Merge pull request #7562 from open-webui/dev

0.4.8

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

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

CHANGELOG.md

@@ -5,6 +5,121 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.8] - 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

CODE_OF_CONDUCT.md

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

README.md

@@ -21,7 +21,7 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 🤝 **Ollama/OpenAI API Integration**: Effortlessly integrate OpenAI-compatible APIs for versatile conversations alongside Ollama models. Customize the OpenAI API URL to link with **LMStudio, GroqCloud, Mistral, OpenRouter, and more**.
 
-- 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
+- 🛡️ **Granular Permissions and User Groups**: By allowing administrators to create detailed user roles and permissions, we ensure a secure user environment. This granularity not only enhances security but also allows for customized user experiences, fostering a sense of ownership and responsibility amongst users.
 
 - 📱 **Responsive Design**: Enjoy a seamless experience across Desktop PC, Laptop, and Mobile devices.
 
@@ -49,6 +49,8 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
 
+- 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
+
 - 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates, fixes, and new features.
 
 Want to learn more about Open WebUI's features? Check out our [Open WebUI documentation](https://docs.openwebui.com/features) for a comprehensive overview!

backend/open_webui/apps/audio/main.py

@@ -8,6 +8,8 @@ from pathlib import Path
 from pydub import AudioSegment
 from pydub.silence import split_on_silence
 
+import aiohttp
+import aiofiles
 import requests
 from open_webui.config import (
     AUDIO_STT_ENGINE,
@@ -292,46 +294,39 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         except Exception:
             pass
 
-        r = None
         try:
-            r = requests.post(
-                url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
-                data=body,
-                headers=headers,
-                stream=True,
-            )
+            async with aiohttp.ClientSession() as session:
+                async with session.post(
+                    url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
+                    data=body,
+                    headers=headers,
+                ) as r:
+                    r.raise_for_status()
+                    async with aiofiles.open(file_path, "wb") as f:
+                        await f.write(await r.read())
 
-            r.raise_for_status()
+                    async with aiofiles.open(file_body_path, "w") as f:
+                        await f.write(json.dumps(json.loads(body.decode("utf-8"))))
 
-            # Save the streaming content to a file
-            with open(file_path, "wb") as f:
-                for chunk in r.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            with open(file_body_path, "w") as f:
-                json.dump(json.loads(body.decode("utf-8")), f)
-
-            # Return the saved file
             return FileResponse(file_path)
 
         except Exception as e:
             log.exception(e)
             error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
+            try:
+                if r.status != 200:
+                    res = await r.json()
                     if "error" in res:
                         error_detail = f"External: {res['error']['message']}"
-                except Exception:
-                    error_detail = f"External: {e}"
+            except Exception:
+                error_detail = f"External: {e}"
 
             raise HTTPException(
-                status_code=r.status_code if r != None else 500,
+                status_code=getattr(r, "status", 500),
                 detail=error_detail,
             )
 
     elif app.state.config.TTS_ENGINE == "elevenlabs":
-        payload = None
         try:
             payload = json.loads(body.decode("utf-8"))
         except Exception as e:
@@ -339,7 +334,6 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             raise HTTPException(status_code=400, detail="Invalid JSON payload")
 
         voice_id = payload.get("voice", "")
-
         if voice_id not in get_available_voices():
             raise HTTPException(
                 status_code=400,
@@ -347,13 +341,11 @@ async def speech(request: Request, user=Depends(get_verified_user)):
             )
 
         url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
-
         headers = {
             "Accept": "audio/mpeg",
             "Content-Type": "application/json",
             "xi-api-key": app.state.config.TTS_API_KEY,
         }
-
         data = {
             "text": payload["input"],
             "model_id": app.state.config.TTS_MODEL,
@@ -361,39 +353,34 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         }
 
         try:
-            r = requests.post(url, json=data, headers=headers)
+            async with aiohttp.ClientSession() as session:
+                async with session.post(url, json=data, headers=headers) as r:
+                    r.raise_for_status()
+                    async with aiofiles.open(file_path, "wb") as f:
+                        await f.write(await r.read())
 
-            r.raise_for_status()
+                    async with aiofiles.open(file_body_path, "w") as f:
+                        await f.write(json.dumps(json.loads(body.decode("utf-8"))))
 
-            # Save the streaming content to a file
-            with open(file_path, "wb") as f:
-                for chunk in r.iter_content(chunk_size=8192):
-                    f.write(chunk)
-
-            with open(file_body_path, "w") as f:
-                json.dump(json.loads(body.decode("utf-8")), f)
-
-            # Return the saved file
             return FileResponse(file_path)
 
         except Exception as e:
             log.exception(e)
             error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
+            try:
+                if r.status != 200:
+                    res = await r.json()
                     if "error" in res:
                         error_detail = f"External: {res['error']['message']}"
-                except Exception:
-                    error_detail = f"External: {e}"
+            except Exception:
+                error_detail = f"External: {e}"
 
             raise HTTPException(
-                status_code=r.status_code if r != None else 500,
+                status_code=getattr(r, "status", 500),
                 detail=error_detail,
             )
 
     elif app.state.config.TTS_ENGINE == "azure":
-        payload = None
         try:
             payload = json.loads(body.decode("utf-8"))
         except Exception as e:
@@ -416,17 +403,20 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                 <voice name="{language}">{payload["input"]}</voice>
             </speak>"""
 
-        response = requests.post(url, headers=headers, data=data)
-
-        if response.status_code == 200:
-            with open(file_path, "wb") as f:
-                f.write(response.content)
-            return FileResponse(file_path)
-        else:
-            log.error(f"Error synthesizing speech - {response.reason}")
-            raise HTTPException(
-                status_code=500, detail=f"Error synthesizing speech - {response.reason}"
-            )
+        try:
+            async with aiohttp.ClientSession() as session:
+                async with session.post(url, headers=headers, data=data) as response:
+                    if response.status == 200:
+                        async with aiofiles.open(file_path, "wb") as f:
+                            await f.write(await response.read())
+                        return FileResponse(file_path)
+                    else:
+                        error_msg = f"Error synthesizing speech - {response.reason}"
+                        log.error(error_msg)
+                        raise HTTPException(status_code=500, detail=error_msg)
+        except Exception as e:
+            log.exception(e)
+            raise HTTPException(status_code=500, detail=str(e))
     elif app.state.config.TTS_ENGINE == "transformers":
         payload = None
         try:

backend/open_webui/apps/ollama/main.py

@@ -9,6 +9,8 @@ from typing import Optional, Union
 from urllib.parse import urlparse
 
 import aiohttp
+from aiocache import cached
+
 import requests
 from open_webui.apps.webui.models.models import Models
 from open_webui.config import (
@@ -22,6 +24,7 @@ from open_webui.config import (
 from open_webui.env import (
     AIOHTTP_CLIENT_TIMEOUT,
     AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
+    BYPASS_MODEL_ACCESS_CONTROL,
 )
 
 
@@ -193,7 +196,10 @@ async def post_streaming_url(
             trust_env=True, timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
         )
 
-        api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+        parsed_url = urlparse(url)
+        base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+        api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
         key = api_config.get("key", None)
 
         headers = {"Content-Type": "application/json"}
@@ -208,13 +214,13 @@ async def post_streaming_url(
         r.raise_for_status()
 
         if stream:
-            headers = dict(r.headers)
+            response_headers = dict(r.headers)
             if content_type:
-                headers["Content-Type"] = content_type
+                response_headers["Content-Type"] = content_type
             return StreamingResponse(
                 r.content,
                 status_code=r.status,
-                headers=headers,
+                headers=response_headers,
                 background=BackgroundTask(
                     cleanup_response, response=r, session=session
                 ),
@@ -256,6 +262,7 @@ def merge_models_lists(model_lists):
     return list(merged_models.values())
 
 
+@cached(ttl=3)
 async def get_all_models():
     log.info("get_all_models()")
     if app.state.config.ENABLE_OLLAMA_API:
@@ -295,8 +302,6 @@ async def get_all_models():
                     for model in response.get("models", []):
                         model["model"] = f"{prefix_id}.{model['model']}"
 
-        print(responses)
-
         models = {
             "models": merge_models_lists(
                 map(
@@ -323,7 +328,10 @@ async def get_ollama_tags(
     else:
         url = app.state.config.OLLAMA_BASE_URLS[url_idx]
 
-        api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+        parsed_url = urlparse(url)
+        base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+        api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
         key = api_config.get("key", None)
 
         headers = {}
@@ -352,7 +360,7 @@ async def get_ollama_tags(
                 detail=error_detail,
             )
 
-    if user.role == "user":
+    if user.role == "user" and not BYPASS_MODEL_ACCESS_CONTROL:
         # Filter models based on user access control
         filtered_models = []
         for model in models.get("models", []):
@@ -524,7 +532,10 @@ async def copy_model(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
     key = api_config.get("key", None)
 
     headers = {"Content-Type": "application/json"}
@@ -583,7 +594,10 @@ async def delete_model(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
     key = api_config.get("key", None)
 
     headers = {"Content-Type": "application/json"}
@@ -634,7 +648,10 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_verified_us
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
     key = api_config.get("key", None)
 
     headers = {"Content-Type": "application/json"}
@@ -690,7 +707,7 @@ async def generate_embeddings(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    return generate_ollama_batch_embeddings(form_data, url_idx)
+    return await generate_ollama_batch_embeddings(form_data, url_idx)
 
 
 @app.post("/api/embeddings")
@@ -729,7 +746,10 @@ async def generate_ollama_embeddings(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
     key = api_config.get("key", None)
 
     headers = {"Content-Type": "application/json"}
@@ -796,7 +816,10 @@ async def generate_ollama_batch_embeddings(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
     key = api_config.get("key", None)
 
     headers = {"Content-Type": "application/json"}
@@ -837,6 +860,7 @@ async def generate_ollama_batch_embeddings(
 class GenerateCompletionForm(BaseModel):
     model: str
     prompt: str
+    suffix: Optional[str] = None
     images: Optional[list[str]] = None
     format: Optional[str] = None
     options: Optional[dict] = None
@@ -972,7 +996,10 @@ async def generate_chat_completion(
     log.info(f"url: {url}")
     log.debug(f"generate_chat_completion() - 2.payload = {payload}")
 
-    api_config = app.state.config.OLLAMA_API_CONFIGS.get(url, {})
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    api_config = app.state.config.OLLAMA_API_CONFIGS.get(base_url, {})
     prefix_id = api_config.get("prefix_id", None)
     if prefix_id:
         payload["model"] = payload["model"].replace(f"{prefix_id}.", "")
@@ -1041,7 +1068,7 @@ async def generate_openai_chat_completion(
             payload = apply_model_system_prompt_to_body(params, payload, user)
 
         # Check if user has access to the model
-        if user.role == "user":
+        if user.role == "user" and not BYPASS_MODEL_ACCESS_CONTROL:
             if not (
                 user.id == model_info.user_id
                 or has_access(
@@ -1130,7 +1157,7 @@ async def get_openai_models(
                 detail=error_detail,
             )
 
-    if user.role == "user":
+    if user.role == "user" and not BYPASS_MODEL_ACCESS_CONTROL:
         # Filter models based on user access control
         filtered_models = []
         for model in models:

backend/open_webui/apps/openai/main.py

@@ -6,7 +6,10 @@ from pathlib import Path
 from typing import Literal, Optional, overload
 
 import aiohttp
+from aiocache import cached
 import requests
+
+
 from open_webui.apps.webui.models.models import Models
 from open_webui.config import (
     CACHE_DIR,
@@ -21,6 +24,7 @@ from open_webui.env import (
     AIOHTTP_CLIENT_TIMEOUT,
     AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
     ENABLE_FORWARD_USER_INFO_HEADERS,
+    BYPASS_MODEL_ACCESS_CONTROL,
 )
 
 from open_webui.constants import ERROR_MESSAGES
@@ -302,6 +306,8 @@ async def get_all_models_responses() -> list:
                     }
 
                     tasks.append(asyncio.ensure_future(asyncio.sleep(0, model_list)))
+            else:
+                tasks.append(asyncio.ensure_future(asyncio.sleep(0, None)))
 
     responses = await asyncio.gather(*tasks)
 
@@ -313,7 +319,9 @@ async def get_all_models_responses() -> list:
             prefix_id = api_config.get("prefix_id", None)
 
             if prefix_id:
-                for model in response["data"]:
+                for model in (
+                    response if isinstance(response, list) else response.get("data", [])
+                ):
                     model["id"] = f"{prefix_id}.{model['id']}"
 
     log.debug(f"get_all_models:responses() {responses}")
@@ -321,6 +329,7 @@ async def get_all_models_responses() -> list:
     return responses
 
 
+@cached(ttl=3)
 async def get_all_models() -> dict[str, list]:
     log.info("get_all_models()")
 
@@ -414,7 +423,7 @@ async def get_models(url_idx: Optional[int] = None, user=Depends(get_verified_us
                 error_detail = f"Unexpected error: {str(e)}"
                 raise HTTPException(status_code=500, detail=error_detail)
 
-    if user.role == "user":
+    if user.role == "user" and not BYPASS_MODEL_ACCESS_CONTROL:
         # Filter models based on user access control
         filtered_models = []
         for model in models.get("data", []):
@@ -577,8 +586,6 @@ async def generate_chat_completion(
     # Convert the modified body back to JSON
     payload = json.dumps(payload)
 
