_children(folder_child)
+
+                        folder = db.query(Folder).filter_by(id=folder_child.id).first()
+                        db.delete(folder)
+                        db.commit()
+
+                delete_children(folder)
+                db.delete(folder)
+                db.commit()
+                return True
+        except Exception as e:
+            log.error(f"delete_folder: {e}")
+            return False
+
+
+Folders = FolderTable()

backend/open_webui/apps/webui/models/groups.py

@@ -0,0 +1,186 @@
+import json
+import logging
+import time
+from typing import Optional
+import uuid
+
+from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.apps.webui.models.files import FileMetadataResponse
+
+
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, String, Text, JSON, func
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+####################
+# UserGroup DB Schema
+####################
+
+
+class Group(Base):
+    __tablename__ = "group"
+
+    id = Column(Text, unique=True, primary_key=True)
+    user_id = Column(Text)
+
+    name = Column(Text)
+    description = Column(Text)
+
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+
+    permissions = Column(JSON, nullable=True)
+    user_ids = Column(JSON, nullable=True)
+
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class GroupModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+    id: str
+    user_id: str
+
+    name: str
+    description: str
+
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+    permissions: Optional[dict] = None
+    user_ids: list[str] = []
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class GroupResponse(BaseModel):
+    id: str
+    user_id: str
+    name: str
+    description: str
+    permissions: Optional[dict] = None
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+    user_ids: list[str] = []
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+class GroupForm(BaseModel):
+    name: str
+    description: str
+
+
+class GroupUpdateForm(GroupForm):
+    permissions: Optional[dict] = None
+    user_ids: Optional[list[str]] = None
+    admin_ids: Optional[list[str]] = None
+
+
+class GroupTable:
+    def insert_new_group(
+        self, user_id: str, form_data: GroupForm
+    ) -> Optional[GroupModel]:
+        with get_db() as db:
+            group = GroupModel(
+                **{
+                    **form_data.model_dump(),
+                    "id": str(uuid.uuid4()),
+                    "user_id": user_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            try:
+                result = Group(**group.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return GroupModel.model_validate(result)
+                else:
+                    return None
+
+            except Exception:
+                return None
+
+    def get_groups(self) -> list[GroupModel]:
+        with get_db() as db:
+            return [
+                GroupModel.model_validate(group)
+                for group in db.query(Group).order_by(Group.updated_at.desc()).all()
+            ]
+
+    def get_groups_by_member_id(self, user_id: str) -> list[GroupModel]:
+        with get_db() as db:
+            return [
+                GroupModel.model_validate(group)
+                for group in db.query(Group)
+                .filter(
+                    func.json_array_length(Group.user_ids) > 0
+                )  # Ensure array exists
+                .filter(
+                    Group.user_ids.cast(String).like(f'%"{user_id}"%')
+                )  # String-based check
+                .order_by(Group.updated_at.desc())
+                .all()
+            ]
+
+    def get_group_by_id(self, id: str) -> Optional[GroupModel]:
+        try:
+            with get_db() as db:
+                group = db.query(Group).filter_by(id=id).first()
+                return GroupModel.model_validate(group) if group else None
+        except Exception:
+            return None
+
+    def update_group_by_id(
+        self, id: str, form_data: GroupUpdateForm, overwrite: bool = False
+    ) -> Optional[GroupModel]:
+        try:
+            with get_db() as db:
+                db.query(Group).filter_by(id=id).update(
+                    {
+                        **form_data.model_dump(exclude_none=True),
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+                return self.get_group_by_id(id=id)
+        except Exception as e:
+            log.exception(e)
+            return None
+
+    def delete_group_by_id(self, id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Group).filter_by(id=id).delete()
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def delete_all_groups(self) -> bool:
+        with get_db() as db:
+            try:
+                db.query(Group).delete()
+                db.commit()
+
+                return True
+            except Exception:
+                return False
+
+
+Groups = GroupTable()

backend/open_webui/apps/webui/models/knowledge.py

@@ -6,9 +6,15 @@ import uuid
 
 from open_webui.apps.webui.internal.db import Base, get_db
 from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.apps.webui.models.files import FileMetadataResponse
+from open_webui.apps.webui.models.users import Users, UserResponse
+
+
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text, JSON
 
+from open_webui.utils.access_control import has_access
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -30,6 +36,23 @@ class Knowledge(Base):
     data = Column(JSON, nullable=True)
     meta = Column(JSON, nullable=True)
 
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
     created_at = Column(BigInteger)
     updated_at = Column(BigInteger)
 
@@ -46,6 +69,8 @@ class KnowledgeModel(BaseModel):
     data: Optional[dict] = None
     meta: Optional[dict] = None
 
+    access_control: Optional[dict] = None
+
     created_at: int  # timestamp in epoch
     updated_at: int  # timestamp in epoch
 
@@ -55,26 +80,23 @@ class KnowledgeModel(BaseModel):
 ####################
 
 
-class KnowledgeResponse(BaseModel):
-    id: str
-    name: str
-    description: str
-    data: Optional[dict] = None
-    meta: Optional[dict] = None
-    created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
+class KnowledgeUserModel(KnowledgeModel):
+    user: Optional[UserResponse] = None
+
+
+class KnowledgeResponse(KnowledgeModel):
+    files: Optional[list[FileMetadataResponse | dict]] = None
+
+
+class KnowledgeUserResponse(KnowledgeUserModel):
+    files: Optional[list[FileMetadataResponse | dict]] = None
 
 
 class KnowledgeForm(BaseModel):
     name: str
     description: str
     data: Optional[dict] = None
-
-
-class KnowledgeUpdateForm(BaseModel):
-    name: Optional[str] = None
-    description: Optional[str] = None
-    data: Optional[dict] = None
+    access_control: Optional[dict] = None
 
 
 class KnowledgeTable:
@@ -104,14 +126,33 @@ class KnowledgeTable:
             except Exception:
                 return None
 
-    def get_knowledge_items(self) -> list[KnowledgeModel]:
+    def get_knowledge_bases(self) -> list[KnowledgeUserModel]:
         with get_db() as db:
-            return [
-                KnowledgeModel.model_validate(knowledge)
-                for knowledge in db.query(Knowledge)
-                .order_by(Knowledge.updated_at.desc())
-                .all()
-            ]
+            knowledge_bases = []
+            for knowledge in (
+                db.query(Knowledge).order_by(Knowledge.updated_at.desc()).all()
+            ):
+                user = Users.get_user_by_id(knowledge.user_id)
+                knowledge_bases.append(
+                    KnowledgeUserModel.model_validate(
+                        {
+                            **KnowledgeModel.model_validate(knowledge).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+            return knowledge_bases
+
+    def get_knowledge_bases_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[KnowledgeUserModel]:
+        knowledge_bases = self.get_knowledge_bases()
+        return [
+            knowledge_base
+            for knowledge_base in knowledge_bases
+            if knowledge_base.user_id == user_id
+            or has_access(user_id, permission, knowledge_base.access_control)
+        ]
 
     def get_knowledge_by_id(self, id: str) -> Optional[KnowledgeModel]:
         try:
@@ -122,14 +163,32 @@ class KnowledgeTable:
             return None
 
     def update_knowledge_by_id(
-        self, id: str, form_data: KnowledgeUpdateForm, overwrite: bool = False
+        self, id: str, form_data: KnowledgeForm, overwrite: bool = False
     ) -> Optional[KnowledgeModel]:
         try:
             with get_db() as db:
                 knowledge = self.get_knowledge_by_id(id=id)
                 db.query(Knowledge).filter_by(id=id).update(
                     {
-                        **form_data.model_dump(exclude_none=True),
+                        **form_data.model_dump(),
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+                return self.get_knowledge_by_id(id=id)
+        except Exception as e:
+            log.exception(e)
+            return None
+
+    def update_knowledge_data_by_id(
+        self, id: str, data: dict
+    ) -> Optional[KnowledgeModel]:
+        try:
+            with get_db() as db:
+                knowledge = self.get_knowledge_by_id(id=id)
+                db.query(Knowledge).filter_by(id=id).update(
+                    {
+                        "data": data,
                         "updated_at": int(time.time()),
                     }
                 )
@@ -148,5 +207,15 @@ class KnowledgeTable:
         except Exception:
             return False
 
+    def delete_all_knowledge(self) -> bool:
+        with get_db() as db:
+            try:
+                db.query(Knowledge).delete()
+                db.commit()
+
+                return True
+            except Exception:
+                return False
+
 
 Knowledges = KnowledgeTable()

backend/open_webui/apps/webui/models/models.py

@@ -4,8 +4,19 @@ from typing import Optional
 
 from open_webui.apps.webui.internal.db import Base, JSONField, get_db
 from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.apps.webui.models.users import Users, UserResponse
+
+
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, Text
+
+from sqlalchemy import or_, and_, func
+from sqlalchemy.dialects import postgresql, sqlite
+from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
+
+
+from open_webui.utils.access_control import has_access
+
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -67,6 +78,25 @@ class Model(Base):
         Holds a JSON encoded blob of metadata, see `ModelMeta`.
     """
 
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
+    is_active = Column(Boolean, default=True)
+
     updated_at = Column(BigInteger)
     created_at = Column(BigInteger)
 
@@ -80,6 +110,9 @@ class ModelModel(BaseModel):
     params: ModelParams
     meta: ModelMeta
 
+    access_control: Optional[dict] = None
+
+    is_active: bool
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
 
@@ -91,12 +124,12 @@ class ModelModel(BaseModel):
 ####################
 
 
-class ModelResponse(BaseModel):
-    id: str
-    name: str
-    meta: ModelMeta
-    updated_at: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
+class ModelUserResponse(ModelModel):
+    user: Optional[UserResponse] = None
+
+
+class ModelResponse(ModelModel):
+    pass
 
 
 class ModelForm(BaseModel):
@@ -105,6 +138,8 @@ class ModelForm(BaseModel):
     name: str
     meta: ModelMeta
     params: ModelParams
+    access_control: Optional[dict] = None
+    is_active: bool = True
 
 
 class ModelsTable:
@@ -138,6 +173,39 @@ class ModelsTable:
         with get_db() as db:
             return [ModelModel.model_validate(model) for model in db.query(Model).all()]
 
+    def get_models(self) -> list[ModelUserResponse]:
+        with get_db() as db:
+            models = []
+            for model in db.query(Model).filter(Model.base_model_id != None).all():
+                user = Users.get_user_by_id(model.user_id)
+                models.append(
+                    ModelUserResponse.model_validate(
+                        {
+                            **ModelModel.model_validate(model).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+            return models
+
+    def get_base_models(self) -> list[ModelModel]:
+        with get_db() as db:
+            return [
+                ModelModel.model_validate(model)
+                for model in db.query(Model).filter(Model.base_model_id == None).all()
+            ]
+
+    def get_models_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[ModelUserResponse]:
+        models = self.get_models()
+        return [
+            model
+            for model in models
+            if model.user_id == user_id
+            or has_access(user_id, permission, model.access_control)
+        ]
+
     def get_model_by_id(self, id: str) -> Optional[ModelModel]:
         try:
             with get_db() as db:
@@ -146,6 +214,23 @@ class ModelsTable:
         except Exception:
             return None
 
+    def toggle_model_by_id(self, id: str) -> Optional[ModelModel]:
+        with get_db() as db:
+            try:
+                is_active = db.query(Model).filter_by(id=id).first().is_active
+
+                db.query(Model).filter_by(id=id).update(
+                    {
+                        "is_active": not is_active,
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+
+                return self.get_model_by_id(id)
+            except Exception:
+                return None
+
     def update_model_by_id(self, id: str, model: ModelForm) -> Optional[ModelModel]:
         try:
             with get_db() as db:
@@ -153,7 +238,7 @@ class ModelsTable:
                 result = (
                     db.query(Model)
                     .filter_by(id=id)
-                    .update(model.model_dump(exclude={"id"}, exclude_none=True))
+                    .update(model.model_dump(exclude={"id"}))
                 )
                 db.commit()
 
@@ -175,5 +260,15 @@ class ModelsTable:
         except Exception:
             return False
 
+    def delete_all_models(self) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Model).delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
 
 Models = ModelsTable()

backend/open_webui/apps/webui/models/prompts.py

@@ -2,8 +2,12 @@ import time
 from typing import Optional
 
 from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.apps.webui.models.users import Users, UserResponse
+
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
+from sqlalchemy import BigInteger, Column, String, Text, JSON
+
+from open_webui.utils.access_control import has_access
 
 ####################
 # Prompts DB Schema
@@ -19,6 +23,23 @@ class Prompt(Base):
     content = Column(Text)
     timestamp = Column(BigInteger)
 
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
 
 class PromptModel(BaseModel):
     command: str
@@ -27,6 +48,7 @@ class PromptModel(BaseModel):
     content: str
     timestamp: int  # timestamp in epoch
 
+    access_control: Optional[dict] = None
     model_config = ConfigDict(from_attributes=True)
 
 
@@ -35,10 +57,15 @@ class PromptModel(BaseModel):
 ####################
 
 
+class PromptUserResponse(PromptModel):
+    user: Optional[UserResponse] = None
+
+
 class PromptForm(BaseModel):
     command: str
     title: str
     content: str
+    access_control: Optional[dict] = None
 
 
 class PromptsTable:
@@ -48,16 +75,14 @@ class PromptsTable:
         prompt = PromptModel(
             **{
                 "user_id": user_id,
-                "command": form_data.command,
-                "title": form_data.title,
-                "content": form_data.content,
+                **form_data.model_dump(),
                 "timestamp": int(time.time()),
             }
         )
 
         try:
             with get_db() as db:
-                result = Prompt(**prompt.dict())
+                result = Prompt(**prompt.model_dump())
                 db.add(result)
                 db.commit()
                 db.refresh(result)
@@ -76,11 +101,34 @@ class PromptsTable:
         except Exception:
             return None
 
-    def get_prompts(self) -> list[PromptModel]:
+    def get_prompts(self) -> list[PromptUserResponse]:
         with get_db() as db:
-            return [
-                PromptModel.model_validate(prompt) for prompt in db.query(Prompt).all()
-            ]
+            prompts = []
+
+            for prompt in db.query(Prompt).order_by(Prompt.timestamp.desc()).all():
+                user = Users.get_user_by_id(prompt.user_id)
+                prompts.append(
+                    PromptUserResponse.model_validate(
+                        {
+                            **PromptModel.model_validate(prompt).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+
+            return prompts
+
+    def get_prompts_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[PromptUserResponse]:
+        prompts = self.get_prompts()
+
+        return [
+            prompt
+            for prompt in prompts
+            if prompt.user_id == user_id
+            or has_access(user_id, permission, prompt.access_control)
+        ]
 
     def update_prompt_by_command(
         self, command: str, form_data: PromptForm
@@ -90,6 +138,7 @@ class PromptsTable:
                 prompt = db.query(Prompt).filter_by(command=command).first()
                 prompt.title = form_data.title
                 prompt.content = form_data.content
+                prompt.access_control = form_data.access_control
                 prompt.timestamp = int(time.time())
                 db.commit()
                 return PromptModel.model_validate(prompt)

backend/open_webui/apps/webui/models/tags.py

@@ -4,53 +4,35 @@ import uuid
 from typing import Optional
 
 from open_webui.apps.webui.internal.db import Base, get_db
+
+
 from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
+from sqlalchemy import BigInteger, Column, String, JSON, PrimaryKeyConstraint
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
 
+
 ####################
 # Tag DB Schema
 ####################
-
-
 class Tag(Base):
     __tablename__ = "tag"
-
-    id = Column(String, primary_key=True)
+    id = Column(String)
     name = Column(String)
     user_id = Column(String)
-    data = Column(Text, nullable=True)
+    meta = Column(JSON, nullable=True)
 
-
-class ChatIdTag(Base):
-    __tablename__ = "chatidtag"
-
-    id = Column(String, primary_key=True)
-    tag_name = Column(String)
-    chat_id = Column(String)
-    user_id = Column(String)
-    timestamp = Column(BigInteger)
+    # Unique constraint ensuring (id, user_id) is unique, not just the `id` column
+    __table_args__ = (PrimaryKeyConstraint("id", "user_id", name="pk_id_user_id"),)
 
 
 class TagModel(BaseModel):
     id: str
     name: str
     user_id: str
-    data: Optional[str] = None
-
-    model_config = ConfigDict(from_attributes=True)
-
-
-class ChatIdTagModel(BaseModel):
-    id: str
-    tag_name: str
-    chat_id: str
-    user_id: str
-    timestamp: int
-
+    meta: Optional[dict] = None
     model_config = ConfigDict(from_attributes=True)
 
 
@@ -59,23 +41,15 @@ class ChatIdTagModel(BaseModel):
 ####################
 
 
-class ChatIdTagForm(BaseModel):
-    tag_name: str
+class TagChatIdForm(BaseModel):
+    name: str
     chat_id: str
 
 
-class TagChatIdsResponse(BaseModel):
-    chat_ids: list[str]
-
-
-class ChatTagsResponse(BaseModel):
-    tags: list[str]
-
-
 class TagTable:
     def insert_new_tag(self, name: str, user_id: str) -> Optional[TagModel]:
         with get_db() as db:
-            id = str(uuid.uuid4())
+            id = name.replace(" ", "_").lower()
             tag = TagModel(**{"id": id, "user_id": user_id, "name": name})
             try:
                 result = Tag(**tag.model_dump())
@@ -86,177 +60,50 @@ class TagTable:
                     return TagModel.model_validate(result)
                 else:
                     return None
-            except Exception:
+            except Exception as e:
+                print(e)
                 return None
 
     def get_tag_by_name_and_user_id(
         self, name: str, user_id: str
     ) -> Optional[TagModel]:
         try:
+            id = name.replace(" ", "_").lower()
             with get_db() as db:
-                tag = db.query(Tag).filter_by(name=name, user_id=user_id).first()
+                tag = db.query(Tag).filter_by(id=id, user_id=user_id).first()
                 return TagModel.model_validate(tag)
         except Exception:
             return None
 
-    def add_tag_to_chat(
-        self, user_id: str, form_data: ChatIdTagForm
-    ) -> Optional[ChatIdTagModel]:
-        tag = self.get_tag_by_name_and_user_id(form_data.tag_name, user_id)
-        if tag is None:
-            tag = self.insert_new_tag(form_data.tag_name, user_id)
-
-        id = str(uuid.uuid4())
-        chatIdTag = ChatIdTagModel(
-            **{
-                "id": id,
-                "user_id": user_id,
-                "chat_id": form_data.chat_id,
-                "tag_name": tag.name,
-                "timestamp": int(time.time()),
-            }
-        )
-        try:
-            with get_db() as db:
-                result = ChatIdTag(**chatIdTag.model_dump())
-                db.add(result)
-                db.commit()
-                db.refresh(result)
-                if result:
-                    return ChatIdTagModel.model_validate(result)
-                else:
-                    return None
-        except Exception:
-            return None
-
     def get_tags_by_user_id(self, user_id: str) -> list[TagModel]:
         with get_db() as db:
-            tag_names = [
-                chat_id_tag.tag_name
-                for chat_id_tag in (
-                    db.query(ChatIdTag)
-                    .filter_by(user_id=user_id)
-                    .order_by(ChatIdTag.timestamp.desc())
-                    .all()
-                )
-            ]
-
             return [
                 TagModel.model_validate(tag)
-                for tag in (
-                    db.query(Tag)
-                    .filter_by(user_id=user_id)
-                    .filter(Tag.name.in_(tag_names))
-                    .all()
-                )
+                for tag in (db.query(Tag).filter_by(user_id=user_id).all())
             ]
 
-    def get_tags_by_chat_id_and_user_id(
-        self, chat_id: str, user_id: str
+    def get_tags_by_ids_and_user_id(
+        self, ids: list[str], user_id: str
     ) -> list[TagModel]:
         with get_db() as db:
-            tag_names = [
-                chat_id_tag.tag_name
-                for chat_id_tag in (
-                    db.query(ChatIdTag)
-                    .filter_by(user_id=user_id, chat_id=chat_id)
-                    .order_by(ChatIdTag.timestamp.desc())
-                    .all()
-                )
-            ]
-
             return [
                 TagModel.model_validate(tag)
                 for tag in (
-                    db.query(Tag)
-                    .filter_by(user_id=user_id)
-                    .filter(Tag.name.in_(tag_names))
-                    .all()
+                    db.query(Tag).filter(Tag.id.in_(ids), Tag.user_id == user_id).all()
                 )
             ]
 
-    def get_chat_ids_by_tag_name_and_user_id(
-        self, tag_name: str, user_id: str
-    ) -> list[ChatIdTagModel]:
-        with get_db() as db:
-            return [
-                ChatIdTagModel.model_validate(chat_id_tag)
-                for chat_id_tag in (
-                    db.query(ChatIdTag)
-                    .filter_by(user_id=user_id, tag_name=tag_name)
-                    .order_by(ChatIdTag.timestamp.desc())
-                    .all()
-                )
-            ]
-
-    def count_chat_ids_by_tag_name_and_user_id(
-        self, tag_name: str, user_id: str
-    ) -> int:
-        with get_db() as db:
-            return (
-                db.query(ChatIdTag)
-                .filter_by(tag_name=tag_name, user_id=user_id)
-                .count()
-            )
-
-    def delete_tag_by_tag_name_and_user_id(self, tag_name: str, user_id: str) -> bool:
+    def delete_tag_by_name_and_user_id(self, name: str, user_id: str) -> bool:
         try:
             with get_db() as db:
-                res = (
-                    db.query(ChatIdTag)
-                    .filter_by(tag_name=tag_name, user_id=user_id)
-                    .delete()
-                )
+                id = name.replace(" ", "_").lower()
+                res = db.query(Tag).filter_by(id=id, user_id=user_id).delete()
                 log.debug(f"res: {res}")
                 db.commit()
-
-                tag_count = self.count_chat_ids_by_tag_name_and_user_id(
-                    tag_name, user_id
-                )
-                if tag_count == 0:
-                    # Remove tag item from Tag col as well
-                    db.query(Tag).filter_by(name=tag_name, user_id=user_id).delete()
-                    db.commit()
                 return True
         except Exception as e:
             log.error(f"delete_tag: {e}")
             return False
 
-    def delete_tag_by_tag_name_and_chat_id_and_user_id(
-        self, tag_name: str, chat_id: str, user_id: str
-    ) -> bool:
-        try:
-            with get_db() as db:
-                res = (
-                    db.query(ChatIdTag)
-                    .filter_by(tag_name=tag_name, chat_id=chat_id, user_id=user_id)
-                    .delete()
-                )
-                log.debug(f"res: {res}")
-                db.commit()
-
-                tag_count = self.count_chat_ids_by_tag_name_and_user_id(
-                    tag_name, user_id
-                )
-                if tag_count == 0:
-                    # Remove tag item from Tag col as well
-                    db.query(Tag).filter_by(name=tag_name, user_id=user_id).delete()
-                    db.commit()
-
-                return True
-        except Exception as e:
-            log.error(f"delete_tag: {e}")
-            return False
-
-    def delete_tags_by_chat_id_and_user_id(self, chat_id: str, user_id: str) -> bool:
-        tags = self.get_tags_by_chat_id_and_user_id(chat_id, user_id)
-
-        for tag in tags:
-            self.delete_tag_by_tag_name_and_chat_id_and_user_id(
-                tag.tag_name, chat_id, user_id
-            )
-
-        return True
-
 
 Tags = TagTable()

backend/open_webui/apps/webui/models/tools.py

@@ -3,10 +3,13 @@ import time
 from typing import Optional
 
 from open_webui.apps.webui.internal.db import Base, JSONField, get_db
-from open_webui.apps.webui.models.users import Users
+from open_webui.apps.webui.models.users import Users, UserResponse
 from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
+from sqlalchemy import BigInteger, Column, String, Text, JSON
+
+from open_webui.utils.access_control import has_access
+
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -26,6 +29,24 @@ class Tool(Base):
     specs = Column(JSONField)
     meta = Column(JSONField)
     valves = Column(JSONField)
+
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
     updated_at = Column(BigInteger)
     created_at = Column(BigInteger)
 
@@ -42,6 +63,8 @@ class ToolModel(BaseModel):
     content: str
     specs: list[dict]
     meta: ToolMeta
+    access_control: Optional[dict] = None
+
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
 
@@ -58,15 +81,21 @@ class ToolResponse(BaseModel):
     user_id: str
     name: str
     meta: ToolMeta
+    access_control: Optional[dict] = None
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
 
 
+class ToolUserResponse(ToolResponse):
+    user: Optional[UserResponse] = None
+
+
 class ToolForm(BaseModel):
     id: str
     name: str
     content: str
     meta: ToolMeta
+    access_control: Optional[dict] = None
 
 
 class ToolValves(BaseModel):
@@ -109,9 +138,32 @@ class ToolsTable:
         except Exception:
             return None
 
-    def get_tools(self) -> list[ToolModel]:
+    def get_tools(self) -> list[ToolUserResponse]:
         with get_db() as db:
-            return [ToolModel.model_validate(tool) for tool in db.query(Tool).all()]
+            tools = []
+            for tool in db.query(Tool).order_by(Tool.updated_at.desc()).all():
+                user = Users.get_user_by_id(tool.user_id)
+                tools.append(
+                    ToolUserResponse.model_validate(
+                        {
+                            **ToolModel.model_validate(tool).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+            return tools
+
+    def get_tools_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[ToolUserResponse]:
+        tools = self.get_tools()
+
+        return [
+            tool
+            for tool in tools
+            if tool.user_id == user_id
+            or has_access(user_id, permission, tool.access_control)
+        ]
 
     def get_tool_valves_by_id(self, id: str) -> Optional[dict]:
         try:

backend/open_webui/apps/webui/models/users.py

@@ -62,6 +62,14 @@ class UserModel(BaseModel):
 ####################
 
 
+class UserResponse(BaseModel):
+    id: str
+    name: str
+    email: str
+    role: str
+    profile_image_url: str
+
+
 class UserRoleUpdateForm(BaseModel):
     id: str
     role: str

backend/open_webui/apps/webui/routers/auths.py

@@ -1,10 +1,15 @@
 import re
 import uuid
+import time
+import datetime
+import logging
 
 from open_webui.apps.webui.models.auths import (
     AddUserForm,
     ApiKey,
     Auths,
+    Token,
+    LdapForm,
     SigninForm,
     SigninResponse,
     SignupForm,
@@ -13,11 +18,15 @@ from open_webui.apps.webui.models.auths import (
     UserResponse,
 )
 from open_webui.apps.webui.models.users import Users
-from open_webui.config import WEBUI_AUTH
+
 from open_webui.constants import ERROR_MESSAGES, WEBHOOK_MESSAGES
 from open_webui.env import (
+    WEBUI_AUTH,
     WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
     WEBUI_AUTH_TRUSTED_NAME_HEADER,
+    WEBUI_SESSION_COOKIE_SAME_SITE,
+    WEBUI_SESSION_COOKIE_SECURE,
+    SRC_LOG_LEVELS,
 )
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from fastapi.responses import Response
@@ -27,40 +36,78 @@ from open_webui.utils.utils import (
     create_api_key,
     create_token,
     get_admin_user,
+    get_verified_user,
     get_current_user,
     get_password_hash,
 )
 from open_webui.utils.webhook import post_webhook
+from open_webui.utils.access_control import get_permissions
+
+from typing import Optional, List
+
+from ssl import CERT_REQUIRED, PROTOCOL_TLS
+from ldap3 import Server, Connection, ALL, Tls
+from ldap3.utils.conv import escape_filter_chars
 
 router = APIRouter()
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
+
 ############################
 # GetSessionUser
 ############################
 
 
-@router.get("/", response_model=UserResponse)
+class SessionUserResponse(Token, UserResponse):
+    expires_at: Optional[int] = None
+    permissions: Optional[dict] = None
+
+
+@router.get("/", response_model=SessionUserResponse)
 async def get_session_user(
     request: Request, response: Response, user=Depends(get_current_user)
 ):
+    expires_delta = parse_duration(request.app.state.config.JWT_EXPIRES_IN)
+    expires_at = None
+    if expires_delta:
+        expires_at = int(time.time()) + int(expires_delta.total_seconds())
+
     token = create_token(
         data={"id": user.id},
-        expires_delta=parse_duration(request.app.state.config.JWT_EXPIRES_IN),
+        expires_delta=expires_delta,
+    )
+
+    datetime_expires_at = (
+        datetime.datetime.fromtimestamp(expires_at, datetime.timezone.utc)
+        if expires_at
+        else None
     )
 
     # Set the cookie token
     response.set_cookie(
         key="token",
         value=token,
+        expires=datetime_expires_at,
         httponly=True,  # Ensures the cookie is not accessible via JavaScript
+        samesite=WEBUI_SESSION_COOKIE_SAME_SITE,
+        secure=WEBUI_SESSION_COOKIE_SECURE,
+    )
+
+    user_permissions = get_permissions(
+        user.id, request.app.state.config.USER_PERMISSIONS
     )
 
     return {
+        "token": token,
+        "token_type": "Bearer",
+        "expires_at": expires_at,
         "id": user.id,
         "email": user.email,
         "name": user.name,
         "role": user.role,
         "profile_image_url": user.profile_image_url,
+        "permissions": user_permissions,
     }
 
 
@@ -71,7 +118,7 @@ async def get_session_user(
 
 @router.post("/update/profile", response_model=UserResponse)
 async def update_profile(
-    form_data: UpdateProfileForm, session_user=Depends(get_current_user)
+    form_data: UpdateProfileForm, session_user=Depends(get_verified_user)
 ):
     if session_user:
         user = Users.update_user_by_id(
@@ -109,12 +156,152 @@ async def update_password(
         raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
 
 
+############################
+# LDAP Authentication
+############################
+@router.post("/ldap", response_model=SigninResponse)
+async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
+    ENABLE_LDAP = request.app.state.config.ENABLE_LDAP
+    LDAP_SERVER_LABEL = request.app.state.config.LDAP_SERVER_LABEL
+    LDAP_SERVER_HOST = request.app.state.config.LDAP_SERVER_HOST
+    LDAP_SERVER_PORT = request.app.state.config.LDAP_SERVER_PORT
+    LDAP_ATTRIBUTE_FOR_USERNAME = request.app.state.config.LDAP_ATTRIBUTE_FOR_USERNAME
+    LDAP_SEARCH_BASE = request.app.state.config.LDAP_SEARCH_BASE
+    LDAP_SEARCH_FILTERS = request.app.state.config.LDAP_SEARCH_FILTERS
+    LDAP_APP_DN = request.app.state.config.LDAP_APP_DN
+    LDAP_APP_PASSWORD = request.app.state.config.LDAP_APP_PASSWORD
+    LDAP_USE_TLS = request.app.state.config.LDAP_USE_TLS
+    LDAP_CA_CERT_FILE = request.app.state.config.LDAP_CA_CERT_FILE
+    LDAP_CIPHERS = (
+        request.app.state.config.LDAP_CIPHERS
+        if request.app.state.config.LDAP_CIPHERS
+        else "ALL"
+    )
+
+    if not ENABLE_LDAP:
+        raise HTTPException(400, detail="LDAP authentication is not enabled")
+
+    try:
+        tls = Tls(
+            validate=CERT_REQUIRED,
+            version=PROTOCOL_TLS,
+            ca_certs_file=LDAP_CA_CERT_FILE,
+            ciphers=LDAP_CIPHERS,
+        )
+    except Exception as e:
+        log.error(f"An error occurred on TLS: {str(e)}")
+        raise HTTPException(400, detail=str(e))
+
+    try:
+        server = Server(
+            host=LDAP_SERVER_HOST,
+            port=LDAP_SERVER_PORT,
+            get_info=ALL,
+            use_ssl=LDAP_USE_TLS,
+            tls=tls,
+        )
+        connection_app = Connection(
+            server,
+            LDAP_APP_DN,
+            LDAP_APP_PASSWORD,
+            auto_bind="NONE",
+            authentication="SIMPLE",
+        )
+        if not connection_app.bind():
+            raise HTTPException(400, detail="Application account bind failed")
+
+        search_success = connection_app.search(
+            search_base=LDAP_SEARCH_BASE,
+            search_filter=f"(&({LDAP_ATTRIBUTE_FOR_USERNAME}={escape_filter_chars(form_data.user.lower())}){LDAP_SEARCH_FILTERS})",
+            attributes=[f"{LDAP_ATTRIBUTE_FOR_USERNAME}", "mail", "cn"],
+        )
+
+        if not search_success:
+            raise HTTPException(400, detail="User not found in the LDAP server")
+
+        entry = connection_app.entries[0]
+        username = str(entry[f"{LDAP_ATTRIBUTE_FOR_USERNAME}"]).lower()
+        mail = str(entry["mail"])
+        cn = str(entry["cn"])
+        user_dn = entry.entry_dn
+
+        if username == form_data.user.lower():
+            connection_user = Connection(
+                server,
+                user_dn,
+                form_data.password,
+                auto_bind="NONE",
+                authentication="SIMPLE",
+            )
+            if not connection_user.bind():
+                raise HTTPException(400, f"Authentication failed for {form_data.user}")
+
+            user = Users.get_user_by_email(mail)
+            if not user:
+                try:
+                    role = (
+                        "admin"
+                        if Users.get_num_users() == 0
+                        else request.app.state.config.DEFAULT_USER_ROLE
+                    )
+
+                    user = Auths.insert_new_auth(
+                        email=mail, password=str(uuid.uuid4()), name=cn, role=role
+                    )
+
+                    if not user:
+                        raise HTTPException(
+                            500, detail=ERROR_MESSAGES.CREATE_USER_ERROR
+                        )
+
+                except HTTPException:
+                    raise
+                except Exception as err:
+                    raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
+
+            user = Auths.authenticate_user_by_trusted_header(mail)
+
+            if user:
+                token = create_token(
+                    data={"id": user.id},
+                    expires_delta=parse_duration(
+                        request.app.state.config.JWT_EXPIRES_IN
+                    ),
+                )
+
+                # Set the cookie token
+                response.set_cookie(
+                    key="token",
+                    value=token,
+                    httponly=True,  # Ensures the cookie is not accessible via JavaScript
+                )
+
+                return {
+                    "token": token,
+                    "token_type": "Bearer",
+                    "id": user.id,
+                    "email": user.email,
+                    "name": user.name,
+                    "role": user.role,
+                    "profile_image_url": user.profile_image_url,
+                }
+            else:
+                raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+        else:
+            raise HTTPException(
+                400,
+                f"User {form_data.user} does not match the record. Search result: {str(entry[f'{LDAP_ATTRIBUTE_FOR_USERNAME}'])}",
+            )
+    except Exception as e:
+        raise HTTPException(400, detail=str(e))
+
+
 ############################
 # SignIn
 ############################
 
