Remove unnecessary `pathlib.Path` conversions. (CACHE_DIR and DATA_DIR)
Use `/` Path joining shorthand to ensure using platform specific Path separators (Windows: \\, Unix: /)
Use `logging.getLevelNamesMapping()` for getting all valid logging levels. This also allows adding new ones using `logging.addLevel()`. This feature was [added](https://docs.python.org/3.11/library/logging.html#logging.getLevelNamesMapping) in Python 3.11 which is above the minimum supported Python version for open-webui.
When the OAuth groups claim does not yield a list, `user_oauth_groups` was previously
set to None, causing a TypeError during membership checks. Changed this default to
an empty list (`[]`) to ensure the variable is always iterable, preventing errors
for non-admin users while logging in.
This fix ensures stability in the `update_user_groups` function.
1. remove the typo ”‘’" for -1 表示无限制，正整数表示具体限制”
2. Token should be kept rather than translated as "标记"
3. Max Tokens (num_predict) should be "最大Token数量 (num_predict)"
4. "Enter Jupyter Token" here “Token" could be translated as ”令牌“ just as "JWT Token": "JWT 令牌", (line 582)
5. "TLS" which means "Transport Layer Security" should be translated to "传输层安全协议"
6. "Tokens To Keep On Context Refresh (num_keep)" "在语境刷新时需保留的 Token 数量"
7. change token to "Token" in the Chinese translation.
This is to bring consistency with apply_model_params_to_body_openai. Both now use a mapping dictionary then call and return apply_model_params_to_body directly.
We copy the params from from the original key to the new key, then delete it. This is to ensure Ollama only gets valid options.
(Add a comment as well)
1) Ollama natively supports frequency_penalty, so this is not necessary.
2) Repeat_penalty is being added to Open WebUI in PR #10016, allowing Ollama users to pick which penalty methods they want.
1) Ollama supports sending the system prompt as a parameter, not as an option. (See https://github.com/ollama/ollama/blob/main/docs/api.md#request-8) However, it is in the options dictionary and needs moved to the payload dictionary.
2) After moving the system parameter from ollama_options to ollama_payload, delete it from ollama_options. This is to prevent Ollama throwing a warning about invalid options.
1) max_tokens was being looked for in openai_payload, but is present in openai_payload['options'], so is never found.
2) After copying the value for max_tokens to num_predict, delete max_tokens from the dictionary. This is to prevent Ollama throwing a warning about invalid option (max_tokens)
1) This may be legacy code?
2) All three of these parameters, temperature, top_p and seed, are found in openai_payload["options"], not openai_payload. They do not need remapped any longer.
1) max_completion_tokens is being looked for in openai_payload, but would be located in openai_payload['options'], so is never found. (This applies to the prior two commits as well).
2) max_completion_tokens is not sent from the frontend, only max_tokens. It does not appear in AdvancedParams.svelte.
2b) Openai.py does use max_completion_tokens, but for o1,o3 models and converts it from max_tokens.
1) Ollama natively supports frequency_penalty.
2) repeat_penaltywas added to Open Webui in PR #10016 and is not merged to main yet at this time. Once both changes go live, Ollama users can freely choose between frequency/presence penalty, or repeat penalty, as they choose.
This feature allows the authentication process to redirect to a
route passed in the querystring. This allows the /auth route
a means of bringing the user to an expected route instead of the
main page (root).
Adds support for Gemini API as an image generation backend. By setting the API Base URL to something like 'https://generativelanguage.googleapis.com/v1beta' and providing their API Key, users should be able to start generating images using models like 'imagen-3.0-generate-002'.
Closes#8885.
During the OAuth signout flow, although the `token` and `oauth_id_token`
cookies were marked for deletion, a new RedirectResponse is created and
returned. This does not contain the header info from the he Response object
used to mark the cookies to be deleted. Hence the cookies remained.
Fixed this by re-using the headers from the other Response object.
to test it use the prompt:
"write please a sample headers (level 1,2,3), text (bold/italic), list, numbered list, quetes, table, code
write each example in hebrew
dont output markdown in code block"
need to be fixed:
* Redundant border properties in quotes:
Removed border-left as border-inline-start properly handles both LTR/RTL and by this prevents double borders in RTL layouts
* table header have `text-align: left` instead of start
e.g.
text-align and direction is not the save thing
the text direction is ok. the `dir="auto"` is fixing the direction שמג the text-align by default is set by the direction, if it set manually is should be start/end to respect the direction attribute
related to this discussion: https://github.com/open-webui/open-webui/discussions/10034. in some cases the previous message have error but it still generate a response. in such case we should also next round chat. so I update the if condition to add another checking of the content in previous message.
- Add Presence Penalty, which I believe most providers have.
- Add repeat_penalty, an Ollama / Llama.cpp only parameter
- Widen temperature range to 2 (supported by many providers and similar front ends)
- Widen Top K range (supported by many providers and similar front ends)
- Adjust description of freqency_penalty in line with OpenAI documentation
- Add presence_penalty with an OpenAI documentation based description
- Add repeat_penalty with an Ollama documentation based description
- This PR aims to address the error 400: "**'OpenSearchClient' object has no attribute 'query'**".
- With the implemented query() method, this issue should be resolved and allow uploaded documents to be vectorized and retrieved based on the given query.
Introducing two new env config options to control cookies settings regarding
authentication. These values are taken into use when setting 'token' and 'oauth_id_token'.
To maintain backwards compatibility, the original session cookie values are used as
fallback.
Separation is done to prevent issues with the session cookie. When the config value was
set as 'strict', the oauth flow was broken (since the session cookie was not provided
after the callback).
Providing a separate config for auth & session cookies allows us to keep the 'strict'
settings for auth related cookies, while also allowing the session cookie to behave as
intended (e.g., by configuring it as 'lax').
The original config was added in commit #af4f8aa. However a later commit #a2e889c reused
this config option for other type of cookies, which was not the original intent.
Related to #7207
Modify the code to allow the docker container to start in an offline environment for versions >= 0.4.0.
* **backend/open_webui/retrieval/utils.py**
- Import `OFFLINE_MODE` from `open_webui.env`.
- Set `local_files_only` to `True` when `OFFLINE_MODE` is enabled in `snapshot_kwargs`.
* **backend/open_webui/env.py**
- Add logic to set `HF_HUB_OFFLINE` environment variable to `1` when `OFFLINE_MODE` is enabled.
* **README.md**
- Document setting `HF_HUB_OFFLINE` environment variable to `1` for offline environments.
Introduce CONTENT_SECURITY_POLICY environment variable to set HTTP header "Content-Security-Policy".
Content Security Policy (CSP) is a feature that helps to prevent or minimize the risk of certain types of security threats. It consists of a series of instructions from a website to a browser, which instruct the browser to place restrictions on the things that the code comprising the site is allowed to do.
https://developer.mozilla.org/en-US/docs/Web/HTTP/CSP
Logging cleanup: removed some extraneous hard prints (including some that revealed message content!); improved debug logging a bit.
+ added chat_id to task metadata (helpful for logging/tracking in some pipe functions)
LDAP will be used as default if no other auth form is enabled.
LDAP now will work with ENABLE_LOGIN_FORM = false.
Fixed exception "User does not match the record."
Now LDAP login is case insensitive.
Integrated with onboarding feature.
When changed via the web interface in Admin's WebSearch, the bypass option is not being persisted.
This change adjusts it to the same name as the one related in the python entity.
I had problems with document handling in rootless containers. Long documents caused the container to hang. Reducing the verbosity of logging from retrieval.main seemed to fix the issues I was experiencing.
This adds `code_executions` as an array of code execution statuses to
chat messages. The intent of this data is to be displayed in a similar
manner as citations: at the bottom of the message, with buttons that open
a modal for more info. However, code execution data doesn't fit well in
citation modals, because they fundamentally differ in their formatting.
Code execution status includes the code that was run (which benefits from
being syntax-highlighted), and the output and generated files. This
differs from citations which are just list of document names and links.
Additionally, code execution is a process, whereas citations are only
emitted once. This is why code execution data uses an ID-based approach,
where each code execution instance is identified by a unique ID and can
be updated by emitting a new `code_execution` message with the same ID.
This allows the code execution status to be updated as code runs.