-    log.debug(payload)
-
     headers = {}
     headers["Authorization"] = f"Bearer {key}"
     headers["Content-Type"] = "application/json"

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

@@ -0,0 +1,117 @@
+import logging
+
+from typing import Any, Dict, Generator, List, Optional, Sequence, Union
+from urllib.parse import parse_qs, urlparse
+from langchain_core.documents import Document
+from open_webui.env import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+ALLOWED_SCHEMES = {"http", "https"}
+ALLOWED_NETLOCS = {
+    "youtu.be",
+    "m.youtube.com",
+    "youtube.com",
+    "www.youtube.com",
+    "www.youtube-nocookie.com",
+    "vid.plus",
+}
+
+
+def _parse_video_id(url: str) -> Optional[str]:
+    """Parse a YouTube URL and return the video ID if valid, otherwise None."""
+    parsed_url = urlparse(url)
+
+    if parsed_url.scheme not in ALLOWED_SCHEMES:
+        return None
+
+    if parsed_url.netloc not in ALLOWED_NETLOCS:
+        return None
+
+    path = parsed_url.path
+
+    if path.endswith("/watch"):
+        query = parsed_url.query
+        parsed_query = parse_qs(query)
+        if "v" in parsed_query:
+            ids = parsed_query["v"]
+            video_id = ids if isinstance(ids, str) else ids[0]
+        else:
+            return None
+    else:
+        path = parsed_url.path.lstrip("/")
+        video_id = path.split("/")[-1]
+
+    if len(video_id) != 11:  # Video IDs are 11 characters long
+        return None
+
+    return video_id
+
+
+class YoutubeLoader:
+    """Load `YouTube` video transcripts."""
+
+    def __init__(
+        self,
+        video_id: str,
+        language: Union[str, Sequence[str]] = "en",
+        proxy_url: Optional[str] = None,
+    ):
+        """Initialize with YouTube video ID."""
+        _video_id = _parse_video_id(video_id)
+        self.video_id = _video_id if _video_id is not None else video_id
+        self._metadata = {"source": video_id}
+        self.language = language
+        self.proxy_url = proxy_url
+        if isinstance(language, str):
+            self.language = [language]
+        else:
+            self.language = language
+
+    def load(self) -> List[Document]:
+        """Load YouTube transcripts into `Document` objects."""
+        try:
+            from youtube_transcript_api import (
+                NoTranscriptFound,
+                TranscriptsDisabled,
+                YouTubeTranscriptApi,
+            )
+        except ImportError:
+            raise ImportError(
+                'Could not import "youtube_transcript_api" Python package. '
+                "Please install it with `pip install youtube-transcript-api`."
+            )
+
+        if self.proxy_url:
+            youtube_proxies = {
+                "http": self.proxy_url,
+                "https": self.proxy_url,
+            }
+            # Don't log complete URL because it might contain secrets
+            log.debug(f"Using proxy URL: {self.proxy_url[:14]}...")
+        else:
+            youtube_proxies = None
+
+        try:
+            transcript_list = YouTubeTranscriptApi.list_transcripts(
+                self.video_id, proxies=youtube_proxies
+            )
+        except Exception as e:
+            log.exception("Loading YouTube transcript failed")
+            return []
+
+        try:
+            transcript = transcript_list.find_transcript(self.language)
+        except NoTranscriptFound:
+            transcript = transcript_list.find_transcript(["en"])
+
+        transcript_pieces: List[Dict[str, Any]] = transcript.fetch()
+
+        transcript = " ".join(
+            map(
+                lambda transcript_piece: transcript_piece["text"].strip(" "),
+                transcript_pieces,
+            )
+        )
+        return [Document(page_content=transcript, metadata=self._metadata)]

backend/open_webui/apps/retrieval/main.py

@@ -23,11 +23,13 @@ from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
 
 # Document loaders
 from open_webui.apps.retrieval.loaders.main import Loader
+from open_webui.apps.retrieval.loaders.youtube import YoutubeLoader
 
 # Web search engines
 from open_webui.apps.retrieval.web.main import SearchResult
 from open_webui.apps.retrieval.web.utils import get_web_loader
 from open_webui.apps.retrieval.web.brave import search_brave
+from open_webui.apps.retrieval.web.mojeek import search_mojeek
 from open_webui.apps.retrieval.web.duckduckgo import search_duckduckgo
 from open_webui.apps.retrieval.web.google_pse import search_google_pse
 from open_webui.apps.retrieval.web.jina_search import search_jina
@@ -52,6 +54,7 @@ from open_webui.apps.retrieval.utils import (
 from open_webui.apps.webui.models.files import Files
 from open_webui.config import (
     BRAVE_SEARCH_API_KEY,
+    MOJEEK_SEARCH_API_KEY,
     TIKTOKEN_ENCODING_NAME,
     RAG_TEXT_SPLITTER,
     CHUNK_OVERLAP,
@@ -102,6 +105,7 @@ from open_webui.config import (
     TIKA_SERVER_URL,
     UPLOAD_DIR,
     YOUTUBE_LOADER_LANGUAGE,
+    YOUTUBE_LOADER_PROXY_URL,
     DEFAULT_LOCALE,
     AppConfig,
 )
@@ -120,9 +124,6 @@ from open_webui.utils.misc import (
 from open_webui.utils.utils import get_admin_user, get_verified_user
 
 from langchain.text_splitter import RecursiveCharacterTextSplitter, TokenTextSplitter
-from langchain_community.document_loaders import (
-    YoutubeLoader,
-)
 from langchain_core.documents import Document
 
 
@@ -171,6 +172,7 @@ app.state.config.OLLAMA_API_KEY = RAG_OLLAMA_API_KEY
 app.state.config.PDF_EXTRACT_IMAGES = PDF_EXTRACT_IMAGES
 
 app.state.config.YOUTUBE_LOADER_LANGUAGE = YOUTUBE_LOADER_LANGUAGE
+app.state.config.YOUTUBE_LOADER_PROXY_URL = YOUTUBE_LOADER_PROXY_URL
 app.state.YOUTUBE_LOADER_TRANSLATION = None
 
 
@@ -182,6 +184,7 @@ app.state.config.SEARXNG_QUERY_URL = SEARXNG_QUERY_URL
 app.state.config.GOOGLE_PSE_API_KEY = GOOGLE_PSE_API_KEY
 app.state.config.GOOGLE_PSE_ENGINE_ID = GOOGLE_PSE_ENGINE_ID
 app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY
+app.state.config.MOJEEK_SEARCH_API_KEY = MOJEEK_SEARCH_API_KEY
 app.state.config.SERPSTACK_API_KEY = SERPSTACK_API_KEY
 app.state.config.SERPSTACK_HTTPS = SERPSTACK_HTTPS
 app.state.config.SERPER_API_KEY = SERPER_API_KEY
@@ -470,6 +473,7 @@ async def get_rag_config(user=Depends(get_admin_user)):
         "youtube": {
             "language": app.state.config.YOUTUBE_LOADER_LANGUAGE,
             "translation": app.state.YOUTUBE_LOADER_TRANSLATION,
+            "proxy_url": app.state.config.YOUTUBE_LOADER_PROXY_URL,
         },
         "web": {
             "web_loader_ssl_verification": app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION,
@@ -480,6 +484,7 @@ async def get_rag_config(user=Depends(get_admin_user)):
                 "google_pse_api_key": app.state.config.GOOGLE_PSE_API_KEY,
                 "google_pse_engine_id": app.state.config.GOOGLE_PSE_ENGINE_ID,
                 "brave_search_api_key": app.state.config.BRAVE_SEARCH_API_KEY,
+                "mojeek_search_api_key": app.state.config.MOJEEK_SEARCH_API_KEY,
                 "serpstack_api_key": app.state.config.SERPSTACK_API_KEY,
                 "serpstack_https": app.state.config.SERPSTACK_HTTPS,
                 "serper_api_key": app.state.config.SERPER_API_KEY,
@@ -516,6 +521,7 @@ class ChunkParamUpdateForm(BaseModel):
 class YoutubeLoaderConfig(BaseModel):
     language: list[str]
     translation: Optional[str] = None
+    proxy_url: str = ""
 
 
 class WebSearchConfig(BaseModel):
@@ -525,6 +531,7 @@ class WebSearchConfig(BaseModel):
     google_pse_api_key: Optional[str] = None
     google_pse_engine_id: Optional[str] = None
     brave_search_api_key: Optional[str] = None
+    mojeek_search_api_key: Optional[str] = None
     serpstack_api_key: Optional[str] = None
     serpstack_https: Optional[bool] = None
     serper_api_key: Optional[str] = None
@@ -577,6 +584,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
 
     if form_data.youtube is not None:
         app.state.config.YOUTUBE_LOADER_LANGUAGE = form_data.youtube.language
+        app.state.config.YOUTUBE_LOADER_PROXY_URL = form_data.youtube.proxy_url
         app.state.YOUTUBE_LOADER_TRANSLATION = form_data.youtube.translation
 
     if form_data.web is not None:
@@ -595,6 +603,9 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
         app.state.config.BRAVE_SEARCH_API_KEY = (
             form_data.web.search.brave_search_api_key
         )
+        app.state.config.MOJEEK_SEARCH_API_KEY = (
+            form_data.web.search.mojeek_search_api_key
+        )
         app.state.config.SERPSTACK_API_KEY = form_data.web.search.serpstack_api_key
         app.state.config.SERPSTACK_HTTPS = form_data.web.search.serpstack_https
         app.state.config.SERPER_API_KEY = form_data.web.search.serper_api_key
@@ -634,6 +645,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
         },
         "youtube": {
             "language": app.state.config.YOUTUBE_LOADER_LANGUAGE,
+            "proxy_url": app.state.config.YOUTUBE_LOADER_PROXY_URL,
             "translation": app.state.YOUTUBE_LOADER_TRANSLATION,
         },
         "web": {
@@ -645,6 +657,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
                 "google_pse_api_key": app.state.config.GOOGLE_PSE_API_KEY,
                 "google_pse_engine_id": app.state.config.GOOGLE_PSE_ENGINE_ID,
                 "brave_search_api_key": app.state.config.BRAVE_SEARCH_API_KEY,
+                "mojeek_search_api_key": app.state.config.MOJEEK_SEARCH_API_KEY,
                 "serpstack_api_key": app.state.config.SERPSTACK_API_KEY,
                 "serpstack_https": app.state.config.SERPSTACK_HTTPS,
                 "serper_api_key": app.state.config.SERPER_API_KEY,
@@ -860,7 +873,7 @@ def save_docs_to_vector_db(
         return True
     except Exception as e:
         log.exception(e)
-        return False
+        raise e
 
 
 class ProcessFileForm(BaseModel):
@@ -886,19 +899,17 @@ def process_file(
             # Update the content in the file
             # Usage: /files/{file_id}/data/content/update
 
-            VECTOR_DB_CLIENT.delete(
-                collection_name=f"file-{file.id}",
-                filter={"file_id": file.id},
-            )
+            VECTOR_DB_CLIENT.delete_collection(collection_name=f"file-{file.id}")
 
             docs = [
                 Document(
-                    page_content=form_data.content,
+                    page_content=form_data.content.replace("<br/>", "\n"),
                     metadata={
-                        "name": file.meta.get("name", file.filename),
+                        **file.meta,
+                        "name": file.filename,
                         "created_by": file.user_id,
                         "file_id": file.id,
-                        **file.meta,
+                        "source": file.filename,
                     },
                 )
             ]
@@ -925,10 +936,11 @@ def process_file(
                     Document(
                         page_content=file.data.get("content", ""),
                         metadata={
-                            "name": file.meta.get("name", file.filename),
+                            **file.meta,
+                            "name": file.filename,
                             "created_by": file.user_id,
                             "file_id": file.id,
-                            **file.meta,
+                            "source": file.filename,
                         },
                     )
                 ]
@@ -948,15 +960,30 @@ def process_file(
                 docs = loader.load(
                     file.filename, file.meta.get("content_type"), file_path
                 )
+
+                docs = [
+                    Document(
+                        page_content=doc.page_content,
+                        metadata={
+                            **doc.metadata,
+                            "name": file.filename,
+                            "created_by": file.user_id,
+                            "file_id": file.id,
+                            "source": file.filename,
+                        },
+                    )
+                    for doc in docs
+                ]
             else:
                 docs = [
                     Document(
                         page_content=file.data.get("content", ""),
                         metadata={
+                            **file.meta,
                             "name": file.filename,
                             "created_by": file.user_id,
                             "file_id": file.id,
-                            **file.meta,
+                            "source": file.filename,
                         },
                     )
                 ]
@@ -977,7 +1004,7 @@ def process_file(
                 collection_name=collection_name,
                 metadata={
                     "file_id": file.id,
-                    "name": file.meta.get("name", file.filename),
+                    "name": file.filename,
                     "hash": hash,
                 },
                 add=(True if form_data.collection_name else False),
@@ -994,7 +1021,7 @@ def process_file(
                 return {
                     "status": True,
                     "collection_name": collection_name,
-                    "filename": file.meta.get("name", file.filename),
+                    "filename": file.filename,
                     "content": text_content,
                 }
         except Exception as e:
@@ -1059,12 +1086,12 @@ def process_youtube_video(form_data: ProcessUrlForm, user=Depends(get_verified_u
         if not collection_name:
             collection_name = calculate_sha256_string(form_data.url)[:63]
 