 
-@router.post("/signin", response_model=SigninResponse)
+@router.post("/signin", response_model=SessionUserResponse)
 async def signin(request: Request, response: Response, form_data: SigninForm):
     if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
         if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers:
@@ -156,26 +343,47 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
         user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
 
     if user:
+
+        expires_delta = parse_duration(request.app.state.config.JWT_EXPIRES_IN)
+        expires_at = None
+        if expires_delta:
+            expires_at = int(time.time()) + int(expires_delta.total_seconds())
+
         token = create_token(
             data={"id": user.id},
-            expires_delta=parse_duration(request.app.state.config.JWT_EXPIRES_IN),
+            expires_delta=expires_delta,
+        )
+
+        datetime_expires_at = (
+            datetime.datetime.fromtimestamp(expires_at, datetime.timezone.utc)
+            if expires_at
+            else None
         )
 
         # Set the cookie token
         response.set_cookie(
             key="token",
             value=token,
+            expires=datetime_expires_at,
             httponly=True,  # Ensures the cookie is not accessible via JavaScript
+            samesite=WEBUI_SESSION_COOKIE_SAME_SITE,
+            secure=WEBUI_SESSION_COOKIE_SECURE,
+        )
+
+        user_permissions = get_permissions(
+            user.id, request.app.state.config.USER_PERMISSIONS
         )
 
         return {
             "token": token,
             "token_type": "Bearer",
+            "expires_at": expires_at,
             "id": user.id,
             "email": user.email,
             "name": user.name,
             "role": user.role,
             "profile_image_url": user.profile_image_url,
+            "permissions": user_permissions,
         }
     else:
         raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
@@ -186,7 +394,7 @@ async def signin(request: Request, response: Response, form_data: SigninForm):
 ############################
 
 
-@router.post("/signup", response_model=SigninResponse)
+@router.post("/signup", response_model=SessionUserResponse)
 async def signup(request: Request, response: Response, form_data: SignupForm):
     if WEBUI_AUTH:
         if (
@@ -216,6 +424,11 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
             if Users.get_num_users() == 0
             else request.app.state.config.DEFAULT_USER_ROLE
         )
+
+        if Users.get_num_users() == 0:
+            # Disable signup after the first user is created
+            request.app.state.config.ENABLE_SIGNUP = False
+
         hashed = get_password_hash(form_data.password)
         user = Auths.insert_new_auth(
             form_data.email.lower(),
@@ -226,16 +439,30 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
         )
 
         if user:
+            expires_delta = parse_duration(request.app.state.config.JWT_EXPIRES_IN)
+            expires_at = None
+            if expires_delta:
+                expires_at = int(time.time()) + int(expires_delta.total_seconds())
+
             token = create_token(
                 data={"id": user.id},
-                expires_delta=parse_duration(request.app.state.config.JWT_EXPIRES_IN),
+                expires_delta=expires_delta,
+            )
+
+            datetime_expires_at = (
+                datetime.datetime.fromtimestamp(expires_at, datetime.timezone.utc)
+                if expires_at
+                else None
             )
 
             # Set the cookie token
             response.set_cookie(
                 key="token",
                 value=token,
+                expires=datetime_expires_at,
                 httponly=True,  # Ensures the cookie is not accessible via JavaScript
+                samesite=WEBUI_SESSION_COOKIE_SAME_SITE,
+                secure=WEBUI_SESSION_COOKIE_SECURE,
             )
 
             if request.app.state.config.WEBHOOK_URL:
@@ -249,14 +476,20 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
                     },
                 )
 
+            user_permissions = get_permissions(
+                user.id, request.app.state.config.USER_PERMISSIONS
+            )
+
             return {
                 "token": token,
                 "token_type": "Bearer",
+                "expires_at": expires_at,
                 "id": user.id,
                 "email": user.email,
                 "name": user.name,
                 "role": user.role,
                 "profile_image_url": user.profile_image_url,
+                "permissions": user_permissions,
             }
         else:
             raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_USER_ERROR)
@@ -264,6 +497,12 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
         raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
 
 
+@router.get("/signout")
+async def signout(response: Response):
+    response.delete_cookie("token")
+    return {"status": True}
+
+
 ############################
 # AddUser
 ############################
@@ -348,6 +587,7 @@ async def get_admin_config(request: Request, user=Depends(get_admin_user)):
     return {
         "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
         "ENABLE_SIGNUP": request.app.state.config.ENABLE_SIGNUP,
+        "ENABLE_API_KEY": request.app.state.config.ENABLE_API_KEY,
         "DEFAULT_USER_ROLE": request.app.state.config.DEFAULT_USER_ROLE,
         "JWT_EXPIRES_IN": request.app.state.config.JWT_EXPIRES_IN,
         "ENABLE_COMMUNITY_SHARING": request.app.state.config.ENABLE_COMMUNITY_SHARING,
@@ -358,6 +598,7 @@ async def get_admin_config(request: Request, user=Depends(get_admin_user)):
 class AdminConfig(BaseModel):
     SHOW_ADMIN_DETAILS: bool
     ENABLE_SIGNUP: bool
+    ENABLE_API_KEY: bool
     DEFAULT_USER_ROLE: str
     JWT_EXPIRES_IN: str
     ENABLE_COMMUNITY_SHARING: bool
@@ -370,6 +611,7 @@ async def update_admin_config(
 ):
     request.app.state.config.SHOW_ADMIN_DETAILS = form_data.SHOW_ADMIN_DETAILS
     request.app.state.config.ENABLE_SIGNUP = form_data.ENABLE_SIGNUP
+    request.app.state.config.ENABLE_API_KEY = form_data.ENABLE_API_KEY
 
     if form_data.DEFAULT_USER_ROLE in ["pending", "user", "admin"]:
         request.app.state.config.DEFAULT_USER_ROLE = form_data.DEFAULT_USER_ROLE
@@ -388,6 +630,7 @@ async def update_admin_config(
     return {
         "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
         "ENABLE_SIGNUP": request.app.state.config.ENABLE_SIGNUP,
+        "ENABLE_API_KEY": request.app.state.config.ENABLE_API_KEY,
         "DEFAULT_USER_ROLE": request.app.state.config.DEFAULT_USER_ROLE,
         "JWT_EXPIRES_IN": request.app.state.config.JWT_EXPIRES_IN,
         "ENABLE_COMMUNITY_SHARING": request.app.state.config.ENABLE_COMMUNITY_SHARING,
@@ -395,6 +638,105 @@ async def update_admin_config(
     }
 
 
+class LdapServerConfig(BaseModel):
+    label: str
+    host: str
+    port: Optional[int] = None
+    attribute_for_username: str = "uid"
+    app_dn: str
+    app_dn_password: str
+    search_base: str
+    search_filters: str = ""
+    use_tls: bool = True
+    certificate_path: Optional[str] = None
+    ciphers: Optional[str] = "ALL"
+
+
+@router.get("/admin/config/ldap/server", response_model=LdapServerConfig)
+async def get_ldap_server(request: Request, user=Depends(get_admin_user)):
+    return {
+        "label": request.app.state.config.LDAP_SERVER_LABEL,
+        "host": request.app.state.config.LDAP_SERVER_HOST,
+        "port": request.app.state.config.LDAP_SERVER_PORT,
+        "attribute_for_username": request.app.state.config.LDAP_ATTRIBUTE_FOR_USERNAME,
+        "app_dn": request.app.state.config.LDAP_APP_DN,
+        "app_dn_password": request.app.state.config.LDAP_APP_PASSWORD,
+        "search_base": request.app.state.config.LDAP_SEARCH_BASE,
+        "search_filters": request.app.state.config.LDAP_SEARCH_FILTERS,
+        "use_tls": request.app.state.config.LDAP_USE_TLS,
+        "certificate_path": request.app.state.config.LDAP_CA_CERT_FILE,
+        "ciphers": request.app.state.config.LDAP_CIPHERS,
+    }
+
+
+@router.post("/admin/config/ldap/server")
+async def update_ldap_server(
+    request: Request, form_data: LdapServerConfig, user=Depends(get_admin_user)
+):
+    required_fields = [
+        "label",
+        "host",
+        "attribute_for_username",
+        "app_dn",
+        "app_dn_password",
+        "search_base",
+    ]
+    for key in required_fields:
+        value = getattr(form_data, key)
+        if not value:
+            raise HTTPException(400, detail=f"Required field {key} is empty")
+
+    if form_data.use_tls and not form_data.certificate_path:
+        raise HTTPException(
+            400, detail="TLS is enabled but certificate file path is missing"
+        )
+
+    request.app.state.config.LDAP_SERVER_LABEL = form_data.label
+    request.app.state.config.LDAP_SERVER_HOST = form_data.host
+    request.app.state.config.LDAP_SERVER_PORT = form_data.port
+    request.app.state.config.LDAP_ATTRIBUTE_FOR_USERNAME = (
+        form_data.attribute_for_username
+    )
+    request.app.state.config.LDAP_APP_DN = form_data.app_dn
+    request.app.state.config.LDAP_APP_PASSWORD = form_data.app_dn_password
+    request.app.state.config.LDAP_SEARCH_BASE = form_data.search_base
+    request.app.state.config.LDAP_SEARCH_FILTERS = form_data.search_filters
+    request.app.state.config.LDAP_USE_TLS = form_data.use_tls
+    request.app.state.config.LDAP_CA_CERT_FILE = form_data.certificate_path
+    request.app.state.config.LDAP_CIPHERS = form_data.ciphers
+
+    return {
+        "label": request.app.state.config.LDAP_SERVER_LABEL,
+        "host": request.app.state.config.LDAP_SERVER_HOST,
+        "port": request.app.state.config.LDAP_SERVER_PORT,
+        "attribute_for_username": request.app.state.config.LDAP_ATTRIBUTE_FOR_USERNAME,
+        "app_dn": request.app.state.config.LDAP_APP_DN,
+        "app_dn_password": request.app.state.config.LDAP_APP_PASSWORD,
+        "search_base": request.app.state.config.LDAP_SEARCH_BASE,
+        "search_filters": request.app.state.config.LDAP_SEARCH_FILTERS,
+        "use_tls": request.app.state.config.LDAP_USE_TLS,
+        "certificate_path": request.app.state.config.LDAP_CA_CERT_FILE,
+        "ciphers": request.app.state.config.LDAP_CIPHERS,
+    }
+
+
+@router.get("/admin/config/ldap")
+async def get_ldap_config(request: Request, user=Depends(get_admin_user)):
+    return {"ENABLE_LDAP": request.app.state.config.ENABLE_LDAP}
+
+
+class LdapConfigForm(BaseModel):
+    enable_ldap: Optional[bool] = None
+
+
+@router.post("/admin/config/ldap")
+async def update_ldap_config(
+    request: Request, form_data: LdapConfigForm, user=Depends(get_admin_user)
+):
+    request.app.state.config.ENABLE_LDAP = form_data.enable_ldap
+    return {"ENABLE_LDAP": request.app.state.config.ENABLE_LDAP}
+
+
 ############################
 # API Key
 ############################
@@ -402,9 +744,16 @@ async def update_admin_config(
 
 # create api key
 @router.post("/api_key", response_model=ApiKey)
-async def create_api_key_(user=Depends(get_current_user)):
+async def generate_api_key(request: Request, user=Depends(get_current_user)):
+    if not request.app.state.config.ENABLE_API_KEY:
+        raise HTTPException(
+            status.HTTP_403_FORBIDDEN,
+            detail=ERROR_MESSAGES.API_KEY_CREATION_NOT_ALLOWED,
+        )
+
     api_key = create_api_key()
     success = Users.update_user_api_key_by_id(user.id, api_key)
+
     if success:
         return {
             "api_key": api_key,

backend/open_webui/apps/webui/routers/chats.py

@@ -4,22 +4,23 @@ from typing import Optional
 
 from open_webui.apps.webui.models.chats import (
     ChatForm,
+    ChatImportForm,
     ChatResponse,
     Chats,
     ChatTitleIdResponse,
 )
-from open_webui.apps.webui.models.tags import (
-    ChatIdTagForm,
-    ChatIdTagModel,
-    TagModel,
-    Tags,
-)
+from open_webui.apps.webui.models.tags import TagModel, Tags
+from open_webui.apps.webui.models.folders import Folders
+
 from open_webui.config import ENABLE_ADMIN_CHAT_ACCESS, ENABLE_ADMIN_EXPORT
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import SRC_LOG_LEVELS
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from pydantic import BaseModel
+
+
 from open_webui.utils.utils import get_admin_user, get_verified_user
+from open_webui.utils.access_control import has_permission
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -52,9 +53,10 @@ async def get_session_user_chat_list(
 
 @router.delete("/", response_model=bool)
 async def delete_all_user_chats(request: Request, user=Depends(get_verified_user)):
-    if user.role == "user" and not request.app.state.config.USER_PERMISSIONS.get(
-        "chat", {}
-    ).get("deletion", {}):
+
+    if user.role == "user" and not has_permission(
+        user.id, "chat.delete", request.app.state.config.USER_PERMISSIONS
+    ):
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
@@ -95,7 +97,35 @@ async def get_user_chat_list_by_user_id(
 async def create_new_chat(form_data: ChatForm, user=Depends(get_verified_user)):
     try:
         chat = Chats.insert_new_chat(user.id, form_data)
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        return ChatResponse(**chat.model_dump())
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
+############################
+# ImportChat
+############################
+
+
+@router.post("/import", response_model=Optional[ChatResponse])
+async def import_chat(form_data: ChatImportForm, user=Depends(get_verified_user)):
+    try:
+        chat = Chats.import_chat(user.id, form_data)
+        if chat:
+            tags = chat.meta.get("tags", [])
+            for tag_id in tags:
+                tag_id = tag_id.replace(" ", "_").lower()
+                tag_name = " ".join([word.capitalize() for word in tag_id.split("_")])
+                if (
+                    tag_id != "none"
+                    and Tags.get_tag_by_name_and_user_id(tag_name, user.id) is None
+                ):
+                    Tags.insert_new_tag(tag_name, user.id)
+
+        return ChatResponse(**chat.model_dump())
     except Exception as e:
         log.exception(e)
         raise HTTPException(
@@ -108,10 +138,77 @@ async def create_new_chat(form_data: ChatForm, user=Depends(get_verified_user)):
 ############################
 
 
+@router.get("/search", response_model=list[ChatTitleIdResponse])
+async def search_user_chats(
+    text: str, page: Optional[int] = None, user=Depends(get_verified_user)
+):
+    if page is None:
+        page = 1
+
+    limit = 60
+    skip = (page - 1) * limit
+
+    chat_list = [
+        ChatTitleIdResponse(**chat.model_dump())
+        for chat in Chats.get_chats_by_user_id_and_search_text(
+            user.id, text, skip=skip, limit=limit
+        )
+    ]
+
+    # Delete tag if no chat is found
+    words = text.strip().split(" ")
+    if page == 1 and len(words) == 1 and words[0].startswith("tag:"):
+        tag_id = words[0].replace("tag:", "")
+        if len(chat_list) == 0:
+            if Tags.get_tag_by_name_and_user_id(tag_id, user.id):
+                log.debug(f"deleting tag: {tag_id}")
+                Tags.delete_tag_by_name_and_user_id(tag_id, user.id)
+
+    return chat_list
+
+
+############################
+# GetChatsByFolderId
+############################
+
+
+@router.get("/folder/{folder_id}", response_model=list[ChatResponse])
+async def get_chats_by_folder_id(folder_id: str, user=Depends(get_verified_user)):
+    folder_ids = [folder_id]
+    children_folders = Folders.get_children_folders_by_id_and_user_id(
+        folder_id, user.id
+    )
+    if children_folders:
+        folder_ids.extend([folder.id for folder in children_folders])
+
+    return [
+        ChatResponse(**chat.model_dump())
+        for chat in Chats.get_chats_by_folder_ids_and_user_id(folder_ids, user.id)
+    ]
+
+
+############################
+# GetPinnedChats
+############################
+
+
+@router.get("/pinned", response_model=list[ChatResponse])
+async def get_user_pinned_chats(user=Depends(get_verified_user)):
+    return [
+        ChatResponse(**chat.model_dump())
+        for chat in Chats.get_pinned_chats_by_user_id(user.id)
+    ]
+
+
+############################
+# GetChats
+############################
+
+
 @router.get("/all", response_model=list[ChatResponse])
 async def get_user_chats(user=Depends(get_verified_user)):
     return [
-        ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        ChatResponse(**chat.model_dump())
         for chat in Chats.get_chats_by_user_id(user.id)
     ]
 
@@ -124,11 +221,28 @@ async def get_user_chats(user=Depends(get_verified_user)):
 @router.get("/all/archived", response_model=list[ChatResponse])
 async def get_user_archived_chats(user=Depends(get_verified_user)):
     return [
-        ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        ChatResponse(**chat.model_dump())
         for chat in Chats.get_archived_chats_by_user_id(user.id)
     ]
 
 
+############################
+# GetAllTags
+############################
+
+
+@router.get("/all/tags", response_model=list[TagModel])
+async def get_all_user_tags(user=Depends(get_verified_user)):
+    try:
+        tags = Tags.get_tags_by_user_id(user.id)
+        return tags
+    except Exception as e:
+        log.exception(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
 ############################
 # GetAllChatsInDB
 ############################
@@ -141,10 +255,7 @@ async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
         )
-    return [
-        ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
-        for chat in Chats.get_chats()
-    ]
+    return [ChatResponse(**chat.model_dump()) for chat in Chats.get_chats()]
 
 
 ############################
@@ -187,7 +298,8 @@ async def get_shared_chat_by_id(share_id: str, user=Depends(get_verified_user)):
         chat = Chats.get_chat_by_id(share_id)
 
     if chat:
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        return ChatResponse(**chat.model_dump())
+
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
@@ -199,48 +311,28 @@ async def get_shared_chat_by_id(share_id: str, user=Depends(get_verified_user)):
 ############################
 
 
-class TagNameForm(BaseModel):
+class TagForm(BaseModel):
     name: str
+
+
+class TagFilterForm(TagForm):
     skip: Optional[int] = 0
     limit: Optional[int] = 50
 
 
 @router.post("/tags", response_model=list[ChatTitleIdResponse])
 async def get_user_chat_list_by_tag_name(
-    form_data: TagNameForm, user=Depends(get_verified_user)
+    form_data: TagFilterForm, user=Depends(get_verified_user)
 ):
-    chat_ids = [
-        chat_id_tag.chat_id
-        for chat_id_tag in Tags.get_chat_ids_by_tag_name_and_user_id(
-            form_data.name, user.id
-        )
-    ]
-
-    chats = Chats.get_chat_list_by_chat_ids(chat_ids, form_data.skip, form_data.limit)
-
+    chats = Chats.get_chat_list_by_user_id_and_tag_name(
+        user.id, form_data.name, form_data.skip, form_data.limit
+    )
     if len(chats) == 0:
-        Tags.delete_tag_by_tag_name_and_user_id(form_data.name, user.id)
+        Tags.delete_tag_by_name_and_user_id(form_data.name, user.id)
 
     return chats
 
 
-############################
-# GetAllTags
-############################
-
-
-@router.get("/tags/all", response_model=list[TagModel])
-async def get_all_tags(user=Depends(get_verified_user)):
-    try:
-        tags = Tags.get_tags_by_user_id(user.id)
-        return tags
-    except Exception as e:
-        log.exception(e)
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT()
-        )
-
-
 ############################
 # GetChatById
 ############################
@@ -251,7 +343,8 @@ async def get_chat_by_id(id: str, user=Depends(get_verified_user)):
     chat = Chats.get_chat_by_id_and_user_id(id, user.id)
 
     if chat:
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        return ChatResponse(**chat.model_dump())
+
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
@@ -269,10 +362,9 @@ async def update_chat_by_id(
 ):
     chat = Chats.get_chat_by_id_and_user_id(id, user.id)
     if chat:
-        updated_chat = {**json.loads(chat.chat), **form_data.chat}
-
+        updated_chat = {**chat.chat, **form_data.chat}
         chat = Chats.update_chat_by_id(id, updated_chat)
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        return ChatResponse(**chat.model_dump())
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -288,40 +380,83 @@ async def update_chat_by_id(
 @router.delete("/{id}", response_model=bool)
 async def delete_chat_by_id(request: Request, id: str, user=Depends(get_verified_user)):
     if user.role == "admin":
+        chat = Chats.get_chat_by_id(id)
+        for tag in chat.meta.get("tags", []):
+            if Chats.count_chats_by_tag_name_and_user_id(tag, user.id) == 1:
+                Tags.delete_tag_by_name_and_user_id(tag, user.id)
+
         result = Chats.delete_chat_by_id(id)
+
         return result
     else:
-        if not request.app.state.config.USER_PERMISSIONS.get("chat", {}).get(
-            "deletion", {}
+        if not has_permission(
+            user.id, "chat.delete", request.app.state.config.USER_PERMISSIONS
         ):
             raise HTTPException(
                 status_code=status.HTTP_401_UNAUTHORIZED,
                 detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
             )
 
+        chat = Chats.get_chat_by_id(id)
+        for tag in chat.meta.get("tags", []):
+            if Chats.count_chats_by_tag_name_and_user_id(tag, user.id) == 1:
+                Tags.delete_tag_by_name_and_user_id(tag, user.id)
+
         result = Chats.delete_chat_by_id_and_user_id(id, user.id)
         return result
 
 
+############################
+# GetPinnedStatusById
+############################
+
+
+@router.get("/{id}/pinned", response_model=Optional[bool])
+async def get_pinned_status_by_id(id: str, user=Depends(get_verified_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        return chat.pinned
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
+############################
+# PinChatById
+############################
+
+
+@router.post("/{id}/pin", response_model=Optional[ChatResponse])
+async def pin_chat_by_id(id: str, user=Depends(get_verified_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        chat = Chats.toggle_chat_pinned_by_id(id)
+        return chat
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
 ############################
 # CloneChat
 ############################
 
 
-@router.get("/{id}/clone", response_model=Optional[ChatResponse])
+@router.post("/{id}/clone", response_model=Optional[ChatResponse])
 async def clone_chat_by_id(id: str, user=Depends(get_verified_user)):
     chat = Chats.get_chat_by_id_and_user_id(id, user.id)
     if chat:
-        chat_body = json.loads(chat.chat)
         updated_chat = {
-            **chat_body,
+            **chat.chat,
             "originalChatId": chat.id,
-            "branchPointMessageId": chat_body["history"]["currentId"],
+            "branchPointMessageId": chat.chat["history"]["currentId"],
             "title": f"Clone of {chat.title}",
         }
 
         chat = Chats.insert_new_chat(user.id, ChatForm(**{"chat": updated_chat}))
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+        return ChatResponse(**chat.model_dump())
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
@@ -333,12 +468,26 @@ async def clone_chat_by_id(id: str, user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/{id}/archive", response_model=Optional[ChatResponse])
+@router.post("/{id}/archive", response_model=Optional[ChatResponse])
 async def archive_chat_by_id(id: str, user=Depends(get_verified_user)):
     chat = Chats.get_chat_by_id_and_user_id(id, user.id)
     if chat:
         chat = Chats.toggle_chat_archive_by_id(id)
-        return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
+
+        # Delete tags if chat is archived
+        if chat.archived:
+            for tag_id in chat.meta.get("tags", []):
+                if Chats.count_chats_by_tag_name_and_user_id(tag_id, user.id) == 0:
+                    log.debug(f"deleting tag: {tag_id}")
+                    Tags.delete_tag_by_name_and_user_id(tag_id, user.id)
+        else:
+            for tag_id in chat.meta.get("tags", []):
+                tag = Tags.get_tag_by_name_and_user_id(tag_id, user.id)
+                if tag is None:
+                    log.debug(f"inserting tag: {tag_id}")
+                    tag = Tags.insert_new_tag(tag_id, user.id)
+
+        return ChatResponse(**chat.model_dump())
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
@@ -356,9 +505,7 @@ async def share_chat_by_id(id: str, user=Depends(get_verified_user)):
     if chat:
         if chat.share_id:
             shared_chat = Chats.update_shared_chat_by_chat_id(chat.id)
-            return ChatResponse(
-                **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
-            )
+            return ChatResponse(**shared_chat.model_dump())
 
         shared_chat = Chats.insert_shared_chat_by_chat_id(chat.id)
         if not shared_chat:
@@ -366,10 +513,8 @@ async def share_chat_by_id(id: str, user=Depends(get_verified_user)):
                 status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
                 detail=ERROR_MESSAGES.DEFAULT(),
             )
+        return ChatResponse(**shared_chat.model_dump())
 
-        return ChatResponse(
-            **{**shared_chat.model_dump(), "chat": json.loads(shared_chat.chat)}
-        )
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -400,6 +545,31 @@ async def delete_shared_chat_by_id(id: str, user=Depends(get_verified_user)):
         )
 
 
+############################
+# UpdateChatFolderIdById
+############################
+
+
+class ChatFolderIdForm(BaseModel):
+    folder_id: Optional[str] = None
+
+
+@router.post("/{id}/folder", response_model=Optional[ChatResponse])
+async def update_chat_folder_id_by_id(
+    id: str, form_data: ChatFolderIdForm, user=Depends(get_verified_user)
+):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        chat = Chats.update_chat_folder_id_by_id_and_user_id(
+            id, user.id, form_data.folder_id
+        )
+        return ChatResponse(**chat.model_dump())
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
+        )
+
+
 ############################
 # GetChatTagsById
 ############################
@@ -407,10 +577,10 @@ async def delete_shared_chat_by_id(id: str, user=Depends(get_verified_user)):
 
 @router.get("/{id}/tags", response_model=list[TagModel])
 async def get_chat_tags_by_id(id: str, user=Depends(get_verified_user)):
-    tags = Tags.get_tags_by_chat_id_and_user_id(id, user.id)
-
-    if tags != None:
-        return tags
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        tags = chat.meta.get("tags", [])
+        return Tags.get_tags_by_ids_and_user_id(tags, user.id)
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
@@ -422,22 +592,30 @@ async def get_chat_tags_by_id(id: str, user=Depends(get_verified_user)):
 ############################
 
 
-@router.post("/{id}/tags", response_model=Optional[ChatIdTagModel])
-async def add_chat_tag_by_id(
-    id: str, form_data: ChatIdTagForm, user=Depends(get_verified_user)
+@router.post("/{id}/tags", response_model=list[TagModel])
+async def add_tag_by_id_and_tag_name(
+    id: str, form_data: TagForm, user=Depends(get_verified_user)
 ):
-    tags = Tags.get_tags_by_chat_id_and_user_id(id, user.id)
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        tags = chat.meta.get("tags", [])
+        tag_id = form_data.name.replace(" ", "_").lower()
 
-    if form_data.tag_name not in tags:
-        tag = Tags.add_tag_to_chat(user.id, form_data)
-
-        if tag:
-            return tag
-        else:
+        if tag_id == "none":
             raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.NOT_FOUND,
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Tag name cannot be 'None'"),
             )
+
+        print(tags, tag_id)
+        if tag_id not in tags:
+            Chats.add_chat_tag_by_id_and_user_id_and_tag_name(
+                id, user.id, form_data.name
+            )
+
+        chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+        tags = chat.meta.get("tags", [])
+        return Tags.get_tags_by_ids_and_user_id(tags, user.id)
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
@@ -449,16 +627,20 @@ async def add_chat_tag_by_id(
 ############################
 
 
-@router.delete("/{id}/tags", response_model=Optional[bool])
-async def delete_chat_tag_by_id(
-    id: str, form_data: ChatIdTagForm, user=Depends(get_verified_user)
+@router.delete("/{id}/tags", response_model=list[TagModel])
+async def delete_tag_by_id_and_tag_name(
+    id: str, form_data: TagForm, user=Depends(get_verified_user)
 ):
-    result = Tags.delete_tag_by_tag_name_and_chat_id_and_user_id(
-        form_data.tag_name, id, user.id
-    )
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        Chats.delete_tag_by_id_and_user_id_and_tag_name(id, user.id, form_data.name)
 
-    if result:
-        return result
+        if Chats.count_chats_by_tag_name_and_user_id(form_data.name, user.id) == 0:
+            Tags.delete_tag_by_name_and_user_id(form_data.name, user.id)
+
+        chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+        tags = chat.meta.get("tags", [])
+        return Tags.get_tags_by_ids_and_user_id(tags, user.id)
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
@@ -466,16 +648,21 @@ async def delete_chat_tag_by_id(
 
 
 ############################
-# DeleteAllChatTagsById
+# DeleteAllTagsById
 ############################
 
 
 @router.delete("/{id}/tags/all", response_model=Optional[bool])
-async def delete_all_chat_tags_by_id(id: str, user=Depends(get_verified_user)):
-    result = Tags.delete_tags_by_chat_id_and_user_id(id, user.id)
+async def delete_all_tags_by_id(id: str, user=Depends(get_verified_user)):
+    chat = Chats.get_chat_by_id_and_user_id(id, user.id)
+    if chat:
+        Chats.delete_all_tags_by_id_and_user_id(id, user.id)
 
-    if result:
-        return result
+        for tag in chat.meta.get("tags", []):
+            if Chats.count_chats_by_tag_name_and_user_id(tag, user.id) == 0:
+                Tags.delete_tag_by_name_and_user_id(tag, user.id)
+
+        return True
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND

backend/open_webui/apps/webui/routers/configs.py

@@ -34,8 +34,32 @@ async def export_config(user=Depends(get_admin_user)):
     return get_config()
 
 
-class SetDefaultModelsForm(BaseModel):
-    models: str
+############################
+# SetDefaultModels
+############################
+class ModelsConfigForm(BaseModel):
+    DEFAULT_MODELS: str
+    MODEL_ORDER_LIST: list[str]
+
+
+@router.get("/models", response_model=ModelsConfigForm)
+async def get_models_config(request: Request, user=Depends(get_admin_user)):
+    return {
+        "DEFAULT_MODELS": request.app.state.config.DEFAULT_MODELS,
+        "MODEL_ORDER_LIST": request.app.state.config.MODEL_ORDER_LIST,
+    }
+
+
+@router.post("/models", response_model=ModelsConfigForm)
+async def set_models_config(
+    request: Request, form_data: ModelsConfigForm, user=Depends(get_admin_user)
+):
+    request.app.state.config.DEFAULT_MODELS = form_data.DEFAULT_MODELS
+    request.app.state.config.MODEL_ORDER_LIST = form_data.MODEL_ORDER_LIST
+    return {
+        "DEFAULT_MODELS": request.app.state.config.DEFAULT_MODELS,
+        "MODEL_ORDER_LIST": request.app.state.config.MODEL_ORDER_LIST,
+    }
 
 
 class PromptSuggestion(BaseModel):
@@ -47,21 +71,8 @@ class SetDefaultSuggestionsForm(BaseModel):
     suggestions: list[PromptSuggestion]
 