When we send a request to `/api/chat/completions` without the `Authorization` header, the server just crashes and creates a stack trace, returning "Internal Server Error" to the calling client. With this fix, the server sends a 401 to the client with the content `{"detail": "Not authenticated"}`.
This fixes "The process cannot access the file
because it is being used by another process"
errors on Windows.
The file is still automatically deleted by the
`os.unlink` call later in the function.
Updates #5606Fixes#5642
Commit cf86ba7786 changed the way toolkits
and functions were imported to use `exec`, whereas they previously were
written to files and `import`ed. The use of `exec` means that
module-global variables such as `__file__` are no longer defined.
This breaks https://github.com/EtiennePerot/open-webui-code-execution
(code execution tool for Open WebUI), as the module needs to re-execute
its own code in a subprocess in order to properly sandbox itself. This
is done using `__file__` in order to know where the module's code is
located.
This PR creates a temporary in-memory file that contains the imported
toolkit or function's code and exists only during the import process.
Then it injects the path to this in-memory file as the `__file__`
variable in the `exec` context. This restores the ability for the
toolkit or function being imported to rely on `__file__`.
This commit makes the optional AUTOMATIC1111 options default to None, and if the value is removed, it resets to None.
Signed-off-by: Balazs Toldi <balazs@toldi.eu>
Ensure that the `manifest/base` folder can be used as a standalone
kustomization resource.
Add a new subfolder `manifest/gpu` which uses `manifest/base` with
additional GPU related patches.
This commit adds 3 new options to the AUTOMATIC1111 settings:
- CFG Scale
- Sampler
- Scheduler
These options allow users to configure these parameters directly through the admin settings, without needing to modify the source code, which was previously required to change the default values in AUTOMATIC1111.
Signed-off-by: Balazs Toldi <balazs@toldi.eu>
[Attach any relevant screenshots to help illustrate the issue]
## Additional Information
[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]
## Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
description:Create a detailed bug report to help us improve Open WebUI.
title: 'issue:'
labels: ['bug', 'triage']
assignees:[]
body:
- type:markdown
attributes:
value:|
# Bug Report
## Important Notes
- **Before submitting a bug report**: Please check the [Issues](https://github.com/open-webui/open-webui/issues) or [Discussions](https://github.com/open-webui/open-webui/discussions) sections to see if a similar issue has already been reported. If unsure, start a discussion first, as this helps us efficiently focus on improving the project.
- **Respectful collaboration**: Open WebUI is a volunteer-driven project with a single maintainer and contributors who also have full-time jobs. Please be constructive and respectful in your communication.
- **Contributing**: If you encounter an issue, consider submitting a pull request or forking the project. We prioritize preventing contributor burnout to maintain Open WebUI's quality.
- **Bug Reproducibility**: If a bug cannot be reproduced using a `:main` or `:dev` Docker setup or with `pip install` on Python 3.11, community assistance may be required. In such cases, we will move it to the "[Issues](https://github.com/open-webui/open-webui/discussions/categories/issues)" Discussions section. Your help is appreciated!
- type:checkboxes
id:issue-check
attributes:
label:Check Existing Issues
description:Confirm that you’ve checked for existing reports before submitting a new one.
options:
- label:I have searched the existing issues and discussions.
required:true
- type:dropdown
id:installation-method
attributes:
label:Installation Method
description:How did you install Open WebUI?
options:
- Git Clone
- Pip Install
- Docker
- Other
validations:
required:true
- type:input
id:open-webui-version
attributes:
label:Open WebUI Version
description:Specify the version (e.g., v0.3.11)
validations:
required:true
- type:input
id:ollama-version
attributes:
label:Ollama Version (if applicable)
description:Specify the version (e.g., v0.2.0, or v0.1.32-rc1)
validations:
required:false
- type:input
id:operating-system
attributes:
label:Operating System
description:Specify the OS (e.g., Windows 10, macOS Sonoma, Ubuntu 22.04)
validations:
required:true
- type:input
id:browser
attributes:
label:Browser (if applicable)
description:Specify the browser/version (e.g., Chrome 100.0, Firefox 98.0)
validations:
required:false
- type:checkboxes
id:confirmation
attributes:
label:Confirmation
description:Ensure the following prerequisites have been met.
options:
- label:I have read and followed all instructions in `README.md`.
required:true
- label:I am using the latest version of **both** Open WebUI and Ollama.
required:true
- label:I have checked the browser console logs.
required:true
- label:I have checked the Docker container logs.
required:true
- label:I have listed steps to reproduce the bug in detail.
required:true
- type:textarea
id:expected-behavior
attributes:
label:Expected Behavior
description:Describe what should have happened.
validations:
required:true
- type:textarea
id:actual-behavior
attributes:
label:Actual Behavior
description:Describe what actually happened.
validations:
required:true
- type:textarea
id:reproduction-steps
attributes:
label:Steps to Reproduce
description:Provide step-by-step instructions to reproduce the issue.
placeholder:|
1. Go to '...'
2. Click on '...'
3. Scroll down to '...'
4. See the error message '...'
validations:
required:true
- type:textarea
id:logs-screenshots
attributes:
label:Logs & Screenshots
description:Include relevant logs, errors, or screenshots to help diagnose the issue.
placeholder:'Attach logs from the browser console, Docker logs, or error messages.'
validations:
required:true
- type:textarea
id:additional-info
attributes:
label:Additional Information
description:Provide any extra details that may assist in understanding the issue.
validations:
required:false
- type:markdown
attributes:
value:|
## Note
If the bug report is incomplete or does not follow instructions, it may not be addressed. Ensure that you've followed all the **README.md** and **troubleshooting.md** guidelines, and provide all necessary information for us to reproduce the issue.
Please check the [Issues](https://github.com/open-webui/open-webui/issues) or [Discussions](https://github.com/open-webui/open-webui/discussions) to see if a similar request has 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**
- It's managed by a **single maintainer**
- It's 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](https://github.com/open-webui/open-webui/discussions/categories/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!
- type:checkboxes
id:existing-issue
attributes:
label:Check Existing Issues
description:Please confirm that you've checked for existing similar requests
options:
- label:I have searched the existing issues and discussions.
required:true
- type:textarea
id:problem-description
attributes:
label:Problem Description
description:Is your feature request related to a problem? Please provide a clear and concise description of what the problem is.
placeholder:"Ex. I'm always frustrated when..."
validations:
required:true
- type:textarea
id:solution-description
attributes:
label:Desired Solution you'd like
description:Clearly describe what you want to happen.
validations:
required:true
- type:textarea
id:alternatives-considered
attributes:
label:Alternatives Considered
description:A clear and concise description of any alternative solutions or features you've considered.
- type:textarea
id:additional-context
attributes:
label:Additional Context
description:Add any other context or screenshots about the feature request here.
@@ -5,6 +5,800 @@ 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).
## [0.5.20] - 2025-03-05
### Added
- **⚡ Toggle Code Execution On/Off**: You can now enable or disable code execution, providing more control over security, ensuring a safer and more customizable experience.
### Fixed
- **📜 Pinyin Keyboard Enter Key Now Works Properly**: Resolved an issue where the Enter key for Pinyin keyboards was not functioning as expected, ensuring seamless input for Chinese users.
- **🖼️ Web Manifest Loading Issue Fixed**: Addressed inconsistencies with 'site.webmanifest', guaranteeing proper loading and representation of the app across different browsers and devices.
- **📦 Non-Root Container Issue Resolved**: Fixed a critical issue where the UI failed to load correctly in non-root containers, ensuring reliable deployment in various environments.
## [0.5.19] - 2025-03-04
### Added
- **📊 Logit Bias Parameter Support**: Fine-tune conversation dynamics by adjusting the Logit Bias parameter directly in chat settings, giving you more control over model responses.
- **⌨️ Customizable Enter Behavior**: You can now configure Enter to send messages only when combined with Ctrl (Ctrl+Enter) via Settings > Interface, preventing accidental message sends.
- **📝 Collapsible Code Blocks**: Easily collapse long code blocks to declutter your chat, making it easier to focus on important details.
- **🏷️ Tag Selector in Model Selector**: Quickly find and categorize models with the new tag filtering system in the Model Selector, streamlining model discovery.