-        loader = YoutubeLoader.from_youtube_url(
+        loader = YoutubeLoader(
             form_data.url,
-            add_video_info=False,
             language=app.state.config.YOUTUBE_LOADER_LANGUAGE,
-            translation=app.state.YOUTUBE_LOADER_TRANSLATION,
+            proxy_url=app.state.config.YOUTUBE_LOADER_PROXY_URL,
         )
+
         docs = loader.load()
         content = " ".join([doc.page_content for doc in docs])
         log.debug(f"text_content: {content}")
@@ -1135,6 +1162,7 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
     - SEARXNG_QUERY_URL
     - GOOGLE_PSE_API_KEY + GOOGLE_PSE_ENGINE_ID
     - BRAVE_SEARCH_API_KEY
+    - MOJEEK_SEARCH_API_KEY
     - SERPSTACK_API_KEY
     - SERPER_API_KEY
     - SERPLY_API_KEY
@@ -1181,6 +1209,16 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
             )
         else:
             raise Exception("No BRAVE_SEARCH_API_KEY found in environment variables")
+    elif engine == "mojeek":
+        if app.state.config.MOJEEK_SEARCH_API_KEY:
+            return search_mojeek(
+                app.state.config.MOJEEK_SEARCH_API_KEY,
+                query,
+                app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+                app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
+            )
+        else:
+            raise Exception("No MOJEEK_SEARCH_API_KEY found in environment variables")
     elif engine == "serpstack":
         if app.state.config.SERPSTACK_API_KEY:
             return search_serpstack(
@@ -1361,7 +1399,7 @@ def query_collection_handler(
         if app.state.config.ENABLE_RAG_HYBRID_SEARCH:
             return query_collection_with_hybrid_search(
                 collection_names=form_data.collection_names,
-                query=form_data.query,
+                queries=[form_data.query],
                 embedding_function=app.state.EMBEDDING_FUNCTION,
                 k=form_data.k if form_data.k else app.state.config.TOP_K,
                 reranking_function=app.state.sentence_transformer_rf,
@@ -1372,7 +1410,7 @@ def query_collection_handler(
         else:
             return query_collection(
                 collection_names=form_data.collection_names,
-                query=form_data.query,
+                queries=[form_data.query],
                 embedding_function=app.state.EMBEDDING_FUNCTION,
                 k=form_data.k if form_data.k else app.state.config.TOP_K,
             )

backend/open_webui/apps/retrieval/utils.py

@@ -15,8 +15,6 @@ from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
 from open_webui.utils.misc import get_last_user_message
 
 from open_webui.env import SRC_LOG_LEVELS
-from open_webui.config import DEFAULT_RAG_TEMPLATE
-
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
@@ -238,44 +236,6 @@ def query_collection_with_hybrid_search(
     return merge_and_sort_query_results(results, k=k, reverse=True)
 
 
-def rag_template(template: str, context: str, query: str):
-    if template == "":
-        template = DEFAULT_RAG_TEMPLATE
-
-    if "[context]" not in template and "{{CONTEXT}}" not in template:
-        log.debug(
-            "WARNING: The RAG template does not contain the '[context]' or '{{CONTEXT}}' placeholder."
-        )
-
-    if "<context>" in context and "</context>" in context:
-        log.debug(
-            "WARNING: Potential prompt injection attack: the RAG "
-            "context contains '<context>' and '</context>'. This might be "
-            "nothing, or the user might be trying to hack something."
-        )
-
-    query_placeholders = []
-    if "[query]" in context:
-        query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
-        template = template.replace("[query]", query_placeholder)
-        query_placeholders.append(query_placeholder)
-
-    if "{{QUERY}}" in context:
-        query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
-        template = template.replace("{{QUERY}}", query_placeholder)
-        query_placeholders.append(query_placeholder)
-
-    template = template.replace("[context]", context)
-    template = template.replace("{{CONTEXT}}", context)
-    template = template.replace("[query]", query)
-    template = template.replace("{{QUERY}}", query)
-
-    for query_placeholder in query_placeholders:
-        template = template.replace(query_placeholder, query)
-
-    return template
-
-
 def get_embedding_function(
     embedding_engine,
     embedding_model,
@@ -307,7 +267,7 @@ def get_embedding_function(
         return lambda query: generate_multiple(query, func)
 
 
-def get_rag_context(
+def get_sources_from_files(
     files,
     queries,
     embedding_function,
@@ -387,43 +347,24 @@ def get_rag_context(
                 del file["data"]
             relevant_contexts.append({**context, "file": file})
 
-    contexts = []
-    citations = []
+    sources = []
     for context in relevant_contexts:
         try:
             if "documents" in context:
-                file_names = list(
-                    set(
-                        [
-                            metadata["name"]
-                            for metadata in context["metadatas"][0]
-                            if metadata is not None and "name" in metadata
-                        ]
-                    )
-                )
-                contexts.append(
-                    ((", ".join(file_names) + ":\n\n") if file_names else "")
-                    + "\n\n".join(
-                        [text for text in context["documents"][0] if text is not None]
-                    )
-                )
-
                 if "metadatas" in context:
-                    citation = {
+                    source = {
                         "source": context["file"],
                         "document": context["documents"][0],
                         "metadata": context["metadatas"][0],
                     }
                     if "distances" in context and context["distances"]:
-                        citation["distances"] = context["distances"][0]
-                    citations.append(citation)
+                        source["distances"] = context["distances"][0]
+
+                    sources.append(source)
         except Exception as e:
             log.exception(e)
 
-    print("contexts", contexts)
-    print("citations", citations)
-
-    return contexts, citations
+    return sources
 
 
 def get_model_path(model: str, update_model: bool = False):
@@ -488,7 +429,7 @@ def generate_openai_batch_embeddings(
 
 
 def generate_ollama_batch_embeddings(
-    model: str, texts: list[str], url: str, key: str
+    model: str, texts: list[str], url: str, key: str = ""
 ) -> Optional[list[list[float]]]:
     try:
         r = requests.post(
@@ -502,7 +443,6 @@ def generate_ollama_batch_embeddings(
         r.raise_for_status()
         data = r.json()
 
-        print(data)
         if "embeddings" in data:
             return data["embeddings"]
         else:

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

@@ -1,7 +1,7 @@
 from opensearchpy import OpenSearch
 from typing import Optional
 
-from open_webui.apps.rag.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.apps.retrieval.vector.main import VectorItem, SearchResult, GetResult
 from open_webui.config import (
     OPENSEARCH_URI,
     OPENSEARCH_SSL,

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

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

backend/open_webui/apps/webui/main.py

@@ -31,6 +31,7 @@ from open_webui.config import (
     DEFAULT_MODELS,
     DEFAULT_PROMPT_SUGGESTIONS,
     DEFAULT_USER_ROLE,
+    MODEL_ORDER_LIST,
     ENABLE_COMMUNITY_SHARING,
     ENABLE_LOGIN_FORM,
     ENABLE_MESSAGE_RATING,
@@ -68,6 +69,7 @@ from open_webui.config import (
 )
 from open_webui.env import (
     ENV,
+    SRC_LOG_LEVELS,
     WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
     WEBUI_AUTH_TRUSTED_NAME_HEADER,
 )
@@ -94,6 +96,7 @@ app = FastAPI(
 )
 
 log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 app.state.config = AppConfig()
 
@@ -118,6 +121,7 @@ app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
 app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
 app.state.config.BANNERS = WEBUI_BANNERS
+app.state.config.MODEL_ORDER_LIST = MODEL_ORDER_LIST
 
 app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
 app.state.config.ENABLE_MESSAGE_RATING = ENABLE_MESSAGE_RATING
@@ -270,7 +274,9 @@ async def get_pipe_models():
                 log.exception(e)
                 sub_pipes = []
 
-            print(sub_pipes)
+            log.debug(
+                f"get_pipe_models: function '{pipe.id}' is a manifold of {sub_pipes}"
+            )
 
             for p in sub_pipes:
                 sub_pipe_id = f'{pipe.id}.{p["id"]}'
@@ -280,6 +286,7 @@ async def get_pipe_models():
                     sub_pipe_name = f"{function_module.name}{sub_pipe_name}"
 
                 pipe_flag = {"type": pipe.type}
+
                 pipe_models.append(
                     {
                         "id": sub_pipe_id,
@@ -293,6 +300,10 @@ async def get_pipe_models():
         else:
             pipe_flag = {"type": "pipe"}
 
+            log.debug(
+                f"get_pipe_models: function '{pipe.id}' is a single pipe {{ 'id': {pipe.id}, 'name': {pipe.name} }}"
+            )
+
             pipe_models.append(
                 {
                     "id": pipe.id,
@@ -346,7 +357,7 @@ def get_pipe_id(form_data: dict) -> str:
     pipe_id = form_data["model"]
     if "." in pipe_id:
         pipe_id, _ = pipe_id.split(".", 1)
-    print(pipe_id)
+
     return pipe_id
 
 
@@ -453,7 +464,7 @@ async def generate_function_chat_completion(form_data, user, models: dict = {}):
                     return
 
             except Exception as e:
-                print(f"Error: {e}")
+                log.error(f"Error: {e}")
                 yield f"data: {json.dumps({'error': {'detail':str(e)}})}\n\n"
                 return
 
@@ -483,7 +494,7 @@ async def generate_function_chat_completion(form_data, user, models: dict = {}):
             res = await execute_pipe(pipe, params)
 
         except Exception as e:
-            print(f"Error: {e}")
+            log.error(f"Error: {e}")
             return {"error": {"detail": str(e)}}
 
         if isinstance(res, StreamingResponse) or isinstance(res, dict):

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

@@ -128,17 +128,20 @@ class KnowledgeTable:
 
     def get_knowledge_bases(self) -> list[KnowledgeUserModel]:
         with get_db() as db:
-            return [
-                KnowledgeUserModel.model_validate(
-                    {
-                        **KnowledgeModel.model_validate(knowledge).model_dump(),
-                        "user": Users.get_user_by_id(knowledge.user_id).model_dump(),
-                    }
+            knowledge_bases = []
+            for knowledge in (
+                db.query(Knowledge).order_by(Knowledge.updated_at.desc()).all()
+            ):
+                user = Users.get_user_by_id(knowledge.user_id)
+                knowledge_bases.append(
+                    KnowledgeUserModel.model_validate(
+                        {
+                            **KnowledgeModel.model_validate(knowledge).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
                 )
-                for knowledge in db.query(Knowledge)
-                .order_by(Knowledge.updated_at.desc())
-                .all()
-            ]
+            return knowledge_bases
 
     def get_knowledge_bases_by_user_id(
         self, user_id: str, permission: str = "write"

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

@@ -175,15 +175,18 @@ class ModelsTable:
 
     def get_models(self) -> list[ModelUserResponse]:
         with get_db() as db:
-            return [
-                ModelUserResponse.model_validate(
-                    {
-                        **ModelModel.model_validate(model).model_dump(),
-                        "user": Users.get_user_by_id(model.user_id).model_dump(),
-                    }
+            models = []
+            for model in db.query(Model).filter(Model.base_model_id != None).all():
+                user = Users.get_user_by_id(model.user_id)
+                models.append(
+                    ModelUserResponse.model_validate(
+                        {
+                            **ModelModel.model_validate(model).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
                 )
-                for model in db.query(Model).filter(Model.base_model_id != None).all()
-            ]
+            return models
 
     def get_base_models(self) -> list[ModelModel]:
         with get_db() as db:

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

@@ -103,15 +103,20 @@ class PromptsTable:
 
     def get_prompts(self) -> list[PromptUserResponse]:
         with get_db() as db:
-            return [
-                PromptUserResponse.model_validate(
-                    {
-                        **PromptModel.model_validate(prompt).model_dump(),
-                        "user": Users.get_user_by_id(prompt.user_id).model_dump(),
-                    }
+            prompts = []
+
+            for prompt in db.query(Prompt).order_by(Prompt.timestamp.desc()).all():
+                user = Users.get_user_by_id(prompt.user_id)
+                prompts.append(
+                    PromptUserResponse.model_validate(
+                        {
+                            **PromptModel.model_validate(prompt).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
                 )
-                for prompt in db.query(Prompt).all()
-            ]
+
+            return prompts
 
     def get_prompts_by_user_id(
         self, user_id: str, permission: str = "write"

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

@@ -76,6 +76,10 @@ class ToolModel(BaseModel):
 ####################
 
 
+class ToolUserModel(ToolModel):
+    user: Optional[UserResponse] = None
+
+
 class ToolResponse(BaseModel):
     id: str
     user_id: str
@@ -138,21 +142,24 @@ class ToolsTable:
         except Exception:
             return None
 