 
-############################
-# SetDefaultModels
-############################
-
-
-@router.post("/default/models", response_model=str)
-async def set_global_default_models(
-    request: Request, form_data: SetDefaultModelsForm, user=Depends(get_admin_user)
-):
-    request.app.state.config.DEFAULT_MODELS = form_data.models
-    return request.app.state.config.DEFAULT_MODELS
-
-
-@router.post("/default/suggestions", response_model=list[PromptSuggestion])
-async def set_global_default_suggestions(
+@router.post("/suggestions", response_model=list[PromptSuggestion])
+async def set_default_suggestions(
     request: Request,
     form_data: SetDefaultSuggestionsForm,
     user=Depends(get_admin_user),

backend/open_webui/apps/webui/routers/documents.py

@@ -1,155 +0,0 @@
-import json
-from typing import Optional
-
-from open_webui.apps.webui.models.documents import (
-    DocumentForm,
-    DocumentResponse,
-    Documents,
-    DocumentUpdateForm,
-)
-from open_webui.constants import ERROR_MESSAGES
-from fastapi import APIRouter, Depends, HTTPException, status
-from pydantic import BaseModel
-from open_webui.utils.utils import get_admin_user, get_verified_user
-
-router = APIRouter()
-
-############################
-# GetDocuments
-############################
-
-
-@router.get("/", response_model=list[DocumentResponse])
-async def get_documents(user=Depends(get_verified_user)):
-    docs = [
-        DocumentResponse(
-            **{
-                **doc.model_dump(),
-                "content": json.loads(doc.content if doc.content else "{}"),
-            }
-        )
-        for doc in Documents.get_docs()
-    ]
-    return docs
-
-
-############################
-# CreateNewDoc
-############################
-
-
-@router.post("/create", response_model=Optional[DocumentResponse])
-async def create_new_doc(form_data: DocumentForm, user=Depends(get_admin_user)):
-    doc = Documents.get_doc_by_name(form_data.name)
-    if doc is None:
-        doc = Documents.insert_new_doc(user.id, form_data)
-
-        if doc:
-            return DocumentResponse(
-                **{
-                    **doc.model_dump(),
-                    "content": json.loads(doc.content if doc.content else "{}"),
-                }
-            )
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.FILE_EXISTS,
-            )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.NAME_TAG_TAKEN,
-        )
-
-
-############################
-# GetDocByName
-############################
-
-
-@router.get("/doc", response_model=Optional[DocumentResponse])
-async def get_doc_by_name(name: str, user=Depends(get_verified_user)):
-    doc = Documents.get_doc_by_name(name)
-
-    if doc:
-        return DocumentResponse(
-            **{
-                **doc.model_dump(),
-                "content": json.loads(doc.content if doc.content else "{}"),
-            }
-        )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-############################
-# TagDocByName
-############################
-
-
-class TagItem(BaseModel):
-    name: str
-
-
-class TagDocumentForm(BaseModel):
-    name: str
-    tags: list[dict]
-
-
-@router.post("/doc/tags", response_model=Optional[DocumentResponse])
-async def tag_doc_by_name(form_data: TagDocumentForm, user=Depends(get_verified_user)):
-    doc = Documents.update_doc_content_by_name(form_data.name, {"tags": form_data.tags})
-
-    if doc:
-        return DocumentResponse(
-            **{
-                **doc.model_dump(),
-                "content": json.loads(doc.content if doc.content else "{}"),
-            }
-        )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-############################
-# UpdateDocByName
-############################
-
-
-@router.post("/doc/update", response_model=Optional[DocumentResponse])
-async def update_doc_by_name(
-    name: str,
-    form_data: DocumentUpdateForm,
-    user=Depends(get_admin_user),
-):
-    doc = Documents.update_doc_by_name(name, form_data)
-    if doc:
-        return DocumentResponse(
-            **{
-                **doc.model_dump(),
-                "content": json.loads(doc.content if doc.content else "{}"),
-            }
-        )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.NAME_TAG_TAKEN,
-        )
-
-
-############################
-# DeleteDocByName
-############################
-
-
-@router.delete("/doc/delete", response_model=bool)
-async def delete_doc_by_name(name: str, user=Depends(get_admin_user)):
-    result = Documents.delete_doc_by_name(name)
-    return result

backend/open_webui/apps/webui/routers/evaluations.py

@@ -0,0 +1,159 @@
+from typing import Optional
+from fastapi import APIRouter, Depends, HTTPException, status, Request
+from pydantic import BaseModel
+
+from open_webui.apps.webui.models.users import Users, UserModel
+from open_webui.apps.webui.models.feedbacks import (
+    FeedbackModel,
+    FeedbackResponse,
+    FeedbackForm,
+    Feedbacks,
+)
+
+from open_webui.constants import ERROR_MESSAGES
+from open_webui.utils.utils import get_admin_user, get_verified_user
+
+router = APIRouter()
+
+
+############################
+# GetConfig
+############################
+
+
+@router.get("/config")
+async def get_config(request: Request, user=Depends(get_admin_user)):
+    return {
+        "ENABLE_EVALUATION_ARENA_MODELS": request.app.state.config.ENABLE_EVALUATION_ARENA_MODELS,
+        "EVALUATION_ARENA_MODELS": request.app.state.config.EVALUATION_ARENA_MODELS,
+    }
+
+
+############################
+# UpdateConfig
+############################
+
+
+class UpdateConfigForm(BaseModel):
+    ENABLE_EVALUATION_ARENA_MODELS: Optional[bool] = None
+    EVALUATION_ARENA_MODELS: Optional[list[dict]] = None
+
+
+@router.post("/config")
+async def update_config(
+    request: Request,
+    form_data: UpdateConfigForm,
+    user=Depends(get_admin_user),
+):
+    config = request.app.state.config
+    if form_data.ENABLE_EVALUATION_ARENA_MODELS is not None:
+        config.ENABLE_EVALUATION_ARENA_MODELS = form_data.ENABLE_EVALUATION_ARENA_MODELS
+    if form_data.EVALUATION_ARENA_MODELS is not None:
+        config.EVALUATION_ARENA_MODELS = form_data.EVALUATION_ARENA_MODELS
+    return {
+        "ENABLE_EVALUATION_ARENA_MODELS": config.ENABLE_EVALUATION_ARENA_MODELS,
+        "EVALUATION_ARENA_MODELS": config.EVALUATION_ARENA_MODELS,
+    }
+
+
+class FeedbackUserResponse(FeedbackResponse):
+    user: Optional[UserModel] = None
+
+
+@router.get("/feedbacks/all", response_model=list[FeedbackUserResponse])
+async def get_all_feedbacks(user=Depends(get_admin_user)):
+    feedbacks = Feedbacks.get_all_feedbacks()
+    return [
+        FeedbackUserResponse(
+            **feedback.model_dump(), user=Users.get_user_by_id(feedback.user_id)
+        )
+        for feedback in feedbacks
+    ]
+
+
+@router.delete("/feedbacks/all")
+async def delete_all_feedbacks(user=Depends(get_admin_user)):
+    success = Feedbacks.delete_all_feedbacks()
+    return success
+
+
+@router.get("/feedbacks/all/export", response_model=list[FeedbackModel])
+async def get_all_feedbacks(user=Depends(get_admin_user)):
+    feedbacks = Feedbacks.get_all_feedbacks()
+    return [
+        FeedbackModel(
+            **feedback.model_dump(), user=Users.get_user_by_id(feedback.user_id)
+        )
+        for feedback in feedbacks
+    ]
+
+
+@router.get("/feedbacks/user", response_model=list[FeedbackUserResponse])
+async def get_feedbacks(user=Depends(get_verified_user)):
+    feedbacks = Feedbacks.get_feedbacks_by_user_id(user.id)
+    return feedbacks
+
+
+@router.delete("/feedbacks", response_model=bool)
+async def delete_feedbacks(user=Depends(get_verified_user)):
+    success = Feedbacks.delete_feedbacks_by_user_id(user.id)
+    return success
+
+
+@router.post("/feedback", response_model=FeedbackModel)
+async def create_feedback(
+    request: Request,
+    form_data: FeedbackForm,
+    user=Depends(get_verified_user),
+):
+    feedback = Feedbacks.insert_new_feedback(user_id=user.id, form_data=form_data)
+    if not feedback:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(),
+        )
+
+    return feedback
+
+
+@router.get("/feedback/{id}", response_model=FeedbackModel)
+async def get_feedback_by_id(id: str, user=Depends(get_verified_user)):
+    feedback = Feedbacks.get_feedback_by_id_and_user_id(id=id, user_id=user.id)
+
+    if not feedback:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+    return feedback
+
+
+@router.post("/feedback/{id}", response_model=FeedbackModel)
+async def update_feedback_by_id(
+    id: str, form_data: FeedbackForm, user=Depends(get_verified_user)
+):
+    feedback = Feedbacks.update_feedback_by_id_and_user_id(
+        id=id, user_id=user.id, form_data=form_data
+    )
+
+    if not feedback:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+    return feedback
+
+
+@router.delete("/feedback/{id}")
+async def delete_feedback_by_id(id: str, user=Depends(get_verified_user)):
+    if user.role == "admin":
+        success = Feedbacks.delete_feedback_by_id(id=id)
+    else:
+        success = Feedbacks.delete_feedback_by_id_and_user_id(id=id, user_id=user.id)
+
+    if not success:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND, detail=ERROR_MESSAGES.NOT_FOUND
+        )
+
+    return success

backend/open_webui/apps/webui/routers/files.py

@@ -1,14 +1,19 @@
 import logging
 import os
-import shutil
 import uuid
 from pathlib import Path
 from typing import Optional
 from pydantic import BaseModel
 import mimetypes
 
+from open_webui.storage.provider import Storage
 
-from open_webui.apps.webui.models.files import FileForm, FileModel, Files
+from open_webui.apps.webui.models.files import (
+    FileForm,
+    FileModel,
+    FileModelResponse,
+    Files,
+)
 from open_webui.apps.retrieval.main import process_file, ProcessFileForm
 
 from open_webui.config import UPLOAD_DIR
@@ -33,7 +38,7 @@ router = APIRouter()
 ############################
 
 
-@router.post("/")
+@router.post("/", response_model=FileModelResponse)
 def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
     log.info(f"file.content_type: {file.content_type}")
     try:
@@ -44,24 +49,19 @@ def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
         id = str(uuid.uuid4())
         name = filename
         filename = f"{id}_{filename}"
-        file_path = f"{UPLOAD_DIR}/{filename}"
+        contents, file_path = Storage.upload_file(file.file, filename)
 
-        contents = file.file.read()
-        with open(file_path, "wb") as f:
-            f.write(contents)
-            f.close()
-
-        file = Files.insert_new_file(
+        file_item = Files.insert_new_file(
             user.id,
             FileForm(
                 **{
                     "id": id,
-                    "filename": filename,
+                    "filename": name,
+                    "path": file_path,
                     "meta": {
                         "name": name,
                         "content_type": file.content_type,
                         "size": len(contents),
-                        "path": file_path,
                     },
                 }
             ),
@@ -69,13 +69,19 @@ def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
 
         try:
             process_file(ProcessFileForm(file_id=id))
-            file = Files.get_file_by_id(id=id)
+            file_item = Files.get_file_by_id(id=id)
         except Exception as e:
             log.exception(e)
-            log.error(f"Error processing file: {file.id}")
+            log.error(f"Error processing file: {file_item.id}")
+            file_item = FileModelResponse(
+                **{
+                    **file_item.model_dump(),
+                    "error": str(e.detail) if hasattr(e, "detail") else str(e),
+                }
+            )
 
-        if file:
-            return file
+        if file_item:
+            return file_item
         else:
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
@@ -95,7 +101,7 @@ def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/", response_model=list[FileModel])
+@router.get("/", response_model=list[FileModelResponse])
 async def list_files(user=Depends(get_verified_user)):
     if user.role == "admin":
         files = Files.get_files()
@@ -112,27 +118,16 @@ async def list_files(user=Depends(get_verified_user)):
 @router.delete("/all")
 async def delete_all_files(user=Depends(get_admin_user)):
     result = Files.delete_all_files()
-
     if result:
-        folder = f"{UPLOAD_DIR}"
         try:
-            # Check if the directory exists
-            if os.path.exists(folder):
-                # Iterate over all the files and directories in the specified directory
-                for filename in os.listdir(folder):
-                    file_path = os.path.join(folder, filename)
-                    try:
-                        if os.path.isfile(file_path) or os.path.islink(file_path):
-                            os.unlink(file_path)  # Remove the file or link
-                        elif os.path.isdir(file_path):
-                            shutil.rmtree(file_path)  # Remove the directory
-                    except Exception as e:
-                        print(f"Failed to delete {file_path}. Reason: {e}")
-            else:
-                print(f"The directory {folder} does not exist")
+            Storage.delete_all_files()
         except Exception as e:
-            print(f"Failed to process the directory {folder}. Reason: {e}")
-
+            log.exception(e)
+            log.error(f"Error deleting files")
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error deleting files"),
+            )
         return {"message": "All files deleted successfully"}
     else:
         raise HTTPException(
@@ -213,21 +208,32 @@ async def update_file_data_content_by_id(
 ############################
 
 
-@router.get("/{id}/content", response_model=Optional[FileModel])
+@router.get("/{id}/content")
 async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
     file = Files.get_file_by_id(id)
-
     if file and (file.user_id == user.id or user.role == "admin"):
-        file_path = Path(file.meta["path"])
+        try:
+            file_path = Storage.get_file(file.path)
+            file_path = Path(file_path)
 
-        # Check if the file already exists in the cache
-        if file_path.is_file():
-            print(f"file_path: {file_path}")
-            return FileResponse(file_path)
-        else:
+            # Check if the file already exists in the cache
+            if file_path.is_file():
+                print(f"file_path: {file_path}")
+                headers = {
+                    "Content-Disposition": f'attachment; filename="{file.meta.get("name", file.filename)}"'
+                }
+                return FileResponse(file_path, headers=headers)
+            else:
+                raise HTTPException(
+                    status_code=status.HTTP_404_NOT_FOUND,
+                    detail=ERROR_MESSAGES.NOT_FOUND,
+                )
+        except Exception as e:
+            log.exception(e)
+            log.error(f"Error getting file content")
             raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=ERROR_MESSAGES.NOT_FOUND,
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error getting file content"),
             )
     else:
         raise HTTPException(
@@ -236,13 +242,12 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
         )
 
 
-@router.get("/{id}/content/{file_name}", response_model=Optional[FileModel])
-async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
+@router.get("/{id}/content/html")
+async def get_html_file_content_by_id(id: str, user=Depends(get_verified_user)):
     file = Files.get_file_by_id(id)
-
     if file and (file.user_id == user.id or user.role == "admin"):
-        file_path = file.meta.get("path")
-        if file_path:
+        try:
+            file_path = Storage.get_file(file.path)
             file_path = Path(file_path)
 
             # Check if the file already exists in the cache
@@ -254,6 +259,42 @@ async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
                     status_code=status.HTTP_404_NOT_FOUND,
                     detail=ERROR_MESSAGES.NOT_FOUND,
                 )
+        except Exception as e:
+            log.exception(e)
+            log.error(f"Error getting file content")
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error getting file content"),
+            )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+@router.get("/{id}/content/{file_name}")
+async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
+    file = Files.get_file_by_id(id)
+
+    if file and (file.user_id == user.id or user.role == "admin"):
+        file_path = file.path
+        if file_path:
+            file_path = Storage.get_file(file_path)
+            file_path = Path(file_path)
+
+            # Check if the file already exists in the cache
+            if file_path.is_file():
+                print(f"file_path: {file_path}")
+                headers = {
+                    "Content-Disposition": f'attachment; filename="{file.meta.get("name", file.filename)}"'
+                }
+                return FileResponse(file_path, headers=headers)
+            else:
+                raise HTTPException(
+                    status_code=status.HTTP_404_NOT_FOUND,
+                    detail=ERROR_MESSAGES.NOT_FOUND,
+                )
         else:
             # File path doesn’t exist, return the content as .txt if possible
             file_content = file.content.get("content", "")
@@ -286,6 +327,15 @@ async def delete_file_by_id(id: str, user=Depends(get_verified_user)):
     if file and (file.user_id == user.id or user.role == "admin"):
         result = Files.delete_file_by_id(id)
         if result:
+            try:
+                Storage.delete_file(file.filename)
+            except Exception as e:
+                log.exception(e)
+                log.error(f"Error deleting files")
+                raise HTTPException(
+                    status_code=status.HTTP_400_BAD_REQUEST,
+                    detail=ERROR_MESSAGES.DEFAULT("Error deleting files"),
+                )
             return {"message": "File deleted successfully"}
         else:
             raise HTTPException(

backend/open_webui/apps/webui/routers/folders.py

@@ -0,0 +1,251 @@
+import logging
+import os
+import shutil
+import uuid
+from pathlib import Path
+from typing import Optional
+from pydantic import BaseModel
+import mimetypes
+
+
+from open_webui.apps.webui.models.folders import (
+    FolderForm,
+    FolderModel,
+    Folders,
+)
+from open_webui.apps.webui.models.chats import Chats
+
+from open_webui.config import UPLOAD_DIR
+from open_webui.env import SRC_LOG_LEVELS
+from open_webui.constants import ERROR_MESSAGES
+
+
+from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
+from fastapi.responses import FileResponse, StreamingResponse
+
+
+from open_webui.utils.utils import get_admin_user, get_verified_user
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+
+router = APIRouter()
+
+
+############################
+# Get Folders
+############################
+
+
+@router.get("/", response_model=list[FolderModel])
+async def get_folders(user=Depends(get_verified_user)):
+    folders = Folders.get_folders_by_user_id(user.id)
+
+    return [
+        {
+            **folder.model_dump(),
+            "items": {
+                "chats": [
+                    {"title": chat.title, "id": chat.id}
+                    for chat in Chats.get_chats_by_folder_id_and_user_id(
+                        folder.id, user.id
+                    )
+                ]
+            },
+        }
+        for folder in folders
+    ]
+
+
+############################
+# Create Folder
+############################
+
+
+@router.post("/")
+def create_folder(form_data: FolderForm, user=Depends(get_verified_user)):
+    folder = Folders.get_folder_by_parent_id_and_user_id_and_name(
+        None, user.id, form_data.name
+    )
+
+    if folder:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT("Folder already exists"),
+        )
+
+    try:
+        folder = Folders.insert_new_folder(user.id, form_data.name)
+        return folder
+    except Exception as e:
+        log.exception(e)
+        log.error("Error creating folder")
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT("Error creating folder"),
+        )
+
+
+############################
+# Get Folders By Id
+############################
+
+
+@router.get("/{id}", response_model=Optional[FolderModel])
+async def get_folder_by_id(id: str, user=Depends(get_verified_user)):
+    folder = Folders.get_folder_by_id_and_user_id(id, user.id)
+    if folder:
+        return folder
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# Update Folder Name By Id
+############################
+
+
+@router.post("/{id}/update")
+async def update_folder_name_by_id(
+    id: str, form_data: FolderForm, user=Depends(get_verified_user)
+):
+    folder = Folders.get_folder_by_id_and_user_id(id, user.id)
+    if folder:
+        existing_folder = Folders.get_folder_by_parent_id_and_user_id_and_name(
+            folder.parent_id, user.id, form_data.name
+        )
+        if existing_folder:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Folder already exists"),
+            )
+
+        try:
+            folder = Folders.update_folder_name_by_id_and_user_id(
+                id, user.id, form_data.name
+            )
+
+            return folder
+        except Exception as e:
+            log.exception(e)
+            log.error(f"Error updating folder: {id}")
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error updating folder"),
+            )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# Update Folder Parent Id By Id
+############################
+
+
+class FolderParentIdForm(BaseModel):
+    parent_id: Optional[str] = None
+
+
+@router.post("/{id}/update/parent")
+async def update_folder_parent_id_by_id(
+    id: str, form_data: FolderParentIdForm, user=Depends(get_verified_user)
+):
+    folder = Folders.get_folder_by_id_and_user_id(id, user.id)
+    if folder:
+        existing_folder = Folders.get_folder_by_parent_id_and_user_id_and_name(
+            form_data.parent_id, user.id, folder.name
+        )
+
+        if existing_folder:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Folder already exists"),
+            )
+
+        try:
+            folder = Folders.update_folder_parent_id_by_id_and_user_id(
+                id, user.id, form_data.parent_id
+            )
+            return folder
+        except Exception as e:
+            log.exception(e)
+            log.error(f"Error updating folder: {id}")
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error updating folder"),
+            )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# Update Folder Is Expanded By Id
+############################
+
+
+class FolderIsExpandedForm(BaseModel):
+    is_expanded: bool
+
+
+@router.post("/{id}/update/expanded")
+async def update_folder_is_expanded_by_id(
+    id: str, form_data: FolderIsExpandedForm, user=Depends(get_verified_user)
+):
+    folder = Folders.get_folder_by_id_and_user_id(id, user.id)
+    if folder:
+        try:
+            folder = Folders.update_folder_is_expanded_by_id_and_user_id(
+                id, user.id, form_data.is_expanded
+            )
+            return folder
+        except Exception as e:
+            log.exception(e)
+            log.error(f"Error updating folder: {id}")
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error updating folder"),
+            )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# Delete Folder By Id
+############################
+
+
+@router.delete("/{id}")
+async def delete_folder_by_id(id: str, user=Depends(get_verified_user)):
+    folder = Folders.get_folder_by_id_and_user_id(id, user.id)
+    if folder:
+        try:
+            result = Folders.delete_folder_by_id_and_user_id(id, user.id)
+            if result:
+                return result
+            else:
+                raise Exception("Error deleting folder")
+        except Exception as e:
+            log.exception(e)
+            log.error(f"Error deleting folder: {id}")
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error deleting folder"),
+            )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )

backend/open_webui/apps/webui/routers/functions.py

@@ -9,7 +9,7 @@ from open_webui.apps.webui.models.functions import (
     Functions,
 )
 from open_webui.apps.webui.utils import load_function_module_by_id, replace_imports
-from open_webui.config import CACHE_DIR, FUNCTIONS_DIR
+from open_webui.config import CACHE_DIR
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from open_webui.utils.utils import get_admin_user, get_verified_user

backend/open_webui/apps/webui/routers/groups.py

@@ -0,0 +1,120 @@
+import os
+from pathlib import Path
+from typing import Optional
+
+from open_webui.apps.webui.models.groups import (
+    Groups,
+    GroupForm,
+    GroupUpdateForm,
+    GroupResponse,
+)
+
+from open_webui.config import CACHE_DIR
+from open_webui.constants import ERROR_MESSAGES
+from fastapi import APIRouter, Depends, HTTPException, Request, status
+from open_webui.utils.utils import get_admin_user, get_verified_user
+
+router = APIRouter()
+
+############################
+# GetFunctions
+############################
+
+
+@router.get("/", response_model=list[GroupResponse])
+async def get_groups(user=Depends(get_verified_user)):
+    if user.role == "admin":
+        return Groups.get_groups()
+    else:
+        return Groups.get_groups_by_member_id(user.id)
+
+
+############################
+# CreateNewGroup
+############################
+
+
+@router.post("/create", response_model=Optional[GroupResponse])
+async def create_new_function(form_data: GroupForm, user=Depends(get_admin_user)):
+    try:
+        group = Groups.insert_new_group(user.id, form_data)
+        if group:
+            return group
+        else:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error creating group"),
+            )
+    except Exception as e:
+        print(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
+
+
+############################
+# GetGroupById
+############################
+
+
+@router.get("/id/{id}", response_model=Optional[GroupResponse])
+async def get_group_by_id(id: str, user=Depends(get_admin_user)):
+    group = Groups.get_group_by_id(id)
+    if group:
+        return group
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# UpdateGroupById
+############################
+
+
+@router.post("/id/{id}/update", response_model=Optional[GroupResponse])
+async def update_group_by_id(
+    id: str, form_data: GroupUpdateForm, user=Depends(get_admin_user)
+):
+    try:
+        group = Groups.update_group_by_id(id, form_data)
+        if group:
+            return group
+        else:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error updating group"),
+            )
+    except Exception as e:
+        print(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )
+
+
+############################
+# DeleteGroupById
+############################
+
+
+@router.delete("/id/{id}/delete", response_model=bool)
+async def delete_group_by_id(id: str, user=Depends(get_admin_user)):
+    try:
+        result = Groups.delete_group_by_id(id)
+        if result:
+            return result
+        else:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=ERROR_MESSAGES.DEFAULT("Error deleting group"),
+            )
+    except Exception as e:
+        print(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )

backend/open_webui/apps/webui/routers/knowledge.py

@@ -1,14 +1,14 @@
 import json
 from typing import Optional, Union
 from pydantic import BaseModel
-from fastapi import APIRouter, Depends, HTTPException, status
+from fastapi import APIRouter, Depends, HTTPException, status, Request
 import logging
 
 from open_webui.apps.webui.models.knowledge import (
     Knowledges,
-    KnowledgeUpdateForm,
     KnowledgeForm,
     KnowledgeResponse,
+    KnowledgeUserResponse,
 )
 from open_webui.apps.webui.models.files import Files, FileModel
 from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
@@ -17,6 +17,9 @@ from open_webui.apps.retrieval.main import process_file, ProcessFileForm
 
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.utils.utils import get_admin_user, get_verified_user
+from open_webui.utils.access_control import has_access, has_permission
+
+
 from open_webui.env import SRC_LOG_LEVELS
 
 
@@ -26,31 +29,103 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
 router = APIRouter()
 
 ############################
-# GetKnowledgeItems
+# getKnowledgeBases
 ############################
 
 
-@router.get(
-    "/", response_model=Optional[Union[list[KnowledgeResponse], KnowledgeResponse]]
-)
-async def get_knowledge_items(
-    id: Optional[str] = None, user=Depends(get_verified_user)
-):
-    if id:
-        knowledge = Knowledges.get_knowledge_by_id(id=id)
+@router.get("/", response_model=list[KnowledgeUserResponse])
+async def get_knowledge(user=Depends(get_verified_user)):
+    knowledge_bases = []
 
-        if knowledge:
-            return knowledge
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
+    if user.role == "admin":
+        knowledge_bases = Knowledges.get_knowledge_bases()
     else:
-        return [
-            KnowledgeResponse(**knowledge.model_dump())
-            for knowledge in Knowledges.get_knowledge_items()
-        ]
+        knowledge_bases = Knowledges.get_knowledge_bases_by_user_id(user.id, "read")
+
+    # Get files for each knowledge base
+    knowledge_with_files = []
+    for knowledge_base in knowledge_bases:
+        files = []
+        if knowledge_base.data:
+            files = Files.get_file_metadatas_by_ids(
+                knowledge_base.data.get("file_ids", [])
+            )
+
+            # Check if all files exist
+            if len(files) != len(knowledge_base.data.get("file_ids", [])):
+                missing_files = list(
+                    set(knowledge_base.data.get("file_ids", []))
+                    - set([file.id for file in files])
+                )
+                if missing_files:
+                    data = knowledge_base.data or {}
+                    file_ids = data.get("file_ids", [])
+
+                    for missing_file in missing_files:
+                        file_ids.remove(missing_file)
+
+                    data["file_ids"] = file_ids
+                    Knowledges.update_knowledge_data_by_id(
+                        id=knowledge_base.id, data=data
+                    )
+
+                    files = Files.get_file_metadatas_by_ids(file_ids)
+
+        knowledge_with_files.append(
+            KnowledgeUserResponse(
+                **knowledge_base.model_dump(),
+                files=files,
+            )
+        )
+
+    return knowledge_with_files
+
+
+@router.get("/list", response_model=list[KnowledgeUserResponse])
+async def get_knowledge_list(user=Depends(get_verified_user)):
+    knowledge_bases = []
+
+    if user.role == "admin":
+        knowledge_bases = Knowledges.get_knowledge_bases()
+    else:
+        knowledge_bases = Knowledges.get_knowledge_bases_by_user_id(user.id, "write")
+
+    # Get files for each knowledge base
+    knowledge_with_files = []
+    for knowledge_base in knowledge_bases:
+        files = []
+        if knowledge_base.data:
+            files = Files.get_file_metadatas_by_ids(
+                knowledge_base.data.get("file_ids", [])
+            )
+
+            # Check if all files exist
+            if len(files) != len(knowledge_base.data.get("file_ids", [])):
+                missing_files = list(
+                    set(knowledge_base.data.get("file_ids", []))
+                    - set([file.id for file in files])
+                )
+                if missing_files:
+                    data = knowledge_base.data or {}
+                    file_ids = data.get("file_ids", [])
+
+                    for missing_file in missing_files:
+                        file_ids.remove(missing_file)
+
+                    data["file_ids"] = file_ids
+                    Knowledges.update_knowledge_data_by_id(
+                        id=knowledge_base.id, data=data
+                    )
+
+                    files = Files.get_file_metadatas_by_ids(file_ids)
+
+        knowledge_with_files.append(
+            KnowledgeUserResponse(
+                **knowledge_base.model_dump(),
+                files=files,
+            )
+        )
+    return knowledge_with_files
 
 
 ############################
@@ -59,7 +134,17 @@ async def get_knowledge_items(
 
 
 @router.post("/create", response_model=Optional[KnowledgeResponse])
-async def create_new_knowledge(form_data: KnowledgeForm, user=Depends(get_admin_user)):
+async def create_new_knowledge(
+    request: Request, form_data: KnowledgeForm, user=Depends(get_verified_user)
+):
+    if user.role != "admin" and not has_permission(
+        user.id, "workspace.knowledge", request.app.state.config.USER_PERMISSIONS
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
     knowledge = Knowledges.insert_new_knowledge(user.id, form_data)
 
     if knowledge:
@@ -85,13 +170,20 @@ async def get_knowledge_by_id(id: str, user=Depends(get_verified_user)):
     knowledge = Knowledges.get_knowledge_by_id(id=id)
 
     if knowledge:
-        file_ids = knowledge.data.get("file_ids", []) if knowledge.data else []
-        files = Files.get_files_by_ids(file_ids)
 
-        return KnowledgeFilesResponse(
-            **knowledge.model_dump(),
-            files=files,
-        )
+        if (
+            user.role == "admin"
+            or knowledge.user_id == user.id
+            or has_access(user.id, "read", knowledge.access_control)
+        ):
+
+            file_ids = knowledge.data.get("file_ids", []) if knowledge.data else []
+            files = Files.get_files_by_ids(file_ids)
+
+            return KnowledgeFilesResponse(
+                **knowledge.model_dump(),
+                files=files,
+            )
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -107,11 +199,23 @@ async def get_knowledge_by_id(id: str, user=Depends(get_verified_user)):
 @router.post("/{id}/update", response_model=Optional[KnowledgeFilesResponse])
 async def update_knowledge_by_id(
     id: str,
-    form_data: KnowledgeUpdateForm,
-    user=Depends(get_admin_user),
+    form_data: KnowledgeForm,
+    user=Depends(get_verified_user),
 ):
-    knowledge = Knowledges.update_knowledge_by_id(id=id, form_data=form_data)
+    knowledge = Knowledges.get_knowledge_by_id(id=id)
+    if not knowledge:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
 
+    if knowledge.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    knowledge = Knowledges.update_knowledge_by_id(id=id, form_data=form_data)
     if knowledge:
         file_ids = knowledge.data.get("file_ids", []) if knowledge.data else []
         files = Files.get_files_by_ids(file_ids)
@@ -140,9 +244,22 @@ class KnowledgeFileIdForm(BaseModel):
 def add_file_to_knowledge_by_id(
     id: str,
     form_data: KnowledgeFileIdForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
     knowledge = Knowledges.get_knowledge_by_id(id=id)
+
+    if not knowledge:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if knowledge.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     file = Files.get_file_by_id(form_data.file_id)
     if not file:
         raise HTTPException(
@@ -173,9 +290,7 @@ def add_file_to_knowledge_by_id(
             file_ids.append(form_data.file_id)
             data["file_ids"] = file_ids
 
-            knowledge = Knowledges.update_knowledge_by_id(
-                id=id, form_data=KnowledgeUpdateForm(data=data)
-            )
+            knowledge = Knowledges.update_knowledge_data_by_id(id=id, data=data)
 
             if knowledge:
                 files = Files.get_files_by_ids(file_ids)
@@ -205,9 +320,21 @@ def add_file_to_knowledge_by_id(
 def update_file_from_knowledge_by_id(
     id: str,
     form_data: KnowledgeFileIdForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
     knowledge = Knowledges.get_knowledge_by_id(id=id)
+    if not knowledge:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if knowledge.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     file = Files.get_file_by_id(form_data.file_id)
     if not file:
         raise HTTPException(
@@ -255,9 +382,21 @@ def update_file_from_knowledge_by_id(
 def remove_file_from_knowledge_by_id(
     id: str,
     form_data: KnowledgeFileIdForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
     knowledge = Knowledges.get_knowledge_by_id(id=id)
+    if not knowledge:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if knowledge.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     file = Files.get_file_by_id(form_data.file_id)
     if not file:
         raise HTTPException(
@@ -285,9 +424,7 @@ def remove_file_from_knowledge_by_id(
             file_ids.remove(form_data.file_id)
             data["file_ids"] = file_ids
 
-            knowledge = Knowledges.update_knowledge_by_id(
-                id=id, form_data=KnowledgeUpdateForm(data=data)
-            )
+            knowledge = Knowledges.update_knowledge_data_by_id(id=id, data=data)
 
             if knowledge:
                 files = Files.get_files_by_ids(file_ids)
@@ -313,32 +450,26 @@ def remove_file_from_knowledge_by_id(
         )
 
 
-############################
-# ResetKnowledgeById
-############################
-
-
-@router.post("/{id}/reset", response_model=Optional[KnowledgeResponse])
-async def reset_knowledge_by_id(id: str, user=Depends(get_admin_user)):
-    try:
-        VECTOR_DB_CLIENT.delete_collection(collection_name=id)
-    except Exception as e:
-        log.debug(e)
-        pass
-
-    knowledge = Knowledges.update_knowledge_by_id(
-        id=id, form_data=KnowledgeUpdateForm(data={"file_ids": []})
-    )
-    return knowledge
-
-
 ############################
 # DeleteKnowledgeById
 ############################
 