- **📈 Experimental Elasticsearch Vector DB Support**: Now supports Elasticsearch as a vector database, offering more flexibility for data retrieval in Retrieval-Augmented Generation (RAG) workflows.
- **⚙️ General Reliability Enhancements**: Various stability improvements across the WebUI, ensuring a smoother, more consistent experience.
- **🌍 Updated Translations**: Refined multilingual support for better localization and accuracy across various languages.
### Fixed
- **🔄 "Stream" Hook Activation**: Fixed an issue where the "Stream" hook only worked when globally enabled, ensuring reliable real-time filtering.
- **📧 LDAP Email Case Sensitivity**: Resolved an issue where LDAP login failed due to email case sensitivity mismatches, improving authentication reliability.
- **💬 WebSocket Chat Event Registration**: Fixed a bug preventing chat event listeners from being registered upon sign-in, ensuring real-time updates work properly.
## [0.5.18] - 2025-02-27
### Fixed
- **🌐 Open WebUI Now Works Over LAN in Insecure Context**: Resolved an issue preventing Open WebUI from functioning when accessed over a local network in an insecure context, ensuring seamless connectivity.
- **🔄 UI Now Reflects Deleted Connections Instantly**: Fixed an issue where deleting a connection did not update the UI in real time, ensuring accurate system state visibility.
- **🛠️ Models Now Display Correctly with ENABLE_FORWARD_USER_INFO_HEADERS**: Addressed a bug where models were not visible when ENABLE_FORWARD_USER_INFO_HEADERS was set, restoring proper model listing.
## [0.5.17] - 2025-02-27
### Added
- **🚀 Instant Document Upload with Bypass Embedding & Retrieval**: Admins can now enable "Bypass Embedding & Retrieval" in Admin Settings > Documents, significantly speeding up document uploads and ensuring full document context is retained without chunking.
- **🔎 "Stream" Hook for Real-Time Filtering**: The new "stream" hook allows dynamic real-time message filtering. Learn more in our documentation (https://docs.openwebui.com/features/plugin/functions/filter).
- **☁️ OneDrive Integration**: Early support for OneDrive storage integration has been introduced, expanding file import options.
- **📈 Enhanced Logging with Loguru**: Backend logging has been improved with Loguru, making debugging and issue tracking far more efficient.
- **⚙️ General Stability Enhancements**: Backend and frontend refactoring improves performance, ensuring a smoother and more reliable user experience.
- **🌍 Updated Translations**: Refined multilingual support for better localization and accuracy across various languages.
### Fixed
- **🔄 Reliable Model Imports from the Community Platform**: Resolved import failures, allowing seamless integration of community-shared models without errors.
- **📊 OpenAI Usage Statistics Restored**: Fixed an issue where OpenAI usage metrics were not displaying correctly, ensuring accurate tracking of usage data.
- **🗂️ Deduplication for Retrieved Documents**: Documents retrieved during searches are now intelligently deduplicated, meaning no more redundant results—helping to keep information concise and relevant.
### Changed
- **📝 "Full Context Mode" Renamed for Clarity**: The "Full Context Mode" toggle in Web Search settings is now labeled "Bypass Embedding & Retrieval" for consistency across the UI.
## [0.5.16] - 2025-02-20
### Fixed
- **🔍 Web Search Retrieval Restored**: Resolved a critical issue that broke web search retrieval by reverting deduplication changes, ensuring complete and accurate search results once again.
## [0.5.15] - 2025-02-20
### Added
- **📄 Full Context Mode for Local Document Search (RAG)**: Toggle full context mode from Admin Settings > Documents to inject entire document content into context, improving accuracy for models with large context windows—ideal for deep context understanding.
- **🌍 Smarter Web Search with Agentic Workflows**: Web searches now intelligently gather and refine multiple relevant terms, similar to RAG handling, delivering significantly better search results for more accurate information retrieval.
- **🔎 Experimental Playwright Support for Web Loader**: Web content retrieval is taken to the next level with Playwright-powered scraping for enhanced accuracy in extracted web data.
- **☁️ Experimental Azure Storage Provider**: Early-stage support for Azure Storage allows more cloud storage flexibility directly within Open WebUI.
- **📊 Improved Jupyter Code Execution with Plots**: Interactive coding now properly displays inline plots, making data visualization more seamless inside chat interactions.
- **⏳ Adjustable Execution Timeout for Jupyter Interpreter**: Customize execution timeout (default: 60s) for Jupyter-based code execution, allowing longer or more constrained execution based on your needs.
- **▶️ "Running..." Indicator for Jupyter Code Execution**: A visual indicator now appears while code execution is in progress, providing real-time status updates on ongoing computations.
- **⚙️ General Backend & Frontend Stability Enhancements**: Extensive refactoring improves reliability, performance, and overall user experience for a more seamless Open WebUI.
- **🌍 Translation Updates**: Various international translation refinements ensure better localization and a more natural user interface experience.
### Fixed
- **📱 Mobile Hover Issue Resolved**: Users can now edit responses smoothly on mobile without interference, fixing a longstanding hover issue.
- **🔄 Temporary Chat Message Duplication Fixed**: Eliminated buggy behavior where messages were being unnecessarily repeated in temporary chat mode, ensuring a smooth and consistent conversation flow.
## [0.5.14] - 2025-02-17
### Fixed
- **🔧 Critical Import Error Resolved**: Fixed a circular import issue preventing 'override_static' from being correctly imported in 'open_webui.config', ensuring smooth system initialization and stability.
## [0.5.13] - 2025-02-17
### Added
- **🌐 Full Context Mode for Web Search**: Enable highly accurate web searches by utilizing full context mode—ideal for models with large context windows, ensuring more precise and insightful results.
- **⚡ Optimized Asynchronous Web Search**: Web searches now load significantly faster with optimized async support, providing users with quicker, more efficient information retrieval.
- **🔄 Auto Text Direction for RTL Languages**: Automatic text alignment based on language input, ensuring seamless conversation flow for Arabic, Hebrew, and other right-to-left scripts.
- **🚀 Jupyter Notebook Support for Code Execution**: The "Run" button in code blocks can now use Jupyter for execution, offering a powerful, dynamic coding experience directly in the chat.
- **🗑️ Message Delete Confirmation Dialog**: Prevent accidental deletions with a new confirmation prompt before removing messages, adding an additional layer of security to your chat history.
- **📥 Download Button for SVG Diagrams**: SVG diagrams generated within chat can now be downloaded instantly, making it easier to save and share complex visual data.
- **✨ General UI/UX Improvements and Backend Stability**: A refined interface with smoother interactions, improved layouts, and backend stability enhancements for a more reliable, polished experience.
### Fixed
- **🛠️ Temporary Chat Message Continue Button Fixed**: The "Continue Response" button for temporary chats now works as expected, ensuring an uninterrupted conversation flow.
### Changed
- **📝 Prompt Variable Update**: Deprecated square bracket '[]' indicators for prompt variables; now requires double curly brackets '{{}}' for consistency and clarity.
- **🔧 Stability Enhancements**: Error handling improved in chat history, ensuring smoother operations when reviewing previous messages.
## [0.5.12] - 2025-02-13
### Added
- **🛠️ Multiple Tool Calls Support for Native Function Mode**: Functions now can call multiple tools within a single response, unlocking better automation and workflow flexibility when using native function calling.
### Fixed
- **📝 Playground Text Completion Restored**: Addressed an issue where text completion in the Playground was not functioning.
- **🔗 Direct Connections Now Work for Regular Users**: Fixed a bug where users with the 'user' role couldn't establish direct API connections, enabling seamless model usage for all user tiers.
- **⚡ Landing Page Input No Longer Lags with Long Text**: Improved input responsiveness on the landing page, ensuring fast and smooth typing experiences even when entering long messages.
- **🔧 Parameter in Functions Fixed**: Fixed an issue where the reserved parameters wasn’t recognized within functions, restoring full functionality for advanced task-based automation.
## [0.5.11] - 2025-02-13
### Added
- **🎤 Kokoro-JS TTS Support**: A new on-device, high-quality text-to-speech engine has been integrated, vastly improving voice generation quality—everything runs directly in your browser.
- **🐍 Jupyter Notebook Support in Code Interpreter**: Now, you can configure Code Interpreter to run Python code not only via Pyodide but also through Jupyter, offering a more robust coding environment for AI-driven computations and analysis.