-    def get_tools(self) -> list[ToolUserResponse]:
+    def get_tools(self) -> list[ToolUserModel]:
         with get_db() as db:
-            return [
-                ToolUserResponse.model_validate(
-                    {
-                        **ToolModel.model_validate(tool).model_dump(),
-                        "user": Users.get_user_by_id(tool.user_id).model_dump(),
-                    }
+            tools = []
+            for tool in db.query(Tool).order_by(Tool.updated_at.desc()).all():
+                user = Users.get_user_by_id(tool.user_id)
+                tools.append(
+                    ToolUserModel.model_validate(
+                        {
+                            **ToolModel.model_validate(tool).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
                 )
-                for tool in db.query(Tool).order_by(Tool.updated_at.desc()).all()
-            ]
+            return tools
 
     def get_tools_by_user_id(
         self, user_id: str, permission: str = "write"
-    ) -> list[ToolUserResponse]:
+    ) -> list[ToolUserModel]:
         tools = self.get_tools()
 
         return [

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

@@ -238,10 +238,16 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
 
             user = Users.get_user_by_email(mail)
             if not user:
-
                 try:
-                    hashed = get_password_hash(form_data.password)
-                    user = Auths.insert_new_auth(mail, hashed, cn)
+                    role = (
+                        "admin"
+                        if Users.get_num_users() == 0
+                        else request.app.state.config.DEFAULT_USER_ROLE
+                    )
+
+                    user = Auths.insert_new_auth(
+                        email=mail, password=str(uuid.uuid4()), name=cn, role=role
+                    )
 
                     if not user:
                         raise HTTPException(
@@ -253,7 +259,7 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm):
                 except Exception as err:
                     raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
 
-            user = Auths.authenticate_user(mail, password=str(form_data.password))
+            user = Auths.authenticate_user_by_trusted_header(mail)
 
             if user:
                 token = create_token(
@@ -738,8 +744,8 @@ async def update_ldap_config(
 
 # create api key
 @router.post("/api_key", response_model=ApiKey)
-async def create_api_key(request: Request, user=Depends(get_current_user)):
-    if not request.app.config.state.ENABLE_API_KEY:
+async def generate_api_key(request: Request, user=Depends(get_current_user)):
+    if not request.app.state.config.ENABLE_API_KEY:
         raise HTTPException(
             status.HTTP_403_FORBIDDEN,
             detail=ERROR_MESSAGES.API_KEY_CREATION_NOT_ALLOWED,

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

@@ -1,10 +1,12 @@
-from open_webui.config import BannerModel
 from fastapi import APIRouter, Depends, Request
 from pydantic import BaseModel
+
+from typing import Optional
+
 from open_webui.utils.utils import get_admin_user, get_verified_user
-
-
 from open_webui.config import get_config, save_config
+from open_webui.config import BannerModel
+
 
 router = APIRouter()
 
@@ -34,8 +36,32 @@ async def export_config(user=Depends(get_admin_user)):
     return get_config()
 
 
-class SetDefaultModelsForm(BaseModel):
-    models: str
+############################
+# SetDefaultModels
+############################
+class ModelsConfigForm(BaseModel):
+    DEFAULT_MODELS: Optional[str]
+    MODEL_ORDER_LIST: Optional[list[str]]
+
+
+@router.get("/models", response_model=ModelsConfigForm)
+async def get_models_config(request: Request, user=Depends(get_admin_user)):
+    return {
+        "DEFAULT_MODELS": request.app.state.config.DEFAULT_MODELS,
+        "MODEL_ORDER_LIST": request.app.state.config.MODEL_ORDER_LIST,
+    }
+
+
+@router.post("/models", response_model=ModelsConfigForm)
+async def set_models_config(
+    request: Request, form_data: ModelsConfigForm, user=Depends(get_admin_user)
+):
+    request.app.state.config.DEFAULT_MODELS = form_data.DEFAULT_MODELS
+    request.app.state.config.MODEL_ORDER_LIST = form_data.MODEL_ORDER_LIST
+    return {
+        "DEFAULT_MODELS": request.app.state.config.DEFAULT_MODELS,
+        "MODEL_ORDER_LIST": request.app.state.config.MODEL_ORDER_LIST,
+    }
 
 
 class PromptSuggestion(BaseModel):
@@ -47,21 +73,8 @@ class SetDefaultSuggestionsForm(BaseModel):
     suggestions: list[PromptSuggestion]
 
 
-############################
-# SetDefaultModels
-############################
-
-
-@router.post("/default/models", response_model=str)
-async def set_global_default_models(
-    request: Request, form_data: SetDefaultModelsForm, user=Depends(get_admin_user)
-):
-    request.app.state.config.DEFAULT_MODELS = form_data.models
-    return request.app.state.config.DEFAULT_MODELS
-
-
-@router.post("/default/suggestions", response_model=list[PromptSuggestion])
-async def set_global_default_suggestions(
+@router.post("/suggestions", response_model=list[PromptSuggestion])
+async def set_default_suggestions(
     request: Request,
     form_data: SetDefaultSuggestionsForm,
     user=Depends(get_admin_user),

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

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

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

@@ -56,7 +56,7 @@ def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
             FileForm(
                 **{
                     "id": id,
-                    "filename": filename,
+                    "filename": name,
                     "path": file_path,
                     "meta": {
                         "name": name,

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

@@ -43,6 +43,7 @@ async def get_knowledge(user=Depends(get_verified_user)):
         knowledge_bases = Knowledges.get_knowledge_bases_by_user_id(user.id, "read")
 
     # Get files for each knowledge base
+    knowledge_with_files = []
     for knowledge_base in knowledge_bases:
         files = []
         if knowledge_base.data:
@@ -70,12 +71,14 @@ async def get_knowledge(user=Depends(get_verified_user)):
 
                     files = Files.get_file_metadatas_by_ids(file_ids)
 
-        knowledge_base = KnowledgeResponse(
-            **knowledge_base.model_dump(),
-            files=files,
+        knowledge_with_files.append(
+            KnowledgeUserResponse(
+                **knowledge_base.model_dump(),
+                files=files,
+            )
         )
 
-    return knowledge_bases
+    return knowledge_with_files
 
 
 @router.get("/list", response_model=list[KnowledgeUserResponse])
@@ -88,6 +91,7 @@ async def get_knowledge_list(user=Depends(get_verified_user)):
         knowledge_bases = Knowledges.get_knowledge_bases_by_user_id(user.id, "write")
 
     # Get files for each knowledge base
+    knowledge_with_files = []
     for knowledge_base in knowledge_bases:
         files = []
         if knowledge_base.data:
@@ -115,12 +119,13 @@ async def get_knowledge_list(user=Depends(get_verified_user)):
 
                     files = Files.get_file_metadatas_by_ids(file_ids)
 
-        knowledge_base = KnowledgeResponse(
-            **knowledge_base.model_dump(),
-            files=files,
+        knowledge_with_files.append(
+            KnowledgeUserResponse(
+                **knowledge_base.model_dump(),
+                files=files,
+            )
         )
-
-    return knowledge_bases
+    return knowledge_with_files
 
 
 ############################

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

@@ -83,7 +83,8 @@ async def create_new_model(
 ###########################
 
 
-@router.get("/id/{id}", response_model=Optional[ModelResponse])
+# Note: We're not using the typical url path param here, but instead using a query parameter to allow '/' in the id
+@router.get("/model", response_model=Optional[ModelResponse])
 async def get_model_by_id(id: str, user=Depends(get_verified_user)):
     model = Models.get_model_by_id(id)
     if model:
@@ -105,7 +106,7 @@ async def get_model_by_id(id: str, user=Depends(get_verified_user)):
 ############################
 
 
-@router.post("/id/{id}/toggle", response_model=Optional[ModelResponse])
+@router.post("/model/toggle", response_model=Optional[ModelResponse])
 async def toggle_model_by_id(id: str, user=Depends(get_verified_user)):
     model = Models.get_model_by_id(id)
     if model:
@@ -140,7 +141,7 @@ async def toggle_model_by_id(id: str, user=Depends(get_verified_user)):
 ############################
 
 
-@router.post("/id/{id}/update", response_model=Optional[ModelModel])
+@router.post("/model/update", response_model=Optional[ModelModel])
 async def update_model_by_id(
     id: str,
     form_data: ModelForm,
@@ -163,7 +164,7 @@ async def update_model_by_id(
 ############################
 
 
-@router.delete("/id/{id}/delete", response_model=bool)
+@router.delete("/model/delete", response_model=bool)
 async def delete_model_by_id(id: str, user=Depends(get_verified_user)):
     model = Models.get_model_by_id(id)
     if not model:

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

@@ -1,4 +1,3 @@
-import os
 from pathlib import Path
 from typing import Optional
 
@@ -10,7 +9,7 @@ from open_webui.apps.webui.models.tools import (
     Tools,
 )
 from open_webui.apps.webui.utils import load_tools_module_by_id, replace_imports
-from open_webui.config import CACHE_DIR, DATA_DIR
+from open_webui.config import CACHE_DIR
 from open_webui.constants import ERROR_MESSAGES
 from fastapi import APIRouter, Depends, HTTPException, Request, status
 from open_webui.utils.tools import get_tools_specs
@@ -300,38 +299,35 @@ async def update_tools_valves_by_id(
     request: Request, id: str, form_data: dict, user=Depends(get_verified_user)
 ):
     tools = Tools.get_tool_by_id(id)
-    if tools:
-        if id in request.app.state.TOOLS:
-            tools_module = request.app.state.TOOLS[id]
-        else:
-            tools_module, _ = load_tools_module_by_id(id)
-            request.app.state.TOOLS[id] = tools_module
-
-        if hasattr(tools_module, "Valves"):
-            Valves = tools_module.Valves
-
-            try:
-                form_data = {k: v for k, v in form_data.items() if v is not None}
-                valves = Valves(**form_data)
-                Tools.update_tool_valves_by_id(id, valves.model_dump())
-                return valves.model_dump()
-            except Exception as e:
-                print(e)
-                raise HTTPException(
-                    status_code=status.HTTP_400_BAD_REQUEST,
-                    detail=ERROR_MESSAGES.DEFAULT(str(e)),
-                )
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
-
-    else:
+    if not tools:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=ERROR_MESSAGES.NOT_FOUND,
         )
+    if id in request.app.state.TOOLS:
+        tools_module = request.app.state.TOOLS[id]
+    else:
+        tools_module, _ = load_tools_module_by_id(id)
+        request.app.state.TOOLS[id] = tools_module
+
+    if not hasattr(tools_module, "Valves"):
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.NOT_FOUND,
+        )
+    Valves = tools_module.Valves
+
+    try:
+        form_data = {k: v for k, v in form_data.items() if v is not None}
+        valves = Valves(**form_data)
+        Tools.update_tool_valves_by_id(id, valves.model_dump())
+        return valves.model_dump()
+    except Exception as e:
+        print(e)
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(str(e)),
+        )
 
 
 ############################

backend/open_webui/apps/webui/utils.py

@@ -5,10 +5,15 @@ import sys
 from importlib import util
 import types
 import tempfile
+import logging
 
+from open_webui.env import SRC_LOG_LEVELS
 from open_webui.apps.webui.models.functions import Functions
 from open_webui.apps.webui.models.tools import Tools
 
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
+
 
 def extract_frontmatter(content):
     """
@@ -95,7 +100,7 @@ def load_tools_module_by_id(toolkit_id, content=None):
         # Executing the modified content in the created module's namespace
         exec(content, module.__dict__)
         frontmatter = extract_frontmatter(content)
-        print(f"Loaded module: {module.__name__}")
+        log.info(f"Loaded module: {module.__name__}")
 
         # Create and return the object if the class 'Tools' is found in the module
         if hasattr(module, "Tools"):
@@ -103,7 +108,7 @@ def load_tools_module_by_id(toolkit_id, content=None):
         else:
             raise Exception("No Tools class found in the module")
     except Exception as e:
-        print(f"Error loading module: {toolkit_id}: {e}")
+        log.error(f"Error loading module: {toolkit_id}: {e}")
         del sys.modules[module_name]  # Clean up
         raise e
     finally:
@@ -139,7 +144,7 @@ def load_function_module_by_id(function_id, content=None):
         # Execute the modified content in the created module's namespace
         exec(content, module.__dict__)
         frontmatter = extract_frontmatter(content)
-        print(f"Loaded module: {module.__name__}")
+        log.info(f"Loaded module: {module.__name__}")
 
         # Create appropriate object based on available class type in the module
         if hasattr(module, "Pipe"):
@@ -151,7 +156,7 @@ def load_function_module_by_id(function_id, content=None):
         else:
             raise Exception("No Function class found in the module")
     except Exception as e:
-        print(f"Error loading module: {function_id}: {e}")
+        log.error(f"Error loading module: {function_id}: {e}")
         del sys.modules[module_name]  # Cleanup by removing the module in case of error
 
         Functions.update_function_by_id(function_id, {"is_active": False})
@@ -164,7 +169,7 @@ def install_frontmatter_requirements(requirements):
     if requirements:
         req_list = [req.strip() for req in requirements.split(",")]
         for req in req_list:
-            print(f"Installing requirement: {req}")
+            log.info(f"Installing requirement: {req}")
             subprocess.check_call([sys.executable, "-m", "pip", "install", req])
     else:
-        print("No requirements found in frontmatter.")
+        log.info("No requirements found in frontmatter.")

backend/open_webui/config.py

@@ -583,6 +583,12 @@ OLLAMA_API_BASE_URL = os.environ.get(
 )
 
 OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
+if OLLAMA_BASE_URL:
+    # Remove trailing slash
+    OLLAMA_BASE_URL = (
+        OLLAMA_BASE_URL[:-1] if OLLAMA_BASE_URL.endswith("/") else OLLAMA_BASE_URL
+    )
+
 
 K8S_FLAG = os.environ.get("K8S_FLAG", "")
 USE_OLLAMA_DOCKER = os.environ.get("USE_OLLAMA_DOCKER", "false")
@@ -696,6 +702,7 @@ ENABLE_LOGIN_FORM = PersistentConfig(
     os.environ.get("ENABLE_LOGIN_FORM", "True").lower() == "true",
 )
 
+
 DEFAULT_LOCALE = PersistentConfig(
     "DEFAULT_LOCALE",
     "ui.default_locale",
@@ -740,13 +747,18 @@ DEFAULT_PROMPT_SUGGESTIONS = PersistentConfig(
     ],
 )
 
+MODEL_ORDER_LIST = PersistentConfig(
+    "MODEL_ORDER_LIST",
+    "ui.model_order_list",
+    [],
+)
+
 DEFAULT_USER_ROLE = PersistentConfig(
     "DEFAULT_USER_ROLE",
     "ui.default_user_role",
     os.getenv("DEFAULT_USER_ROLE", "pending"),
 )
 
-
 USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS = (
     os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS", "False").lower()
     == "true"
@@ -969,19 +981,20 @@ QUERY_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
 )
 
 DEFAULT_QUERY_GENERATION_PROMPT_TEMPLATE = """### Task:
-Based on the chat history, determine whether a search is necessary, and if so, generate a 1-3 broad search queries to retrieve comprehensive and updated information. If no search is required, return an empty list.
+Analyze the chat history to determine the necessity of generating search queries, in the given language. By default, **prioritize generating 1-3 broad and relevant search queries** unless it is absolutely certain that no additional information is required. The aim is to retrieve comprehensive, updated, and valuable information even with minimal uncertainty. If no search is unequivocally needed, return an empty list.
 
 ### Guidelines:
-- Respond exclusively with a JSON object.
-- If a search query is needed, return an object like: { "queries": ["query1", "query2"] } where each query is distinct and concise.
-- If no search query is necessary, output should be: { "queries": [] }
-- Default to suggesting a search query to ensure accurate and updated information, unless it is definitively clear no search is required.
-- Be concise, focusing strictly on composing search queries with no additional commentary or text.
-- When in doubt, prefer to suggest a search for comprehensiveness.
-- Today's date is: {{CURRENT_DATE}}
+- Respond **EXCLUSIVELY** with a JSON object. Any form of extra commentary, explanation, or additional text is strictly prohibited.
+- When generating search queries, respond in the format: { "queries": ["query1", "query2"] }, ensuring each query is distinct, concise, and relevant to the topic.
+- If and only if it is entirely certain that no useful results can be retrieved by a search, return: { "queries": [] }.
+- Err on the side of suggesting search queries if there is **any chance** they might provide useful or updated information.
+- Be concise and focused on composing high-quality search queries, avoiding unnecessary elaboration, commentary, or assumptions.
+- Today's date is: {{CURRENT_DATE}}.
+- Always prioritize providing actionable and broad queries that maximize informational coverage.
 
 ### Output:
-JSON format: {
+Strictly return in JSON format: 
+{
   "queries": ["query1", "query2"]
 }
 
@@ -991,6 +1004,66 @@ JSON format: {
 </chat_history>
 """
 
+ENABLE_AUTOCOMPLETE_GENERATION = PersistentConfig(
+    "ENABLE_AUTOCOMPLETE_GENERATION",
+    "task.autocomplete.enable",
+    os.environ.get("ENABLE_AUTOCOMPLETE_GENERATION", "True").lower() == "true",
+)
+
+AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = PersistentConfig(
+    "AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH",
+    "task.autocomplete.input_max_length",
+    int(os.environ.get("AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH", "-1")),
+)
+
+AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE",
+    "task.autocomplete.prompt_template",
+    os.environ.get("AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE", ""),
+)
+
+
+DEFAULT_AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE = """### Task:
+You are an autocompletion system. Continue the text in `<text>` based on the **completion type** in `<type>` and the given language.  
+
+### **Instructions**:
+1. Analyze `<text>` for context and meaning.  
+2. Use `<type>` to guide your output:  
+   - **General**: Provide a natural, concise continuation.  
+   - **Search Query**: Complete as if generating a realistic search query.  
+3. Start as if you are directly continuing `<text>`. Do **not** repeat, paraphrase, or respond as a model. Simply complete the text.  
+4. Ensure the continuation:
+   - Flows naturally from `<text>`.  
+   - Avoids repetition, overexplaining, or unrelated ideas.  
+5. If unsure, return: `{ "text": "" }`.  
+
+### **Output Rules**:
+- Respond only in JSON format: `{ "text": "<your_completion>" }`.
+
+### **Examples**:
+#### Example 1:  
+Input:  
+<type>General</type>  
+<text>The sun was setting over the horizon, painting the sky</text>  
+Output:  
+{ "text": "with vibrant shades of orange and pink." }
+
+#### Example 2:  
+Input:  
+<type>Search Query</type>  
+<text>Top-rated restaurants in</text>  
+Output:  
+{ "text": "New York City for Italian cuisine." }  
+
+---
+### Context:
+<chat_history>
+{{MESSAGES:END:6}}
+</chat_history>
+<type>{{TYPE}}</type>  
+<text>{{PROMPT}}</text>  
+#### Output:
+"""
 
 TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
     "TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE",
@@ -1181,21 +1254,32 @@ CHUNK_OVERLAP = PersistentConfig(
     int(os.environ.get("CHUNK_OVERLAP", "100")),
 )
 
-DEFAULT_RAG_TEMPLATE = """You are given a user query, some textual context and rules, all inside xml tags. You have to answer the query based on the context while respecting the rules.
+DEFAULT_RAG_TEMPLATE = """### Task:
+Respond to the user query using the provided context, incorporating inline citations in the format [source_id] **only when the <source_id> tag is explicitly provided** in the context.
+
+### Guidelines:
+- If you don't know the answer, clearly state that.
+- If uncertain, ask the user for clarification.
+- Respond in the same language as the user's query.
+- If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
+- If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
+- **Only include inline citations using [source_id] when a <source_id> tag is explicitly provided in the context.**  
+- Do not cite if the <source_id> tag is not provided in the context.  
+- Do not use XML tags in your response.
+- Ensure citations are concise and directly related to the information provided.
+
+### Example of Citation:
+If the user asks about a specific topic and the information is found in "whitepaper.pdf" with a provided <source_id>, the response should include the citation like so:  
+* "According to the study, the proposed method increases efficiency by 20% [whitepaper.pdf]."
+If no <source_id> is present, the response should omit the citation.
+
+### Output:
+Provide a clear and direct response to the user's query, including inline citations in the format [source_id] only when the <source_id> tag is present in the context.
 
 <context>
 {{CONTEXT}}
 </context>
 
-<rules>
-- If you don't know, just say so.
-- If you are not sure, ask for clarification.
-- Answer in the same language as the user query.
-- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
-- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
-- Answer directly and without using xml tags.
-</rules>
-
 <user_query>
 {{QUERY}}
 </user_query>
@@ -1241,6 +1325,12 @@ YOUTUBE_LOADER_LANGUAGE = PersistentConfig(
     os.getenv("YOUTUBE_LOADER_LANGUAGE", "en").split(","),
 )
 
+YOUTUBE_LOADER_PROXY_URL = PersistentConfig(
+    "YOUTUBE_LOADER_PROXY_URL",
+    "rag.youtube_loader_proxy_url",
+    os.getenv("YOUTUBE_LOADER_PROXY_URL", ""),
+)
+
 
 ENABLE_RAG_WEB_SEARCH = PersistentConfig(
     "ENABLE_RAG_WEB_SEARCH",
@@ -1290,6 +1380,12 @@ BRAVE_SEARCH_API_KEY = PersistentConfig(
     os.getenv("BRAVE_SEARCH_API_KEY", ""),
 )
 
+MOJEEK_SEARCH_API_KEY = PersistentConfig(
+    "MOJEEK_SEARCH_API_KEY",
+    "rag.web.search.mojeek_search_api_key",
+    os.getenv("MOJEEK_SEARCH_API_KEY", ""),
+)
+
 SERPSTACK_API_KEY = PersistentConfig(
     "SERPSTACK_API_KEY",
     "rag.web.search.serpstack_api_key",

backend/open_webui/constants.py

@@ -113,5 +113,6 @@ class TASKS(str, Enum):
     TAGS_GENERATION = "tags_generation"
     EMOJI_GENERATION = "emoji_generation"
     QUERY_GENERATION = "query_generation"
+    AUTOCOMPLETE_GENERATION = "autocomplete_generation"
     FUNCTION_CALLING = "function_calling"
     MOA_RESPONSE_GENERATION = "moa_response_generation"

backend/open_webui/env.py

@@ -329,6 +329,9 @@ WEBUI_AUTH_TRUSTED_EMAIL_HEADER = os.environ.get(
 )
 WEBUI_AUTH_TRUSTED_NAME_HEADER = os.environ.get("WEBUI_AUTH_TRUSTED_NAME_HEADER", None)
 
+BYPASS_MODEL_ACCESS_CONTROL = (
+    os.environ.get("BYPASS_MODEL_ACCESS_CONTROL", "False").lower() == "true"
+)
 
 ####################################
 # WEBUI_SECRET_KEY
@@ -373,7 +376,7 @@ else:
         AIOHTTP_CLIENT_TIMEOUT = 300
 
 AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = os.environ.get(
-    "AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", "3"
+    "AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", "5"
 )
 
 if AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST == "":
@@ -384,7 +387,7 @@ else:
             AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST
         )
     except Exception:
-        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = 3
+        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = 5
 
 ####################################
 # OFFLINE_MODE

backend/open_webui/main.py

@@ -49,7 +49,9 @@ from open_webui.apps.openai.main import (
     get_all_models_responses as get_openai_models_responses,
 )
 from open_webui.apps.retrieval.main import app as retrieval_app
-from open_webui.apps.retrieval.utils import get_rag_context, rag_template
+from open_webui.apps.retrieval.utils import get_sources_from_files
+
+
 from open_webui.apps.socket.main import (
     app as socket_app,
     periodic_usage_pool_cleanup,
@@ -87,6 +89,10 @@ from open_webui.config import (
     DEFAULT_QUERY_GENERATION_PROMPT_TEMPLATE,
     TITLE_GENERATION_PROMPT_TEMPLATE,
     TAGS_GENERATION_PROMPT_TEMPLATE,
+    ENABLE_AUTOCOMPLETE_GENERATION,
+    AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH,
+    AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE,
+    DEFAULT_AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE,
     TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE,
     WEBHOOK_URL,
     WEBUI_AUTH,
@@ -106,6 +112,7 @@ from open_webui.env import (
     WEBUI_SESSION_COOKIE_SAME_SITE,
     WEBUI_SESSION_COOKIE_SECURE,
     WEBUI_URL,
+    BYPASS_MODEL_ACCESS_CONTROL,
     RESET_CONFIG_ON_START,
     OFFLINE_MODE,
 )
@@ -122,11 +129,13 @@ from open_webui.utils.response import (
 )
 from open_webui.utils.security_headers import SecurityHeadersMiddleware
 from open_webui.utils.task import (
-    moa_response_generation_template,
-    tags_generation_template,
-    query_generation_template,
-    emoji_generation_template,
+    rag_template,
     title_generation_template,
+    query_generation_template,
+    autocomplete_generation_template,
+    tags_generation_template,
+    emoji_generation_template,
+    moa_response_generation_template,
     tools_function_calling_generation_template,
 )
 from open_webui.utils.tools import get_tools
@@ -204,6 +213,11 @@ app.state.config.TASK_MODEL_EXTERNAL = TASK_MODEL_EXTERNAL
 
 app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE = TITLE_GENERATION_PROMPT_TEMPLATE
 
+app.state.config.ENABLE_AUTOCOMPLETE_GENERATION = ENABLE_AUTOCOMPLETE_GENERATION
+app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = (
+    AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH
+)
+
 app.state.config.ENABLE_TAGS_GENERATION = ENABLE_TAGS_GENERATION
 app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE = TAGS_GENERATION_PROMPT_TEMPLATE
 
@@ -212,6 +226,10 @@ app.state.config.ENABLE_SEARCH_QUERY_GENERATION = ENABLE_SEARCH_QUERY_GENERATION
 app.state.config.ENABLE_RETRIEVAL_QUERY_GENERATION = ENABLE_RETRIEVAL_QUERY_GENERATION
 app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE = QUERY_GENERATION_PROMPT_TEMPLATE
 
+app.state.config.AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE = (
+    AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE
+)
+
 app.state.config.TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = (
     TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE
 )
@@ -380,8 +398,7 @@ async def chat_completion_tools_handler(
         return body, {}
 
     skip_files = False
-    contexts = []
-    citations = []
+    sources = []
 
     task_model_id = get_task_model_id(
         body["model"],
@@ -463,21 +480,39 @@ async def chat_completion_tools_handler(
             except Exception as e:
                 tool_output = str(e)
 