 
 @router.delete("/{id}/delete", response_model=bool)
-async def delete_knowledge_by_id(id: str, user=Depends(get_admin_user)):
+async def delete_knowledge_by_id(id: str, user=Depends(get_verified_user)):
+    knowledge = Knowledges.get_knowledge_by_id(id=id)
+    if not knowledge:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if knowledge.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     try:
         VECTOR_DB_CLIENT.delete_collection(collection_name=id)
     except Exception as e:
@@ -346,3 +477,34 @@ async def delete_knowledge_by_id(id: str, user=Depends(get_admin_user)):
         pass
     result = Knowledges.delete_knowledge_by_id(id=id)
     return result
+
+
+############################
+# ResetKnowledgeById
+############################
+
+
+@router.post("/{id}/reset", response_model=Optional[KnowledgeResponse])
+async def reset_knowledge_by_id(id: str, user=Depends(get_verified_user)):
+    knowledge = Knowledges.get_knowledge_by_id(id=id)
+    if not knowledge:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if knowledge.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
+    try:
+        VECTOR_DB_CLIENT.delete_collection(collection_name=id)
+    except Exception as e:
+        log.debug(e)
+        pass
+
+    knowledge = Knowledges.update_knowledge_data_by_id(id=id, data={"file_ids": []})
+
+    return knowledge

backend/open_webui/apps/webui/routers/models.py

@@ -4,53 +4,71 @@ from open_webui.apps.webui.models.models import (
     ModelForm,
     ModelModel,
     ModelResponse,
+    ModelUserResponse,
     Models,
 )
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Request, status
+
+
 from open_webui.utils.utils import get_admin_user, get_verified_user
+from open_webui.utils.access_control import has_access, has_permission
+
 
 router = APIRouter()
 
+
 ###########################
-# getModels
+# GetModels
 ###########################
 
 
-@router.get("/", response_model=list[ModelResponse])
+@router.get("/", response_model=list[ModelUserResponse])
 async def get_models(id: Optional[str] = None, user=Depends(get_verified_user)):
-    if id:
-        model = Models.get_model_by_id(id)
-        if model:
-            return [model]
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
+    if user.role == "admin":
+        return Models.get_models()
     else:
-        return Models.get_all_models()
+        return Models.get_models_by_user_id(user.id)
+
+
+###########################
+# GetBaseModels
+###########################
+
+
+@router.get("/base", response_model=list[ModelResponse])
+async def get_base_models(user=Depends(get_admin_user)):
+    return Models.get_base_models()
 
 
 ############################
-# AddNewModel
+# CreateNewModel
 ############################
 
 
-@router.post("/add", response_model=Optional[ModelModel])
-async def add_new_model(
+@router.post("/create", response_model=Optional[ModelModel])
+async def create_new_model(
     request: Request,
     form_data: ModelForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
-    if form_data.id in request.app.state.MODELS:
+    if user.role != "admin" and not has_permission(
+        user.id, "workspace.models", request.app.state.config.USER_PERMISSIONS
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
+    model = Models.get_model_by_id(form_data.id)
+    if model:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.MODEL_ID_TAKEN,
         )
+
     else:
         model = Models.insert_new_model(form_data, user.id)
-
         if model:
             return model
         else:
@@ -60,37 +78,85 @@ async def add_new_model(
             )
 
 
+###########################
+# GetModelById
+###########################
+
+
+# Note: We're not using the typical url path param here, but instead using a query parameter to allow '/' in the id
+@router.get("/model", response_model=Optional[ModelResponse])
+async def get_model_by_id(id: str, user=Depends(get_verified_user)):
+    model = Models.get_model_by_id(id)
+    if model:
+        if (
+            user.role == "admin"
+            or model.user_id == user.id
+            or has_access(user.id, "read", model.access_control)
+        ):
+            return model
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
+############################
+# ToggelModelById
+############################
+
+
+@router.post("/model/toggle", response_model=Optional[ModelResponse])
+async def toggle_model_by_id(id: str, user=Depends(get_verified_user)):
+    model = Models.get_model_by_id(id)
+    if model:
+        if (
+            user.role == "admin"
+            or model.user_id == user.id
+            or has_access(user.id, "write", model.access_control)
+        ):
+            model = Models.toggle_model_by_id(id)
+
+            if model:
+                return model
+            else:
+                raise HTTPException(
+                    status_code=status.HTTP_400_BAD_REQUEST,
+                    detail=ERROR_MESSAGES.DEFAULT("Error updating function"),
+                )
+        else:
+            raise HTTPException(
+                status_code=status.HTTP_401_UNAUTHORIZED,
+                detail=ERROR_MESSAGES.UNAUTHORIZED,
+            )
+    else:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+
 ############################
 # UpdateModelById
 ############################
 
 
-@router.post("/update", response_model=Optional[ModelModel])
+@router.post("/model/update", response_model=Optional[ModelModel])
 async def update_model_by_id(
-    request: Request,
     id: str,
     form_data: ModelForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
     model = Models.get_model_by_id(id)
-    if model:
-        model = Models.update_model_by_id(id, form_data)
-        return model
-    else:
-        if form_data.id in request.app.state.MODELS:
-            model = Models.insert_new_model(form_data, user.id)
-            if model:
-                return model
-            else:
-                raise HTTPException(
-                    status_code=status.HTTP_401_UNAUTHORIZED,
-                    detail=ERROR_MESSAGES.DEFAULT(),
-                )
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.DEFAULT(),
-            )
+
+    if not model:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    model = Models.update_model_by_id(id, form_data)
+    return model
 
 
 ############################
@@ -98,7 +164,26 @@ async def update_model_by_id(
 ############################
 
 
-@router.delete("/delete", response_model=bool)
-async def delete_model_by_id(id: str, user=Depends(get_admin_user)):
+@router.delete("/model/delete", response_model=bool)
+async def delete_model_by_id(id: str, user=Depends(get_verified_user)):
+    model = Models.get_model_by_id(id)
+    if not model:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if model.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
     result = Models.delete_model_by_id(id)
     return result
+
+
+@router.delete("/delete/all", response_model=bool)
+async def delete_all_models(user=Depends(get_admin_user)):
+    result = Models.delete_all_models()
+    return result

backend/open_webui/apps/webui/routers/prompts.py

@@ -1,9 +1,15 @@
 from typing import Optional
 
-from open_webui.apps.webui.models.prompts import PromptForm, PromptModel, Prompts
+from open_webui.apps.webui.models.prompts import (
+    PromptForm,
+    PromptUserResponse,
+    PromptModel,
+    Prompts,
+)
 from open_webui.constants import ERROR_MESSAGES
-from fastapi import APIRouter, Depends, HTTPException, status
+from fastapi import APIRouter, Depends, HTTPException, status, Request
 from open_webui.utils.utils import get_admin_user, get_verified_user
+from open_webui.utils.access_control import has_access, has_permission
 
 router = APIRouter()
 
@@ -14,7 +20,22 @@ router = APIRouter()
 
 @router.get("/", response_model=list[PromptModel])
 async def get_prompts(user=Depends(get_verified_user)):
-    return Prompts.get_prompts()
+    if user.role == "admin":
+        prompts = Prompts.get_prompts()
+    else:
+        prompts = Prompts.get_prompts_by_user_id(user.id, "read")
+
+    return prompts
+
+
+@router.get("/list", response_model=list[PromptUserResponse])
+async def get_prompt_list(user=Depends(get_verified_user)):
+    if user.role == "admin":
+        prompts = Prompts.get_prompts()
+    else:
+        prompts = Prompts.get_prompts_by_user_id(user.id, "write")
+
+    return prompts
 
 
 ############################
@@ -23,7 +44,17 @@ async def get_prompts(user=Depends(get_verified_user)):
 
 
 @router.post("/create", response_model=Optional[PromptModel])
-async def create_new_prompt(form_data: PromptForm, user=Depends(get_admin_user)):
+async def create_new_prompt(
+    request: Request, form_data: PromptForm, user=Depends(get_verified_user)
+):
+    if user.role != "admin" and not has_permission(
+        user.id, "workspace.prompts", request.app.state.config.USER_PERMISSIONS
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
     prompt = Prompts.get_prompt_by_command(form_data.command)
     if prompt is None:
         prompt = Prompts.insert_new_prompt(user.id, form_data)
@@ -50,7 +81,12 @@ async def get_prompt_by_command(command: str, user=Depends(get_verified_user)):
     prompt = Prompts.get_prompt_by_command(f"/{command}")
 
     if prompt:
-        return prompt
+        if (
+            user.role == "admin"
+            or prompt.user_id == user.id
+            or has_access(user.id, "read", prompt.access_control)
+        ):
+            return prompt
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -67,8 +103,21 @@ async def get_prompt_by_command(command: str, user=Depends(get_verified_user)):
 async def update_prompt_by_command(
     command: str,
     form_data: PromptForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
+    prompt = Prompts.get_prompt_by_command(f"/{command}")
+    if not prompt:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if prompt.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     prompt = Prompts.update_prompt_by_command(f"/{command}", form_data)
     if prompt:
         return prompt
@@ -85,6 +134,19 @@ async def update_prompt_by_command(
 
 
 @router.delete("/command/{command}/delete", response_model=bool)
-async def delete_prompt_by_command(command: str, user=Depends(get_admin_user)):
+async def delete_prompt_by_command(command: str, user=Depends(get_verified_user)):
+    prompt = Prompts.get_prompt_by_command(f"/{command}")
+    if not prompt:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if prompt.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
+
     result = Prompts.delete_prompt_by_command(f"/{command}")
     return result

backend/open_webui/apps/webui/routers/tools.py

@@ -1,54 +1,82 @@
-import os
 from pathlib import Path
 from typing import Optional
 
-from open_webui.apps.webui.models.tools import ToolForm, ToolModel, ToolResponse, Tools
-from open_webui.apps.webui.utils import load_toolkit_module_by_id, replace_imports
-from open_webui.config import CACHE_DIR, DATA_DIR
+from open_webui.apps.webui.models.tools import (
+    ToolForm,
+    ToolModel,
+    ToolResponse,
+    ToolUserResponse,
+    Tools,
+)
+from open_webui.apps.webui.utils import load_tools_module_by_id, replace_imports
+from open_webui.config import CACHE_DIR
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from open_webui.utils.tools import get_tools_specs
 from open_webui.utils.utils import get_admin_user, get_verified_user
-
-TOOLS_DIR = f"{DATA_DIR}/tools"
-os.makedirs(TOOLS_DIR, exist_ok=True)
+from open_webui.utils.access_control import has_access, has_permission
 
 
 router = APIRouter()
 
 ############################
-# GetToolkits
+# GetTools
 ############################
 
 
-@router.get("/", response_model=list[ToolResponse])
-async def get_toolkits(user=Depends(get_verified_user)):
-    toolkits = [toolkit for toolkit in Tools.get_tools()]
-    return toolkits
+@router.get("/", response_model=list[ToolUserResponse])
+async def get_tools(user=Depends(get_verified_user)):
+    if user.role == "admin":
+        tools = Tools.get_tools()
+    else:
+        tools = Tools.get_tools_by_user_id(user.id, "read")
+    return tools
 
 
 ############################
-# ExportToolKits
+# GetToolList
+############################
+
+
+@router.get("/list", response_model=list[ToolUserResponse])
+async def get_tool_list(user=Depends(get_verified_user)):
+    if user.role == "admin":
+        tools = Tools.get_tools()
+    else:
+        tools = Tools.get_tools_by_user_id(user.id, "write")
+    return tools
+
+
+############################
+# ExportTools
 ############################
 
 
 @router.get("/export", response_model=list[ToolModel])
-async def get_toolkits(user=Depends(get_admin_user)):
-    toolkits = [toolkit for toolkit in Tools.get_tools()]
-    return toolkits
+async def export_tools(user=Depends(get_admin_user)):
+    tools = Tools.get_tools()
+    return tools
 
 
 ############################
-# CreateNewToolKit
+# CreateNewTools
 ############################
 
 
 @router.post("/create", response_model=Optional[ToolResponse])
-async def create_new_toolkit(
+async def create_new_tools(
     request: Request,
     form_data: ToolForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
+    if user.role != "admin" and not has_permission(
+        user.id, "workspace.knowledge", request.app.state.config.USER_PERMISSIONS
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
     if not form_data.id.isidentifier():
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
@@ -57,30 +85,30 @@ async def create_new_toolkit(
 
     form_data.id = form_data.id.lower()
 
-    toolkit = Tools.get_tool_by_id(form_data.id)
-    if toolkit is None:
+    tools = Tools.get_tool_by_id(form_data.id)
+    if tools is None:
         try:
             form_data.content = replace_imports(form_data.content)
-            toolkit_module, frontmatter = load_toolkit_module_by_id(
+            tools_module, frontmatter = load_tools_module_by_id(
                 form_data.id, content=form_data.content
             )
             form_data.meta.manifest = frontmatter
 
             TOOLS = request.app.state.TOOLS
-            TOOLS[form_data.id] = toolkit_module
+            TOOLS[form_data.id] = tools_module
 
             specs = get_tools_specs(TOOLS[form_data.id])
-            toolkit = Tools.insert_new_tool(user.id, form_data, specs)
+            tools = Tools.insert_new_tool(user.id, form_data, specs)
 
             tool_cache_dir = Path(CACHE_DIR) / "tools" / form_data.id
             tool_cache_dir.mkdir(parents=True, exist_ok=True)
 
-            if toolkit:
-                return toolkit
+            if tools:
+                return tools
             else:
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
-                    detail=ERROR_MESSAGES.DEFAULT("Error creating toolkit"),
+                    detail=ERROR_MESSAGES.DEFAULT("Error creating tools"),
                 )
         except Exception as e:
             print(e)
@@ -96,16 +124,21 @@ async def create_new_toolkit(
 
 
 ############################
-# GetToolkitById
+# GetToolsById
 ############################
 
 
 @router.get("/id/{id}", response_model=Optional[ToolModel])
-async def get_toolkit_by_id(id: str, user=Depends(get_admin_user)):
-    toolkit = Tools.get_tool_by_id(id)
+async def get_tools_by_id(id: str, user=Depends(get_verified_user)):
+    tools = Tools.get_tool_by_id(id)
 
-    if toolkit:
-        return toolkit
+    if tools:
+        if (
+            user.role == "admin"
+            or tools.user_id == user.id
+            or has_access(user.id, "read", tools.access_control)
+        ):
+            return tools
     else:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
@@ -114,26 +147,39 @@ async def get_toolkit_by_id(id: str, user=Depends(get_admin_user)):
 
 
 ############################
-# UpdateToolkitById
+# UpdateToolsById
 ############################
 
 
 @router.post("/id/{id}/update", response_model=Optional[ToolModel])
-async def update_toolkit_by_id(
+async def update_tools_by_id(
     request: Request,
     id: str,
     form_data: ToolForm,
-    user=Depends(get_admin_user),
+    user=Depends(get_verified_user),
 ):
+    tools = Tools.get_tool_by_id(id)
+    if not tools:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+
+    if tools.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
     try:
         form_data.content = replace_imports(form_data.content)
-        toolkit_module, frontmatter = load_toolkit_module_by_id(
+        tools_module, frontmatter = load_tools_module_by_id(
             id, content=form_data.content
         )
         form_data.meta.manifest = frontmatter
 
         TOOLS = request.app.state.TOOLS
-        TOOLS[id] = toolkit_module
+        TOOLS[id] = tools_module
 
         specs = get_tools_specs(TOOLS[id])
 
@@ -143,14 +189,14 @@ async def update_toolkit_by_id(
         }
 
         print(updated)
-        toolkit = Tools.update_tool_by_id(id, updated)
+        tools = Tools.update_tool_by_id(id, updated)
 
-        if toolkit:
-            return toolkit
+        if tools:
+            return tools
         else:
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.DEFAULT("Error updating toolkit"),
+                detail=ERROR_MESSAGES.DEFAULT("Error updating tools"),
             )
 
     except Exception as e:
@@ -161,14 +207,28 @@ async def update_toolkit_by_id(
 
 
 ############################
-# DeleteToolkitById
+# DeleteToolsById
 ############################
 
 
 @router.delete("/id/{id}/delete", response_model=bool)
-async def delete_toolkit_by_id(request: Request, id: str, user=Depends(get_admin_user)):
-    result = Tools.delete_tool_by_id(id)
+async def delete_tools_by_id(
+    request: Request, id: str, user=Depends(get_verified_user)
+):
+    tools = Tools.get_tool_by_id(id)
+    if not tools:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
 
+    if tools.user_id != user.id and user.role != "admin":
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.UNAUTHORIZED,
+        )
+
+    result = Tools.delete_tool_by_id(id)
     if result:
         TOOLS = request.app.state.TOOLS
         if id in TOOLS:
@@ -183,9 +243,9 @@ async def delete_toolkit_by_id(request: Request, id: str, user=Depends(get_admin
 
 
 @router.get("/id/{id}/valves", response_model=Optional[dict])
-async def get_toolkit_valves_by_id(id: str, user=Depends(get_admin_user)):
-    toolkit = Tools.get_tool_by_id(id)
-    if toolkit:
+async def get_tools_valves_by_id(id: str, user=Depends(get_verified_user)):
+    tools = Tools.get_tool_by_id(id)
+    if tools:
         try:
             valves = Tools.get_tool_valves_by_id(id)
             return valves
@@ -207,19 +267,19 @@ async def get_toolkit_valves_by_id(id: str, user=Depends(get_admin_user)):
 
 
 @router.get("/id/{id}/valves/spec", response_model=Optional[dict])
-async def get_toolkit_valves_spec_by_id(
-    request: Request, id: str, user=Depends(get_admin_user)
+async def get_tools_valves_spec_by_id(
+    request: Request, id: str, user=Depends(get_verified_user)
 ):
-    toolkit = Tools.get_tool_by_id(id)
-    if toolkit:
+    tools = Tools.get_tool_by_id(id)
+    if tools:
         if id in request.app.state.TOOLS:
-            toolkit_module = request.app.state.TOOLS[id]
+            tools_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, _ = load_toolkit_module_by_id(id)
-            request.app.state.TOOLS[id] = toolkit_module
+            tools_module, _ = load_tools_module_by_id(id)
+            request.app.state.TOOLS[id] = tools_module
 
-        if hasattr(toolkit_module, "Valves"):
-            Valves = toolkit_module.Valves
+        if hasattr(tools_module, "Valves"):
+            Valves = tools_module.Valves
             return Valves.schema()
         return None
     else:
@@ -235,42 +295,39 @@ async def get_toolkit_valves_spec_by_id(
 
 
 @router.post("/id/{id}/valves/update", response_model=Optional[dict])
-async def update_toolkit_valves_by_id(
-    request: Request, id: str, form_data: dict, user=Depends(get_admin_user)
+async def update_tools_valves_by_id(
+    request: Request, id: str, form_data: dict, user=Depends(get_verified_user)
 ):
-    toolkit = Tools.get_tool_by_id(id)
-    if toolkit:
-        if id in request.app.state.TOOLS:
-            toolkit_module = request.app.state.TOOLS[id]
-        else:
-            toolkit_module, _ = load_toolkit_module_by_id(id)
-            request.app.state.TOOLS[id] = toolkit_module
-
-        if hasattr(toolkit_module, "Valves"):
-            Valves = toolkit_module.Valves
-
-            try:
-                form_data = {k: v for k, v in form_data.items() if v is not None}
-                valves = Valves(**form_data)
-                Tools.update_tool_valves_by_id(id, valves.model_dump())
-                return valves.model_dump()
-            except Exception as e:
-                print(e)
-                raise HTTPException(
-                    status_code=status.HTTP_400_BAD_REQUEST,
-                    detail=ERROR_MESSAGES.DEFAULT(str(e)),
-                )
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
-
-    else:
+    tools = Tools.get_tool_by_id(id)
+    if not tools:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.NOT_FOUND,
         )
+    if id in request.app.state.TOOLS:
+        tools_module = request.app.state.TOOLS[id]
+    else:
+        tools_module, _ = load_tools_module_by_id(id)
+        request.app.state.TOOLS[id] = tools_module
+
+    if not hasattr(tools_module, "Valves"):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+    Valves = tools_module.Valves
+
+    try:
+        form_data = {k: v for k, v in form_data.items() if v is not None}
+        valves = Valves(**form_data)
+        Tools.update_tool_valves_by_id(id, valves.model_dump())
+        return valves.model_dump()
+    except Exception as e:
+        print(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(str(e)),
+        )
 
 
 ############################
@@ -279,9 +336,9 @@ async def update_toolkit_valves_by_id(
 
 
 @router.get("/id/{id}/valves/user", response_model=Optional[dict])
-async def get_toolkit_user_valves_by_id(id: str, user=Depends(get_verified_user)):
-    toolkit = Tools.get_tool_by_id(id)
-    if toolkit:
+async def get_tools_user_valves_by_id(id: str, user=Depends(get_verified_user)):
+    tools = Tools.get_tool_by_id(id)
+    if tools:
         try:
             user_valves = Tools.get_user_valves_by_id_and_user_id(id, user.id)
             return user_valves
@@ -298,19 +355,19 @@ async def get_toolkit_user_valves_by_id(id: str, user=Depends(get_verified_user)
 
 
 @router.get("/id/{id}/valves/user/spec", response_model=Optional[dict])
-async def get_toolkit_user_valves_spec_by_id(
+async def get_tools_user_valves_spec_by_id(
     request: Request, id: str, user=Depends(get_verified_user)
 ):
-    toolkit = Tools.get_tool_by_id(id)
-    if toolkit:
+    tools = Tools.get_tool_by_id(id)
+    if tools:
         if id in request.app.state.TOOLS:
-            toolkit_module = request.app.state.TOOLS[id]
+            tools_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, _ = load_toolkit_module_by_id(id)
-            request.app.state.TOOLS[id] = toolkit_module
+            tools_module, _ = load_tools_module_by_id(id)
+            request.app.state.TOOLS[id] = tools_module
 
-        if hasattr(toolkit_module, "UserValves"):
-            UserValves = toolkit_module.UserValves
+        if hasattr(tools_module, "UserValves"):
+            UserValves = tools_module.UserValves
             return UserValves.schema()
         return None
     else:
@@ -321,20 +378,20 @@ async def get_toolkit_user_valves_spec_by_id(
 
 
 @router.post("/id/{id}/valves/user/update", response_model=Optional[dict])
-async def update_toolkit_user_valves_by_id(
+async def update_tools_user_valves_by_id(
     request: Request, id: str, form_data: dict, user=Depends(get_verified_user)
 ):
-    toolkit = Tools.get_tool_by_id(id)
+    tools = Tools.get_tool_by_id(id)
 
-    if toolkit:
+    if tools:
         if id in request.app.state.TOOLS:
-            toolkit_module = request.app.state.TOOLS[id]
+            tools_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, _ = load_toolkit_module_by_id(id)
-            request.app.state.TOOLS[id] = toolkit_module
+            tools_module, _ = load_tools_module_by_id(id)
+            request.app.state.TOOLS[id] = tools_module
 
-        if hasattr(toolkit_module, "UserValves"):
-            UserValves = toolkit_module.UserValves
+        if hasattr(tools_module, "UserValves"):
+            UserValves = tools_module.UserValves
 
             try:
                 form_data = {k: v for k, v in form_data.items() if v is not None}

backend/open_webui/apps/webui/routers/users.py

@@ -31,21 +31,58 @@ async def get_users(skip: int = 0, limit: int = 50, user=Depends(get_admin_user)
     return Users.get_users(skip, limit)
 
 
+############################
+# User Groups
+############################
+
+
+@router.get("/groups")
+async def get_user_groups(user=Depends(get_verified_user)):
+    return Users.get_user_groups(user.id)
+
+
 ############################
 # User Permissions
 ############################
 
 
-@router.get("/permissions/user")
+@router.get("/permissions")
+async def get_user_permissisions(user=Depends(get_verified_user)):
+    return Users.get_user_groups(user.id)
+
+
+############################
+# User Default Permissions
+############################
+class WorkspacePermissions(BaseModel):
+    models: bool
+    knowledge: bool
+    prompts: bool
+    tools: bool
+
+
+class ChatPermissions(BaseModel):
+    file_upload: bool
+    delete: bool
+    edit: bool
+    temporary: bool
+
+
+class UserPermissions(BaseModel):
+    workspace: WorkspacePermissions
+    chat: ChatPermissions
+
+
+@router.get("/default/permissions")
 async def get_user_permissions(request: Request, user=Depends(get_admin_user)):
     return request.app.state.config.USER_PERMISSIONS
 
 
-@router.post("/permissions/user")
+@router.post("/default/permissions")
 async def update_user_permissions(
-    request: Request, form_data: dict, user=Depends(get_admin_user)
+    request: Request, form_data: UserPermissions, user=Depends(get_admin_user)
 ):
-    request.app.state.config.USER_PERMISSIONS = form_data
+    request.app.state.config.USER_PERMISSIONS = form_data.model_dump()
     return request.app.state.config.USER_PERMISSIONS
 
 

backend/open_webui/apps/webui/routers/utils.py

@@ -1,16 +1,14 @@
-import site
-from pathlib import Path
-
 import black
 import markdown
+
+from open_webui.apps.webui.models.chats import ChatTitleMessagesForm
 from open_webui.config import DATA_DIR, ENABLE_ADMIN_EXPORT
-from open_webui.env import FONTS_DIR
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Response, status
-from fpdf import FPDF
 from pydantic import BaseModel
 from starlette.responses import FileResponse
 from open_webui.utils.misc import get_gravatar_url
+from open_webui.utils.pdf_generator import PDFGenerator
 from open_webui.utils.utils import get_admin_user
 
 router = APIRouter()
@@ -56,58 +54,19 @@ class ChatForm(BaseModel):
 
 @router.post("/pdf")
 async def download_chat_as_pdf(
-    form_data: ChatForm,
+    form_data: ChatTitleMessagesForm,
 ):
-    global FONTS_DIR
+    try:
+        pdf_bytes = PDFGenerator(form_data).generate_chat_pdf()
 
-    pdf = FPDF()
-    pdf.add_page()
-
-    # When running using `pip install` the static directory is in the site packages.
-    if not FONTS_DIR.exists():
-        FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
-    # When running using `pip install -e .` the static directory is in the site packages.
-    # This path only works if `open-webui serve` is run from the root of this project.
-    if not FONTS_DIR.exists():
-        FONTS_DIR = Path("./backend/static/fonts")
-
-    pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
-    pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
-    pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
-    pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
-    pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
-    pdf.add_font("NotoSansSC", "", f"{FONTS_DIR}/NotoSansSC-Regular.ttf")
-
-    pdf.set_font("NotoSans", size=12)
-    pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP", "NotoSansSC"])
-
-    pdf.set_auto_page_break(auto=True, margin=15)
-
-    # Adjust the effective page width for multi_cell
-    effective_page_width = (
-        pdf.w - 2 * pdf.l_margin - 10
-    )  # Subtracted an additional 10 for extra padding
-
-    # Add chat messages
-    for message in form_data.messages:
-        role = message["role"]
-        content = message["content"]
-        pdf.set_font("NotoSans", "B", size=14)  # Bold for the role
-        pdf.multi_cell(effective_page_width, 10, f"{role.upper()}", 0, "L")
-        pdf.ln(1)  # Extra space between messages
-
-        pdf.set_font("NotoSans", size=10)  # Regular for content
-        pdf.multi_cell(effective_page_width, 6, content, 0, "L")
-        pdf.ln(1.5)  # Extra space between messages
-
-    # Save the pdf with name .pdf
-    pdf_bytes = pdf.output()
-
-    return Response(
-        content=bytes(pdf_bytes),
-        media_type="application/pdf",
-        headers={"Content-Disposition": "attachment;filename=chat.pdf"},
-    )
+        return Response(
+            content=pdf_bytes,
+            media_type="application/pdf",
+            headers={"Content-Disposition": "attachment;filename=chat.pdf"},
+        )
+    except Exception as e:
+        print(e)
+        raise HTTPException(status_code=400, detail=str(e))
 
 
 @router.get("/db/download")

backend/open_webui/apps/webui/utils.py

@@ -5,10 +5,14 @@ import sys
 from importlib import util
 import types
 import tempfile
+import logging
 
+from open_webui.env import SRC_LOG_LEVELS
 from open_webui.apps.webui.models.functions import Functions
 from open_webui.apps.webui.models.tools import Tools
-from open_webui.config import FUNCTIONS_DIR, TOOLS_DIR
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
 def extract_frontmatter(content):
@@ -64,7 +68,7 @@ def replace_imports(content):
     return content
 
 
-def load_toolkit_module_by_id(toolkit_id, content=None):
+def load_tools_module_by_id(toolkit_id, content=None):
 
     if content is None:
         tool = Tools.get_tool_by_id(toolkit_id)
@@ -96,7 +100,7 @@ def load_toolkit_module_by_id(toolkit_id, content=None):
         # Executing the modified content in the created module's namespace
         exec(content, module.__dict__)
         frontmatter = extract_frontmatter(content)
-        print(f"Loaded module: {module.__name__}")
+        log.info(f"Loaded module: {module.__name__}")
 
         # Create and return the object if the class 'Tools' is found in the module
         if hasattr(module, "Tools"):
@@ -104,7 +108,7 @@ def load_toolkit_module_by_id(toolkit_id, content=None):
         else:
             raise Exception("No Tools class found in the module")
     except Exception as e:
-        print(f"Error loading module: {toolkit_id}: {e}")
+        log.error(f"Error loading module: {toolkit_id}: {e}")
         del sys.modules[module_name]  # Clean up
         raise e
     finally:
@@ -140,7 +144,7 @@ def load_function_module_by_id(function_id, content=None):
         # Execute the modified content in the created module's namespace
         exec(content, module.__dict__)
         frontmatter = extract_frontmatter(content)
-        print(f"Loaded module: {module.__name__}")
+        log.info(f"Loaded module: {module.__name__}")
 
         # Create appropriate object based on available class type in the module
         if hasattr(module, "Pipe"):
@@ -152,7 +156,7 @@ def load_function_module_by_id(function_id, content=None):
         else:
             raise Exception("No Function class found in the module")
     except Exception as e:
-        print(f"Error loading module: {function_id}: {e}")
+        log.error(f"Error loading module: {function_id}: {e}")
         del sys.modules[module_name]  # Cleanup by removing the module in case of error
 
         Functions.update_function_by_id(function_id, {"is_active": False})
@@ -165,7 +169,7 @@ def install_frontmatter_requirements(requirements):
     if requirements:
         req_list = [req.strip() for req in requirements.split(",")]
         for req in req_list:
-            print(f"Installing requirement: {req}")
+            log.info(f"Installing requirement: {req}")
             subprocess.check_call([sys.executable, "-m", "pip", "install", req])
     else:
-        print("No requirements found in frontmatter.")
+        log.info("No requirements found in frontmatter.")

backend/open_webui/config.py

@@ -20,6 +20,7 @@ from open_webui.env import (
     WEBUI_FAVICON_URL,
     WEBUI_NAME,
     log,
+    DATABASE_URL,
 )
 from pydantic import BaseModel
 from sqlalchemy import JSON, Column, DateTime, Integer, func
@@ -264,6 +265,13 @@ class AppConfig:
 # WEBUI_AUTH (Required for security)
 ####################################
 
+ENABLE_API_KEY = PersistentConfig(
+    "ENABLE_API_KEY",
+    "auth.api_key.enable",
+    os.environ.get("ENABLE_API_KEY", "True").lower() == "true",
+)
+
+
 JWT_EXPIRES_IN = PersistentConfig(
     "JWT_EXPIRES_IN", "auth.jwt_expiry", os.environ.get("JWT_EXPIRES_IN", "-1")
 )
@@ -383,7 +391,7 @@ OAUTH_USERNAME_CLAIM = PersistentConfig(
 )
 
 OAUTH_PICTURE_CLAIM = PersistentConfig(
-    "OAUTH_USERNAME_CLAIM",
+    "OAUTH_PICTURE_CLAIM",
     "oauth.oidc.avatar_claim",
     os.environ.get("OAUTH_PICTURE_CLAIM", "picture"),
 )
@@ -394,6 +402,33 @@ OAUTH_EMAIL_CLAIM = PersistentConfig(
     os.environ.get("OAUTH_EMAIL_CLAIM", "email"),
 )
 
+ENABLE_OAUTH_ROLE_MANAGEMENT = PersistentConfig(
+    "ENABLE_OAUTH_ROLE_MANAGEMENT",
+    "oauth.enable_role_mapping",
+    os.environ.get("ENABLE_OAUTH_ROLE_MANAGEMENT", "False").lower() == "true",
+)
+
+OAUTH_ROLES_CLAIM = PersistentConfig(
+    "OAUTH_ROLES_CLAIM",
+    "oauth.roles_claim",
+    os.environ.get("OAUTH_ROLES_CLAIM", "roles"),
+)
+
+OAUTH_ALLOWED_ROLES = PersistentConfig(
+    "OAUTH_ALLOWED_ROLES",
+    "oauth.allowed_roles",
+    [
+        role.strip()
+        for role in os.environ.get("OAUTH_ALLOWED_ROLES", "user,admin").split(",")
+    ],
+)
+
+OAUTH_ADMIN_ROLES = PersistentConfig(
+    "OAUTH_ADMIN_ROLES",
+    "oauth.admin_roles",
+    [role.strip() for role in os.environ.get("OAUTH_ADMIN_ROLES", "admin").split(",")],
+)
+
 
 def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
@@ -506,6 +541,18 @@ if CUSTOM_NAME:
         pass
 