- **🔗 Direct API Connections for Private & Local Inference**: You can now connect Open WebUI to your private or localhost API inference endpoints. CORS must be enabled, but this unlocks direct, on-device AI infrastructure support.
- **🔍 Advanced Domain Filtering for Web Search**: You can now specify which domains should be included or excluded from web searches, refining results for more relevant information retrieval.
- **🚀 Improved Image Generation Metadata Handling**: Generated images now retain metadata for better organization and future retrieval.
- **📂 S3 Key Prefix Support**: Fine-grained control over S3 storage file structuring with configurable key prefixes.
- **📸 Support for Image-Only Messages**: Send messages containing only images, facilitating more visual-centric interactions.
- **🌍 Updated Translations**: German, Spanish, Traditional Chinese, and Catalan translations updated for better multilingual support.
### Fixed
- **🔧 OAuth Debug Logs & Username Claim Fixes**: Debug logs have been added for OAuth role and group management, with fixes ensuring proper OAuth username retrieval and claim handling.
- **📌 Citations Formatting & Toggle Fixes**: Inline citation toggles now function correctly, and citations with more than three sources are now fully visible when expanded.
- **📸 ComfyUI Maximum Seed Value Constraint Fixed**: The maximum allowed seed value for ComfyUI has been corrected, preventing unintended behavior.
- **🔑 Connection Settings Stability**: Addressed connection settings issues that were causing instability when saving configurations.
- **📂 GGUF Model Upload Stability**: Fixed upload inconsistencies for GGUF models, ensuring reliable local model handling.
- **🔧 Web Search Configuration Bug**: Fixed issues where web search filters and settings weren't correctly applied.
- **💾 User Settings Persistence Fix**: Ensured user-specific settings are correctly saved and applied across sessions.
- **🔄 OpenID Username Retrieval Enhancement**: Usernames are now correctly picked up and assigned for OpenID Connect (OIDC) logins.
## [0.5.10] - 2025-02-05
### Fixed
- **⚙️ System Prompts Now Properly Templated via API**: Resolved an issue where system prompts were not being correctly processed when used through the API, ensuring template variables now function as expected.
- **📝 '<thinking>' Tag Display Issue Fixed**: Fixed a bug where the 'thinking' tag was disrupting content rendering, ensuring clean and accurate text display.
- **💻 Code Interpreter Stability with Custom Functions**: Addressed failures when using the Code Interpreter with certain custom functions like Anthropic, ensuring smoother execution and better compatibility.
## [0.5.9] - 2025-02-05
### Fixed
- **💡 "Think" Tag Display Issue**: Resolved a bug where the "Think" tag was not functioning correctly, ensuring proper visualization of the model's reasoning process before delivering responses.
## [0.5.8] - 2025-02-05
### Added
- **🖥️ Code Interpreter**: Models can now execute code in real time to refine their answers dynamically, running securely within a sandboxed browser environment using Pyodide. Perfect for calculations, data analysis, and AI-assisted coding tasks!
- **💬 Redesigned Chat Input UI**: Enjoy a sleeker and more intuitive message input with improved feature selection, making it easier than ever to toggle tools, enable search, and interact with AI seamlessly.
- **🛠️ Native Tool Calling Support (Experimental)**: Supported models can now call tools natively, reducing query latency and improving contextual responses. More enhancements coming soon!
- **🔗 Exa Search Engine Integration**: A new search provider has been added, allowing users to retrieve up-to-date and relevant information without leaving the chat interface.
- **🌍 Localized Dates & Times**: Date and time formats now match your system locale, ensuring a more natural, region-specific experience.
- **📎 User Headers for External Embedding APIs**: API calls to external embedding services now include user-related headers.
- **🌍 "Always On" Web Search Toggle**: A new option under Settings > Interface allows users to enable Web Search by default—transform Open WebUI into your go-to search engine, ensuring AI-powered results with every query.
- **🚀 General Performance & Stability**: Significant improvements across the platform for a faster, more reliable experience.
- **🌍 Improved Translations**: Chinese, Korean, French, Ukrainian and Serbian translations have been updated with refined terminologies for better clarity.
### Fixed
- **🔄 OAuth Name Field Fallback**: Resolves OAuth login failures by using the email field as a fallback when a name is missing.
- **🔑 Google Drive Credentials Restriction**: Ensures only authenticated users can access Google Drive credentials for enhanced security.
- **🌐 DuckDuckGo Search Rate Limit Handling**: Fixes issues where users would encounter 202 errors due to rate limits when using DuckDuckGo for web search.
- **📁 File Upload Permission Indicator**: Users are now notified when they lack permission to upload files, improving clarity on system restrictions.
- **🔧 Max Tokens Issue**: Fixes cases where 'max_tokens' were not applied correctly, ensuring proper model behavior.
- **🔍 Validation for RAG Web Search URLs**: Filters out invalid or unsupported URLs when using web-based retrieval augmentation.
- **🖋️ Title Generation Bug**: Fixes inconsistencies in title generation, ensuring proper chat organization.
### Removed
- **⚡ Deprecated Non-Web Worker Pyodide Execution**: Moves entirely to browser sandboxing for better performance and security.
## [0.5.7] - 2025-01-23
### Added
- **🌍 Enhanced Internationalization (i18n)**: Refined and expanded translations for greater global accessibility and a smoother experience for international users.
### Fixed
- **🔗 Connection Model ID Resolution**: Resolved an issue preventing model IDs from registering in connections.
- **💡 Prefix ID for Ollama Connections**: Fixed a bug where prefix IDs in Ollama connections were non-functional.
- **🔧 Ollama Model Enable/Disable Functionality**: Addressed the issue of enable/disable toggles not working for Ollama base models.
- **🔒 RBAC Permissions for Tools and Models**: Corrected incorrect Role-Based Access Control (RBAC) permissions for tools and models, ensuring that users now only access features according to their assigned privileges, enhancing security and role clarity.
## [0.5.6] - 2025-01-22
### Added
- **🧠 Effortful Reasoning Control for OpenAI Models**: Introduced the reasoning_effort parameter in chat controls for supported OpenAI models, enabling users to fine-tune how much cognitive effort a model dedicates to its responses, offering greater customization for complex queries and reasoning tasks.
### Fixed
- **🔄 Chat Controls Loading UI Bug**: Resolved an issue where collapsible chat controls appeared as "loading," ensuring a smoother and more intuitive user experience for managing chat settings.
### Changed
- **🔧 Updated Ollama Model Creation**: Revamped the Ollama model creation method to align with their new JSON payload format, ensuring seamless compatibility and more efficient model setup workflows.
## [0.5.5] - 2025-01-22
### Added
- **🤔 Native 'Think' Tag Support**: Introduced the new 'think' tag support that visually displays how long the model is thinking, omitting the reasoning content itself until the next turn. Ideal for creating a more streamlined and focused interaction experience.
- **🖼️ Toggle Image Generation On/Off**: In the chat input menu, you can now easily toggle image generation before initiating chats, providing greater control and flexibility to suit your needs.
- **🔒 Chat Controls Permissions**: Admins can now disable chat controls access for users, offering tighter management and customization over user interactions.
- **🔍 Web Search & Image Generation Permissions**: Easily disable web search and image generation for specific users, improving workflow governance and security for certain environments.
- **🗂️ S3 and GCS Storage Provider Support**: Scaled deployments now benefit from expanded storage options with Amazon S3 and Google Cloud Storage seamlessly integrated as providers.
- **🎨 Enhanced Model Management**: Reintroduced the ability to download and delete models directly in the admin models settings page to minimize user confusion and aid efficient model management.
- **🔗 Improved Connection Handling**: Enhanced backend to smoothly handle multiple identical base URLs, allowing more flexible multi-instance configurations with fewer hiccups.
- **✨ General UI/UX Refinements**: Numerous tweaks across the WebUI make navigation and usability even more user-friendly and intuitive.
- **🌍 Translation Enhancements**: Various translation updates ensure smoother and more polished interactions for international users.
### Fixed
- **⚡ MPS Functionality for Mac Users**: Fixed MPS support, ensuring smooth performance and compatibility for Mac users leveraging MPS.
- **📡 Ollama Connection Management**: Resolved the issue where deleting all Ollama connections prevented adding new ones.