-            if tools[tool_function_name]["citation"]:
-                citations.append(
-                    {
-                        "source": {
-                            "name": f"TOOL:{tools[tool_function_name]['toolkit_id']}/{tool_function_name}"
-                        },
-                        "document": [tool_output],
-                        "metadata": [{"source": tool_function_name}],
-                    }
-                )
-            if tools[tool_function_name]["file_handler"]:
-                skip_files = True
+            print(tools[tool_function_name]["citation"])
 
             if isinstance(tool_output, str):
-                contexts.append(tool_output)
+                if tools[tool_function_name]["citation"]:
+                    sources.append(
+                        {
+                            "source": {
+                                "name": f"TOOL:{tools[tool_function_name]['toolkit_id']}/{tool_function_name}"
+                            },
+                            "document": [tool_output],
+                            "metadata": [
+                                {
+                                    "source": f"TOOL:{tools[tool_function_name]['toolkit_id']}/{tool_function_name}"
+                                }
+                            ],
+                        }
+                    )
+                else:
+                    sources.append(
+                        {
+                            "source": {},
+                            "document": [tool_output],
+                            "metadata": [
+                                {
+                                    "source": f"TOOL:{tools[tool_function_name]['toolkit_id']}/{tool_function_name}"
+                                }
+                            ],
+                        }
+                    )
+
+                if tools[tool_function_name]["file_handler"]:
+                    skip_files = True
+
         except Exception as e:
             log.exception(f"Error: {e}")
             content = None
@@ -485,47 +520,51 @@ async def chat_completion_tools_handler(
         log.exception(f"Error: {e}")
         content = None
 
-    log.debug(f"tool_contexts: {contexts}")
+    log.debug(f"tool_contexts: {sources}")
 
     if skip_files and "files" in body.get("metadata", {}):
         del body["metadata"]["files"]
 
-    return body, {"contexts": contexts, "citations": citations}
+    return body, {"sources": sources}
 
 
 async def chat_completion_files_handler(
     body: dict, user: UserModel
 ) -> tuple[dict, dict[str, list]]:
-    contexts = []
-    citations = []
-
-    try:
-        queries_response = await generate_queries(
-            {
-                "model": body["model"],
-                "messages": body["messages"],
-                "type": "retrieval",
-            },
-            user,
-        )
-        queries_response = queries_response["choices"][0]["message"]["content"]
-
-        try:
-            queries_response = json.loads(queries_response)
-        except Exception as e:
-            queries_response = {"queries": []}
-
-        queries = queries_response.get("queries", [])
-    except Exception as e:
-        queries = []
-
-    if len(queries) == 0:
-        queries = [get_last_user_message(body["messages"])]
-
-    print(f"{queries=}")
+    sources = []
 
     if files := body.get("metadata", {}).get("files", None):
-        contexts, citations = get_rag_context(
+        try:
+            queries_response = await generate_queries(
+                {
+                    "model": body["model"],
+                    "messages": body["messages"],
+                    "type": "retrieval",
+                },
+                user,
+            )
+            queries_response = queries_response["choices"][0]["message"]["content"]
+
+            try:
+                bracket_start = queries_response.find("{")
+                bracket_end = queries_response.rfind("}") + 1
+
+                if bracket_start == -1 or bracket_end == -1:
+                    raise Exception("No JSON object found in the response")
+
+                queries_response = queries_response[bracket_start:bracket_end]
+                queries_response = json.loads(queries_response)
+            except Exception as e:
+                queries_response = {"queries": [queries_response]}
+
+            queries = queries_response.get("queries", [])
+        except Exception as e:
+            queries = []
+
+        if len(queries) == 0:
+            queries = [get_last_user_message(body["messages"])]
+
+        sources = get_sources_from_files(
             files=files,
             queries=queries,
             embedding_function=retrieval_app.state.EMBEDDING_FUNCTION,
@@ -535,9 +574,8 @@ async def chat_completion_files_handler(
             hybrid_search=retrieval_app.state.config.ENABLE_RAG_HYBRID_SEARCH,
         )
 
-        log.debug(f"rag_contexts: {contexts}, citations: {citations}")
-
-    return body, {"contexts": contexts, "citations": citations}
+        log.debug(f"rag_contexts:sources: {sources}")
+    return body, {"sources": sources}
 
 
 def is_chat_completion_request(request):
@@ -584,7 +622,7 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
             )
 
         model_info = Models.get_model_by_id(model["id"])
-        if user.role == "user":
+        if user.role == "user" and not BYPASS_MODEL_ACCESS_CONTROL:
             if model.get("arena"):
                 if not has_access(
                     user.id,
@@ -638,8 +676,7 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
         # Initialize data_items to store additional data to be sent to the client
         # Initialize contexts and citation
         data_items = []
-        contexts = []
-        citations = []
+        sources = []
 
         try:
             body, flags = await chat_completion_filter_functions_handler(
@@ -665,21 +702,37 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
             body, flags = await chat_completion_tools_handler(
                 body, user, models, extra_params
             )
-            contexts.extend(flags.get("contexts", []))
-            citations.extend(flags.get("citations", []))
+            sources.extend(flags.get("sources", []))
         except Exception as e:
             log.exception(e)
 
         try:
             body, flags = await chat_completion_files_handler(body, user)
-            contexts.extend(flags.get("contexts", []))
-            citations.extend(flags.get("citations", []))
+            sources.extend(flags.get("sources", []))
         except Exception as e:
             log.exception(e)
 
         # If context is not empty, insert it into the messages
-        if len(contexts) > 0:
-            context_string = "/n".join(contexts).strip()
+        if len(sources) > 0:
+            context_string = ""
+            for source_idx, source in enumerate(sources):
+                source_id = source.get("source", {}).get("name", "")
+
+                if "document" in source:
+                    for doc_idx, doc_context in enumerate(source["document"]):
+                        metadata = source.get("metadata")
+                        doc_source_id = None
+
+                        if metadata:
+                            doc_source_id = metadata[doc_idx].get("source", source_id)
+
+                        if source_id:
+                            context_string += f"<source><source_id>{doc_source_id if doc_source_id is not None else source_id}</source_id><source_context>{doc_context}</source_context></source>\n"
+                        else:
+                            # If there is no source_id, then do not include the source_id tag
+                            context_string += f"<source><source_context>{doc_context}</source_context></source>\n"
+
+            context_string = context_string.strip()
             prompt = get_last_user_message(body["messages"])
 
             if prompt is None:
@@ -710,8 +763,11 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
                 )
 
         # If there are citations, add them to the data_items
-        if len(citations) > 0:
-            data_items.append({"citations": citations})
+        sources = [
+            source for source in sources if source.get("source", {}).get("name", "")
+        ]
+        if len(sources) > 0:
+            data_items.append({"sources": sources})
 
         modified_body_bytes = json.dumps(body).encode("utf-8")
         # Replace the request body with the modified one
@@ -855,6 +911,11 @@ class PipelineMiddleware(BaseHTTPMiddleware):
                     status_code=status.HTTP_401_UNAUTHORIZED,
                     content={"detail": "Not authenticated"},
                 )
+        except HTTPException as e:
+            return JSONResponse(
+                status_code=e.status_code,
+                content={"detail": e.detail},
+            )
 
         model_list = await get_all_models()
         models = {model["id"]: model for model in model_list}
@@ -932,7 +993,7 @@ app.add_middleware(SecurityHeadersMiddleware)
 @app.middleware("http")
 async def commit_session_after_request(request: Request, call_next):
     response = await call_next(request)
-    log.debug("Commit session after request")
+    # log.debug("Commit session after request")
     Session.commit()
     return response
 
@@ -1015,7 +1076,7 @@ async def get_all_base_models():
     return models
 
 
-@cached(ttl=1)
+@cached(ttl=3)
 async def get_all_models():
     models = await get_all_base_models()
 
@@ -1139,6 +1200,8 @@ async def get_all_models():
             model["actions"].extend(
                 get_action_items_from_module(action_function, function_module)
             )
+    log.debug(f"get_all_models() returned {len(models)} models")
+
     return models
 
 
@@ -1153,8 +1216,16 @@ async def get_models(user=Depends(get_verified_user)):
         if "pipeline" not in model or model["pipeline"].get("type", None) != "filter"
     ]
 
+    model_order_list = webui_app.state.config.MODEL_ORDER_LIST
+    if model_order_list:
+        model_order_dict = {model_id: i for i, model_id in enumerate(model_order_list)}
+        # Sort models by order list priority, with fallback for those not in the list
+        models.sort(
+            key=lambda x: (model_order_dict.get(x["id"], float("inf")), x["name"])
+        )
+
     # Filter out models that the user does not have access to
-    if user.role == "user":
+    if user.role == "user" and not BYPASS_MODEL_ACCESS_CONTROL:
         filtered_models = []
         for model in models:
             if model.get("arena"):
@@ -1176,6 +1247,10 @@ async def get_models(user=Depends(get_verified_user)):
                     filtered_models.append(model)
         models = filtered_models
 
+    log.debug(
+        f"/api/models returned filtered models accessible to the user: {json.dumps([model['id'] for model in models])}"
+    )
+
     return {"data": models}
 
 
@@ -1308,7 +1383,6 @@ async def generate_chat_completions(
 
 @app.post("/api/chat/completed")
 async def chat_completed(form_data: dict, user=Depends(get_verified_user)):
-
     model_list = await get_all_models()
     models = {model["id"]: model for model in model_list}
 
@@ -1606,6 +1680,8 @@ async def get_task_config(user=Depends(get_verified_user)):
         "TASK_MODEL": app.state.config.TASK_MODEL,
         "TASK_MODEL_EXTERNAL": app.state.config.TASK_MODEL_EXTERNAL,
         "TITLE_GENERATION_PROMPT_TEMPLATE": app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE,
+        "ENABLE_AUTOCOMPLETE_GENERATION": app.state.config.ENABLE_AUTOCOMPLETE_GENERATION,
+        "AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH": app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH,
         "TAGS_GENERATION_PROMPT_TEMPLATE": app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE,
         "ENABLE_TAGS_GENERATION": app.state.config.ENABLE_TAGS_GENERATION,
         "ENABLE_SEARCH_QUERY_GENERATION": app.state.config.ENABLE_SEARCH_QUERY_GENERATION,
@@ -1619,6 +1695,8 @@ class TaskConfigForm(BaseModel):
     TASK_MODEL: Optional[str]
     TASK_MODEL_EXTERNAL: Optional[str]
     TITLE_GENERATION_PROMPT_TEMPLATE: str
+    ENABLE_AUTOCOMPLETE_GENERATION: bool
+    AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH: int
     TAGS_GENERATION_PROMPT_TEMPLATE: str
     ENABLE_TAGS_GENERATION: bool
     ENABLE_SEARCH_QUERY_GENERATION: bool
@@ -1634,6 +1712,14 @@ async def update_task_config(form_data: TaskConfigForm, user=Depends(get_admin_u
     app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE = (
         form_data.TITLE_GENERATION_PROMPT_TEMPLATE
     )
+
+    app.state.config.ENABLE_AUTOCOMPLETE_GENERATION = (
+        form_data.ENABLE_AUTOCOMPLETE_GENERATION
+    )
+    app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH = (
+        form_data.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH
+    )
+
     app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE = (
         form_data.TAGS_GENERATION_PROMPT_TEMPLATE
     )
@@ -1656,6 +1742,8 @@ async def update_task_config(form_data: TaskConfigForm, user=Depends(get_admin_u
         "TASK_MODEL": app.state.config.TASK_MODEL,
         "TASK_MODEL_EXTERNAL": app.state.config.TASK_MODEL_EXTERNAL,
         "TITLE_GENERATION_PROMPT_TEMPLATE": app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE,
+        "ENABLE_AUTOCOMPLETE_GENERATION": app.state.config.ENABLE_AUTOCOMPLETE_GENERATION,
+        "AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH": app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH,
         "TAGS_GENERATION_PROMPT_TEMPLATE": app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE,
         "ENABLE_TAGS_GENERATION": app.state.config.ENABLE_TAGS_GENERATION,
         "ENABLE_SEARCH_QUERY_GENERATION": app.state.config.ENABLE_SEARCH_QUERY_GENERATION,
@@ -1667,7 +1755,6 @@ async def update_task_config(form_data: TaskConfigForm, user=Depends(get_admin_u
 
 @app.post("/api/task/title/completions")
 async def generate_title(form_data: dict, user=Depends(get_verified_user)):
-    print("generate_title")
 
     model_list = await get_all_models()
     models = {model["id"]: model for model in model_list}
@@ -1688,9 +1775,9 @@ async def generate_title(form_data: dict, user=Depends(get_verified_user)):
         models,
     )
 
-    print(task_model_id)
-
-    model = models[task_model_id]
+    log.debug(
+        f"generating chat title using model {task_model_id} for user {user.email} "
+    )
 
     if app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE != "":
         template = app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE
@@ -1729,10 +1816,12 @@ Artificial Intelligence in Healthcare
                 "max_completion_tokens": 50,
             }
         ),
-        "chat_id": form_data.get("chat_id", None),
-        "metadata": {"task": str(TASKS.TITLE_GENERATION), "task_body": form_data},
+        "metadata": {
+            "task": str(TASKS.TITLE_GENERATION),
+            "task_body": form_data,
+            "chat_id": form_data.get("chat_id", None),
+        },
     }
-    log.debug(payload)
 