 
+####################################
+# STORAGE PROVIDER
+####################################
+
+STORAGE_PROVIDER = os.environ.get("STORAGE_PROVIDER", "")  # defaults to local, s3
+
+S3_ACCESS_KEY_ID = os.environ.get("S3_ACCESS_KEY_ID", None)
+S3_SECRET_ACCESS_KEY = os.environ.get("S3_SECRET_ACCESS_KEY", None)
+S3_REGION_NAME = os.environ.get("S3_REGION_NAME", None)
+S3_BUCKET_NAME = os.environ.get("S3_BUCKET_NAME", None)
+S3_ENDPOINT_URL = os.environ.get("S3_ENDPOINT_URL", None)
+
 ####################################
 # File Upload DIR
 ####################################
@@ -521,26 +568,10 @@ Path(UPLOAD_DIR).mkdir(parents=True, exist_ok=True)
 CACHE_DIR = f"{DATA_DIR}/cache"
 Path(CACHE_DIR).mkdir(parents=True, exist_ok=True)
 
-####################################
-# Tools DIR
-####################################
-
-TOOLS_DIR = os.getenv("TOOLS_DIR", f"{DATA_DIR}/tools")
-Path(TOOLS_DIR).mkdir(parents=True, exist_ok=True)
-
-
-####################################
-# Functions DIR
-####################################
-
-FUNCTIONS_DIR = os.getenv("FUNCTIONS_DIR", f"{DATA_DIR}/functions")
-Path(FUNCTIONS_DIR).mkdir(parents=True, exist_ok=True)
-
 ####################################
 # OLLAMA_BASE_URL
 ####################################
 
-
 ENABLE_OLLAMA_API = PersistentConfig(
     "ENABLE_OLLAMA_API",
     "ollama.enable",
@@ -583,6 +614,12 @@ OLLAMA_BASE_URLS = PersistentConfig(
     "OLLAMA_BASE_URLS", "ollama.base_urls", OLLAMA_BASE_URLS
 )
 
+OLLAMA_API_CONFIGS = PersistentConfig(
+    "OLLAMA_API_CONFIGS",
+    "ollama.api_configs",
+    {},
+)
+
 ####################################
 # OPENAI_API
 ####################################
@@ -623,15 +660,20 @@ OPENAI_API_BASE_URLS = PersistentConfig(
     "OPENAI_API_BASE_URLS", "openai.api_base_urls", OPENAI_API_BASE_URLS
 )
 
-OPENAI_API_KEY = ""
+OPENAI_API_CONFIGS = PersistentConfig(
+    "OPENAI_API_CONFIGS",
+    "openai.api_configs",
+    {},
+)
 
+# Get the actual OpenAI API key based on the base URL
+OPENAI_API_KEY = ""
 try:
     OPENAI_API_KEY = OPENAI_API_KEYS.value[
         OPENAI_API_BASE_URLS.value.index("https://api.openai.com/v1")
     ]
 except Exception:
     pass
-
 OPENAI_API_BASE_URL = "https://api.openai.com/v1"
 
 ####################################
@@ -698,18 +740,48 @@ DEFAULT_PROMPT_SUGGESTIONS = PersistentConfig(
     ],
 )
 
+MODEL_ORDER_LIST = PersistentConfig(
+    "MODEL_ORDER_LIST",
+    "ui.model_order_list",
+    [],
+)
+
 DEFAULT_USER_ROLE = PersistentConfig(
     "DEFAULT_USER_ROLE",
     "ui.default_user_role",
     os.getenv("DEFAULT_USER_ROLE", "pending"),
 )
 
-USER_PERMISSIONS_CHAT_DELETION = (
-    os.environ.get("USER_PERMISSIONS_CHAT_DELETION", "True").lower() == "true"
+
+USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS", "False").lower()
+    == "true"
 )
 
-USER_PERMISSIONS_CHAT_EDITING = (
-    os.environ.get("USER_PERMISSIONS_CHAT_EDITING", "True").lower() == "true"
+USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS", "False").lower() == "true"
+)
+
+USER_PERMISSIONS_CHAT_FILE_UPLOAD = (
+    os.environ.get("USER_PERMISSIONS_CHAT_FILE_UPLOAD", "True").lower() == "true"
+)
+
+USER_PERMISSIONS_CHAT_DELETE = (
+    os.environ.get("USER_PERMISSIONS_CHAT_DELETE", "True").lower() == "true"
+)
+
+USER_PERMISSIONS_CHAT_EDIT = (
+    os.environ.get("USER_PERMISSIONS_CHAT_EDIT", "True").lower() == "true"
 )
 
 USER_PERMISSIONS_CHAT_TEMPORARY = (
@@ -718,28 +790,45 @@ USER_PERMISSIONS_CHAT_TEMPORARY = (
 
 USER_PERMISSIONS = PersistentConfig(
     "USER_PERMISSIONS",
-    "ui.user_permissions",
+    "user.permissions",
     {
+        "workspace": {
+            "models": USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS,
+            "knowledge": USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS,
+            "prompts": USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS,
+            "tools": USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS,
+        },
         "chat": {
-            "deletion": USER_PERMISSIONS_CHAT_DELETION,
-            "editing": USER_PERMISSIONS_CHAT_EDITING,
+            "file_upload": USER_PERMISSIONS_CHAT_FILE_UPLOAD,
+            "delete": USER_PERMISSIONS_CHAT_DELETE,
+            "edit": USER_PERMISSIONS_CHAT_EDIT,
             "temporary": USER_PERMISSIONS_CHAT_TEMPORARY,
-        }
+        },
     },
 )
 
-ENABLE_MODEL_FILTER = PersistentConfig(
-    "ENABLE_MODEL_FILTER",
-    "model_filter.enable",
-    os.environ.get("ENABLE_MODEL_FILTER", "False").lower() == "true",
+
+ENABLE_EVALUATION_ARENA_MODELS = PersistentConfig(
+    "ENABLE_EVALUATION_ARENA_MODELS",
+    "evaluation.arena.enable",
+    os.environ.get("ENABLE_EVALUATION_ARENA_MODELS", "True").lower() == "true",
 )
-MODEL_FILTER_LIST = os.environ.get("MODEL_FILTER_LIST", "")
-MODEL_FILTER_LIST = PersistentConfig(
-    "MODEL_FILTER_LIST",
-    "model_filter.list",
-    [model.strip() for model in MODEL_FILTER_LIST.split(";")],
+EVALUATION_ARENA_MODELS = PersistentConfig(
+    "EVALUATION_ARENA_MODELS",
+    "evaluation.arena.models",
+    [],
 )
 
+DEFAULT_ARENA_MODEL = {
+    "id": "arena-model",
+    "name": "Arena Model",
+    "meta": {
+        "profile_image_url": "/favicon.png",
+        "description": "Submit your questions to anonymous AI chatbots and vote on the best response.",
+        "model_ids": None,
+    },
+}
+
 WEBHOOK_URL = PersistentConfig(
     "WEBHOOK_URL", "webhook_url", os.environ.get("WEBHOOK_URL", "")
 )
@@ -853,19 +942,62 @@ TITLE_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
     os.environ.get("TITLE_GENERATION_PROMPT_TEMPLATE", ""),
 )
 
-ENABLE_SEARCH_QUERY = PersistentConfig(
-    "ENABLE_SEARCH_QUERY",
-    "task.search.enable",
-    os.environ.get("ENABLE_SEARCH_QUERY", "True").lower() == "true",
+TAGS_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "TAGS_GENERATION_PROMPT_TEMPLATE",
+    "task.tags.prompt_template",
+    os.environ.get("TAGS_GENERATION_PROMPT_TEMPLATE", ""),
+)
+
+ENABLE_TAGS_GENERATION = PersistentConfig(
+    "ENABLE_TAGS_GENERATION",
+    "task.tags.enable",
+    os.environ.get("ENABLE_TAGS_GENERATION", "True").lower() == "true",
 )
 
 
-SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
-    "SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE",
-    "task.search.prompt_template",
-    os.environ.get("SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE", ""),
+ENABLE_SEARCH_QUERY_GENERATION = PersistentConfig(
+    "ENABLE_SEARCH_QUERY_GENERATION",
+    "task.query.search.enable",
+    os.environ.get("ENABLE_SEARCH_QUERY_GENERATION", "True").lower() == "true",
 )
 
+ENABLE_RETRIEVAL_QUERY_GENERATION = PersistentConfig(
+    "ENABLE_RETRIEVAL_QUERY_GENERATION",
+    "task.query.retrieval.enable",
+    os.environ.get("ENABLE_RETRIEVAL_QUERY_GENERATION", "True").lower() == "true",
+)
+
+
+QUERY_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "QUERY_GENERATION_PROMPT_TEMPLATE",
+    "task.query.prompt_template",
+    os.environ.get("QUERY_GENERATION_PROMPT_TEMPLATE", ""),
+)
+
+DEFAULT_QUERY_GENERATION_PROMPT_TEMPLATE = """### Task:
+Analyze the chat history to determine the necessity of generating search queries. By default, **prioritize generating 1-3 broad and relevant search queries** unless it is absolutely certain that no additional information is required. The aim is to retrieve comprehensive, updated, and valuable information even with minimal uncertainty. If no search is unequivocally needed, return an empty list.
+
+### Guidelines:
+- Respond **EXCLUSIVELY** with a JSON object. Any form of extra commentary, explanation, or additional text is strictly prohibited.
+- When generating search queries, respond in the format: { "queries": ["query1", "query2"] }, ensuring each query is distinct, concise, and relevant to the topic.
+- If and only if it is entirely certain that no useful results can be retrieved by a search, return: { "queries": [] }.
+- Err on the side of suggesting search queries if there is **any chance** they might provide useful or updated information.
+- Be concise and focused on composing high-quality search queries, avoiding unnecessary elaboration, commentary, or assumptions.
+- Assume today's date is: {{CURRENT_DATE}}.
+- Always prioritize providing actionable and broad queries that maximize informational coverage.
+
+### Output:
+Strictly return in JSON format: 
+{
+  "queries": ["query1", "query2"]
+}
+
+### Chat History:
+<chat_history>
+{{MESSAGES:END:6}}
+</chat_history>
+"""
+
 
 TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
     "TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE",
@@ -886,6 +1018,8 @@ CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
 CHROMA_DATABASE = os.environ.get("CHROMA_DATABASE", chromadb.DEFAULT_DATABASE)
 CHROMA_HTTP_HOST = os.environ.get("CHROMA_HTTP_HOST", "")
 CHROMA_HTTP_PORT = int(os.environ.get("CHROMA_HTTP_PORT", "8000"))
+CHROMA_CLIENT_AUTH_PROVIDER = os.environ.get("CHROMA_CLIENT_AUTH_PROVIDER", "")
+CHROMA_CLIENT_AUTH_CREDENTIALS = os.environ.get("CHROMA_CLIENT_AUTH_CREDENTIALS", "")
 # Comma-separated list of header=value pairs
 CHROMA_HTTP_HEADERS = os.environ.get("CHROMA_HTTP_HEADERS", "")
 if CHROMA_HTTP_HEADERS:
@@ -901,6 +1035,24 @@ CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
 
 MILVUS_URI = os.environ.get("MILVUS_URI", f"{DATA_DIR}/vector_db/milvus.db")
 
+# Qdrant
+QDRANT_URI = os.environ.get("QDRANT_URI", None)
+QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY", None)
+
+# OpenSearch
+OPENSEARCH_URI = os.environ.get("OPENSEARCH_URI", "https://localhost:9200")
+OPENSEARCH_SSL = os.environ.get("OPENSEARCH_SSL", True)
+OPENSEARCH_CERT_VERIFY = os.environ.get("OPENSEARCH_CERT_VERIFY", False)
+OPENSEARCH_USERNAME = os.environ.get("OPENSEARCH_USERNAME", None)
+OPENSEARCH_PASSWORD = os.environ.get("OPENSEARCH_PASSWORD", None)
+
+# Pgvector
+PGVECTOR_DB_URL = os.environ.get("PGVECTOR_DB_URL", DATABASE_URL)
+if VECTOR_DB == "pgvector" and not PGVECTOR_DB_URL.startswith("postgres"):
+    raise ValueError(
+        "Pgvector requires setting PGVECTOR_DB_URL or using Postgres with vector extension as the primary database."
+    )
+
 ####################################
 # Information Retrieval (RAG)
 ####################################
@@ -979,17 +1131,20 @@ RAG_EMBEDDING_MODEL = PersistentConfig(
 log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL.value}")
 
 RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
-    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
+    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "True").lower() == "true"
 )
 
 RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE = (
-    os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
+    os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "True").lower() == "true"
 )
 
-RAG_EMBEDDING_OPENAI_BATCH_SIZE = PersistentConfig(
-    "RAG_EMBEDDING_OPENAI_BATCH_SIZE",
-    "rag.embedding_openai_batch_size",
-    int(os.environ.get("RAG_EMBEDDING_OPENAI_BATCH_SIZE", "1")),
+RAG_EMBEDDING_BATCH_SIZE = PersistentConfig(
+    "RAG_EMBEDDING_BATCH_SIZE",
+    "rag.embedding_batch_size",
+    int(
+        os.environ.get("RAG_EMBEDDING_BATCH_SIZE")
+        or os.environ.get("RAG_EMBEDDING_OPENAI_BATCH_SIZE", "1")
+    ),
 )
 
 RAG_RERANKING_MODEL = PersistentConfig(
@@ -1001,13 +1156,29 @@ if RAG_RERANKING_MODEL.value != "":
     log.info(f"Reranking model set: {RAG_RERANKING_MODEL.value}")
 
 RAG_RERANKING_MODEL_AUTO_UPDATE = (
-    os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "").lower() == "true"
+    os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "True").lower() == "true"
 )
 
 RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
-    os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
+    os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "True").lower() == "true"
 )
 
+
+RAG_TEXT_SPLITTER = PersistentConfig(
+    "RAG_TEXT_SPLITTER",
+    "rag.text_splitter",
+    os.environ.get("RAG_TEXT_SPLITTER", ""),
+)
+
+
+TIKTOKEN_CACHE_DIR = os.environ.get("TIKTOKEN_CACHE_DIR", f"{CACHE_DIR}/tiktoken")
+TIKTOKEN_ENCODING_NAME = PersistentConfig(
+    "TIKTOKEN_ENCODING_NAME",
+    "rag.tiktoken_encoding_name",
+    os.environ.get("TIKTOKEN_ENCODING_NAME", "cl100k_base"),
+)
+
+
 CHUNK_SIZE = PersistentConfig(
     "CHUNK_SIZE", "rag.chunk_size", int(os.environ.get("CHUNK_SIZE", "1000"))
 )
@@ -1017,23 +1188,34 @@ CHUNK_OVERLAP = PersistentConfig(
     int(os.environ.get("CHUNK_OVERLAP", "100")),
 )
 
-DEFAULT_RAG_TEMPLATE = """You are given a user query, some textual context and rules, all inside xml tags. You have to answer the query based on the context while respecting the rules.
+DEFAULT_RAG_TEMPLATE = """### Task:
+Respond to the user query using the provided context, incorporating inline citations in the format [source_id] **only when the <source_id> tag is explicitly provided** in the context.
+
+### Guidelines:
+- If you don't know the answer, clearly state that.
+- If uncertain, ask the user for clarification.
+- Respond in the same language as the user's query.
+- If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
+- If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
+- **Only include inline citations using [source_id] when a <source_id> tag is explicitly provided in the context.**  
+- Do not cite if the <source_id> tag is not provided in the context.  
+- Do not use XML tags in your response.
+- Ensure citations are concise and directly related to the information provided.
+
+### Example of Citation:
+If the user asks about a specific topic and the information is found in "whitepaper.pdf" with a provided <source_id>, the response should include the citation like so:  
+* "According to the study, the proposed method increases efficiency by 20% [whitepaper.pdf]."
+If no <source_id> is present, the response should omit the citation.
+
+### Output:
+Provide a clear and direct response to the user's query, including inline citations in the format [source_id] only when the <source_id> tag is present in the context.
 
 <context>
-[context]
+{{CONTEXT}}
 </context>
 
-<rules>
-- If you don't know, just say so.
-- If you are not sure, ask for clarification.
-- Answer in the same language as the user query.
-- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
-- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
-- Answer directly and without using xml tags.
-</rules>
-
 <user_query>
-[query]
+{{QUERY}}
 </user_query>
 """
 
@@ -1054,6 +1236,19 @@ RAG_OPENAI_API_KEY = PersistentConfig(
     os.getenv("RAG_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+RAG_OLLAMA_BASE_URL = PersistentConfig(
+    "RAG_OLLAMA_BASE_URL",
+    "rag.ollama.url",
+    os.getenv("RAG_OLLAMA_BASE_URL", OLLAMA_BASE_URL),
+)
+
+RAG_OLLAMA_API_KEY = PersistentConfig(
+    "RAG_OLLAMA_API_KEY",
+    "rag.ollama.key",
+    os.getenv("RAG_OLLAMA_API_KEY", ""),
+)
+
+
 ENABLE_RAG_LOCAL_WEB_FETCH = (
     os.getenv("ENABLE_RAG_LOCAL_WEB_FETCH", "False").lower() == "true"
 )
@@ -1113,6 +1308,12 @@ BRAVE_SEARCH_API_KEY = PersistentConfig(
     os.getenv("BRAVE_SEARCH_API_KEY", ""),
 )
 
+MOJEEK_SEARCH_API_KEY = PersistentConfig(
+    "MOJEEK_SEARCH_API_KEY",
+    "rag.web.search.mojeek_search_api_key",
+    os.getenv("MOJEEK_SEARCH_API_KEY", ""),
+)
+
 SERPSTACK_API_KEY = PersistentConfig(
     "SERPSTACK_API_KEY",
     "rag.web.search.serpstack_api_key",
@@ -1143,6 +1344,12 @@ TAVILY_API_KEY = PersistentConfig(
     os.getenv("TAVILY_API_KEY", ""),
 )
 
+JINA_API_KEY = PersistentConfig(
+    "JINA_API_KEY",
+    "rag.web.search.jina_api_key",
+    os.getenv("JINA_API_KEY", ""),
+)
+
 SEARCHAPI_API_KEY = PersistentConfig(
     "SEARCHAPI_API_KEY",
     "rag.web.search.searchapi_api_key",
@@ -1155,6 +1362,21 @@ SEARCHAPI_ENGINE = PersistentConfig(
     os.getenv("SEARCHAPI_ENGINE", ""),
 )
 
+BING_SEARCH_V7_ENDPOINT = PersistentConfig(
+    "BING_SEARCH_V7_ENDPOINT",
+    "rag.web.search.bing_search_v7_endpoint",
+    os.environ.get(
+        "BING_SEARCH_V7_ENDPOINT", "https://api.bing.microsoft.com/v7.0/search"
+    ),
+)
+
+BING_SEARCH_V7_SUBSCRIPTION_KEY = PersistentConfig(
+    "BING_SEARCH_V7_SUBSCRIPTION_KEY",
+    "rag.web.search.bing_search_v7_subscription_key",
+    os.environ.get("BING_SEARCH_V7_SUBSCRIPTION_KEY", ""),
+)
+
+
 RAG_WEB_SEARCH_RESULT_COUNT = PersistentConfig(
     "RAG_WEB_SEARCH_RESULT_COUNT",
     "rag.web.search.result_count",
@@ -1168,17 +1390,6 @@ RAG_WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
 )
 
 
-####################################
-# Transcribe
-####################################
-
-WHISPER_MODEL = os.getenv("WHISPER_MODEL", "base")
-WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
-WHISPER_MODEL_AUTO_UPDATE = (
-    os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
-)
-
-
 ####################################
 # Images
 ####################################
@@ -1217,7 +1428,7 @@ AUTOMATIC1111_CFG_SCALE = PersistentConfig(
 
 
 AUTOMATIC1111_SAMPLER = PersistentConfig(
-    "AUTOMATIC1111_SAMPLERE",
+    "AUTOMATIC1111_SAMPLER",
     "image_generation.automatic1111.sampler",
     (
         os.environ.get("AUTOMATIC1111_SAMPLER")
@@ -1394,6 +1605,19 @@ IMAGE_GENERATION_MODEL = PersistentConfig(
 # Audio
 ####################################
 
+# Transcription
+WHISPER_MODEL = PersistentConfig(
+    "WHISPER_MODEL",
+    "audio.stt.whisper_model",
+    os.getenv("WHISPER_MODEL", "base"),
+)
+
+WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
+WHISPER_MODEL_AUTO_UPDATE = (
+    os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
+)
+
+
 AUDIO_STT_OPENAI_API_BASE_URL = PersistentConfig(
     "AUDIO_STT_OPENAI_API_BASE_URL",
     "audio.stt.openai.api_base_url",
@@ -1415,7 +1639,7 @@ AUDIO_STT_ENGINE = PersistentConfig(
 AUDIO_STT_MODEL = PersistentConfig(
     "AUDIO_STT_MODEL",
     "audio.stt.model",
-    os.getenv("AUDIO_STT_MODEL", "whisper-1"),
+    os.getenv("AUDIO_STT_MODEL", ""),
 )
 
 AUDIO_TTS_OPENAI_API_BASE_URL = PersistentConfig(
@@ -1473,3 +1697,74 @@ AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT = PersistentConfig(
         "AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT", "audio-24khz-160kbitrate-mono-mp3"
     ),
 )
+
+
+####################################
+# LDAP
+####################################
+
+ENABLE_LDAP = PersistentConfig(
+    "ENABLE_LDAP",
+    "ldap.enable",
+    os.environ.get("ENABLE_LDAP", "false").lower() == "true",
+)
+
+LDAP_SERVER_LABEL = PersistentConfig(
+    "LDAP_SERVER_LABEL",
+    "ldap.server.label",
+    os.environ.get("LDAP_SERVER_LABEL", "LDAP Server"),
+)
+
+LDAP_SERVER_HOST = PersistentConfig(
+    "LDAP_SERVER_HOST",
+    "ldap.server.host",
+    os.environ.get("LDAP_SERVER_HOST", "localhost"),
+)
+
+LDAP_SERVER_PORT = PersistentConfig(
+    "LDAP_SERVER_PORT",
+    "ldap.server.port",
+    int(os.environ.get("LDAP_SERVER_PORT", "389")),
+)
+
+LDAP_ATTRIBUTE_FOR_USERNAME = PersistentConfig(
+    "LDAP_ATTRIBUTE_FOR_USERNAME",
+    "ldap.server.attribute_for_username",
+    os.environ.get("LDAP_ATTRIBUTE_FOR_USERNAME", "uid"),
+)
+
+LDAP_APP_DN = PersistentConfig(
+    "LDAP_APP_DN", "ldap.server.app_dn", os.environ.get("LDAP_APP_DN", "")
+)
+
+LDAP_APP_PASSWORD = PersistentConfig(
+    "LDAP_APP_PASSWORD",
+    "ldap.server.app_password",
+    os.environ.get("LDAP_APP_PASSWORD", ""),
+)
+
+LDAP_SEARCH_BASE = PersistentConfig(
+    "LDAP_SEARCH_BASE", "ldap.server.users_dn", os.environ.get("LDAP_SEARCH_BASE", "")
+)
+
+LDAP_SEARCH_FILTERS = PersistentConfig(
+    "LDAP_SEARCH_FILTER",
+    "ldap.server.search_filter",
+    os.environ.get("LDAP_SEARCH_FILTER", ""),
+)
+
+LDAP_USE_TLS = PersistentConfig(
+    "LDAP_USE_TLS",
+    "ldap.server.use_tls",
+    os.environ.get("LDAP_USE_TLS", "True").lower() == "true",
+)
+
+LDAP_CA_CERT_FILE = PersistentConfig(
+    "LDAP_CA_CERT_FILE",
+    "ldap.server.ca_cert_file",
+    os.environ.get("LDAP_CA_CERT_FILE", ""),
+)
+
+LDAP_CIPHERS = PersistentConfig(
+    "LDAP_CIPHERS", "ldap.server.ciphers", os.environ.get("LDAP_CIPHERS", "ALL")
+)

backend/open_webui/constants.py

@@ -20,7 +20,9 @@ class ERROR_MESSAGES(str, Enum):
     def __str__(self) -> str:
         return super().__str__()
 
-    DEFAULT = lambda err="": f"Something went wrong :/\n{err if err else ''}"
+    DEFAULT = (
+        lambda err="": f'{"Something went wrong :/" if err == "" else "[ERROR: " + str(err) + "]"}'
+    )
     ENV_VAR_NOT_FOUND = "Required environment variable not found. Terminating now."
     CREATE_USER_ERROR = "Oops! Something went wrong while creating your account. Please try again later. If the issue persists, contact support for assistance."
     DELETE_USER_ERROR = "Oops! Something went wrong. We encountered an issue while trying to delete the user. Please give it another shot."
@@ -60,6 +62,7 @@ class ERROR_MESSAGES(str, Enum):
     NOT_FOUND = "We could not find what you're looking for :/"
     USER_NOT_FOUND = "We could not find what you're looking for :/"
     API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature."
+    API_KEY_NOT_ALLOWED = "Use of API key is not enabled in the environment."
 
     MALICIOUS = "Unusual activities detected, please try again in a few minutes."
 
@@ -73,6 +76,7 @@ class ERROR_MESSAGES(str, Enum):
     OPENAI_NOT_FOUND = lambda name="": "OpenAI API was not found"
     OLLAMA_NOT_FOUND = "WebUI could not connect to Ollama"
     CREATE_API_KEY_ERROR = "Oops! Something went wrong while creating your API key. Please try again later. If the issue persists, contact support for assistance."
+    API_KEY_CREATION_NOT_ALLOWED = "API key creation is not allowed in the environment."
 
     EMPTY_CONTENT = "The content provided is empty. Please ensure that there is text or data present before proceeding."
 
@@ -106,6 +110,7 @@ class TASKS(str, Enum):
 
     DEFAULT = lambda task="": f"{task if task else 'generation'}"
     TITLE_GENERATION = "title_generation"
+    TAGS_GENERATION = "tags_generation"
     EMOJI_GENERATION = "emoji_generation"
     QUERY_GENERATION = "query_generation"
     FUNCTION_CALLING = "function_calling"

backend/open_webui/env.py

@@ -195,6 +195,15 @@ CHANGELOG = changelog_json
 
 SAFE_MODE = os.environ.get("SAFE_MODE", "false").lower() == "true"
 
+####################################
+# ENABLE_FORWARD_USER_INFO_HEADERS
+####################################
+
+ENABLE_FORWARD_USER_INFO_HEADERS = (
+    os.environ.get("ENABLE_FORWARD_USER_INFO_HEADERS", "False").lower() == "true"
+)
+
+
 ####################################
 # WEBUI_BUILD_HASH
 ####################################
@@ -230,6 +239,8 @@ if FROM_INIT_PY:
     DATA_DIR = Path(os.getenv("DATA_DIR", OPEN_WEBUI_DIR / "data"))
 
 
+STATIC_DIR = Path(os.getenv("STATIC_DIR", OPEN_WEBUI_DIR / "static"))
+
 FONTS_DIR = Path(os.getenv("FONTS_DIR", OPEN_WEBUI_DIR / "static" / "fonts"))
 
 FRONTEND_BUILD_DIR = Path(os.getenv("FRONTEND_BUILD_DIR", BASE_DIR / "build")).resolve()
@@ -302,6 +313,12 @@ RESET_CONFIG_ON_START = (
     os.environ.get("RESET_CONFIG_ON_START", "False").lower() == "true"
 )
 
+####################################
+# REDIS
+####################################
+
+REDIS_URL = os.environ.get("REDIS_URL", "redis://localhost:6379/0")
+
 ####################################
 # WEBUI_AUTH (Required for security)
 ####################################
@@ -343,8 +360,7 @@ ENABLE_WEBSOCKET_SUPPORT = (
 
 WEBSOCKET_MANAGER = os.environ.get("WEBSOCKET_MANAGER", "")
 
-WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", "redis://localhost:6379/0")
-
+WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", REDIS_URL)
 
 AIOHTTP_CLIENT_TIMEOUT = os.environ.get("AIOHTTP_CLIENT_TIMEOUT", "")
 
@@ -355,3 +371,23 @@ else:
         AIOHTTP_CLIENT_TIMEOUT = int(AIOHTTP_CLIENT_TIMEOUT)
     except Exception:
         AIOHTTP_CLIENT_TIMEOUT = 300
+
+AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = os.environ.get(
+    "AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", "3"
+)
+
+if AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST == "":
+    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = None
+else:
+    try:
+        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = int(
+            AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST
+        )
+    except Exception:
+        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = 3
+
+####################################
+# OFFLINE_MODE
+####################################
+
+OFFLINE_MODE = os.environ.get("OFFLINE_MODE", "false").lower() == "true"

backend/open_webui/migrations/versions/1af9b942657b_migrate_tags.py

@@ -0,0 +1,151 @@
+"""Migrate tags
+
+Revision ID: 1af9b942657b
+Revises: 242a2047eae0
+Create Date: 2024-10-09 21:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table, select, update, column
+from sqlalchemy.engine.reflection import Inspector
+
+import json
+
+revision = "1af9b942657b"
+down_revision = "242a2047eae0"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # Setup an inspection on the existing table to avoid issues
+    conn = op.get_bind()
+    inspector = Inspector.from_engine(conn)
+
+    # Clean up potential leftover temp table from previous failures
+    conn.execute(sa.text("DROP TABLE IF EXISTS _alembic_tmp_tag"))
+
+    # Check if the 'tag' table exists
+    tables = inspector.get_table_names()
+
+    # Step 1: Modify Tag table using batch mode for SQLite support
+    if "tag" in tables:
+        # Get the current columns in the 'tag' table
+        columns = [col["name"] for col in inspector.get_columns("tag")]
+
+        # Get any existing unique constraints on the 'tag' table
+        current_constraints = inspector.get_unique_constraints("tag")
+
+        with op.batch_alter_table("tag", schema=None) as batch_op:
+            # Check if the unique constraint already exists
+            if not any(
+                constraint["name"] == "uq_id_user_id"
+                for constraint in current_constraints
+            ):
+                # Create unique constraint if it doesn't exist
+                batch_op.create_unique_constraint("uq_id_user_id", ["id", "user_id"])
+
+            # Check if the 'data' column exists before trying to drop it
+            if "data" in columns:
+                batch_op.drop_column("data")
+
+            # Check if the 'meta' column needs to be created
+            if "meta" not in columns:
+                # Add the 'meta' column if it doesn't already exist
+                batch_op.add_column(sa.Column("meta", sa.JSON(), nullable=True))
+
+    tag = table(
+        "tag",
+        column("id", sa.String()),
+        column("name", sa.String()),
+        column("user_id", sa.String()),
+        column("meta", sa.JSON()),
+    )
+
+    # Step 2: Migrate tags
+    conn = op.get_bind()
+    result = conn.execute(sa.select(tag.c.id, tag.c.name, tag.c.user_id))
+
+    tag_updates = {}
+    for row in result:
+        new_id = row.name.replace(" ", "_").lower()
+        tag_updates[row.id] = new_id
+
+    for tag_id, new_tag_id in tag_updates.items():
+        print(f"Updating tag {tag_id} to {new_tag_id}")
+        if new_tag_id == "pinned":
+            # delete tag
+            delete_stmt = sa.delete(tag).where(tag.c.id == tag_id)
+            conn.execute(delete_stmt)
+        else:
+            # Check if the new_tag_id already exists in the database
+            existing_tag_query = sa.select(tag.c.id).where(tag.c.id == new_tag_id)
+            existing_tag_result = conn.execute(existing_tag_query).fetchone()
+
+            if existing_tag_result:
+                # Handle duplicate case: the new_tag_id already exists
+                print(
+                    f"Tag {new_tag_id} already exists. Removing current tag with ID {tag_id} to avoid duplicates."
+                )
+                # Option 1: Delete the current tag if an update to new_tag_id would cause duplication
+                delete_stmt = sa.delete(tag).where(tag.c.id == tag_id)
+                conn.execute(delete_stmt)
+            else:
+                update_stmt = sa.update(tag).where(tag.c.id == tag_id)
+                update_stmt = update_stmt.values(id=new_tag_id)
+                conn.execute(update_stmt)
+
+    # Add columns `pinned` and `meta` to 'chat'
+    op.add_column("chat", sa.Column("pinned", sa.Boolean(), nullable=True))
+    op.add_column(
+        "chat", sa.Column("meta", sa.JSON(), nullable=False, server_default="{}")
+    )
+
+    chatidtag = table(
+        "chatidtag", column("chat_id", sa.String()), column("tag_name", sa.String())
+    )
+    chat = table(
+        "chat",
+        column("id", sa.String()),
+        column("pinned", sa.Boolean()),
+        column("meta", sa.JSON()),
+    )
+
+    # Fetch existing tags
+    conn = op.get_bind()
+    result = conn.execute(sa.select(chatidtag.c.chat_id, chatidtag.c.tag_name))
+
+    chat_updates = {}
+    for row in result:
+        chat_id = row.chat_id
+        tag_name = row.tag_name.replace(" ", "_").lower()
+
+        if tag_name == "pinned":
+            # Specifically handle 'pinned' tag
+            if chat_id not in chat_updates:
+                chat_updates[chat_id] = {"pinned": True, "meta": {}}
+            else:
+                chat_updates[chat_id]["pinned"] = True
+        else:
+            if chat_id not in chat_updates:
+                chat_updates[chat_id] = {"pinned": False, "meta": {"tags": [tag_name]}}
+            else:
+                tags = chat_updates[chat_id]["meta"].get("tags", [])
+                tags.append(tag_name)
+
+                chat_updates[chat_id]["meta"]["tags"] = list(set(tags))
+
+    # Update chats based on accumulated changes
+    for chat_id, updates in chat_updates.items():
+        update_stmt = sa.update(chat).where(chat.c.id == chat_id)
+        update_stmt = update_stmt.values(
+            meta=updates.get("meta", {}), pinned=updates.get("pinned", False)
+        )
+        conn.execute(update_stmt)
+    pass
+
+
+def downgrade():
+    pass