### Changed
- **⚙️ General Stability Refac**: Backend refactoring delivers a more stable, robust platform.
- **🖥️ Desktop App Preparations**: Ongoing work to support the upcoming Open WebUI desktop app. Follow our progress and updates here: https://github.com/open-webui/desktop
## [0.5.4] - 2025-01-05
### Added
- **🔄 Clone Shared Chats**: Effortlessly clone shared chats to save time and streamline collaboration, perfect for reusing insightful discussions or custom setups.
- **📣 Native Notifications for Channel Messages**: Stay informed with integrated desktop notifications for channel messages, ensuring you never miss important updates while multitasking.
- **🔥 Torch MPS Support**: MPS support for Mac users when Open WebUI is installed directly, offering better performance and compatibility for AI workloads.
- **🌍 Enhanced Translations**: Small improvements to various translations, ensuring a smoother global user experience.
### Fixed
- **🖼️ Image-Only Messages in Channels**: You can now send images without accompanying text or content in channels.
- **❌ Proper Exception Handling**: Enhanced error feedback by ensuring exceptions are raised clearly, reducing confusion and promoting smoother debugging.
- **🔍 RAG Query Generation Restored**: Fixed query generation issues for Retrieval-Augmented Generation, improving retrieval accuracy and ensuring seamless functionality.
- **📩 MOA Response Functionality Fixed**: Addressed an error with the MOA response generation feature.
- **💬 Channel Thread Loading with 50+ Messages**: Resolved an issue where channel threads stalled when exceeding 50 messages, ensuring smooth navigation in active discussions.
- **🔑 API Endpoint Restrictions Resolution**: Fixed a critical bug where the 'API_KEY_ALLOWED_ENDPOINTS' setting was not functioning as intended, ensuring API access is limited to specified endpoints for enhanced security.
- **🛠️ Action Functions Restored**: Corrected an issue preventing action functions from working, restoring their utility for customized automations and workflows.
- **📂 Temporary Chat JSON Export Fix**: Resolved a bug blocking temporary chats from being exported in JSON format, ensuring seamless data portability.
### Changed
- **🎛️ Sidebar UI Tweaks**: Chat folders, including pinned folders, now display below the Chats section for better organization; the "New Folder" button has been relocated to the Chats section for a more intuitive workflow.
- **🏗️ Real-Time Save Disabled by Default**: The 'ENABLE_REALTIME_CHAT_SAVE' setting is now off by default, boosting response speed for users who prioritize performance in high-paced workflows or less critical scenarios.
- **🎤 Audio Input Echo Cancellation**: Audio input now features echo cancellation enabled by default, reducing audio feedback for improved clarity during conversations or voice-based interactions.
- **🔧 General Reliability Improvements**: Numerous under-the-hood enhancements have been made to improve platform stability, boost overall performance, and ensure a more seamless, dependable experience across workflows.
## [0.5.3] - 2024-12-31
### Added
- **💬 Channel Reactions with Built-In Emoji Picker**: Easily express yourself in channel threads and messages with reactions, featuring an intuitive built-in emoji picker for seamless selection.
- **🧵 Threads for Channels**: Organize discussions within channels by creating threads, improving clarity and fostering focused conversations.
- **🔄 Reset Button for SVG Pan/Zoom**: Added a handy reset button to SVG Pan/Zoom, allowing users to quickly return diagrams or visuals to their default state without hassle.
- **⚡ Realtime Chat Save Environment Variable**: Introduced the ENABLE_REALTIME_CHAT_SAVE environment variable. Choose between faster responses by disabling realtime chat saving or ensuring chunk-by-chunk data persistency for critical operations.
- **🌍 Translation Enhancements**: Updated and refined translations across multiple languages, providing a smoother experience for international users.
- **📚 Improved Documentation**: Expanded documentation on functions, including clearer guidance on function plugins and detailed instructions for migrating to v0.5. This ensures users can adapt and harness new updates more effectively. (https://docs.openwebui.com/features/plugin/)
### Fixed
- **🛠️ Ollama Parameters Respected**: Resolved an issue where input parameters for Ollama were being ignored, ensuring precise and consistent model behavior.
- **🔧 Function Plugin Outlet Hook Reliability**: Fixed a bug causing issues with 'event_emitter' and outlet hooks in filter function plugins, guaranteeing smoother operation within custom extensions.
- **🖋️ Weird Custom Status Descriptions**: Adjusted the formatting and functionality for custom user statuses, ensuring they display correctly and intuitively.
- **🔗 Restored API Functionality**: Fixed a critical issue where APIs were not operational for certain configurations, ensuring uninterrupted access.
- **⏳ Custom Pipe Function Completion**: Resolved an issue where chats using specific custom pipe function plugins weren’t finishing properly, restoring consistent chat workflows.
- **✅ General Stability Enhancements**: Implemented various under-the-hood improvements to boost overall reliability, ensuring smoother and more consistent performance across the WebUI.
## [0.5.2] - 2024-12-26
### Added
- **🖊️ Typing Indicators in Channels**: Know exactly who’s typing in real-time within your channels, enhancing collaboration and keeping everyone engaged.
- **👤 User Status Indicators**: Quickly view a user’s status by clicking their profile image in channels for better coordination and availability insights.
- **🔒 Configurable API Key Authentication Restrictions**: Flexibly configure endpoint restrictions for API key authentication, now off by default for a smoother setup in trusted environments.
### Fixed
- **🔧 Playground Functionality Restored**: Resolved a critical issue where the playground wasn’t working, ensuring seamless experimentation and troubleshooting workflows.
- **📊 Corrected Ollama Usage Statistics**: Fixed a calculation error in Ollama’s usage statistics, providing more accurate tracking and insights for better resource management.
- **🔗 Pipelines Outlet Hook Registration**: Addressed an issue where outlet hooks for pipelines weren’t registered, restoring functionality and consistency in pipeline workflows.
- **🎨 Image Generation Error**: Resolved a persistent issue causing errors with 'get_automatic1111_api_auth()' to ensure smooth image generation workflows.
- **🎙️ Text-to-Speech Error**: Fixed the missing argument in Eleven Labs’ 'get_available_voices()', restoring full text-to-speech capabilities for uninterrupted voice interactions.
- **🖋️ Title Generation Issue**: Fixed a bug where title generation was not working in certain cases, ensuring consistent and reliable chat organization.
## [0.5.1] - 2024-12-25
### Added
- **🔕 Notification Sound Toggle**: Added a new setting under Settings > Interface to disable notification sounds, giving you greater control over your workspace environment and focus.
### Fixed
- **🔄 Non-Streaming Response Visibility**: Resolved an issue where non-streaming responses were not displayed, ensuring all responses are now reliably shown in your conversations.
- **🖋️ Title Generation with OpenAI APIs**: Fixed a bug preventing title generation when using OpenAI APIs, restoring the ability to automatically generate chat titles for smoother organization.
- **👥 Admin Panel User List**: Addressed the issue where only 50 users were visible in the admin panel. You can now manage and view all users without restrictions.
- **🖼️ Image Generation Error**: Fixed the issue causing 'get_automatic1111_api_auth()' errors in image generation, ensuring seamless creative workflows.
- **⚙️ Pipeline Settings Loading Issue**: Resolved a problem where pipeline settings were stuck at the loading screen, restoring full configurability in the admin panel.
## [0.5.0] - 2024-12-25
### Added
- **💬 True Asynchronous Chat Support**: Create chats, navigate away, and return anytime with responses ready. Ideal for reasoning models and multi-agent workflows, enhancing multitasking like never before.
- **🔔 Chat Completion Notifications**: Never miss a completed response. Receive instant in-UI notifications when a chat finishes in a non-active tab, keeping you updated while you work elsewhere.
- **🌐 Notification Webhook Integration**: Get alerts via webhooks even when your tab is closed! Configure your webhook URL in Settings > Account and receive timely updates for long-running chats or external integration needs.
- **📚 Channels (Beta)**: Explore Discord/Slack-style chat rooms designed for real-time collaboration between users and AIs. Build bots for channels and unlock asynchronous communication for proactive multi-agent workflows. Opt-in via Admin Settings > General. A Comprehensive Bot SDK tutorial (https://github.com/open-webui/bot) is incoming, so stay tuned!