     # Handle pipeline filters
     try:
@@ -1756,7 +1845,7 @@ Artificial Intelligence in Healthcare
 
 @app.post("/api/task/tags/completions")
 async def generate_chat_tags(form_data: dict, user=Depends(get_verified_user)):
-    print("generate_chat_tags")
+
     if not app.state.config.ENABLE_TAGS_GENERATION:
         return JSONResponse(
             status_code=status.HTTP_200_OK,
@@ -1781,7 +1870,10 @@ async def generate_chat_tags(form_data: dict, user=Depends(get_verified_user)):
         app.state.config.TASK_MODEL_EXTERNAL,
         models,
     )
-    print(task_model_id)
+
+    log.debug(
+        f"generating chat tags using model {task_model_id} for user {user.email} "
+    )
 
     if app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE != "":
         template = app.state.config.TAGS_GENERATION_PROMPT_TEMPLATE
@@ -1812,9 +1904,12 @@ JSON format: { "tags": ["tag1", "tag2", "tag3"] }
         "model": task_model_id,
         "messages": [{"role": "user", "content": content}],
         "stream": False,
-        "metadata": {"task": str(TASKS.TAGS_GENERATION), "task_body": form_data},
+        "metadata": {
+            "task": str(TASKS.TAGS_GENERATION),
+            "task_body": form_data,
+            "chat_id": form_data.get("chat_id", None),
+        },
     }
-    log.debug(payload)
 
     # Handle pipeline filters
     try:
@@ -1838,7 +1933,7 @@ JSON format: { "tags": ["tag1", "tag2", "tag3"] }
 
 @app.post("/api/task/queries/completions")
 async def generate_queries(form_data: dict, user=Depends(get_verified_user)):
-    print("generate_queries")
+
     type = form_data.get("type")
     if type == "web_search":
         if not app.state.config.ENABLE_SEARCH_QUERY_GENERATION:
@@ -1871,11 +1966,12 @@ async def generate_queries(form_data: dict, user=Depends(get_verified_user)):
         app.state.config.TASK_MODEL_EXTERNAL,
         models,
     )
-    print(task_model_id)
 
-    model = models[task_model_id]
+    log.debug(
+        f"generating {type} queries using model {task_model_id} for user {user.email}"
+    )
 
-    if app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE != "":
+    if (app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE).strip() != "":
         template = app.state.config.QUERY_GENERATION_PROMPT_TEMPLATE
     else:
         template = DEFAULT_QUERY_GENERATION_PROMPT_TEMPLATE
@@ -1888,9 +1984,96 @@ async def generate_queries(form_data: dict, user=Depends(get_verified_user)):
         "model": task_model_id,
         "messages": [{"role": "user", "content": content}],
         "stream": False,
-        "metadata": {"task": str(TASKS.QUERY_GENERATION), "task_body": form_data},
+        "metadata": {
+            "task": str(TASKS.QUERY_GENERATION),
+            "task_body": form_data,
+            "chat_id": form_data.get("chat_id", None),
+        },
     }
-    log.debug(payload)
+
+    # Handle pipeline filters
+    try:
+        payload = filter_pipeline(payload, user, models)
+    except Exception as e:
+        if len(e.args) > 1:
+            return JSONResponse(
+                status_code=e.args[0],
+                content={"detail": e.args[1]},
+            )
+        else:
+            return JSONResponse(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                content={"detail": str(e)},
+            )
+    if "chat_id" in payload:
+        del payload["chat_id"]
+
+    return await generate_chat_completions(form_data=payload, user=user)
+
+
+@app.post("/api/task/auto/completions")
+async def generate_autocompletion(form_data: dict, user=Depends(get_verified_user)):
+    if not app.state.config.ENABLE_AUTOCOMPLETE_GENERATION:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=f"Autocompletion generation is disabled",
+        )
+
+    type = form_data.get("type")
+    prompt = form_data.get("prompt")
+    messages = form_data.get("messages")
+
+    if app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH > 0:
+        if len(prompt) > app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail=f"Input prompt exceeds maximum length of {app.state.config.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH}",
+            )
+
+    model_list = await get_all_models()
+    models = {model["id"]: model for model in model_list}
+
+    model_id = form_data["model"]
+    if model_id not in models:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Model not found",
+        )
+
+    # Check if the user has a custom task model
+    # If the user has a custom task model, use that model
+    task_model_id = get_task_model_id(
+        model_id,
+        app.state.config.TASK_MODEL,
+        app.state.config.TASK_MODEL_EXTERNAL,
+        models,
+    )
+
+    log.debug(
+        f"generating autocompletion using model {task_model_id} for user {user.email}"
+    )
+
+    if (app.state.config.AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE).strip() != "":
+        template = app.state.config.AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE
+    else:
+        template = DEFAULT_AUTOCOMPLETE_GENERATION_PROMPT_TEMPLATE
+
+    content = autocomplete_generation_template(
+        template, prompt, messages, type, {"name": user.name}
+    )
+
+    payload = {
+        "model": task_model_id,
+        "messages": [{"role": "user", "content": content}],
+        "stream": False,
+        "metadata": {
+            "task": str(TASKS.AUTOCOMPLETE_GENERATION),
+            "task_body": form_data,
+            "chat_id": form_data.get("chat_id", None),
+        },
+    }
+
+    print(payload)
 
     # Handle pipeline filters
     try:
@@ -1914,7 +2097,6 @@ async def generate_queries(form_data: dict, user=Depends(get_verified_user)):
 
 @app.post("/api/task/emoji/completions")
 async def generate_emoji(form_data: dict, user=Depends(get_verified_user)):
-    print("generate_emoji")
 
     model_list = await get_all_models()
     models = {model["id"]: model for model in model_list}
@@ -1934,9 +2116,8 @@ async def generate_emoji(form_data: dict, user=Depends(get_verified_user)):
         app.state.config.TASK_MODEL_EXTERNAL,
         models,
     )
-    print(task_model_id)
 
-    model = models[task_model_id]
+    log.debug(f"generating emoji using model {task_model_id} for user {user.email} ")
 
     template = '''
 Your task is to reflect the speaker's likely facial expression through a fitting emoji. Interpret emotions from the message and reflect their facial expression using fitting, diverse emojis (e.g., 😊, 😢, 😡, 😱).
@@ -1966,7 +2147,6 @@ Message: """{{prompt}}"""
         "chat_id": form_data.get("chat_id", None),
         "metadata": {"task": str(TASKS.EMOJI_GENERATION), "task_body": form_data},
     }
-    log.debug(payload)
 
     # Handle pipeline filters
     try:
@@ -1990,7 +2170,6 @@ Message: """{{prompt}}"""
 
 @app.post("/api/task/moa/completions")
 async def generate_moa_response(form_data: dict, user=Depends(get_verified_user)):
-    print("generate_moa_response")
 
     model_list = await get_all_models()
     models = {model["id"]: model for model in model_list}
@@ -2010,9 +2189,8 @@ async def generate_moa_response(form_data: dict, user=Depends(get_verified_user)
         app.state.config.TASK_MODEL_EXTERNAL,
         models,
     )
-    print(task_model_id)
 
-    model = models[task_model_id]
+    log.debug(f"generating MOA model {task_model_id} for user {user.email} ")
 
     template = """You have been provided with a set of responses from various models to the latest user query: "{{prompt}}"
 
@@ -2036,7 +2214,6 @@ Responses from models: {{responses}}"""
             "task_body": form_data,
         },
     }
-    log.debug(payload)
 
     try:
         payload = filter_pipeline(payload, user, models)
@@ -2071,7 +2248,7 @@ Responses from models: {{responses}}"""
 async def get_pipelines_list(user=Depends(get_admin_user)):
     responses = await get_openai_models_responses()
 
-    print(responses)
+    log.debug(f"get_pipelines_list: get_openai_models_responses returned {responses}")
     urlIdxs = [
         idx
         for idx, response in enumerate(responses)

backend/open_webui/utils/schemas.py

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

backend/open_webui/utils/security_headers.py

@@ -27,6 +27,7 @@ def set_security_headers() -> Dict[str, str]:
     - x-download-options
     - x-frame-options
     - x-permitted-cross-domain-policies
+    - content-security-policy
 
     Each environment variable is associated with a specific setter function
     that constructs the header. If the environment variable is set, the
@@ -45,6 +46,7 @@ def set_security_headers() -> Dict[str, str]:
         "XDOWNLOAD_OPTIONS": set_xdownload_options,
         "XFRAME_OPTIONS": set_xframe,
         "XPERMITTED_CROSS_DOMAIN_POLICIES": set_xpermitted_cross_domain_policies,
+        "CONTENT_SECURITY_POLICY": set_content_security_policy,
     }
 
     for env_var, setter in header_setters.items():
@@ -124,3 +126,8 @@ def set_xpermitted_cross_domain_policies(value: str):
     if not match:
         value = "none"
     return {"X-Permitted-Cross-Domain-Policies": value}
+
+
+# Set Content-Security-Policy response header
+def set_content_security_policy(value: str):
+    return {"Content-Security-Policy": value}

backend/open_webui/utils/task.py

@@ -1,11 +1,20 @@
+import logging
 import math
 import re
 from datetime import datetime
 from typing import Optional
+import uuid
 
 
 from open_webui.utils.misc import get_last_user_message, get_messages_content
 
+from open_webui.env import SRC_LOG_LEVELS
+from open_webui.config import DEFAULT_RAG_TEMPLATE
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
 
 def prompt_template(
     template: str, user_name: Optional[str] = None, user_location: Optional[str] = None
@@ -16,12 +25,14 @@ def prompt_template(
     # Format the date to YYYY-MM-DD
     formatted_date = current_date.strftime("%Y-%m-%d")
     formatted_time = current_date.strftime("%I:%M:%S %p")
+    formatted_weekday = current_date.strftime("%A")
 
     template = template.replace("{{CURRENT_DATE}}", formatted_date)
     template = template.replace("{{CURRENT_TIME}}", formatted_time)
     template = template.replace(
         "{{CURRENT_DATETIME}}", f"{formatted_date} {formatted_time}"
     )
+    template = template.replace("{{CURRENT_WEEKDAY}}", formatted_weekday)
 
     if user_name:
         # Replace {{USER_NAME}} in the template with the user's name
@@ -42,7 +53,9 @@ def prompt_template(
 
 def replace_prompt_variable(template: str, prompt: str) -> str:
     def replacement_function(match):
-        full_match = match.group(0)
+        full_match = match.group(
+            0
+        ).lower()  # Normalize to lowercase for consistent handling
         start_length = match.group(1)
         end_length = match.group(2)
         middle_length = match.group(3)
@@ -62,20 +75,23 @@ def replace_prompt_variable(template: str, prompt: str) -> str:
             return f"{start}...{end}"
         return ""
 
-    template = re.sub(
-        r"{{prompt}}|{{prompt:start:(\d+)}}|{{prompt:end:(\d+)}}|{{prompt:middletruncate:(\d+)}}",
-        replacement_function,
-        template,
-    )
+    # Updated regex pattern to make it case-insensitive with the `(?i)` flag
+    pattern = r"(?i){{prompt}}|{{prompt:start:(\d+)}}|{{prompt:end:(\d+)}}|{{prompt:middletruncate:(\d+)}}"
+    template = re.sub(pattern, replacement_function, template)
     return template
 
 
-def replace_messages_variable(template: str, messages: list[str]) -> str:
+def replace_messages_variable(
+    template: str, messages: Optional[list[str]] = None
+) -> str:
     def replacement_function(match):
         full_match = match.group(0)
         start_length = match.group(1)
         end_length = match.group(2)
         middle_length = match.group(3)
+        # If messages is None, handle it as an empty list
+        if messages is None:
+            return ""
 
         # Process messages based on the number of messages required
         if full_match == "{{MESSAGES}}":
@@ -110,6 +126,44 @@ def replace_messages_variable(template: str, messages: list[str]) -> str:
 # {{prompt:middletruncate:8000}}
 
 
+def rag_template(template: str, context: str, query: str):
+    if template.strip() == "":
+        template = DEFAULT_RAG_TEMPLATE
+
+    if "[context]" not in template and "{{CONTEXT}}" not in template:
+        log.debug(
+            "WARNING: The RAG template does not contain the '[context]' or '{{CONTEXT}}' placeholder."
+        )
+
+    if "<context>" in context and "</context>" in context:
+        log.debug(
+            "WARNING: Potential prompt injection attack: the RAG "
+            "context contains '<context>' and '</context>'. This might be "
+            "nothing, or the user might be trying to hack something."
+        )
+
+    query_placeholders = []
+    if "[query]" in context:
+        query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
+        template = template.replace("[query]", query_placeholder)
+        query_placeholders.append(query_placeholder)
+
+    if "{{QUERY}}" in context:
+        query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
+        template = template.replace("{{QUERY}}", query_placeholder)
+        query_placeholders.append(query_placeholder)
+
+    template = template.replace("[context]", context)
+    template = template.replace("{{CONTEXT}}", context)
+    template = template.replace("[query]", query)
+    template = template.replace("{{QUERY}}", query)
+
+    for query_placeholder in query_placeholders:
+        template = template.replace(query_placeholder, query)
+
+    return template
+
+
 def title_generation_template(
     template: str, messages: list[dict], user: Optional[dict] = None
 ) -> str:
@@ -163,6 +217,28 @@ def emoji_generation_template(
     return template
 