backend/open_webui/migrations/versions/242a2047eae0_update_chat_table.py

@@ -0,0 +1,107 @@
+"""Update chat table
+
+Revision ID: 242a2047eae0
+Revises: 6a39f3d8e55c
+Create Date: 2024-10-09 21:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table, select, update
+
+import json
+
+revision = "242a2047eae0"
+down_revision = "6a39f3d8e55c"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+
+    columns = inspector.get_columns("chat")
+    column_dict = {col["name"]: col for col in columns}
+
+    chat_column = column_dict.get("chat")
+    old_chat_exists = "old_chat" in column_dict
+
+    if chat_column:
+        if isinstance(chat_column["type"], sa.Text):
+            print("Converting 'chat' column to JSON")
+
+            if old_chat_exists:
+                print("Dropping old 'old_chat' column")
+                op.drop_column("chat", "old_chat")
+
+            # Step 1: Rename current 'chat' column to 'old_chat'
+            print("Renaming 'chat' column to 'old_chat'")
+            op.alter_column(
+                "chat", "chat", new_column_name="old_chat", existing_type=sa.Text()
+            )
+
+            # Step 2: Add new 'chat' column of type JSON
+            print("Adding new 'chat' column of type JSON")
+            op.add_column("chat", sa.Column("chat", sa.JSON(), nullable=True))
+        else:
+            # If the column is already JSON, no need to do anything
+            pass
+
+    # Step 3: Migrate data from 'old_chat' to 'chat'
+    chat_table = table(
+        "chat",
+        sa.Column("id", sa.String(), primary_key=True),
+        sa.Column("old_chat", sa.Text()),
+        sa.Column("chat", sa.JSON()),
+    )
+
+    # - Selecting all data from the table
+    connection = op.get_bind()
+    results = connection.execute(select(chat_table.c.id, chat_table.c.old_chat))
+    for row in results:
+        try:
+            # Convert text JSON to actual JSON object, assuming the text is in JSON format
+            json_data = json.loads(row.old_chat)
+        except json.JSONDecodeError:
+            json_data = None  # Handle cases where the text cannot be converted to JSON
+
+        connection.execute(
+            sa.update(chat_table)
+            .where(chat_table.c.id == row.id)
+            .values(chat=json_data)
+        )
+
+    # Step 4: Drop 'old_chat' column
+    print("Dropping 'old_chat' column")
+    op.drop_column("chat", "old_chat")
+
+
+def downgrade():
+    # Step 1: Add 'old_chat' column back as Text
+    op.add_column("chat", sa.Column("old_chat", sa.Text(), nullable=True))
+
+    # Step 2: Convert 'chat' JSON data back to text and store in 'old_chat'
+    chat_table = table(
+        "chat",
+        sa.Column("id", sa.String(), primary_key=True),
+        sa.Column("chat", sa.JSON()),
+        sa.Column("old_chat", sa.Text()),
+    )
+
+    connection = op.get_bind()
+    results = connection.execute(select(chat_table.c.id, chat_table.c.chat))
+    for row in results:
+        text_data = json.dumps(row.chat) if row.chat is not None else None
+        connection.execute(
+            sa.update(chat_table)
+            .where(chat_table.c.id == row.id)
+            .values(old_chat=text_data)
+        )
+
+    # Step 3: Remove the new 'chat' JSON column
+    op.drop_column("chat", "chat")
+
+    # Step 4: Rename 'old_chat' back to 'chat'
+    op.alter_column("chat", "old_chat", new_column_name="chat", existing_type=sa.Text())

backend/open_webui/migrations/versions/3ab32c4b8f59_update_tags.py

@@ -0,0 +1,81 @@
+"""Update tags
+
+Revision ID: 3ab32c4b8f59
+Revises: 1af9b942657b
+Create Date: 2024-10-09 21:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table, select, update, column
+from sqlalchemy.engine.reflection import Inspector
+
+import json
+
+revision = "3ab32c4b8f59"
+down_revision = "1af9b942657b"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    conn = op.get_bind()
+    inspector = Inspector.from_engine(conn)
+
+    # Inspecting the 'tag' table constraints and structure
+    existing_pk = inspector.get_pk_constraint("tag")
+    unique_constraints = inspector.get_unique_constraints("tag")
+    existing_indexes = inspector.get_indexes("tag")
+
+    print(f"Primary Key: {existing_pk}")
+    print(f"Unique Constraints: {unique_constraints}")
+    print(f"Indexes: {existing_indexes}")
+
+    with op.batch_alter_table("tag", schema=None) as batch_op:
+        # Drop existing primary key constraint if it exists
+        if existing_pk and existing_pk.get("constrained_columns"):
+            pk_name = existing_pk.get("name")
+            if pk_name:
+                print(f"Dropping primary key constraint: {pk_name}")
+                batch_op.drop_constraint(pk_name, type_="primary")
+
+        # Now create the new primary key with the combination of 'id' and 'user_id'
+        print("Creating new primary key with 'id' and 'user_id'.")
+        batch_op.create_primary_key("pk_id_user_id", ["id", "user_id"])
+
+        # Drop unique constraints that could conflict with the new primary key
+        for constraint in unique_constraints:
+            if (
+                constraint["name"] == "uq_id_user_id"
+            ):  # Adjust this name according to what is actually returned by the inspector
+                print(f"Dropping unique constraint: {constraint['name']}")
+                batch_op.drop_constraint(constraint["name"], type_="unique")
+
+        for index in existing_indexes:
+            if index["unique"]:
+                if not any(
+                    constraint["name"] == index["name"]
+                    for constraint in unique_constraints
+                ):
+                    # You are attempting to drop unique indexes
+                    print(f"Dropping unique index: {index['name']}")
+                    batch_op.drop_index(index["name"])
+
+
+def downgrade():
+    conn = op.get_bind()
+    inspector = Inspector.from_engine(conn)
+
+    current_pk = inspector.get_pk_constraint("tag")
+
+    with op.batch_alter_table("tag", schema=None) as batch_op:
+        # Drop the current primary key first, if it matches the one we know we added in upgrade
+        if current_pk and "pk_id_user_id" == current_pk.get("name"):
+            batch_op.drop_constraint("pk_id_user_id", type_="primary")
+
+        # Restore the original primary key
+        batch_op.create_primary_key("pk_id", ["id"])
+
+        # Since primary key on just 'id' is restored, we now add back any unique constraints if necessary
+        batch_op.create_unique_constraint("uq_id_user_id", ["id", "user_id"])

backend/open_webui/migrations/versions/4ace53fd72c8_update_folder_table_datetime.py

@@ -0,0 +1,67 @@
+"""Update folder table and change DateTime to BigInteger for timestamp fields
+
+Revision ID: 4ace53fd72c8
+Revises: af906e964978
+Create Date: 2024-10-23 03:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+revision = "4ace53fd72c8"
+down_revision = "af906e964978"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # Perform safe alterations using batch operation
+    with op.batch_alter_table("folder", schema=None) as batch_op:
+        # Step 1: Remove server defaults for created_at and updated_at
+        batch_op.alter_column(
+            "created_at",
+            server_default=None,  # Removing server default
+        )
+        batch_op.alter_column(
+            "updated_at",
+            server_default=None,  # Removing server default
+        )
+
+        # Step 2: Change the column types to BigInteger for created_at
+        batch_op.alter_column(
+            "created_at",
+            type_=sa.BigInteger(),
+            existing_type=sa.DateTime(),
+            existing_nullable=False,
+            postgresql_using="extract(epoch from created_at)::bigint",  # Conversion for PostgreSQL
+        )
+
+        # Change the column types to BigInteger for updated_at
+        batch_op.alter_column(
+            "updated_at",
+            type_=sa.BigInteger(),
+            existing_type=sa.DateTime(),
+            existing_nullable=False,
+            postgresql_using="extract(epoch from updated_at)::bigint",  # Conversion for PostgreSQL
+        )
+
+
+def downgrade():
+    # Downgrade: Convert columns back to DateTime and restore defaults
+    with op.batch_alter_table("folder", schema=None) as batch_op:
+        batch_op.alter_column(
+            "created_at",
+            type_=sa.DateTime(),
+            existing_type=sa.BigInteger(),
+            existing_nullable=False,
+            server_default=sa.func.now(),  # Restoring server default on downgrade
+        )
+        batch_op.alter_column(
+            "updated_at",
+            type_=sa.DateTime(),
+            existing_type=sa.BigInteger(),
+            existing_nullable=False,
+            server_default=sa.func.now(),  # Restoring server default on downgrade
+            onupdate=sa.func.now(),  # Restoring onupdate behavior if it was there
+        )

backend/open_webui/migrations/versions/922e7a387820_add_group_table.py

@@ -0,0 +1,85 @@
+"""Add group table
+
+Revision ID: 922e7a387820
+Revises: 4ace53fd72c8
+Create Date: 2024-11-14 03:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+revision = "922e7a387820"
+down_revision = "4ace53fd72c8"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.create_table(
+        "group",
+        sa.Column("id", sa.Text(), nullable=False, primary_key=True, unique=True),
+        sa.Column("user_id", sa.Text(), nullable=True),
+        sa.Column("name", sa.Text(), nullable=True),
+        sa.Column("description", sa.Text(), nullable=True),
+        sa.Column("data", sa.JSON(), nullable=True),
+        sa.Column("meta", sa.JSON(), nullable=True),
+        sa.Column("permissions", sa.JSON(), nullable=True),
+        sa.Column("user_ids", sa.JSON(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=True),
+        sa.Column("updated_at", sa.BigInteger(), nullable=True),
+    )
+
+    # Add 'access_control' column to 'model' table
+    op.add_column(
+        "model",
+        sa.Column("access_control", sa.JSON(), nullable=True),
+    )
+
+    # Add 'is_active' column to 'model' table
+    op.add_column(
+        "model",
+        sa.Column(
+            "is_active",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.sql.expression.true(),
+        ),
+    )
+
+    # Add 'access_control' column to 'knowledge' table
+    op.add_column(
+        "knowledge",
+        sa.Column("access_control", sa.JSON(), nullable=True),
+    )
+
+    # Add 'access_control' column to 'prompt' table
+    op.add_column(
+        "prompt",
+        sa.Column("access_control", sa.JSON(), nullable=True),
+    )
+
+    # Add 'access_control' column to 'tools' table
+    op.add_column(
+        "tool",
+        sa.Column("access_control", sa.JSON(), nullable=True),
+    )
+
+
+def downgrade():
+    op.drop_table("group")
+
+    # Drop 'access_control' column from 'model' table
+    op.drop_column("model", "access_control")
+
+    # Drop 'is_active' column from 'model' table
+    op.drop_column("model", "is_active")
+
+    # Drop 'access_control' column from 'knowledge' table
+    op.drop_column("knowledge", "access_control")
+
+    # Drop 'access_control' column from 'prompt' table
+    op.drop_column("prompt", "access_control")
+
+    # Drop 'access_control' column from 'tools' table
+    op.drop_column("tool", "access_control")

backend/open_webui/migrations/versions/af906e964978_add_feedback_table.py

@@ -0,0 +1,51 @@
+"""Add feedback table
+
+Revision ID: af906e964978
+Revises: c29facfe716b
+Create Date: 2024-10-20 17:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# Revision identifiers, used by Alembic.
+revision = "af906e964978"
+down_revision = "c29facfe716b"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### Create feedback table ###
+    op.create_table(
+        "feedback",
+        sa.Column(
+            "id", sa.Text(), primary_key=True
+        ),  # Unique identifier for each feedback (TEXT type)
+        sa.Column(
+            "user_id", sa.Text(), nullable=True
+        ),  # ID of the user providing the feedback (TEXT type)
+        sa.Column(
+            "version", sa.BigInteger(), default=0
+        ),  # Version of feedback (BIGINT type)
+        sa.Column("type", sa.Text(), nullable=True),  # Type of feedback (TEXT type)
+        sa.Column("data", sa.JSON(), nullable=True),  # Feedback data (JSON type)
+        sa.Column(
+            "meta", sa.JSON(), nullable=True
+        ),  # Metadata for feedback (JSON type)
+        sa.Column(
+            "snapshot", sa.JSON(), nullable=True
+        ),  # snapshot data for feedback (JSON type)
+        sa.Column(
+            "created_at", sa.BigInteger(), nullable=False
+        ),  # Feedback creation timestamp (BIGINT representing epoch)
+        sa.Column(
+            "updated_at", sa.BigInteger(), nullable=False
+        ),  # Feedback update timestamp (BIGINT representing epoch)
+    )
+
+
+def downgrade():
+    # ### Drop feedback table ###
+    op.drop_table("feedback")

backend/open_webui/migrations/versions/c29facfe716b_update_file_table_path.py

@@ -0,0 +1,79 @@
+"""Update file table path
+
+Revision ID: c29facfe716b
+Revises: c69f45358db4
+Create Date: 2024-10-20 17:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+import json
+from sqlalchemy.sql import table, column
+from sqlalchemy import String, Text, JSON, and_
+
+
+revision = "c29facfe716b"
+down_revision = "c69f45358db4"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # 1. Add the `path` column to the "file" table.
+    op.add_column("file", sa.Column("path", sa.Text(), nullable=True))
+
+    # 2. Convert the `meta` column from Text/JSONField to `JSON()`
+    # Use Alembic's default batch_op for dialect compatibility.
+    with op.batch_alter_table("file", schema=None) as batch_op:
+        batch_op.alter_column(
+            "meta",
+            type_=sa.JSON(),
+            existing_type=sa.Text(),
+            existing_nullable=True,
+            nullable=True,
+            postgresql_using="meta::json",
+        )
+
+    # 3. Migrate legacy data from `meta` JSONField
+    # Fetch and process `meta` data from the table, add values to the new `path` column as necessary.
+    # We will use SQLAlchemy core bindings to ensure safety across different databases.
+
+    file_table = table(
+        "file", column("id", String), column("meta", JSON), column("path", Text)
+    )
+
+    # Create connection to the database
+    connection = op.get_bind()
+
+    # Get the rows where `meta` has a path and `path` column is null (new column)
+    # Loop through each row in the result set to update the path
+    results = connection.execute(
+        sa.select(file_table.c.id, file_table.c.meta).where(
+            and_(file_table.c.path.is_(None), file_table.c.meta.isnot(None))
+        )
+    ).fetchall()
+
+    # Iterate over each row to extract and update the `path` from `meta` column
+    for row in results:
+        if "path" in row.meta:
+            # Extract the `path` field from the `meta` JSON
+            path = row.meta.get("path")
+
+            # Update the `file` table with the new `path` value
+            connection.execute(
+                file_table.update()
+                .where(file_table.c.id == row.id)
+                .values({"path": path})
+            )
+
+
+def downgrade():
+    # 1. Remove the `path` column
+    op.drop_column("file", "path")
+
+    # 2. Revert the `meta` column back to Text/JSONField
+    with op.batch_alter_table("file", schema=None) as batch_op:
+        batch_op.alter_column(
+            "meta", type_=sa.Text(), existing_type=sa.JSON(), existing_nullable=True
+        )

backend/open_webui/migrations/versions/c69f45358db4_add_folder_table.py

@@ -0,0 +1,50 @@
+"""Add folder table
+
+Revision ID: c69f45358db4
+Revises: 3ab32c4b8f59
+Create Date: 2024-10-16 02:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+revision = "c69f45358db4"
+down_revision = "3ab32c4b8f59"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.create_table(
+        "folder",
+        sa.Column("id", sa.Text(), nullable=False),
+        sa.Column("parent_id", sa.Text(), nullable=True),
+        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column("name", sa.Text(), nullable=False),
+        sa.Column("items", sa.JSON(), nullable=True),
+        sa.Column("meta", sa.JSON(), nullable=True),
+        sa.Column("is_expanded", sa.Boolean(), default=False, nullable=False),
+        sa.Column(
+            "created_at", sa.DateTime(), server_default=sa.func.now(), nullable=False
+        ),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(),
+            nullable=False,
+            server_default=sa.func.now(),
+            onupdate=sa.func.now(),
+        ),
+        sa.PrimaryKeyConstraint("id", "user_id"),
+    )
+
+    op.add_column(
+        "chat",
+        sa.Column("folder_id", sa.Text(), nullable=True),
+    )
+
+
+def downgrade():
+    op.drop_column("chat", "folder_id")
+
+    op.drop_table("folder")

backend/open_webui/static/assets/pdf-style.css

@@ -0,0 +1,319 @@
+/* HTML and Body */
+@font-face {
+	font-family: 'NotoSans';
+	src: url('fonts/NotoSans-Variable.ttf');
+}
+
+@font-face {
+	font-family: 'NotoSansJP';
+	src: url('fonts/NotoSansJP-Variable.ttf');
+}
+
+@font-face {
+	font-family: 'NotoSansKR';
+	src: url('fonts/NotoSansKR-Variable.ttf');
+}
+
+@font-face {
+	font-family: 'NotoSansSC';
+	src: url('fonts/NotoSansSC-Variable.ttf');
+}
+
+@font-face {
+	font-family: 'NotoSansSC-Regular';
+	src: url('fonts/NotoSansSC-Regular.ttf');
+}
+
+html {
+	font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', 'NotoSans', 'NotoSansJP', 'NotoSansKR',
+		'NotoSansSC', 'STSong-Light', 'MSung-Light', 'HeiseiMin-W3', 'HYSMyeongJo-Medium', Roboto,
+		'Helvetica Neue', Arial, sans-serif;
+	font-size: 14px; /* Default font size */
+	line-height: 1.5;
+}
+
+*,
+*::before,
+*::after {
+	box-sizing: inherit;
+}
+
+body {
+	margin: 0;
+	color: #212529;
+	background-color: #fff;
+	width: auto;
+}
+
+/* Typography */
+h1,
+h2,
+h3,
+h4,
+h5,
+h6 {
+	font-weight: 500;
+	margin: 0;
+}
+
+h1 {
+	font-size: 2.5rem;
+}
+
+h2 {
+	font-size: 2rem;
+}
+
+h3 {
+	font-size: 1.75rem;
+}
+
+h4 {
+	font-size: 1.5rem;
+}
+
+h5 {
+	font-size: 1.25rem;
+}
+
+h6 {
+	font-size: 1rem;
+}
+
+p {
+	margin-top: 0;
+	margin-bottom: 1rem;
+}
+
+/* Grid System */
+.container {
+	width: 100%;
+	padding-right: 15px;
+	padding-left: 15px;
+	margin-right: auto;
+	margin-left: auto;
+}
+
+/* Utilities */
+.text-center {
+	text-align: center;
+}
+
+/* Additional Text Utilities */
+.text-muted {
+	color: #6c757d; /* Muted text color */
+}
+
+/* Small Text */
+small {
+	font-size: 80%; /* Smaller font size relative to the base */
+	color: #6c757d; /* Lighter text color for secondary information */
+	margin-bottom: 0;
+	margin-top: 0;
+}
+
+/* Strong Element Styles */
+strong {
+	font-weight: bolder; /* Ensures the text is bold */
+	color: inherit; /* Inherits the color from its parent element */
+}
+
+/* link */
+a {
+	color: #007bff;
+	text-decoration: none;
+	background-color: transparent;
+}
+
+a:hover {
+	color: #0056b3;
+	text-decoration: underline;
+}
+
+/* General styles for lists */
+ol,
+ul,
+li {
+	padding-left: 40px; /* Increase padding to move bullet points to the right */
+	margin-left: 20px; /* Indent lists from the left */
+}
+
+/* Ordered list styles */
+ol {
+	list-style-type: decimal; /* Use numbers for ordered lists */
+	margin-bottom: 10px; /* Space after each list */
+}
+
+ol li {
+	margin-bottom: 0.5rem; /* Space between ordered list items */
+}
+
+/* Unordered list styles */
+ul {
+	list-style-type: disc; /* Use bullets for unordered lists */
+	margin-bottom: 10px; /* Space after each list */
+}
+
+ul li {
+	margin-bottom: 0.5rem; /* Space between unordered list items */
+}
+
+/* List item styles */
+li {
+	margin-bottom: 5px; /* Space between list items */
+	line-height: 1.5; /* Line height for better readability */
+}
+
+/* Nested lists */
+ol ol,
+ol ul,
+ul ol,
+ul ul {
+	padding-left: 20px;
+	margin-left: 30px; /* Further indent nested lists */
+	margin-bottom: 0; /* Remove extra margin at the bottom of nested lists */
+}
+
+/* Code blocks */
+pre {
+	background-color: #f4f4f4;
+	padding: 10px;
+	overflow-x: auto;
+	max-width: 100%; /* Ensure it doesn't overflow the page */
+	width: 80%; /* Set a specific width for a container-like appearance */
+	margin: 0 1em; /* Center the pre block */
+	box-sizing: border-box; /* Include padding in the width */
+	border: 1px solid #ccc; /* Optional: Add a border for better definition */
+	border-radius: 4px; /* Optional: Add rounded corners */
+}
+
+code {
+	font-family: 'Courier New', Courier, monospace;
+	background-color: #f4f4f4;
+	padding: 2px 4px;
+	border-radius: 4px;
+	box-sizing: border-box; /* Include padding in the width */
+}
+
+.message {
+	margin-top: 8px;
+	margin-bottom: 8px;
+	max-width: 100%;
+	overflow-wrap: break-word;
+}
+
+/* Table Styles */
+table {
+	width: 100%;
+	margin-bottom: 1rem;
+	color: #212529;
+	border-collapse: collapse; /* Removes the space between borders */
+}
+
+th,
+td {
+	margin: 0;
+	padding: 0.75rem;
+	vertical-align: top;
+	border-top: 1px solid #dee2e6;
+}
+
+thead th {
+	vertical-align: bottom;
+	border-bottom: 2px solid #dee2e6;
+}
+
+tbody + tbody {
+	border-top: 2px solid #dee2e6;
+}
+
+/* markdown-section styles */
+.markdown-section blockquote,
+.markdown-section h1,
+.markdown-section h2,
+.markdown-section h3,
+.markdown-section h4,
+.markdown-section h5,
+.markdown-section h6,
+.markdown-section p,
+.markdown-section pre,
+.markdown-section table,
+.markdown-section ul {
+	/* Give most block elements margin top and bottom */
+	margin-top: 1rem;
+}
+
+/* Remove top margin if it's the first child */
+.markdown-section blockquote:first-child,
+.markdown-section h1:first-child,
+.markdown-section h2:first-child,
+.markdown-section h3:first-child,
+.markdown-section h4:first-child,
+.markdown-section h5:first-child,
+.markdown-section h6:first-child,
+.markdown-section p:first-child,
+.markdown-section pre:first-child,
+.markdown-section table:first-child,
+.markdown-section ul:first-child {
+	margin-top: 0;
+}
+
+/* Remove top margin of <ul> following a <p> */
+.markdown-section p + ul {
+	margin-top: 0;
+}
+
+/* Remove bottom margin of <p> if it is followed by a <ul> */
+/* Note: :has is not supported in CSS, so you would need JavaScript for this behavior */
+.markdown-section p {
+	margin-bottom: 0;
+}
+
+/* Add a rule to reset margin-bottom for <p> not followed by <ul> */
+.markdown-section p + ul {
+	margin-top: 0;
+}
+
+/* List item styles */
+.markdown-section li {
+	padding: 2px;
+}
+
+.markdown-section li p {
+	margin-bottom: 0;
+	padding: 0;
+}
+
+/* Avoid margins for nested lists */
+.markdown-section li > ul {
+	margin-top: 0;
+	margin-bottom: 0;
+}
+
+/* Table styles */
+.markdown-section table {
+	width: 100%;
+	border-collapse: collapse;
+	margin: 1rem 0;
+}
+
+.markdown-section th,
+.markdown-section td {
+	border: 1px solid #ddd;
+	padding: 0.5rem;
+	text-align: left;
+}
+
+.markdown-section th {
+	background-color: #f2f2f2;
+}
+
+.markdown-section pre {
+	padding: 10px;
+	margin: 10px;
+}
+
+.markdown-section pre code {
+	position: relative;
+	color: rgb(172, 0, 95);
+}

backend/open_webui/storage/provider.py

@@ -0,0 +1,167 @@
+import os
+import boto3
+from botocore.exceptions import ClientError
+import shutil
+
+
+from typing import BinaryIO, Tuple, Optional, Union
+
+from open_webui.constants import ERROR_MESSAGES
+from open_webui.config import (
+    STORAGE_PROVIDER,
+    S3_ACCESS_KEY_ID,
+    S3_SECRET_ACCESS_KEY,
+    S3_BUCKET_NAME,
+    S3_REGION_NAME,
+    S3_ENDPOINT_URL,
+    UPLOAD_DIR,
+)
+
+
+import boto3
+from botocore.exceptions import ClientError
+from typing import BinaryIO, Tuple, Optional
+
+
+class StorageProvider:
+    def __init__(self, provider: Optional[str] = None):
+        self.storage_provider: str = provider or STORAGE_PROVIDER
+
+        self.s3_client = None
+        self.s3_bucket_name: Optional[str] = None
+
+        if self.storage_provider == "s3":
+            self._initialize_s3()
+
+    def _initialize_s3(self) -> None:
+        """Initializes the S3 client and bucket name if using S3 storage."""
+        self.s3_client = boto3.client(
+            "s3",
+            region_name=S3_REGION_NAME,
+            endpoint_url=S3_ENDPOINT_URL,
+            aws_access_key_id=S3_ACCESS_KEY_ID,
+            aws_secret_access_key=S3_SECRET_ACCESS_KEY,
+        )
+        self.bucket_name = S3_BUCKET_NAME
+
+    def _upload_to_s3(self, file_path: str, filename: str) -> Tuple[bytes, str]:
+        """Handles uploading of the file to S3 storage."""
+        if not self.s3_client:
+            raise RuntimeError("S3 Client is not initialized.")
+
+        try:
+            self.s3_client.upload_file(file_path, self.bucket_name, filename)
+            return (
+                open(file_path, "rb").read(),
+                "s3://" + self.bucket_name + "/" + filename,
+            )
+        except ClientError as e:
+            raise RuntimeError(f"Error uploading file to S3: {e}")
+
+    def _upload_to_local(self, contents: bytes, filename: str) -> Tuple[bytes, str]:
+        """Handles uploading of the file to local storage."""
+        file_path = f"{UPLOAD_DIR}/{filename}"
+        with open(file_path, "wb") as f:
+            f.write(contents)
+        return contents, file_path
+
+    def _get_file_from_s3(self, file_path: str) -> str:
+        """Handles downloading of the file from S3 storage."""
+        if not self.s3_client:
+            raise RuntimeError("S3 Client is not initialized.")
+
+        try:
+            bucket_name, key = file_path.split("//")[1].split("/")
+            local_file_path = f"{UPLOAD_DIR}/{key}"
+            self.s3_client.download_file(bucket_name, key, local_file_path)
+            return local_file_path
+        except ClientError as e:
+            raise RuntimeError(f"Error downloading file from S3: {e}")
+
+    def _get_file_from_local(self, file_path: str) -> str:
+        """Handles downloading of the file from local storage."""
+        return file_path
+
+    def _delete_from_s3(self, filename: str) -> None:
+        """Handles deletion of the file from S3 storage."""
+        if not self.s3_client:
+            raise RuntimeError("S3 Client is not initialized.")
+
+        try:
+            self.s3_client.delete_object(Bucket=self.bucket_name, Key=filename)
+        except ClientError as e:
+            raise RuntimeError(f"Error deleting file from S3: {e}")
+
+    def _delete_from_local(self, filename: str) -> None:
+        """Handles deletion of the file from local storage."""
+        file_path = f"{UPLOAD_DIR}/{filename}"
+        if os.path.isfile(file_path):
+            os.remove(file_path)
+        else:
+            print(f"File {file_path} not found in local storage.")
+
+    def _delete_all_from_s3(self) -> None:
+        """Handles deletion of all files from S3 storage."""
+        if not self.s3_client:
+            raise RuntimeError("S3 Client is not initialized.")
+
+        try:
+            response = self.s3_client.list_objects_v2(Bucket=self.bucket_name)
+            if "Contents" in response:
+                for content in response["Contents"]:
+                    self.s3_client.delete_object(
+                        Bucket=self.bucket_name, Key=content["Key"]
+                    )
+        except ClientError as e:
+            raise RuntimeError(f"Error deleting all files from S3: {e}")
+
+    def _delete_all_from_local(self) -> None:
+        """Handles deletion of all files from local storage."""
+        if os.path.exists(UPLOAD_DIR):
+            for filename in os.listdir(UPLOAD_DIR):
+                file_path = os.path.join(UPLOAD_DIR, filename)
+                try:
+                    if os.path.isfile(file_path) or os.path.islink(file_path):
+                        os.unlink(file_path)  # Remove the file or link
+                    elif os.path.isdir(file_path):
+                        shutil.rmtree(file_path)  # Remove the directory
+                except Exception as e:
+                    print(f"Failed to delete {file_path}. Reason: {e}")
+        else:
+            print(f"Directory {UPLOAD_DIR} not found in local storage.")
+
+    def upload_file(self, file: BinaryIO, filename: str) -> Tuple[bytes, str]:
+        """Uploads a file either to S3 or the local file system."""
+        contents = file.read()
+        if not contents:
+            raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
+        contents, file_path = self._upload_to_local(contents, filename)
+
+        if self.storage_provider == "s3":
+            return self._upload_to_s3(file_path, filename)
+        return contents, file_path
+
+    def get_file(self, file_path: str) -> str:
+        """Downloads a file either from S3 or the local file system and returns the file path."""
+        if self.storage_provider == "s3":
+            return self._get_file_from_s3(file_path)
+        return self._get_file_from_local(file_path)
+
+    def delete_file(self, filename: str) -> None:
+        """Deletes a file either from S3 or the local file system."""
+        if self.storage_provider == "s3":
+            self._delete_from_s3(filename)
+
+        # Always delete from local storage
+        self._delete_from_local(filename)
+
+    def delete_all_files(self) -> None:
+        """Deletes all files from the storage."""
+        if self.storage_provider == "s3":
+            self._delete_all_from_s3()
+
+        # Always delete from local storage
+        self._delete_all_from_local()
+
+
+Storage = StorageProvider(provider=STORAGE_PROVIDER)

backend/open_webui/test/apps/webui/routers/test_documents.py

@@ -1,105 +0,0 @@
-from test.util.abstract_integration_test import AbstractPostgresTest
-from test.util.mock_user import mock_webui_user
-
-
-class TestDocuments(AbstractPostgresTest):
-    BASE_PATH = "/api/v1/documents"
-
-    def setup_class(cls):
-        super().setup_class()
-        from open_webui.apps.webui.models.documents import Documents
-
-        cls.documents = Documents
-
-    def test_documents(self):
-        # Empty database
-        assert len(self.documents.get_docs()) == 0
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.get(self.create_url("/"))
-        assert response.status_code == 200
-        assert len(response.json()) == 0
-
-        # Create a new document
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.post(
-                self.create_url("/create"),
-                json={
-                    "name": "doc_name",
-                    "title": "doc title",
-                    "collection_name": "custom collection",
-                    "filename": "doc_name.pdf",
-                    "content": "",
-                },
-            )
-        assert response.status_code == 200
-        assert response.json()["name"] == "doc_name"
-        assert len(self.documents.get_docs()) == 1
-
-        # Get the document
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.get(self.create_url("/doc?name=doc_name"))
-        assert response.status_code == 200
-        data = response.json()
-        assert data["collection_name"] == "custom collection"
-        assert data["name"] == "doc_name"
-        assert data["title"] == "doc title"
-        assert data["filename"] == "doc_name.pdf"
-        assert data["content"] == {}
-
-        # Create another document
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.post(
-                self.create_url("/create"),
-                json={
-                    "name": "doc_name 2",
-                    "title": "doc title 2",
-                    "collection_name": "custom collection 2",
-                    "filename": "doc_name2.pdf",
-                    "content": "",
-                },
-            )
-        assert response.status_code == 200
-        assert response.json()["name"] == "doc_name 2"
-        assert len(self.documents.get_docs()) == 2
-
-        # Get all documents
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.get(self.create_url("/"))
-        assert response.status_code == 200
-        assert len(response.json()) == 2
-
-        # Update the first document
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.post(
-                self.create_url("/doc/update?name=doc_name"),
-                json={"name": "doc_name rework", "title": "updated title"},
-            )
-        assert response.status_code == 200
-        data = response.json()
-        assert data["name"] == "doc_name rework"
-        assert data["title"] == "updated title"
-
-        # Tag the first document
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.post(
-                self.create_url("/doc/tags"),
-                json={
-                    "name": "doc_name rework",
-                    "tags": [{"name": "testing-tag"}, {"name": "another-tag"}],
-                },
-            )
-        assert response.status_code == 200
-        data = response.json()
-        assert data["name"] == "doc_name rework"
-        assert data["content"] == {
-            "tags": [{"name": "testing-tag"}, {"name": "another-tag"}]
-        }
-        assert len(self.documents.get_docs()) == 2
-
-        # Delete the first document
-        with mock_webui_user(id="2"):
-            response = self.fast_api_client.delete(
-                self.create_url("/doc/delete?name=doc_name rework")
-            )
-        assert response.status_code == 200
-        assert len(self.documents.get_docs()) == 1