- **🖼️ Client-Side Image Compression**: Now compress images before upload (Settings > Interface), saving bandwidth and improving performance seamlessly.
- **🛠️ OAuth Management for User Groups**: Enable group-level management via OAuth integration for enhanced control and scalability in collaborative environments.
- **✅ Structured Output for Ollama**: Pass structured data output directly to Ollama, unlocking new possibilities for streamlined automation and precise data handling.
- **📜 Offline Swagger Documentation**: Developer-friendly Swagger API docs are now available offline, ensuring full accessibility wherever you are.
- **📸 Quick Screen Capture Button**: Effortlessly capture your screen with a single click from the message input menu.
- **🌍 i18n Updates**: Improved and refined translations across several languages, including Ukrainian, German, Brazilian Portuguese, Catalan, and more, ensuring a seamless global user experience.
### Fixed
- **📋 Table Export to CSV**: Resolved issues with CSV export where headers were missing or errors occurred due to values with commas, ensuring smooth and reliable data handling.
- **🔓 BYPASS_MODEL_ACCESS_CONTROL**: Fixed an issue where users could see models but couldn’t use them with 'BYPASS_MODEL_ACCESS_CONTROL=True', restoring proper functionality for environments leveraging this setting.
### Changed
- **💡 API Key Authentication Restriction**: Narrowed API key auth permissions to '/api/models' and '/api/chat/completions' for enhanced security and better API governance.
- **⚙️ Backend Overhaul for Performance**: Major backend restructuring; a heads-up that some "Functions" using internal variables may face compatibility issues. Moving forward, websocket support is mandatory to ensure Open WebUI operates seamlessly.
### Removed
- **⚠️ Legacy Functionality Clean-Up**: Deprecated outdated backend systems that were non-essential or overlapped with newer implementations, allowing for a leaner, more efficient platform.
## [0.4.8] - 2024-12-07
### Added
- **🔓 Bypass Model Access Control**: Introduced the 'BYPASS_MODEL_ACCESS_CONTROL' environment variable. Easily bypass model access controls for user roles when access control isn't required, simplifying workflows for trusted environments.
- **📝 Markdown in Banners**: Now supports markdown for banners, enabling richer, more visually engaging announcements.
- **🌐 Internationalization Updates**: Enhanced translations across multiple languages, further improving accessibility and global user experience.
- **🎨 Styling Enhancements**: General UI style refinements for a cleaner and more polished interface.
- **📋 Rich Text Reliability**: Improved the reliability and stability of rich text input across chats for smoother interactions.
### Fixed
- **💡 Tailwind Build Issue**: Resolved a breaking bug caused by Tailwind, ensuring smoother builds and overall system reliability.
- **📚 Knowledge Collection Query Fix**: Addressed API endpoint issues with querying knowledge collections, ensuring accurate and reliable information retrieval.
## [0.4.7] - 2024-12-01
### Added
- **✨ Prompt Input Auto-Completion**: Type a prompt and let AI intelligently suggest and complete your inputs. Simply press 'Tab' or swipe right on mobile to confirm. Available only with Rich Text Input (default setting). Disable via Admin Settings for full control.
- **🌍 Improved Translations**: Enhanced localization for multiple languages, ensuring a more polished and accessible experience for international users.
### Fixed
- **🛠️ Tools Export Issue**: Resolved a critical issue where exporting tools wasn’t functioning, restoring seamless export capabilities.
- **🔗 Model ID Registration**: Fixed an issue where model IDs weren’t registering correctly in the model editor, ensuring reliable model setup and tracking.
- **🖋️ Textarea Auto-Expansion**: Corrected a bug where textareas didn’t expand automatically on certain browsers, improving usability for multi-line inputs.
- **🔧 Ollama Embed Endpoint**: Addressed the /ollama/embed endpoint malfunction, ensuring consistent performance and functionality.
### Changed
- **🎨 Knowledge Base Styling**: Refined knowledge base visuals for a cleaner, more modern look, laying the groundwork for further enhancements in upcoming releases.
## [0.4.6] - 2024-11-26
### Added
- **🌍 Enhanced Translations**: Various language translations improved to make the WebUI more accessible and user-friendly worldwide.
### Fixed
- **✏️ Textarea Shifting Bug**: Resolved the issue where the textarea shifted unexpectedly, ensuring a smoother typing experience.
- **⚙️ Model Configuration Modal**: Fixed the issue where the models configuration modal introduced in 0.4.5 wasn’t working for some users.
- **🔍 Legacy Query Support**: Restored functionality for custom query generation in RAG when using legacy prompts, ensuring both default and custom templates now work seamlessly.
- **⚡ Improved General Reliability**: Various minor fixes improve platform stability and ensure a smoother overall experience across workflows.
## [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
- **🔢 Workspace Enhancements**: Added a display count for models, prompts, tools, and functions in the workspace, providing a clear overview and easier management.
### Fixed
- **🖥️ Web and YouTube Attachment Fix**: Resolved an issue where attaching web links and YouTube videos was malfunctioning, ensuring seamless integration and display within chats.
- **📞 Call Mode Activation on Landing Page**: Fixed a bug where call mode was not operational from the landing page.
### Changed
- **🔄 URL Parameter Refinement**: Updated the 'tool_ids' URL parameter to 'tools' or 'tool-ids' for more intuitive and consistent user experience.
- **🎨 Floating Buttons Styling Update**: Refactored the styling of floating buttons to intelligently adjust to the left side when there isn't enough room on the right, improving interface usability and aesthetic.
- **🔧 Enhanced Accessibility for Floating Buttons**: Implemented the ability to close floating buttons with the 'Esc' key, making workflow smoother and more efficient for users navigating via keyboard.
- **🖇️ Updated Information URL**: Information URLs now direct users to a general release page rather than a version-specific URL, ensuring access to the latest and relevant details all in one place.
- **📦 Library Dependencies Update**: Upgraded dependencies to ensure compatibility and performance optimization for pip installs.
## [0.3.31] - 2024-10-06
### Added
- **📚 Knowledge Feature**: Reimagined documents feature, now more performant with a better UI for enhanced organization; includes streamlined API integration for Retrieval-Augmented Generation (RAG). Detailed documentation forthcoming: https://docs.openwebui.com/
- **🌐 New Landing Page**: Freshly designed landing page; toggle between the new UI and the classic chat UI from Settings > Interface for a personalized experience.
- **📁 Full Document Retrieval Mode**: Toggle between full document retrieval or traditional snippets by clicking on the file item. This mode enhances document capabilities and supports comprehensive tasks like summarization by utilizing the entire content instead of RAG.
- **📄 Extracted File Content Display**: View extracted content directly by clicking on the file item, simplifying file analysis.
- **🎨 Artifacts Feature**: Render web content and SVGs directly in the interface, supporting quick iterations and live changes.
- **🖊️ Editable Code Blocks**: Supercharged code blocks now allow live editing directly in the LLM response, with live reloads supported by artifacts.
- **🔧 Code Block Enhancements**: Introduced a floating copy button in code blocks to facilitate easier code copying without scrolling.
- **🔍 SVG Pan/Zoom**: Enhanced interaction with SVG images, including Mermaid diagrams, via new pan and zoom capabilities.
- **🔍 Text Select Quick Actions**: New floating buttons appear when text is highlighted in LLM responses, offering deeper interactions like "Ask a Question" or "Explain".
- **🗃️ Database Pool Configuration**: Enhanced database handling to support scalable user growth.
- **🔊 Experimental Audio Compression**: Compress audio files to navigate around the 25MB limit for OpenAI's speech-to-text processing.
- **🔍 Query Embedding**: Adjusted embedding behavior to enhance system performance by not repeating query embedding.
- **💾 Lazy Load Optimizations**: Implemented lazy loading of large dependencies to minimize initial memory usage, boosting performance.
- **🍏 Apple Touch Icon Support**: Optimizes the display of icons for web bookmarks on Apple mobile devices.
- **🔽 Expandable Content Markdown Support**: Introducing 'details', 'summary' tag support for creating expandable content sections in markdown, facilitating cleaner, organized documentation and interactive content display.
### Fixed
- **🔘 Action Button Issue**: Resolved a bug where action buttons were not functioning, enhancing UI reliability.
- **🔄 Multi-Model Chat Loop**: Fixed an infinite loop issue in multi-model chat environments, ensuring smoother chat operations.
- **📄 Chat PDF/TXT Export Issue**: Resolved problems with exporting chat logs to PDF and TXT formats.
- **🔊 Call to Text-to-Speech Issues**: Rectified problems with text-to-speech functions to improve audio interactions.
### Changed
- **⚙️ Endpoint Renaming**: Renamed 'rag' endpoints to 'retrieval' for clearer function description.
- **🎨 Styling and Interface Updates**: Multiple refinements across the platform to enhance visual appeal and user interaction.
### Removed
- **🗑️ Deprecated 'DOCS_DIR'**: Removed the outdated 'docs_dir' variable in favor of more direct file management solutions, with direct file directory syncing and API uploads for a more integrated experience.
## [0.3.30] - 2024-09-26
### Fixed
- **🍞 Update Available Toast Dismissal**: Enhanced user experience by ensuring that once the update available notification is dismissed, it won't reappear for 24 hours.
- **📋 Ollama /embed Form Data**: Adjusted the integration inaccuracies in the /embed form data to ensure it perfectly matches with Ollama's specifications.
- **🔧 O1 Max Completion Tokens Issue**: Resolved compatibility issues with OpenAI's o1 models max_completion_tokens param to ensure smooth operation.
- **🔄 Pip Install Database Issue**: Fixed a critical issue where database changes during pip installations were reverting and not saving chat logs, now ensuring data persistence and reliability in chat operations.
- **🏷️ Chat Rename Tab Update**: Fixed the functionality to change the web browser's tab title simultaneously when a chat is renamed, keeping tab titles consistent.
## [0.3.29] - 2023-09-25
### Fixed
- **🔧 KaTeX Rendering Improvement**: Resolved specific corner cases in KaTeX rendering to enhance the display of complex mathematical notation.
- **📞 'Call' URL Parameter Fix**: Corrected functionality for 'call' URL search parameter ensuring reliable activation of voice calls through URL triggers.
- **🔄 Configuration Reset Fix**: Fixed the RESET_CONFIG_ON_START to ensure settings revert to default correctly upon each startup, improving reliability in configuration management.
- **🌍 Filter Outlet Hook Fix**: Addressed issues in the filter outlet hook, ensuring all filter functions operate as intended.
## [0.3.28] - 2024-09-24
### Fixed
- **🔍 Web Search Functionality**: Corrected an issue where the web search option was not functioning properly.
## [0.3.27] - 2024-09-24
### Fixed
- **🔄 Periodic Cleanup Error Resolved**: Fixed a critical RuntimeError related to the 'periodic_usage_pool_cleanup' coroutine, ensuring smooth and efficient performance post-pip install, correcting a persisting issue from version 0.3.26.
- **📊 Enhanced LaTeX Rendering**: Improved rendering for LaTeX content, enhancing clarity and visual presentation in documents and mathematical models.
## [0.3.26] - 2024-09-24
### Fixed
- **🔄 Event Loop Error Resolution**: Addressed a critical error where a missing running event loop caused 'periodic_usage_pool_cleanup' to fail with pip installs. This fix ensures smoother and more reliable updates and installations, enhancing overall system stability.
## [0.3.25] - 2024-09-24
### Fixed
- **🖼️ Image Generation Functionality**: Resolved an issue where image generation was not functioning, restoring full capability for visual content creation.
- **⚖️ Rate Response Corrections**: Addressed a problem where rate responses were not working, ensuring reliable feedback mechanisms are operational.
## [0.3.24] - 2024-09-24
### Added
- **🚀 Rendering Optimization**: Significantly improved message rendering performance, enhancing user experience and webui responsiveness.
- **💖 Favorite Response Feature in Chat Overview**: Users can now mark responses as favorite directly from the chat overview, enhancing ease of retrieval and organization of preferred responses.
- **💬 Create Message Pairs with Shortcut**: Implemented creation of new message pairs using Cmd/Ctrl+Shift+Enter, making conversation editing faster and more intuitive.
- **🌍 Expanded User Prompt Variables**: Added weekday, timezone, and language information variables to user prompts to match system prompt variables.
- **🎵 Enhanced Audio Support**: Now includes support for 'audio/x-m4a' files, broadening compatibility with audio content within the platform.
- **🔏 Model URL Search Parameter**: Added an ability to select a model directly via URL parameters, streamlining navigation and model access.
- **📄 Enhanced PDF Citations**: PDF citations now open at the associated page, streamlining reference checks and document handling.
- **🔧Use of Redis in Sockets**: Enhanced socket implementation to fully support Redis, enabling effective stateless instances suitable for scalable load balancing.
- **🌍 Stream Individual Model Responses**: Allows specific models to have individualized streaming settings, enhancing performance and customization.
- **🕒 Display Model Hash and Last Modified Timestamp for Ollama Models**: Provides critical model details directly in the Models workspace for enhanced tracking.
- **❗ Update Info Notification for Admins**: Ensures administrators receive immediate updates upon login, keeping them informed of the latest changes and system statuses.
### Fixed
- **🗑️ Temporary File Handling On Windows**: Fixed an issue causing errors when accessing a temporary file being used by another process, Tools & Functions should now work as intended.
- **🔓 Authentication Toggle Issue**: Resolved the malfunction where setting 'WEBUI_AUTH=False' did not appropriately disable authentication, ensuring that user experience and system security settings function as configured.
- **🔧 Save As Copy Issue for Many Model Chats**: Resolved an error preventing users from save messages as copies in many model chats.
- **🔒 Sidebar Closure on Mobile**: Resolved an issue where the mobile sidebar remained open after menu engagement, improving user interface responsivity and comfort.
- **🛡️ Tooltip XSS Vulnerability**: Resolved a cross-site scripting (XSS) issue within tooltips, ensuring enhanced security and data integrity during user interactions.
### Changed
- **↩️ Deprecated Interface Stream Response Settings**: Moved to advanced parameters to streamline interface settings and enhance user clarity.
- **⚙️ Renamed 'speedRate' to 'playbackRate'**: Standardizes terminology, improving usability and understanding in media settings.
## [0.3.23] - 2024-09-21
### Added
- **🚀 WebSocket Redis Support**: Enhanced load balancing capabilities for multiple instance setups, promoting better performance and reliability in WebUI.
- **🔧 Adjustable Chat Controls**: Introduced width-adjustable chat controls, enabling a personalized and more comfortable user interface.
- **🌎 i18n Updates**: Improved and updated the Chinese translations.
### Fixed
- **🌐 Task Model Unloading Issue**: Modified task handling to use the Ollama /api/chat endpoint instead of OpenAI compatible endpoint, ensuring models stay loaded and ready with custom parameters, thus minimizing delays in task execution.
- **📝 Title Generation Fix for OpenAI Compatible APIs**: Resolved an issue preventing the generation of titles, enhancing consistency and reliability when using multiple API providers.
- **🗃️ RAG Duplicate Collection Issue**: Fixed a bug causing repeated processing of the same uploaded file. Now utilizes indexed files to prevent unnecessary duplications, optimizing resource usage.
- **🖼️ Image Generation Enhancement**: Refactored OpenAI image generation endpoint to be asynchronous, preventing the WebUI from becoming unresponsive during processing, thus enhancing user experience.
- **🔓 Downgrade Authlib**: Reverted Authlib to version 1.3.1 to address and resolve issues concerning OAuth functionality.
### Changed
- **🔍 Improved Message Interaction**: Enhanced the message node interface to allow for easier focus redirection with a simple click, streamlining user interaction.
- **✨ Styling Refactor**: Updated WebUI styling for a cleaner, more modern look, enhancing user experience across the platform.
## [0.3.22] - 2024-09-19
### Added
- **⭐ Chat Overview**: Introducing a node-based interactive messages diagram for improved visualization of conversation flows.
- **🔗 Multiple Vector DB Support**: Now supports multiple vector databases, including the newly added Milvus support. Community contributions for additional database support are highly encouraged!
- **📡 Experimental Non-Stream Chat Completion**: Experimental feature allowing the use of OpenAI o1 models, which do not support streaming, ensuring more versatile model deployment.
- **🔍 Experimental Colbert-AI Reranker Integration**: Added support for "jinaai/jina-colbert-v2" as a reranker, enhancing search relevance and accuracy. Note: it may not function at all on low-spec computers.