backend/open_webui/utils/access_control.py

@@ -0,0 +1,95 @@
+from typing import Optional, Union, List, Dict, Any
+from open_webui.apps.webui.models.groups import Groups
+import json
+
+
+def get_permissions(
+    user_id: str,
+    default_permissions: Dict[str, Any],
+) -> Dict[str, Any]:
+    """
+    Get all permissions for a user by combining the permissions of all groups the user is a member of.
+    If a permission is defined in multiple groups, the most permissive value is used (True > False).
+    Permissions are nested in a dict with the permission key as the key and a boolean as the value.
+    """
+
+    def combine_permissions(
+        permissions: Dict[str, Any], group_permissions: Dict[str, Any]
+    ) -> Dict[str, Any]:
+        """Combine permissions from multiple groups by taking the most permissive value."""
+        for key, value in group_permissions.items():
+            if isinstance(value, dict):
+                if key not in permissions:
+                    permissions[key] = {}
+                permissions[key] = combine_permissions(permissions[key], value)
+            else:
+                if key not in permissions:
+                    permissions[key] = value
+                else:
+                    permissions[key] = permissions[key] or value
+        return permissions
+
+    user_groups = Groups.get_groups_by_member_id(user_id)
+
+    # deep copy default permissions to avoid modifying the original dict
+    permissions = json.loads(json.dumps(default_permissions))
+
+    for group in user_groups:
+        group_permissions = group.permissions
+        permissions = combine_permissions(permissions, group_permissions)
+
+    return permissions
+
+
+def has_permission(
+    user_id: str,
+    permission_key: str,
+    default_permissions: Dict[str, bool] = {},
+) -> bool:
+    """
+    Check if a user has a specific permission by checking the group permissions
+    and falls back to default permissions if not found in any group.
+
+    Permission keys can be hierarchical and separated by dots ('.').
+    """
+
+    def get_permission(permissions: Dict[str, bool], keys: List[str]) -> bool:
+        """Traverse permissions dict using a list of keys (from dot-split permission_key)."""
+        for key in keys:
+            if key not in permissions:
+                return False  # If any part of the hierarchy is missing, deny access
+            permissions = permissions[key]  # Go one level deeper
+
+        return bool(permissions)  # Return the boolean at the final level
+
+    permission_hierarchy = permission_key.split(".")
+
+    # Retrieve user group permissions
+    user_groups = Groups.get_groups_by_member_id(user_id)
+
+    for group in user_groups:
+        group_permissions = group.permissions
+        if get_permission(group_permissions, permission_hierarchy):
+            return True
+
+    # Check default permissions afterwards if the group permissions don't allow it
+    return get_permission(default_permissions, permission_hierarchy)
+
+
+def has_access(
+    user_id: str,
+    type: str = "write",
+    access_control: Optional[dict] = None,
+) -> bool:
+    if access_control is None:
+        return type == "read"
+
+    user_groups = Groups.get_groups_by_member_id(user_id)
+    user_group_ids = [group.id for group in user_groups]
+    permission_access = access_control.get(type, {})
+    permitted_group_ids = permission_access.get("group_ids", [])
+    permitted_user_ids = permission_access.get("user_ids", [])
+
+    return user_id in permitted_user_ids or any(
+        group_id in permitted_group_ids for group_id in user_group_ids
+    )

backend/open_webui/utils/oauth.py

@@ -0,0 +1,261 @@
+import base64
+import logging
+import mimetypes
+import uuid
+
+import aiohttp
+from authlib.integrations.starlette_client import OAuth
+from authlib.oidc.core import UserInfo
+from fastapi import (
+    HTTPException,
+    status,
+)
+from starlette.responses import RedirectResponse
+
+from open_webui.apps.webui.models.auths import Auths
+from open_webui.apps.webui.models.users import Users
+from open_webui.config import (
+    DEFAULT_USER_ROLE,
+    ENABLE_OAUTH_SIGNUP,
+    OAUTH_MERGE_ACCOUNTS_BY_EMAIL,
+    OAUTH_PROVIDERS,
+    ENABLE_OAUTH_ROLE_MANAGEMENT,
+    OAUTH_ROLES_CLAIM,
+    OAUTH_EMAIL_CLAIM,
+    OAUTH_PICTURE_CLAIM,
+    OAUTH_USERNAME_CLAIM,
+    OAUTH_ALLOWED_ROLES,
+    OAUTH_ADMIN_ROLES,
+    WEBHOOK_URL,
+    JWT_EXPIRES_IN,
+    AppConfig,
+)
+from open_webui.constants import ERROR_MESSAGES
+from open_webui.env import WEBUI_SESSION_COOKIE_SAME_SITE, WEBUI_SESSION_COOKIE_SECURE
+from open_webui.utils.misc import parse_duration
+from open_webui.utils.utils import get_password_hash, create_token
+from open_webui.utils.webhook import post_webhook
+
+log = logging.getLogger(__name__)
+
+auth_manager_config = AppConfig()
+auth_manager_config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
+auth_manager_config.ENABLE_OAUTH_SIGNUP = ENABLE_OAUTH_SIGNUP
+auth_manager_config.OAUTH_MERGE_ACCOUNTS_BY_EMAIL = OAUTH_MERGE_ACCOUNTS_BY_EMAIL
+auth_manager_config.ENABLE_OAUTH_ROLE_MANAGEMENT = ENABLE_OAUTH_ROLE_MANAGEMENT
+auth_manager_config.OAUTH_ROLES_CLAIM = OAUTH_ROLES_CLAIM
+auth_manager_config.OAUTH_EMAIL_CLAIM = OAUTH_EMAIL_CLAIM
+auth_manager_config.OAUTH_PICTURE_CLAIM = OAUTH_PICTURE_CLAIM
+auth_manager_config.OAUTH_USERNAME_CLAIM = OAUTH_USERNAME_CLAIM
+auth_manager_config.OAUTH_ALLOWED_ROLES = OAUTH_ALLOWED_ROLES
+auth_manager_config.OAUTH_ADMIN_ROLES = OAUTH_ADMIN_ROLES
+auth_manager_config.WEBHOOK_URL = WEBHOOK_URL
+auth_manager_config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
+
+
+class OAuthManager:
+    def __init__(self):
+        self.oauth = OAuth()
+        for provider_name, provider_config in OAUTH_PROVIDERS.items():
+            self.oauth.register(
+                name=provider_name,
+                client_id=provider_config["client_id"],
+                client_secret=provider_config["client_secret"],
+                server_metadata_url=provider_config["server_metadata_url"],
+                client_kwargs={
+                    "scope": provider_config["scope"],
+                },
+                redirect_uri=provider_config["redirect_uri"],
+            )
+
+    def get_client(self, provider_name):
+        return self.oauth.create_client(provider_name)
+
+    def get_user_role(self, user, user_data):
+        if user and Users.get_num_users() == 1:
+            # If the user is the only user, assign the role "admin" - actually repairs role for single user on login
+            return "admin"
+        if not user and Users.get_num_users() == 0:
+            # If there are no users, assign the role "admin", as the first user will be an admin
+            return "admin"
+
+        if auth_manager_config.ENABLE_OAUTH_ROLE_MANAGEMENT:
+            oauth_claim = auth_manager_config.OAUTH_ROLES_CLAIM
+            oauth_allowed_roles = auth_manager_config.OAUTH_ALLOWED_ROLES
+            oauth_admin_roles = auth_manager_config.OAUTH_ADMIN_ROLES
+            oauth_roles = None
+            role = "pending"  # Default/fallback role if no matching roles are found
+
+            # Next block extracts the roles from the user data, accepting nested claims of any depth
+            if oauth_claim and oauth_allowed_roles and oauth_admin_roles:
+                claim_data = user_data
+                nested_claims = oauth_claim.split(".")
+                for nested_claim in nested_claims:
+                    claim_data = claim_data.get(nested_claim, {})
+                oauth_roles = claim_data if isinstance(claim_data, list) else None
+
+            # If any roles are found, check if they match the allowed or admin roles
+            if oauth_roles:
+                # If role management is enabled, and matching roles are provided, use the roles
+                for allowed_role in oauth_allowed_roles:
+                    # If the user has any of the allowed roles, assign the role "user"
+                    if allowed_role in oauth_roles:
+                        role = "user"
+                        break
+                for admin_role in oauth_admin_roles:
+                    # If the user has any of the admin roles, assign the role "admin"
+                    if admin_role in oauth_roles:
+                        role = "admin"
+                        break
+        else:
+            if not user:
+                # If role management is disabled, use the default role for new users
+                role = auth_manager_config.DEFAULT_USER_ROLE
+            else:
+                # If role management is disabled, use the existing role for existing users
+                role = user.role
+
+        return role
+
+    async def handle_login(self, provider, request):
+        if provider not in OAUTH_PROVIDERS:
+            raise HTTPException(404)
+        # If the provider has a custom redirect URL, use that, otherwise automatically generate one
+        redirect_uri = OAUTH_PROVIDERS[provider].get("redirect_uri") or request.url_for(
+            "oauth_callback", provider=provider
+        )
+        client = self.get_client(provider)
+        if client is None:
+            raise HTTPException(404)
+        return await client.authorize_redirect(request, redirect_uri)
+
+    async def handle_callback(self, provider, request, response):
+        if provider not in OAUTH_PROVIDERS:
+            raise HTTPException(404)
+        client = self.get_client(provider)
+        try:
+            token = await client.authorize_access_token(request)
+        except Exception as e:
+            log.warning(f"OAuth callback error: {e}")
+            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+        user_data: UserInfo = token["userinfo"]
+        if not user_data:
+            user_data: UserInfo = await client.userinfo(token=token)
+        if not user_data:
+            log.warning(f"OAuth callback failed, user data is missing: {token}")
+            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+
+        sub = user_data.get("sub")
+        if not sub:
+            log.warning(f"OAuth callback failed, sub is missing: {user_data}")
+            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+        provider_sub = f"{provider}@{sub}"
+        email_claim = auth_manager_config.OAUTH_EMAIL_CLAIM
+        email = user_data.get(email_claim, "").lower()
+        # We currently mandate that email addresses are provided
+        if not email:
+            log.warning(f"OAuth callback failed, email is missing: {user_data}")
+            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
+
+        # Check if the user exists
+        user = Users.get_user_by_oauth_sub(provider_sub)
+
+        if not user:
+            # If the user does not exist, check if merging is enabled
+            if auth_manager_config.OAUTH_MERGE_ACCOUNTS_BY_EMAIL:
+                # Check if the user exists by email
+                user = Users.get_user_by_email(email)
+                if user:
+                    # Update the user with the new oauth sub
+                    Users.update_user_oauth_sub_by_id(user.id, provider_sub)
+
+        if user:
+            determined_role = self.get_user_role(user, user_data)
+            if user.role != determined_role:
+                Users.update_user_role_by_id(user.id, determined_role)
+
+        if not user:
+            # If the user does not exist, check if signups are enabled
+            if auth_manager_config.ENABLE_OAUTH_SIGNUP:
+                # Check if an existing user with the same email already exists
+                existing_user = Users.get_user_by_email(
+                    user_data.get("email", "").lower()
+                )
+                if existing_user:
+                    raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
+
+                picture_claim = auth_manager_config.OAUTH_PICTURE_CLAIM
+                picture_url = user_data.get(picture_claim, "")
+                if picture_url:
+                    # Download the profile image into a base64 string
+                    try:
+                        async with aiohttp.ClientSession() as session:
+                            async with session.get(picture_url) as resp:
+                                picture = await resp.read()
+                                base64_encoded_picture = base64.b64encode(
+                                    picture
+                                ).decode("utf-8")
+                                guessed_mime_type = mimetypes.guess_type(picture_url)[0]
+                                if guessed_mime_type is None:
+                                    # assume JPG, browsers are tolerant enough of image formats
+                                    guessed_mime_type = "image/jpeg"
+                                picture_url = f"data:{guessed_mime_type};base64,{base64_encoded_picture}"
+                    except Exception as e:
+                        log.error(
+                            f"Error downloading profile image '{picture_url}': {e}"
+                        )
+                        picture_url = ""
+                if not picture_url:
+                    picture_url = "/user.png"
+                username_claim = auth_manager_config.OAUTH_USERNAME_CLAIM
+
+                role = self.get_user_role(None, user_data)
+
+                user = Auths.insert_new_auth(
+                    email=email,
+                    password=get_password_hash(
+                        str(uuid.uuid4())
+                    ),  # Random password, not used
+                    name=user_data.get(username_claim, "User"),
+                    profile_image_url=picture_url,
+                    role=role,
+                    oauth_sub=provider_sub,
+                )
+
+                if auth_manager_config.WEBHOOK_URL:
+                    post_webhook(
+                        auth_manager_config.WEBHOOK_URL,
+                        auth_manager_config.WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
+                        {
+                            "action": "signup",
+                            "message": auth_manager_config.WEBHOOK_MESSAGES.USER_SIGNUP(
+                                user.name
+                            ),
+                            "user": user.model_dump_json(exclude_none=True),
+                        },
+                    )
+            else:
+                raise HTTPException(
+                    status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
+                )
+
+        jwt_token = create_token(
+            data={"id": user.id},
+            expires_delta=parse_duration(auth_manager_config.JWT_EXPIRES_IN),
+        )
+
+        # Set the cookie token
+        response.set_cookie(
+            key="token",
+            value=jwt_token,
+            httponly=True,  # Ensures the cookie is not accessible via JavaScript
+            samesite=WEBUI_SESSION_COOKIE_SAME_SITE,
+            secure=WEBUI_SESSION_COOKIE_SECURE,
+        )
+
+        # Redirect back to the frontend with the JWT token
+        redirect_url = f"{request.base_url}auth#token={jwt_token}"
+        return RedirectResponse(url=redirect_url)
+
+
+oauth_manager = OAuthManager()

backend/open_webui/utils/payload.py

@@ -88,6 +88,53 @@ def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
     return form_data
 
 
+def convert_messages_openai_to_ollama(messages: list[dict]) -> list[dict]:
+    ollama_messages = []
+
+    for message in messages:
+        # Initialize the new message structure with the role
+        new_message = {"role": message["role"]}
+
+        content = message.get("content", [])
+
+        # Check if the content is a string (just a simple message)
+        if isinstance(content, str):
+            # If the content is a string, it's pure text
+            new_message["content"] = content
+        else:
+            # Otherwise, assume the content is a list of dicts, e.g., text followed by an image URL
+            content_text = ""
+            images = []
+
+            # Iterate through the list of content items
+            for item in content:
+                # Check if it's a text type
+                if item.get("type") == "text":
+                    content_text += item.get("text", "")
+
+                # Check if it's an image URL type
+                elif item.get("type") == "image_url":
+                    img_url = item.get("image_url", {}).get("url", "")
+                    if img_url:
+                        # If the image url starts with data:, it's a base64 image and should be trimmed
+                        if img_url.startswith("data:"):
+                            img_url = img_url.split(",")[-1]
+                        images.append(img_url)
+
+            # Add content text (if any)
+            if content_text:
+                new_message["content"] = content_text.strip()
+
+            # Add images (if any)
+            if images:
+                new_message["images"] = images
+
+        # Append the new formatted message to the result
+        ollama_messages.append(new_message)
+
+    return ollama_messages
+
+
 def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
     """
     Converts a payload formatted for OpenAI's API to be compatible with Ollama's API endpoint for chat completions.
@@ -102,7 +149,9 @@ def convert_payload_openai_to_ollama(openai_payload: dict) -> dict:
 
     # Mapping basic model and message details
     ollama_payload["model"] = openai_payload.get("model")
-    ollama_payload["messages"] = openai_payload.get("messages")
+    ollama_payload["messages"] = convert_messages_openai_to_ollama(
+        openai_payload.get("messages")
+    )
     ollama_payload["stream"] = openai_payload.get("stream", False)
 
     # If there are advanced parameters in the payload, format them in Ollama's options field

backend/open_webui/utils/pdf_generator.py

@@ -0,0 +1,139 @@
+from datetime import datetime
+from io import BytesIO
+from pathlib import Path
+from typing import Dict, Any, List
+
+from markdown import markdown
+
+import site
+from fpdf import FPDF
+
+from open_webui.env import STATIC_DIR, FONTS_DIR
+from open_webui.apps.webui.models.chats import ChatTitleMessagesForm
+
+
+class PDFGenerator:
+    """
+    Description:
+    The `PDFGenerator` class is designed to create PDF documents from chat messages.
+    The process involves transforming markdown content into HTML and then into a PDF format
+
+    Attributes:
+    - `form_data`: An instance of `ChatTitleMessagesForm` containing title and messages.
+
+    """
+
+    def __init__(self, form_data: ChatTitleMessagesForm):
+        self.html_body = None
+        self.messages_html = None
+        self.form_data = form_data
+
+        self.css = Path(STATIC_DIR / "assets" / "pdf-style.css").read_text()
+
+    def format_timestamp(self, timestamp: float) -> str:
+        """Convert a UNIX timestamp to a formatted date string."""
+        try:
+            date_time = datetime.fromtimestamp(timestamp)
+            return date_time.strftime("%Y-%m-%d, %H:%M:%S")
+        except (ValueError, TypeError) as e:
+            # Log the error if necessary
+            return ""
+
+    def _build_html_message(self, message: Dict[str, Any]) -> str:
+        """Build HTML for a single message."""
+        role = message.get("role", "user")
+        content = message.get("content", "")
+        timestamp = message.get("timestamp")
+
+        model = message.get("model") if role == "assistant" else ""
+
+        date_str = self.format_timestamp(timestamp) if timestamp else ""
+
+        # extends pymdownx extension to convert markdown to html.
+        # - https://facelessuser.github.io/pymdown-extensions/usage_notes/
+        html_content = markdown(content, extensions=["pymdownx.extra"])
+
+        html_message = f"""
+            <div> {date_str} </div>
+            <div class="message">
+                <div>
+                    <h2>
+                        <strong>{role.title()}</strong>
+                        <span style="font-size: 12px; color: #888;">{model}</span>
+                    </h2>
+                </div>
+                <pre class="markdown-section">
+                    {content}
+                </pre>
+            </div>
+          """
+        return html_message
+
+    def _generate_html_body(self) -> str:
+        """Generate the full HTML body for the PDF."""
+        return f"""
+        <html>
+            <head>
+                <meta charset="UTF-8">
+                <meta name="viewport" content="width=device-width, initial-scale=1.0">
+            </head>
+            <body>
+                <div class="container"> 
+                    <div class="text-center">
+                        <h1>{self.form_data.title}</h1>
+                    </div>
+                    <div>
+                        {self.messages_html}
+                    </div>
+                </div>
+            </body>
+        </html>
+        """
+
+    def generate_chat_pdf(self) -> bytes:
+        """
+        Generate a PDF from chat messages.
+        """
+        try:
+            global FONTS_DIR
+
+            pdf = FPDF()
+            pdf.add_page()
+
+            # When running using `pip install` the static directory is in the site packages.
+            if not FONTS_DIR.exists():
+                FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
+            # When running using `pip install -e .` the static directory is in the site packages.
+            # This path only works if `open-webui serve` is run from the root of this project.
+            if not FONTS_DIR.exists():
+                FONTS_DIR = Path("./backend/static/fonts")
+
+            pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
+            pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
+            pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
+            pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
+            pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
+            pdf.add_font("NotoSansSC", "", f"{FONTS_DIR}/NotoSansSC-Regular.ttf")
+
+            pdf.set_font("NotoSans", size=12)
+            pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP", "NotoSansSC"])
+
+            pdf.set_auto_page_break(auto=True, margin=15)
+
+            # Build HTML messages
+            messages_html_list: List[str] = [
+                self._build_html_message(msg) for msg in self.form_data.messages
+            ]
+            self.messages_html = "<div>" + "".join(messages_html_list) + "</div>"
+
+            # Generate full HTML body
+            self.html_body = self._generate_html_body()
+
+            pdf.write_html(self.html_body)
+
+            # Save the pdf with name .pdf
+            pdf_bytes = pdf.output()
+
+            return bytes(pdf_bytes)
+        except Exception as e:
+            raise e

backend/open_webui/utils/response.py

@@ -26,7 +26,6 @@ async def convert_streaming_response_ollama_to_openai(ollama_streaming_response)
         )
 
         line = f"data: {json.dumps(data)}\n\n"
-        if done:
-            line += "data: [DONE]\n\n"
-
         yield line
+
+    yield "data: [DONE]\n\n"

backend/open_webui/utils/schemas.py

@@ -1,112 +0,0 @@
-from ast import literal_eval
-from typing import Any, Literal, Optional, Type
-
-from pydantic import BaseModel, Field, create_model
-
-
-def json_schema_to_model(tool_dict: dict[str, Any]) -> Type[BaseModel]:
-    """
-    Converts a JSON schema to a Pydantic BaseModel class.
-
-    Args:
-        json_schema: The JSON schema to convert.
-
-    Returns:
-        A Pydantic BaseModel class.
-    """
-
-    # Extract the model name from the schema title.
-    model_name = tool_dict["name"]
-    schema = tool_dict["parameters"]
-
-    # Extract the field definitions from the schema properties.
-    field_definitions = {
-        name: json_schema_to_pydantic_field(name, prop, schema.get("required", []))
-        for name, prop in schema.get("properties", {}).items()
-    }
-
-    # Create the BaseModel class using create_model().
-    return create_model(model_name, **field_definitions)
-
-
-def json_schema_to_pydantic_field(
-    name: str, json_schema: dict[str, Any], required: list[str]
-) -> Any:
-    """
-    Converts a JSON schema property to a Pydantic field definition.
-
-    Args:
-        name: The field name.
-        json_schema: The JSON schema property.
-
-    Returns:
-        A Pydantic field definition.
-    """
-
-    # Get the field type.
-    type_ = json_schema_to_pydantic_type(json_schema)
-
-    # Get the field description.
-    description = json_schema.get("description")
-
-    # Get the field examples.
-    examples = json_schema.get("examples")
-
-    # Create a Field object with the type, description, and examples.
-    # The 'required' flag will be set later when creating the model.
-    return (
-        type_,
-        Field(
-            description=description,
-            examples=examples,
-            default=... if name in required else None,
-        ),
-    )
-
-
-def json_schema_to_pydantic_type(json_schema: dict[str, Any]) -> Any:
-    """
-    Converts a JSON schema type to a Pydantic type.
-
-    Args:
-        json_schema: The JSON schema to convert.
-
-    Returns:
-        A Pydantic type.
-    """
-
-    type_ = json_schema.get("type")
-
-    if type_ == "string" or type_ == "str":
-        return str
-    elif type_ == "integer" or type_ == "int":
-        return int
-    elif type_ == "number" or type_ == "float":
-        return float
-    elif type_ == "boolean" or type_ == "bool":
-        return bool
-    elif type_ == "array" or type_ == "list":
-        items_schema = json_schema.get("items")
-        if items_schema:
-            item_type = json_schema_to_pydantic_type(items_schema)
-            return list[item_type]
-        else:
-            return list
-    elif type_ == "object":
-        # Handle nested models.
-        properties = json_schema.get("properties")
-        if properties:
-            nested_model = json_schema_to_model(json_schema)
-            return nested_model
-        else:
-            return dict
-    elif type_ == "null":
-        return Optional[Any]  # Use Optional[Any] for nullable fields
-    elif type_ == "literal":
-        return Literal[literal_eval(json_schema.get("enum"))]
-    elif type_ == "optional":
-        inner_schema = json_schema.get("items", {"type": "string"})
-        inner_type = json_schema_to_pydantic_type(inner_schema)
-        return Optional[inner_type]
-    else:
-        raise ValueError(f"Unsupported JSON schema type: {type_}")

backend/open_webui/utils/security_headers.py

@@ -20,6 +20,7 @@ def set_security_headers() -> Dict[str, str]:
     This function reads specific environment variables and uses their values
     to set corresponding security headers. The headers that can be set are:
     - cache-control
+    - permissions-policy
     - strict-transport-security
     - referrer-policy
     - x-content-type-options
@@ -38,6 +39,7 @@ def set_security_headers() -> Dict[str, str]:
     header_setters = {
         "CACHE_CONTROL": set_cache_control,
         "HSTS": set_hsts,
+        "PERMISSIONS_POLICY": set_permissions_policy,
         "REFERRER_POLICY": set_referrer,
         "XCONTENT_TYPE": set_xcontent_type,
         "XDOWNLOAD_OPTIONS": set_xdownload_options,
@@ -60,7 +62,7 @@ def set_hsts(value: str):
     pattern = r"^max-age=(\d+)(;includeSubDomains)?(;preload)?$"
     match = re.match(pattern, value, re.IGNORECASE)
     if not match:
-        return "max-age=31536000;includeSubDomains"
+        value = "max-age=31536000;includeSubDomains"
     return {"Strict-Transport-Security": value}
 
 
@@ -73,6 +75,15 @@ def set_xframe(value: str):
     return {"X-Frame-Options": value}
 
 
+# Set Permissions-Policy response header
+def set_permissions_policy(value: str):
+    pattern = r"^(?:(accelerometer|autoplay|camera|clipboard-read|clipboard-write|fullscreen|geolocation|gyroscope|magnetometer|microphone|midi|payment|picture-in-picture|sync-xhr|usb|xr-spatial-tracking)=\((self)?\),?)*$"
+    match = re.match(pattern, value, re.IGNORECASE)
+    if not match:
+        value = "none"
+    return {"Permissions-Policy": value}
+
+
 # Set Referrer-Policy response header
 def set_referrer(value: str):
     pattern = r"^(no-referrer|no-referrer-when-downgrade|origin|origin-when-cross-origin|same-origin|strict-origin|strict-origin-when-cross-origin|unsafe-url)$"

backend/open_webui/utils/task.py

@@ -1,11 +1,20 @@
+import logging
 import math
 import re
 from datetime import datetime
 from typing import Optional
+import uuid
 
 
 from open_webui.utils.misc import get_last_user_message, get_messages_content
 
+from open_webui.env import SRC_LOG_LEVELS
+from open_webui.config import DEFAULT_RAG_TEMPLATE
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
 
 def prompt_template(
     template: str, user_name: Optional[str] = None, user_location: Optional[str] = None
@@ -70,22 +79,6 @@ def replace_prompt_variable(template: str, prompt: str) -> str:
     return template
 
 
-def title_generation_template(
-    template: str, prompt: str, user: Optional[dict] = None
-) -> str:
-    template = replace_prompt_variable(template, prompt)
-    template = prompt_template(
-        template,
-        **(
-            {"user_name": user.get("name"), "user_location": user.get("location")}
-            if user
-            else {}
-        ),
-    )
-
-    return template
-
-
 def replace_messages_variable(template: str, messages: list[str]) -> str:
     def replacement_function(match):
         full_match = match.group(0)
@@ -123,7 +116,101 @@ def replace_messages_variable(template: str, messages: list[str]) -> str:
     return template
 
 
-def search_query_generation_template(
+# {{prompt:middletruncate:8000}}
+
+
+def rag_template(template: str, context: str, query: str):
+    if template == "":
+        template = DEFAULT_RAG_TEMPLATE
+
+    if "[context]" not in template and "{{CONTEXT}}" not in template:
+        log.debug(
+            "WARNING: The RAG template does not contain the '[context]' or '{{CONTEXT}}' placeholder."
+        )
+
+    if "<context>" in context and "</context>" in context:
+        log.debug(
+            "WARNING: Potential prompt injection attack: the RAG "
+            "context contains '<context>' and '</context>'. This might be "
+            "nothing, or the user might be trying to hack something."
+        )
+
+    query_placeholders = []
+    if "[query]" in context:
+        query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
+        template = template.replace("[query]", query_placeholder)
+        query_placeholders.append(query_placeholder)
+
+    if "{{QUERY}}" in context:
+        query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
+        template = template.replace("{{QUERY}}", query_placeholder)
+        query_placeholders.append(query_placeholder)
+
+    template = template.replace("[context]", context)
+    template = template.replace("{{CONTEXT}}", context)
+    template = template.replace("[query]", query)
+    template = template.replace("{{QUERY}}", query)
+
+    for query_placeholder in query_placeholders:
+        template = template.replace(query_placeholder, query)
+
+    return template
+
+
+def title_generation_template(
+    template: str, messages: list[dict], user: Optional[dict] = None
+) -> str:
+    prompt = get_last_user_message(messages)
+    template = replace_prompt_variable(template, prompt)
+    template = replace_messages_variable(template, messages)
+
+    template = prompt_template(
+        template,
+        **(
+            {"user_name": user.get("name"), "user_location": user.get("location")}
+            if user
+            else {}
+        ),
+    )
+
+    return template
+
+
+def tags_generation_template(
+    template: str, messages: list[dict], user: Optional[dict] = None
+) -> str:
+    prompt = get_last_user_message(messages)
+    template = replace_prompt_variable(template, prompt)
+    template = replace_messages_variable(template, messages)
+
+    template = prompt_template(
+        template,
+        **(
+            {"user_name": user.get("name"), "user_location": user.get("location")}
+            if user
+            else {}
+        ),
+    )
+    return template
+
+
+def emoji_generation_template(
+    template: str, prompt: str, user: Optional[dict] = None
+) -> str:
+    template = replace_prompt_variable(template, prompt)
+    template = prompt_template(
+        template,
+        **(
+            {"user_name": user.get("name"), "user_location": user.get("location")}
+            if user
+            else {}
+        ),
+    )
+
+    return template
+
+
+def query_generation_template(
     template: str, messages: list[dict], user: Optional[dict] = None
 ) -> str:
     prompt = get_last_user_message(messages)

backend/open_webui/utils/tools.py

@@ -1,11 +1,14 @@
 import inspect
 import logging
-from typing import Awaitable, Callable, get_type_hints
+import re
+from typing import Any, Awaitable, Callable, get_type_hints
+from functools import update_wrapper, partial
 
+from langchain_core.utils.function_calling import convert_to_openai_function
 from open_webui.apps.webui.models.tools import Tools
 from open_webui.apps.webui.models.users import UserModel
-from open_webui.apps.webui.utils import load_toolkit_module_by_id
-from open_webui.utils.schemas import json_schema_to_model
+from open_webui.apps.webui.utils import load_tools_module_by_id
+from pydantic import BaseModel, Field, create_model
 
 log = logging.getLogger(__name__)
 
@@ -14,17 +17,16 @@ def apply_extra_params_to_tool_function(
     function: Callable, extra_params: dict
 ) -> Callable[..., Awaitable]:
     sig = inspect.signature(function)
-    extra_params = {
-        key: value for key, value in extra_params.items() if key in sig.parameters
-    }
-    is_coroutine = inspect.iscoroutinefunction(function)
+    extra_params = {k: v for k, v in extra_params.items() if k in sig.parameters}
+    partial_func = partial(function, **extra_params)
+    if inspect.iscoroutinefunction(function):
+        update_wrapper(partial_func, function)
+        return partial_func
 
-    async def new_function(**kwargs):
-        extra_kwargs = kwargs | extra_params
-        if is_coroutine:
-            return await function(**extra_kwargs)
-        return function(**extra_kwargs)
+    async def new_function(*args, **kwargs):
+        return partial_func(*args, **kwargs)
 
+    update_wrapper(new_function, function)
     return new_function
 
 
@@ -32,15 +34,16 @@ def apply_extra_params_to_tool_function(
 def get_tools(
     webui_app, tool_ids: list[str], user: UserModel, extra_params: dict
 ) -> dict[str, dict]:
-    tools = {}
+    tools_dict = {}
+
     for tool_id in tool_ids:
-        toolkit = Tools.get_tool_by_id(tool_id)
-        if toolkit is None:
+        tools = Tools.get_tool_by_id(tool_id)
+        if tools is None:
             continue
 
         module = webui_app.state.TOOLS.get(tool_id, None)
         if module is None:
-            module, _ = load_toolkit_module_by_id(tool_id)
+            module, _ = load_tools_module_by_id(tool_id)
             webui_app.state.TOOLS[tool_id] = module
 
         extra_params["__id__"] = tool_id
@@ -53,111 +56,143 @@ def get_tools(
                 **Tools.get_user_valves_by_id_and_user_id(tool_id, user.id)
             )
 
-        for spec in toolkit.specs:
-            # TODO: Fix hack for OpenAI API
-            for val in spec.get("parameters", {}).get("properties", {}).values():
-                if val["type"] == "str":
-                    val["type"] = "string"
+        for spec in tools.specs:
+            # Remove internal parameters
+            spec["parameters"]["properties"] = {
+                key: val
+                for key, val in spec["parameters"]["properties"].items()
+                if not key.startswith("__")
+            }
+
             function_name = spec["name"]
 
             # convert to function that takes only model params and inserts custom params
             original_func = getattr(module, function_name)
             callable = apply_extra_params_to_tool_function(original_func, extra_params)
-            if hasattr(original_func, "__doc__"):
-                callable.__doc__ = original_func.__doc__
-
             # TODO: This needs to be a pydantic model
             tool_dict = {
                 "toolkit_id": tool_id,
                 "callable": callable,
                 "spec": spec,
-                "pydantic_model": json_schema_to_model(spec),
+                "pydantic_model": function_to_pydantic_model(callable),
                 "file_handler": hasattr(module, "file_handler") and module.file_handler,
                 "citation": hasattr(module, "citation") and module.citation,
             }
 