- **🕸️ ENABLE_WEBSOCKET_SUPPORT**: Added environment variable for instances to ignore websocket upgrades, stabilizing connections on platforms with websocket issues.
- **🔊 Azure Speech Service Integration**: Added support for Azure Speech services for Text-to-Speech (TTS).
- **🎚️ Customizable Playback Speed**: Playback speed control is now available in Call mode settings, allowing users to adjust audio playback speed to their preferences.
- **🧠 Enhanced Error Messaging**: System now displays helpful error messages directly to users during chat completion issues.
- **📂 Save Model as Transparent PNG**: Model profile images are now saved as PNGs, supporting transparency and improving visual integration.
- **📱 iPhone Compatibility Adjustments**: Added padding to accommodate the iPhone navigation bar, improving UI display on these devices.
- **🔧 Enhanced AUTOMATIC1111 Settings**: Users can now configure 'CFG Scale', 'Sampler', and 'Scheduler' parameters directly in the admin settings, enhancing workflow flexibility without source code modifications.
- **🌍 i18n Updates**: Enhanced translations for Chinese, Ukrainian, Russian, and French, fostering a better localized experience.
### Fixed
- **🛠️ Chat Message Deletion**: Resolved issues with chat message deletion, ensuring a smoother user interaction and system stability.
- **🔢 Ordered List Numbering**: Fixed the incorrect ordering in lists.
### Changed
- **🎨 Transparent Icon Handling**: Allowed model icons to be displayed on transparent backgrounds, improving UI aesthetics.
- **📝 Improved RAG Template**: Enhanced Retrieval-Augmented Generation template, optimizing context handling and error checking for more precise operation.
## [0.3.21] - 2024-09-08
### Added
- **📊 Document Count Display**: Now displays the total number of documents directly within the dashboard.
- **🐳 Docker Launch Issue**: Resolved the problem preventing Open-WebUI from launching correctly when using Docker.
### Changed
- **🔍 Enhanced Search Prompts**: Improved the search query generation prompts for better accuracy and user interaction, enhancing the overall search experience.
## [0.3.20] - 2024-09-07
### Added
- **🌐 Translation Update**: Updated Catalan translations to improve user experience for Catalan speakers.
### Fixed
- **📄 PDF Download**: Resolved a configuration issue with fonts directory, ensuring PDFs are now downloaded with the correct formatting.
- **🛠️ Installation of Tools & Functions Requirements**: Fixed a bug where necessary requirements for tools and functions were not properly installing.
- **🔗 Inline Image Link Rendering**: Enabled rendering of images directly from links in chat.
- **📞 Post-Call User Interface Cleanup**: Adjusted UI behavior to automatically close chat controls after a voice call ends, reducing screen clutter.
- **🎙️ Microphone Deactivation Post-Call**: Addressed an issue where the microphone remained active after calls.
- **✍️ Markdown Spacing Correction**: Corrected spacing in Markdown rendering, ensuring text appears neatly and as expected.
- **🔄 Message Re-rendering**: Fixed an issue causing all response messages to re-render with each new message, now improving chat performance.
### Changed
- **🌐 Refined Web Search Integration**: Deprecated the Search Query Generation Prompt threshold; introduced a toggle button for "Enable Web Search Query Generation" allowing users to opt-in to using web search more judiciously.
- **📝 Default Prompt Templates Update**: Emptied environment variable templates for search and title generation now default to the Open WebUI default prompt templates, simplifying configuration efforts.
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, socioeconomic 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
# 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"
ARGUSE_CUDA=false
ARGUSE_OLLAMA=false
# Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
@@ -11,13 +11,17 @@ 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.
Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
**Open WebUI is an [extensible](https://docs.openwebui.com/features/plugin/), feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline.** It supports various LLM runners like **Ollama** and **OpenAI-compatible APIs**, with **built-in inference engine** for RAG, making it a **powerful AI deployment solution**.
> [!TIP]
> **Looking for an [Enterprise Plan](https://docs.openwebui.com/enterprise)?** – **[Speak with Our Sales Team Today!](mailto:sales@openwebui.com)**
>
> Get **enhanced capabilities**, including **custom theming and branding**, **Service Level Agreement (SLA) support**, **Long-Term Support (LTS) versions**, and **more!**
For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
## Key Features of Open WebUI ⭐
- 🚀 **Effortless Setup**: Install seamlessly using Docker or Kubernetes (kubectl, kustomize or helm) for a hassle-free experience with support for both `:ollama` and `:cuda` tagged images.
- 🤝 **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 +44,7 @@ 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 +56,8 @@ 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!
> Please note that for certain Docker environments, additional configurations might be needed. If you encounter any connection issues, our detailed guide on [Open WebUI Documentation](https://docs.openwebui.com/) is ready to assist you.
### Installation via Python pip 🐍
Open WebUI can be installed using pip, the Python package installer. Before proceeding, ensure you're using **Python 3.11** to avoid compatibility issues.
1.**Install Open WebUI**:
Open your terminal and run the following command to install Open WebUI:
```bash
pip install open-webui
```
2. **Running Open WebUI**:
After installation, you can start Open WebUI by executing:
```bash
open-webui serve
```
This will start the Open WebUI server, which you can access at [http://localhost:8080](http://localhost:8080)
### Quick Start with Docker 🐳
> [!NOTE]
> Please note that for certain Docker environments, additional configurations might be needed. If you encounter any connection issues, our detailed guide on [Open WebUI Documentation](https://docs.openwebui.com/) is ready to assist you.
> [!WARNING]
> When using Docker to install Open WebUI, make sure to include the `-v open-webui:/app/backend/data` in your Docker command. This step is crucial as it ensures your database is properly mounted and prevents any loss of data.
If you are running Open WebUI in an offline environment, you can set the `HF_HUB_OFFLINE` environment variable to `1` to prevent attempts to download models from the internet.
```bash
export HF_HUB_OFFLINE=1
```
## What's Next? 🌟
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. 📄
This project is licensed under the [BSD-3-Clause License](LICENSE) - see the [LICENSE](LICENSE) file for details. 📄
## Support 💬
@@ -200,4 +225,4 @@ If you have any questions, suggestions, or need assistance, please open an issue
---
Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open WebUI even more amazing together! 💪
Created by [Timothy Jaeryang Baek](https://github.com/tjbck) - Let's make Open WebUI even more amazing together! 💪
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.
@@ -20,7 +20,9 @@ class ERROR_MESSAGES(str, Enum):
def__str__(self)->str:
returnsuper().__str__()
DEFAULT=lambdaerr="":f"Something went wrong :/\n{erriferrelse''}"
DEFAULT=(
lambdaerr="":f'{"Something went wrong :/"iferr==""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."
@@ -34,8 +36,8 @@ class ERROR_MESSAGES(str, Enum):
ID_TAKEN="Uh-oh! This id is already registered. Please choose another id string."
MODEL_ID_TAKEN="Uh-oh! This model id is already registered. Please choose another model id string."
NAME_TAG_TAKEN="Uh-oh! This name tag is already registered. Please choose another name tag string."
INVALID_TOKEN=(
"Your session has expired or the token is invalid. Please sign in again."
)
@@ -55,11 +57,12 @@ class ERROR_MESSAGES(str, Enum):
)
FILE_NOT_SENT="FILE_NOT_SENT"
FILE_NOT_SUPPORTED="Oops! It seems like the file format you're trying to upload is not supported. Please upload a file with a supported format (e.g., JPG, PNG, PDF, TXT) and try again."
FILE_NOT_SUPPORTED="Oops! It seems like the file format you're trying to upload is not supported. Please upload a file with a supported format and try again."
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=lambdaname="":"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."
@@ -90,6 +94,15 @@ class ERROR_MESSAGES(str, Enum):
"The Ollama API is disabled. Please enable it to use this feature."
)
FILE_TOO_LARGE=(
lambdasize="":f"Oops! The file you're trying to upload is too large. Please upload a file that is less than {size}."
)
DUPLICATE_CONTENT=(
"Duplicate content detected. Please provide unique content to proceed."
)
FILE_NOT_PROCESSED="Extracted content is not available for this file. Please ensure that the file is processed before proceeding."
# device type embedding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
SamiAhmed7777