             # TODO: if collision, prepend toolkit name
-            if function_name in tools:
-                log.warning(f"Tool {function_name} already exists in another toolkit!")
-                log.warning(f"Collision between {toolkit} and {tool_id}.")
-                log.warning(f"Discarding {toolkit}.{function_name}")
+            if function_name in tools_dict:
+                log.warning(f"Tool {function_name} already exists in another tools!")
+                log.warning(f"Collision between {tools} and {tool_id}.")
+                log.warning(f"Discarding {tools}.{function_name}")
             else:
-                tools[function_name] = tool_dict
-    return tools
+                tools_dict[function_name] = tool_dict
+
+    return tools_dict
 
 
-def doc_to_dict(docstring):
-    lines = docstring.split("\n")
-    description = lines[1].strip()
-    param_dict = {}
+def parse_description(docstring: str | None) -> str:
+    """
+    Parse a function's docstring to extract the description.
+
+    Args:
+        docstring (str): The docstring to parse.
+
+    Returns:
+        str: The description.
+    """
+
+    if not docstring:
+        return ""
+
+    lines = [line.strip() for line in docstring.strip().split("\n")]
+    description_lines: list[str] = []
 
     for line in lines:
-        if ":param" in line:
-            line = line.replace(":param", "").strip()
-            param, desc = line.split(":", 1)
-            param_dict[param.strip()] = desc.strip()
-    ret_dict = {"description": description, "params": param_dict}
-    return ret_dict
+        if re.match(r":param", line) or re.match(r":return", line):
+            break
+
+        description_lines.append(line)
+
+    return "\n".join(description_lines)
 
 
-def get_tools_specs(tools) -> list[dict]:
-    function_list = [
-        {"name": func, "function": getattr(tools, func)}
-        for func in dir(tools)
-        if callable(getattr(tools, func))
+def parse_docstring(docstring):
+    """
+    Parse a function's docstring to extract parameter descriptions in reST format.
+
+    Args:
+        docstring (str): The docstring to parse.
+
+    Returns:
+        dict: A dictionary where keys are parameter names and values are descriptions.
+    """
+    if not docstring:
+        return {}
+
+    # Regex to match `:param name: description` format
+    param_pattern = re.compile(r":param (\w+):\s*(.+)")
+    param_descriptions = {}
+
+    for line in docstring.splitlines():
+        match = param_pattern.match(line.strip())
+        if not match:
+            continue
+        param_name, param_description = match.groups()
+        if param_name.startswith("__"):
+            continue
+        param_descriptions[param_name] = param_description
+
+    return param_descriptions
+
+
+def function_to_pydantic_model(func: Callable) -> type[BaseModel]:
+    """
+    Converts a Python function's type hints and docstring to a Pydantic model,
+    including support for nested types, default values, and descriptions.
+
+    Args:
+        func: The function whose type hints and docstring should be converted.
+        model_name: The name of the generated Pydantic model.
+
+    Returns:
+        A Pydantic model class.
+    """
+    type_hints = get_type_hints(func)
+    signature = inspect.signature(func)
+    parameters = signature.parameters
+
+    docstring = func.__doc__
+    descriptions = parse_docstring(docstring)
+
+    tool_description = parse_description(docstring)
+
+    field_defs = {}
+    for name, param in parameters.items():
+        type_hint = type_hints.get(name, Any)
+        default_value = param.default if param.default is not param.empty else ...
+        description = descriptions.get(name, None)
+        if not description:
+            field_defs[name] = type_hint, default_value
+            continue
+        field_defs[name] = type_hint, Field(default_value, description=description)
+
+    model = create_model(func.__name__, **field_defs)
+    model.__doc__ = tool_description
+
+    return model
+
+
+def get_callable_attributes(tool: object) -> list[Callable]:
+    return [
+        getattr(tool, func)
+        for func in dir(tool)
+        if callable(getattr(tool, func))
         and not func.startswith("__")
-        and not inspect.isclass(getattr(tools, func))
+        and not inspect.isclass(getattr(tool, func))
     ]
 
-    specs = []
-    for function_item in function_list:
-        function_name = function_item["name"]
-        function = function_item["function"]
 
-        function_doc = doc_to_dict(function.__doc__ or function_name)
-        specs.append(
-            {
-                "name": function_name,
-                # TODO: multi-line desc?
-                "description": function_doc.get("description", function_name),
-                "parameters": {
-                    "type": "object",
-                    "properties": {
-                        param_name: {
-                            "type": param_annotation.__name__.lower(),
-                            **(
-                                {
-                                    "enum": (
-                                        str(param_annotation.__args__)
-                                        if hasattr(param_annotation, "__args__")
-                                        else None
-                                    )
-                                }
-                                if hasattr(param_annotation, "__args__")
-                                else {}
-                            ),
-                            "description": function_doc.get("params", {}).get(
-                                param_name, param_name
-                            ),
-                        }
-                        for param_name, param_annotation in get_type_hints(
-                            function
-                        ).items()
-                        if param_name != "return"
-                        and not (
-                            param_name.startswith("__") and param_name.endswith("__")
-                        )
-                    },
-                    "required": [
-                        name
-                        for name, param in inspect.signature(
-                            function
-                        ).parameters.items()
-                        if param.default is param.empty
-                        and not (name.startswith("__") and name.endswith("__"))
-                    ],
-                },
-            }
-        )
-
-    return specs
+def get_tools_specs(tool_class: object) -> list[dict]:
+    function_list = get_callable_attributes(tool_class)
+    models = map(function_to_pydantic_model, function_list)
+    return [convert_to_openai_function(tool) for tool in models]

backend/open_webui/utils/utils.py

@@ -1,13 +1,16 @@
 import logging
 import uuid
-from datetime import UTC, datetime, timedelta
-from typing import Optional, Union
-
 import jwt
+
+from datetime import UTC, datetime, timedelta
+from typing import Optional, Union, List, Dict
+
 from open_webui.apps.webui.models.users import Users
+
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import WEBUI_SECRET_KEY
-from fastapi import Depends, HTTPException, Request, status
+
+from fastapi import Depends, HTTPException, Request, Response, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
 from passlib.context import CryptContext
 
@@ -88,10 +91,21 @@ def get_current_user(
 
     # auth by api key
     if token.startswith("sk-"):
+        if not request.state.enable_api_key:
+            raise HTTPException(
+                status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.API_KEY_NOT_ALLOWED
+            )
         return get_current_user_by_api_key(token)
 
     # auth by jwt token
-    data = decode_token(token)
+    try:
+        data = decode_token(token)
+    except Exception as e:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail="Invalid token",
+        )
+
     if data is not None and "id" in data:
         user = Users.get_user_by_id(data["id"])
         if user is None:

backend/requirements.txt

@@ -1,7 +1,7 @@
 fastapi==0.111.0
 uvicorn[standard]==0.30.6
 pydantic==2.9.2
-python-multipart==0.0.9
+python-multipart==0.0.17
 
 Flask==3.0.3
 Flask-Cors==5.0.0
@@ -12,18 +12,22 @@ passlib[bcrypt]==1.7.4
 
 requests==2.32.3
 aiohttp==3.10.8
+async-timeout
+aiocache
+aiofiles
 
 sqlalchemy==2.0.32
 alembic==1.13.2
 peewee==3.17.6
 peewee-migrate==1.12.2
 psycopg2-binary==2.9.9
+pgvector==0.3.5
 PyMySQL==1.1.1
 bcrypt==4.2.0
 
 pymongo
 redis
-boto3==1.35.0
+boto3==1.35.53
 
 argon2-cffi==23.1.0
 APScheduler==3.10.4
@@ -34,21 +38,25 @@ anthropic
 google-generativeai==0.7.2
 tiktoken
 
-langchain==0.2.15
-langchain-community==0.2.12
+langchain==0.3.7
+langchain-community==0.3.7
 langchain-chroma==0.1.4
 
 fake-useragent==1.5.1
-chromadb==0.5.9
-pymilvus==2.4.7
+chromadb==0.5.15
+pymilvus==2.4.9
+qdrant-client~=1.12.0
+opensearch-py==2.7.1
 
-sentence-transformers==3.0.1
+sentence-transformers==3.2.0
 colbert-ai==0.2.21
 einops==0.8.0
 
 
 ftfy==6.2.3
 pypdf==4.3.1
+fpdf2==2.7.9
+pymdown-extensions==10.11.2
 docx2txt==0.8
 python-pptx==1.0.0
 unstructured==0.15.9
@@ -61,11 +69,11 @@ pyxlsb==1.0.10
 xlrd==2.0.1
 validators==0.33.0
 psutil
+sentencepiece
+soundfile==0.12.1
 
 opencv-python-headless==4.10.0.84
 rapidocr-onnxruntime==1.3.24
-
-fpdf2==2.7.9
 rank-bm25==0.2.2
 
 faster-whisper==1.0.3
@@ -75,14 +83,19 @@ authlib==1.3.2
 
 black==24.8.0
 langfuse==2.44.0
-youtube-transcript-api==0.6.2
+youtube-transcript-api==0.6.3
 pytube==15.0.0
 
 extract_msg
 pydub
-duckduckgo-search~=6.2.13
+duckduckgo-search~=6.3.5
 
 ## Tests
 docker~=7.1.0
 pytest~=8.3.2
 pytest-docker~=3.1.1
+
+googleapis-common-protos==1.63.2
+
+## LDAP
+ldap3==2.9.1

cypress/e2e/chat.cy.ts

@@ -30,7 +30,7 @@ describe('Settings', () => {
 			// Select the first model
 			cy.get('button[aria-label="model-item"]').first().click();
 			// Type a message
-			cy.get('#chat-textarea').type('Hi, what can you do? A single sentence only please.', {
+			cy.get('#chat-input').type('Hi, what can you do? A single sentence only please.', {
 				force: true
 			});
 			// Send the message
@@ -50,7 +50,7 @@ describe('Settings', () => {
 			// Select the first model
 			cy.get('button[aria-label="model-item"]').first().click();
 			// Type a message
-			cy.get('#chat-textarea').type('Hi, what can you do? A single sentence only please.', {
+			cy.get('#chat-input').type('Hi, what can you do? A single sentence only please.', {
 				force: true
 			});
 			// Send the message
@@ -85,7 +85,7 @@ describe('Settings', () => {
 			// Select the first model
 			cy.get('button[aria-label="model-item"]').first().click();
 			// Type a message
-			cy.get('#chat-textarea').type('Hi, what can you do? A single sentence only please.', {
+			cy.get('#chat-input').type('Hi, what can you do? A single sentence only please.', {
 				force: true
 			});
 			// Send the message

cypress/e2e/documents.cy.ts

@@ -1,46 +1,2 @@
 // eslint-disable-next-line @typescript-eslint/triple-slash-reference
 /// <reference path="../support/index.d.ts" />
-
-describe('Documents', () => {
-	const timestamp = Date.now();
-
-	before(() => {
-		cy.uploadTestDocument(timestamp);
-	});
-
-	after(() => {
-		cy.deleteTestDocument(timestamp);
-	});
-
-	context('Admin', () => {
-		beforeEach(() => {
-			// Login as the admin user
-			cy.loginAdmin();
-			// Visit the home page
-			cy.visit('/workspace/documents');
-			cy.get('button').contains('#cypress-test').click();
-		});
-
-		it('can see documents', () => {
-			cy.get('div').contains(`document-test-initial-${timestamp}.txt`).should('have.length', 1);
-		});
-
-		it('can see edit button', () => {
-			cy.get('div')
-				.contains(`document-test-initial-${timestamp}.txt`)
-				.get("button[aria-label='Edit Doc']")
-				.should('exist');
-		});
-
-		it('can see delete button', () => {
-			cy.get('div')
-				.contains(`document-test-initial-${timestamp}.txt`)
-				.get("button[aria-label='Delete Doc']")
-				.should('exist');
-		});
-
-		it('can see upload button', () => {
-			cy.get("button[aria-label='Add Docs']").should('exist');
-		});
-	});
-});

cypress/support/e2e.ts

@@ -73,50 +73,6 @@ Cypress.Commands.add('register', (name, email, password) => register(name, email
 Cypress.Commands.add('registerAdmin', () => registerAdmin());
 Cypress.Commands.add('loginAdmin', () => loginAdmin());
 
-Cypress.Commands.add('uploadTestDocument', (suffix: any) => {
-	// Login as admin
-	cy.loginAdmin();
-	// upload example document
-	cy.visit('/workspace/documents');
-	// Create a document
-	cy.get("button[aria-label='Add Docs']").click();
-	cy.readFile('cypress/data/example-doc.txt').then((text) => {
-		// select file
-		cy.get('#upload-doc-input').selectFile(
-			{
-				contents: Cypress.Buffer.from(text + Date.now()),
-				fileName: `document-test-initial-${suffix}.txt`,
-				mimeType: 'text/plain',
-				lastModified: Date.now()
-			},
-			{
-				force: true
-			}
-		);
-		// open tag input
-		cy.get("button[aria-label='Add Tag']").click();
-		cy.get("input[placeholder='Add a tag']").type('cypress-test');
-		cy.get("button[aria-label='Save Tag']").click();
-
-		// submit to upload
-		cy.get("button[type='submit']").click();
-
-		// wait for upload to finish
-		cy.get('button').contains('#cypress-test').should('exist');
-		cy.get('div').contains(`document-test-initial-${suffix}.txt`).should('exist');
-	});
-});
-
-Cypress.Commands.add('deleteTestDocument', (suffix: any) => {
-	cy.loginAdmin();
-	cy.visit('/workspace/documents');
-	// clean up uploaded documents
-	cy.get('div')
-		.contains(`document-test-initial-${suffix}.txt`)
-		.find("button[aria-label='Delete Doc']")
-		.click();
-});
-
 before(() => {
 	cy.registerAdmin();
 });

docs/apache.md

@@ -118,7 +118,7 @@ Navigate to the apache sites-available directory:
 
 `nano models.server.city.conf` # match this with your ollama server domain
 
-Add the folloing virtualhost containing this example (modify as needed):
+Add the following virtualhost containing this example (modify as needed):
 
 ```
 

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.3.32",
+	"version": "0.4.5",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -37,6 +37,7 @@
 		"postcss": "^8.4.31",
 		"prettier": "^3.3.3",
 		"prettier-plugin-svelte": "^3.2.6",
+		"sass-embedded": "^1.81.0",
 		"svelte": "^4.2.18",
 		"svelte-check": "^3.8.5",
 		"svelte-confetti": "^1.3.2",
@@ -52,8 +53,17 @@
 		"@codemirror/lang-python": "^6.1.6",
 		"@codemirror/language-data": "^6.5.1",
 		"@codemirror/theme-one-dark": "^6.1.2",
+		"@huggingface/transformers": "^3.0.0",
+		"@mediapipe/tasks-vision": "^0.10.17",
 		"@pyscript/core": "^0.4.32",
 		"@sveltejs/adapter-node": "^2.0.0",
+		"@tiptap/core": "^2.10.0",
+		"@tiptap/extension-code-block-lowlight": "^2.10.0",
+		"@tiptap/extension-highlight": "^2.10.0",
+		"@tiptap/extension-placeholder": "^2.10.0",
+		"@tiptap/extension-typography": "^2.10.0",
+		"@tiptap/pm": "^2.10.0",
+		"@tiptap/starter-kit": "^2.10.0",
 		"@xyflow/svelte": "^0.1.19",
 		"async": "^3.2.5",
 		"bits-ui": "^0.19.7",
@@ -72,9 +82,19 @@
 		"js-sha256": "^0.10.1",
 		"katex": "^0.16.9",
 		"marked": "^9.1.0",
-		"mermaid": "^10.9.1",
+		"mermaid": "^10.9.3",
 		"paneforge": "^0.0.6",
 		"panzoom": "^9.4.3",
+		"prosemirror-commands": "^1.6.0",
+		"prosemirror-example-setup": "^1.2.3",
+		"prosemirror-history": "^1.4.1",
+		"prosemirror-keymap": "^1.2.2",
+		"prosemirror-markdown": "^1.13.1",
+		"prosemirror-model": "^1.23.0",
+		"prosemirror-schema-basic": "^1.2.3",
+		"prosemirror-schema-list": "^1.4.1",
+		"prosemirror-state": "^1.4.3",
+		"prosemirror-view": "^1.34.3",
 		"pyodide": "^0.26.1",
 		"socket.io-client": "^4.2.0",
 		"sortablejs": "^1.15.2",

pyproject.toml

@@ -9,7 +9,7 @@ dependencies = [
     "fastapi==0.111.0",
     "uvicorn[standard]==0.30.6",
     "pydantic==2.9.2",
-    "python-multipart==0.0.9",
+    "python-multipart==0.0.17",
 
     "Flask==3.0.3",
     "Flask-Cors==5.0.0",
@@ -20,18 +20,22 @@ dependencies = [
 
     "requests==2.32.3",
     "aiohttp==3.10.8",
+    "async-timeout",
+    "aiocache",
+    "aiofiles",
 
     "sqlalchemy==2.0.32",
     "alembic==1.13.2",
     "peewee==3.17.6",
     "peewee-migrate==1.12.2",
     "psycopg2-binary==2.9.9",
+    "pgvector==0.3.5",
     "PyMySQL==1.1.1",
     "bcrypt==4.2.0",
 
     "pymongo",
     "redis",
-    "boto3==1.35.0",
+    "boto3==1.35.53",
 
     "argon2-cffi==23.1.0",
     "APScheduler==3.10.4",
@@ -41,21 +45,24 @@ dependencies = [
     "google-generativeai==0.7.2",
     "tiktoken",
 
-    "langchain==0.2.15",
-    "langchain-community==0.2.12",
+    "langchain==0.3.7",
+    "langchain-community==0.3.7",
     "langchain-chroma==0.1.4",
 
     "fake-useragent==1.5.1",
-    "chromadb==0.5.9",
-    "pymilvus==2.4.7",
+    "chromadb==0.5.15",
+    "pymilvus==2.4.9",
+    "qdrant-client~=1.12.0",
+    "opensearch-py==2.7.1",
 
-    "sentence-transformers==3.0.1",
+    "sentence-transformers==3.2.0",
     "colbert-ai==0.2.21",
     "einops==0.8.0",
-    
 
     "ftfy==6.2.3",
     "pypdf==4.3.1",
+    "fpdf2==2.7.9",
+    "pymdown-extensions==10.11.2",
     "docx2txt==0.8",
     "python-pptx==1.0.0",
     "unstructured==0.15.9",
@@ -68,11 +75,11 @@ dependencies = [
     "xlrd==2.0.1",
     "validators==0.33.0",
     "psutil",
+    "sentencepiece",
+    "soundfile==0.12.1",
 
     "opencv-python-headless==4.10.0.84",
     "rapidocr-onnxruntime==1.3.24",
-
-    "fpdf2==2.7.9",
     "rank-bm25==0.2.2",
 
     "faster-whisper==1.0.3",
@@ -82,16 +89,20 @@ dependencies = [
 
     "black==24.8.0",
     "langfuse==2.44.0",
-    "youtube-transcript-api==0.6.2",
+    "youtube-transcript-api==0.6.3",
     "pytube==15.0.0",
 
     "extract_msg",
     "pydub",
-    "duckduckgo-search~=6.2.13",
+    "duckduckgo-search~=6.3.5",
 
     "docker~=7.1.0",
     "pytest~=8.3.2",
-    "pytest-docker~=3.1.1"
+    "pytest-docker~=3.1.1",
+
+    "googleapis-common-protos==1.63.2",
+
+    "ldap3==2.9.1"
 ]
 readme = "README.md"
 requires-python = ">= 3.11, < 3.12.0a1"

src/app.css

@@ -16,6 +16,12 @@
 	font-display: swap;
 }
 
+@font-face {
+	font-family: 'InstrumentSerif';
+	src: url('/assets/fonts/InstrumentSerif-Regular.ttf');
+	font-display: swap;
+}
+
 html {
 	word-break: break-word;
 }
@@ -26,6 +32,10 @@ code {
 	width: auto;
 }
 
+.font-secondary {
+	font-family: 'InstrumentSerif', sans-serif;
+}
+
 math {
 	margin-top: 1rem;
 }
@@ -34,6 +44,14 @@ math {
 	@apply rounded-lg;
 }
 
+.input-prose {
+	@apply prose dark:prose-invert prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
+}
+
+.input-prose-sm {
+	@apply prose dark:prose-invert prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line text-sm;
+}
+
 .markdown-prose {
 	@apply prose dark:prose-invert prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
 }
@@ -56,7 +74,7 @@ li p {
 
 ::-webkit-scrollbar-thumb {
 	--tw-border-opacity: 1;
-	background-color: rgba(217, 217, 227, 0.8);
+	background-color: rgba(236, 236, 236, 0.8);
 	border-color: rgba(255, 255, 255, var(--tw-border-opacity));
 	border-radius: 9999px;
 	border-width: 1px;
@@ -64,7 +82,7 @@ li p {
 
 /* Dark theme scrollbar styles */
 .dark ::-webkit-scrollbar-thumb {
-	background-color: rgba(69, 69, 74, 0.8); /* Darker color for dark theme */
+	background-color: rgba(33, 33, 33, 0.8); /* Darker color for dark theme */
 	border-color: rgba(0, 0, 0, var(--tw-border-opacity));
 }
 
@@ -179,3 +197,97 @@ input[type='number'] {
 .bg-gray-950-90 {
 	background-color: rgba(var(--color-gray-950, #0d0d0d), 0.9);
 }
+
+.ProseMirror {
+	@apply h-full min-h-fit max-h-full whitespace-pre-wrap;
+}
+
+.ProseMirror:focus {
+	outline: none;
+}
+
+.ProseMirror p.is-editor-empty:first-child::before {
+	content: attr(data-placeholder);
+	float: left;
+	color: #adb5bd;
+	pointer-events: none;
+	height: 0;
+}
+
+.tiptap > pre > code {
+	border-radius: 0.4rem;
+	font-size: 0.85rem;
+	padding: 0.25em 0.3em;
+
+	@apply dark:bg-gray-800 bg-gray-100;
+}
+
+.tiptap > pre {
+	border-radius: 0.5rem;
+	font-family: 'JetBrainsMono', monospace;
+	margin: 1.5rem 0;
+	padding: 0.75rem 1rem;
+
+	@apply dark:bg-gray-800 bg-gray-100;
+}
+
+.tiptap p code {
+	color: #eb5757;
+	border-width: 0px;
+	padding: 3px 8px;
+	font-size: 0.8em;
+	font-weight: 600;
+	@apply rounded-md dark:bg-gray-800 bg-gray-100 mx-0.5;
+}
+
+/* Code styling */
+.hljs-comment,
+.hljs-quote {
+	color: #616161;
+}
+
+.hljs-variable,
+.hljs-template-variable,
+.hljs-attribute,
+.hljs-tag,
+.hljs-regexp,
+.hljs-link,
+.hljs-name,
+.hljs-selector-id,
+.hljs-selector-class {
+	color: #f98181;
+}
+
+.hljs-number,
+.hljs-meta,
+.hljs-built_in,
+.hljs-builtin-name,
+.hljs-literal,
+.hljs-type,
+.hljs-params {
+	color: #fbbc88;
+}
+
+.hljs-string,
+.hljs-symbol,
+.hljs-bullet {
+	color: #b9f18d;
+}
+
+.hljs-title,
+.hljs-section {
+	color: #faf594;
+}
+
+.hljs-keyword,
+.hljs-selector-tag {
+	color: #70cff8;
+}
+
+.hljs-emphasis {
+	font-style: italic;
+}
+
+.hljs-strong {
+	font-weight: 700;
+}

src/lib/apis/auths/index.ts

@@ -110,6 +110,150 @@ export const getSessionUser = async (token: string) => {
 	return res;
 };
 
+export const ldapUserSignIn = async (user: string, password: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/ldap`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json'
+		},
+		credentials: 'include',
+		body: JSON.stringify({
+			user: user,
+			password: password
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getLdapConfig = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/admin/config/ldap`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateLdapConfig = async (token: string = '', enable_ldap: boolean) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/admin/config/ldap`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			enable_ldap: enable_ldap
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getLdapServer = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/admin/config/ldap/server`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateLdapServer = async (token: string = '', body: object) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/admin/config/ldap/server`, {
+		method: 'POST',
+		headers: {
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify(body)
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const userSignIn = async (email: string, password: string) => {
 	let error = null;
 
@@ -180,6 +324,31 @@ export const userSignUp = async (
 	return res;
 };
 
+export const userSignOut = async () => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/auths/signout`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json'
+		},
+		credentials: 'include'
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res;
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+};
+
 export const addUser = async (
 	token: string,
 	name: string,

src/lib/apis/chats/index.ts

@@ -32,6 +32,46 @@ export const createNewChat = async (token: string, chat: object) => {
 	return res;
 };
 
+export const importChat = async (
+	token: string,
+	chat: object,
+	meta: object | null,
+	pinned?: boolean,
+	folderId?: string | null
+) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/import`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			chat: chat,
+			meta: meta ?? {},
+			pinned: pinned,
+			folder_id: folderId
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getChatList = async (token: string = '', page: number | null = null) => {
 	let error = null;
 	const searchParams = new URLSearchParams();
@@ -167,6 +207,75 @@ export const getAllChats = async (token: string) => {
 	return res;
 };
 
+export const getChatListBySearchText = async (token: string, text: string, page: number = 1) => {
+	let error = null;
+
+	const searchParams = new URLSearchParams();
+	searchParams.append('text', text);
+	searchParams.append('page', `${page}`);
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/search?${searchParams.toString()}`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.map((chat) => ({
+		...chat,
+		time_range: getTimeRange(chat.updated_at)
+	}));
+};
+
+export const getChatsByFolderId = async (token: string, folderId: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/folder/${folderId}`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const getAllArchivedChats = async (token: string) => {
 	let error = null;
 
@@ -229,10 +338,10 @@ export const getAllUserChats = async (token: string) => {
 	return res;
 };
 
-export const getAllChatTags = async (token: string) => {
+export const getAllTags = async (token: string) => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/tags/all`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/all/tags`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -260,6 +369,40 @@ export const getAllChatTags = async (token: string) => {
 	return res;
 };
 
+export const getPinnedChatList = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/pinned`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res.map((chat) => ({
+		...chat,
+		time_range: getTimeRange(chat.updated_at)
+	}));
+};
+
 export const getChatListByTagName = async (token: string = '', tagName: string) => {
 	let error = null;
 
@@ -361,11 +504,87 @@ export const getChatByShareId = async (token: string, share_id: string) => {
 	return res;
 };
 
+export const getChatPinnedStatusById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/pinned`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = err;
+			}
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const toggleChatPinnedStatusById = async (token: string, id: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/pin`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = err;
+			}
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const cloneChatById = async (token: string, id: string) => {
 	let error = null;
 
 	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/clone`, {
-		method: 'GET',
+		method: 'POST',
 		headers: {
 			Accept: 'application/json',
 			'Content-Type': 'application/json',
@@ -431,11 +650,46 @@ export const shareChatById = async (token: string, id: string) => {
 	return res;
 };
 
+export const updateChatFolderIdById = async (token: string, id: string, folderId?: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/folder`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify({
+			folder_id: folderId
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.then((json) => {
+			return json;
+		})
+		.catch((err) => {
+			error = err;
+
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const archiveChatById = async (token: string, id: string) => {
 	let error = null;
 
 	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/${id}/archive`, {
-		method: 'GET',
+		method: 'POST',
 		headers: {
 			Accept: 'application/json',
 			'Content-Type': 'application/json',
@@ -605,8 +859,7 @@ export const addTagById = async (token: string, id: string, tagName: string) =>
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			tag_name: tagName,
-			chat_id: id
+			name: tagName
 		})
 	})
 		.then(async (res) => {
@@ -617,8 +870,7 @@ export const addTagById = async (token: string, id: string, tagName: string) =>
 			return json;
 		})
 		.catch((err) => {
-			error = err;
-
+			error = err.detail;
 			console.log(err);
 			return null;
 		});
@@ -641,8 +893,7 @@ export const deleteTagById = async (token: string, id: string, tagName: string)
 			...(token && { authorization: `Bearer ${token}` })
 		},
 		body: JSON.stringify({
-			tag_name: tagName,
-			chat_id: id
+			name: tagName
 		})
 	})
 		.then(async (res) => {

src/lib/apis/configs/index.ts

@@ -58,17 +58,44 @@ export const exportConfig = async (token: string) => {
 	return res;
 };
 
-export const setDefaultModels = async (token: string, models: string) => {
+export const getModelsConfig = async (token: string) => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/default/models`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/models`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const setModelsConfig = async (token: string, config: object) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/models`, {
 		method: 'POST',
 		headers: {
 			'Content-Type': 'application/json',
 			Authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
-			models: models
+			...config
 		})
 	})
 		.then(async (res) => {
@@ -91,7 +118,7 @@ export const setDefaultModels = async (token: string, models: string) => {
 export const setDefaultPromptSuggestions = async (token: string, promptSuggestions: string) => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/default/suggestions`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/configs/suggestions`, {
 		method: 'POST',
 		headers: {
 			'Content-Type': 'application/json',

src/lib/apis/evaluations/index.ts

@@ -1,51 +1,9 @@
 import { WEBUI_API_BASE_URL } from '$lib/constants';
 
-export const createNewDoc = async (
-	token: string,
-	collection_name: string,
-	filename: string,
-	name: string,
-	title: string,
-	content: object | null = null
-) => {
+export const getConfig = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/documents/create`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			collection_name: collection_name,
-			filename: filename,
-			name: name,
-			title: title,
-			...(content ? { content: JSON.stringify(content) } : {})
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			error = err.detail;
-			console.log(err);
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res;
-};
-
-export const getDocs = async (token: string = '') => {
-	let error = null;
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/documents/`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/config`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -73,13 +31,41 @@ export const getDocs = async (token: string = '') => {
 	return res;
 };
 
-export const getDocByName = async (token: string, name: string) => {
+export const updateConfig = async (token: string, config: object) => {
 	let error = null;
 
-	const searchParams = new URLSearchParams();
-	searchParams.append('name', name);
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/config`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...config
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+			return null;
+		});
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/documents/docs?${searchParams.toString()}`, {
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getAllFeedbacks = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/feedbacks/all`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -96,7 +82,6 @@ export const getDocByName = async (token: string, name: string) => {
 		})
 		.catch((err) => {
 			error = err.detail;
-
 			console.log(err);
 			return null;
 		});
@@ -108,28 +93,16 @@ export const getDocByName = async (token: string, name: string) => {
 	return res;
 };
 
-type DocUpdateForm = {
-	name: string;
-	title: string;
-};
-
-export const updateDocByName = async (token: string, name: string, form: DocUpdateForm) => {
+export const exportAllFeedbacks = async (token: string = '') => {
 	let error = null;
 
-	const searchParams = new URLSearchParams();
-	searchParams.append('name', name);
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/documents/doc/update?${searchParams.toString()}`, {
-		method: 'POST',
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/feedbacks/all/export`, {
+		method: 'GET',
 		headers: {
 			Accept: 'application/json',
 			'Content-Type': 'application/json',
 			authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			name: form.name,
-			title: form.title
-		})
+		}
 	})
 		.then(async (res) => {
 			if (!res.ok) throw await res.json();
@@ -140,7 +113,6 @@ export const updateDocByName = async (token: string, name: string, form: DocUpda
 		})
 		.catch((err) => {
 			error = err.detail;
-
 			console.log(err);
 			return null;
 		});
@@ -152,18 +124,10 @@ export const updateDocByName = async (token: string, name: string, form: DocUpda
 	return res;
 };
 
-type TagDocForm = {
-	name: string;
-	tags: string[];
-};
-
-export const tagDocByName = async (token: string, name: string, form: TagDocForm) => {
+export const createNewFeedback = async (token: string, feedback: object) => {
 	let error = null;
 
-	const searchParams = new URLSearchParams();
-	searchParams.append('name', name);
-
-	const res = await fetch(`${WEBUI_API_BASE_URL}/documents/doc/tags?${searchParams.toString()}`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/feedback`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -171,9 +135,36 @@ export const tagDocByName = async (token: string, name: string, form: TagDocForm
 			authorization: `Bearer ${token}`
 		},
 		body: JSON.stringify({
-			name: form.name,
-			tags: form.tags
+			...feedback
 		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getFeedbackById = async (token: string, feedbackId: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/feedback/${feedbackId}`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			authorization: `Bearer ${token}`
+		}
 	})
 		.then(async (res) => {
 			if (!res.ok) throw await res.json();
@@ -184,7 +175,6 @@ export const tagDocByName = async (token: string, name: string, form: TagDocForm
 		})
 		.catch((err) => {
 			error = err.detail;
-
 			console.log(err);
 			return null;
 		});
@@ -196,13 +186,41 @@ export const tagDocByName = async (token: string, name: string, form: TagDocForm
 	return res;
 };
 
-export const deleteDocByName = async (token: string, name: string) => {
+export const updateFeedbackById = async (token: string, feedbackId: string, feedback: object) => {
 	let error = null;
 
-	const searchParams = new URLSearchParams();
-	searchParams.append('name', name);
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/feedback/${feedbackId}`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			...feedback
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+			return null;
+		});
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/documents/doc/delete?${searchParams.toString()}`, {
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const deleteFeedbackById = async (token: string, feedbackId: string) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/evaluations/feedback/${feedbackId}`, {
 		method: 'DELETE',
 		headers: {
 			Accept: 'application/json',
@@ -214,12 +232,8 @@ export const deleteDocByName = async (token: string, name: string) => {
 			if (!res.ok) throw await res.json();
 			return res.json();
 		})
-		.then((json) => {
-			return json;
-		})
 		.catch((err) => {
 			error = err.detail;
-
 			console.log(err);
 			return null;
 		});