 
+def autocomplete_generation_template(
+    template: str,
+    prompt: str,
+    messages: Optional[list[dict]] = None,
+    type: Optional[str] = None,
+    user: Optional[dict] = None,
+) -> str:
+    template = template.replace("{{TYPE}}", type if type else "")
+    template = replace_prompt_variable(template, prompt)
+    template = replace_messages_variable(template, messages)
+
+    template = prompt_template(
+        template,
+        **(
+            {"user_name": user.get("name"), "user_location": user.get("location")}
+            if user
+            else {}
+        ),
+    )
+    return template
+
+
 def query_generation_template(
     template: str, messages: list[dict], user: Optional[dict] = None
 ) -> str:

backend/open_webui/utils/tools.py

@@ -1,11 +1,14 @@
 import inspect
 import logging
-from typing import Awaitable, Callable, get_type_hints
+import re
+from typing import Any, Awaitable, Callable, get_type_hints
+from functools import update_wrapper, partial
 
+from langchain_core.utils.function_calling import convert_to_openai_function
 from open_webui.apps.webui.models.tools import Tools
 from open_webui.apps.webui.models.users import UserModel
 from open_webui.apps.webui.utils import load_tools_module_by_id
-from open_webui.utils.schemas import json_schema_to_model
+from pydantic import BaseModel, Field, create_model
 
 log = logging.getLogger(__name__)
 
@@ -14,17 +17,16 @@ def apply_extra_params_to_tool_function(
     function: Callable, extra_params: dict
 ) -> Callable[..., Awaitable]:
     sig = inspect.signature(function)
-    extra_params = {
-        key: value for key, value in extra_params.items() if key in sig.parameters
-    }
-    is_coroutine = inspect.iscoroutinefunction(function)
+    extra_params = {k: v for k, v in extra_params.items() if k in sig.parameters}
+    partial_func = partial(function, **extra_params)
+    if inspect.iscoroutinefunction(function):
+        update_wrapper(partial_func, function)
+        return partial_func
 
-    async def new_function(**kwargs):
-        extra_kwargs = kwargs | extra_params
-        if is_coroutine:
-            return await function(**extra_kwargs)
-        return function(**extra_kwargs)
+    async def new_function(*args, **kwargs):
+        return partial_func(*args, **kwargs)
 
+    update_wrapper(new_function, function)
     return new_function
 
 
@@ -55,11 +57,6 @@ def get_tools(
             )
 
         for spec in tools.specs:
-            # TODO: Fix hack for OpenAI API
-            for val in spec.get("parameters", {}).get("properties", {}).values():
-                if val["type"] == "str":
-                    val["type"] = "string"
-
             # Remove internal parameters
             spec["parameters"]["properties"] = {
                 key: val
@@ -72,15 +69,12 @@ def get_tools(
             # convert to function that takes only model params and inserts custom params
             original_func = getattr(module, function_name)
             callable = apply_extra_params_to_tool_function(original_func, extra_params)
-            if hasattr(original_func, "__doc__"):
-                callable.__doc__ = original_func.__doc__
-
             # TODO: This needs to be a pydantic model
             tool_dict = {
                 "toolkit_id": tool_id,
                 "callable": callable,
                 "spec": spec,
-                "pydantic_model": json_schema_to_model(spec),
+                "pydantic_model": function_to_pydantic_model(callable),
                 "file_handler": hasattr(module, "file_handler") and module.file_handler,
                 "citation": hasattr(module, "citation") and module.citation,
             }
@@ -96,78 +90,109 @@ def get_tools(
     return tools_dict
 
 
-def doc_to_dict(docstring):
-    lines = docstring.split("\n")
-    description = lines[1].strip()
-    param_dict = {}
+def parse_description(docstring: str | None) -> str:
+    """
+    Parse a function's docstring to extract the description.
+
+    Args:
+        docstring (str): The docstring to parse.
+
+    Returns:
+        str: The description.
+    """
+
+    if not docstring:
+        return ""
+
+    lines = [line.strip() for line in docstring.strip().split("\n")]
+    description_lines: list[str] = []
 
     for line in lines:
-        if ":param" in line:
-            line = line.replace(":param", "").strip()
-            param, desc = line.split(":", 1)
-            param_dict[param.strip()] = desc.strip()
-    ret_dict = {"description": description, "params": param_dict}
-    return ret_dict
+        if re.match(r":param", line) or re.match(r":return", line):
+            break
+
+        description_lines.append(line)
+
+    return "\n".join(description_lines)
 
 
-def get_tools_specs(tools) -> list[dict]:
-    function_list = [
-        {"name": func, "function": getattr(tools, func)}
-        for func in dir(tools)
-        if callable(getattr(tools, func))
+def parse_docstring(docstring):
+    """
+    Parse a function's docstring to extract parameter descriptions in reST format.
+
+    Args:
+        docstring (str): The docstring to parse.
+
+    Returns:
+        dict: A dictionary where keys are parameter names and values are descriptions.
+    """
+    if not docstring:
+        return {}
+
+    # Regex to match `:param name: description` format
+    param_pattern = re.compile(r":param (\w+):\s*(.+)")
+    param_descriptions = {}
+
+    for line in docstring.splitlines():
+        match = param_pattern.match(line.strip())
+        if not match:
+            continue
+        param_name, param_description = match.groups()
+        if param_name.startswith("__"):
+            continue
+        param_descriptions[param_name] = param_description
+
+    return param_descriptions
+
+
+def function_to_pydantic_model(func: Callable) -> type[BaseModel]:
+    """
+    Converts a Python function's type hints and docstring to a Pydantic model,
+    including support for nested types, default values, and descriptions.
+
+    Args:
+        func: The function whose type hints and docstring should be converted.
+        model_name: The name of the generated Pydantic model.
+
+    Returns:
+        A Pydantic model class.
+    """
+    type_hints = get_type_hints(func)
+    signature = inspect.signature(func)
+    parameters = signature.parameters
+
+    docstring = func.__doc__
+    descriptions = parse_docstring(docstring)
+
+    tool_description = parse_description(docstring)
+
+    field_defs = {}
+    for name, param in parameters.items():
+        type_hint = type_hints.get(name, Any)
+        default_value = param.default if param.default is not param.empty else ...
+        description = descriptions.get(name, None)
+        if not description:
+            field_defs[name] = type_hint, default_value
+            continue
+        field_defs[name] = type_hint, Field(default_value, description=description)
+
+    model = create_model(func.__name__, **field_defs)
+    model.__doc__ = tool_description
+
+    return model
+
+
+def get_callable_attributes(tool: object) -> list[Callable]:
+    return [
+        getattr(tool, func)
+        for func in dir(tool)
+        if callable(getattr(tool, func))
         and not func.startswith("__")
-        and not inspect.isclass(getattr(tools, func))
+        and not inspect.isclass(getattr(tool, func))
     ]
 
-    specs = []
-    for function_item in function_list:
-        function_name = function_item["name"]
-        function = function_item["function"]
 
-        function_doc = doc_to_dict(function.__doc__ or function_name)
-        specs.append(
-            {
-                "name": function_name,
-                # TODO: multi-line desc?
-                "description": function_doc.get("description", function_name),
-                "parameters": {
-                    "type": "object",
-                    "properties": {
-                        param_name: {
-                            "type": param_annotation.__name__.lower(),
-                            **(
-                                {
-                                    "enum": (
-                                        str(param_annotation.__args__)
-                                        if hasattr(param_annotation, "__args__")
-                                        else None
-                                    )
-                                }
-                                if hasattr(param_annotation, "__args__")
-                                else {}
-                            ),
-                            "description": function_doc.get("params", {}).get(
-                                param_name, param_name
-                            ),
-                        }
-                        for param_name, param_annotation in get_type_hints(
-                            function
-                        ).items()
-                        if param_name != "return"
-                        and not (
-                            param_name.startswith("__") and param_name.endswith("__")
-                        )
-                    },
-                    "required": [
-                        name
-                        for name, param in inspect.signature(
-                            function
-                        ).parameters.items()
-                        if param.default is param.empty
-                        and not (name.startswith("__") and name.endswith("__"))
-                    ],
-                },
-            }
-        )
-
-    return specs
+def get_tools_specs(tool_class: object) -> list[dict]:
+    function_list = get_callable_attributes(tool_class)
+    models = map(function_to_pydantic_model, function_list)
+    return [convert_to_openai_function(tool) for tool in models]

backend/requirements.txt

@@ -1,7 +1,7 @@
 fastapi==0.111.0
 uvicorn[standard]==0.30.6
 pydantic==2.9.2
-python-multipart==0.0.17
+python-multipart==0.0.18
 
 Flask==3.0.3
 Flask-Cors==5.0.0
@@ -11,12 +11,13 @@ python-jose==3.3.0
 passlib[bcrypt]==1.7.4
 
 requests==2.32.3
-aiohttp==3.10.8
+aiohttp==3.11.8
 async-timeout
 aiocache
+aiofiles
 
 sqlalchemy==2.0.32
-alembic==1.13.2
+alembic==1.14.0
 peewee==3.17.6
 peewee-migrate==1.12.2
 psycopg2-binary==2.9.9
@@ -37,17 +38,17 @@ anthropic
 google-generativeai==0.7.2
 tiktoken
 
-langchain==0.3.5
-langchain-community==0.3.3
+langchain==0.3.7
+langchain-community==0.3.7
 langchain-chroma==0.1.4
 
 fake-useragent==1.5.1
 chromadb==0.5.15
-pymilvus==2.4.9
+pymilvus==2.5.0
 qdrant-client~=1.12.0
 opensearch-py==2.7.1
 
-sentence-transformers==3.2.0
+sentence-transformers==3.3.1
 colbert-ai==0.2.21
 einops==0.8.0
 
@@ -82,7 +83,7 @@ authlib==1.3.2
 
 black==24.8.0
 langfuse==2.44.0
-youtube-transcript-api==0.6.2
+youtube-transcript-api==0.6.3
 pytube==15.0.0
 
 extract_msg

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.4.0",
+	"version": "0.4.8",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -37,6 +37,7 @@
 		"postcss": "^8.4.31",
 		"prettier": "^3.3.3",
 		"prettier-plugin-svelte": "^3.2.6",
+		"sass-embedded": "^1.81.0",
 		"svelte": "^4.2.18",
 		"svelte-check": "^3.8.5",
 		"svelte-confetti": "^1.3.2",
@@ -56,6 +57,13 @@
 		"@mediapipe/tasks-vision": "^0.10.17",
 		"@pyscript/core": "^0.4.32",
 		"@sveltejs/adapter-node": "^2.0.0",
+		"@tiptap/core": "^2.10.0",
+		"@tiptap/extension-code-block-lowlight": "^2.10.0",
+		"@tiptap/extension-highlight": "^2.10.0",
+		"@tiptap/extension-placeholder": "^2.10.0",
+		"@tiptap/extension-typography": "^2.10.0",
+		"@tiptap/pm": "^2.10.0",
+		"@tiptap/starter-kit": "^2.10.0",
 		"@xyflow/svelte": "^0.1.19",
 		"async": "^3.2.5",
 		"bits-ui": "^0.19.7",

pyproject.toml

@@ -9,7 +9,7 @@ dependencies = [
     "fastapi==0.111.0",
     "uvicorn[standard]==0.30.6",
     "pydantic==2.9.2",
-    "python-multipart==0.0.17",
+    "python-multipart==0.0.18",
 
     "Flask==3.0.3",
     "Flask-Cors==5.0.0",
@@ -19,12 +19,13 @@ dependencies = [
     "passlib[bcrypt]==1.7.4",
 
     "requests==2.32.3",
-    "aiohttp==3.10.8",
+    "aiohttp==3.11.8",
     "async-timeout",
     "aiocache",
+    "aiofiles",
 
     "sqlalchemy==2.0.32",
-    "alembic==1.13.2",
+    "alembic==1.14.0",
     "peewee==3.17.6",
     "peewee-migrate==1.12.2",
     "psycopg2-binary==2.9.9",
@@ -44,17 +45,17 @@ dependencies = [
     "google-generativeai==0.7.2",
     "tiktoken",
 
-    "langchain==0.3.5",
-    "langchain-community==0.3.3",
+    "langchain==0.3.7",
+    "langchain-community==0.3.7",
     "langchain-chroma==0.1.4",
 
     "fake-useragent==1.5.1",
     "chromadb==0.5.15",
-    "pymilvus==2.4.9",
+    "pymilvus==2.5.0",
     "qdrant-client~=1.12.0",
     "opensearch-py==2.7.1",
 
-    "sentence-transformers==3.2.0",
+    "sentence-transformers==3.3.1",
     "colbert-ai==0.2.21",
     "einops==0.8.0",
 
@@ -88,7 +89,7 @@ dependencies = [
 
     "black==24.8.0",
     "langfuse==2.44.0",
-    "youtube-transcript-api==0.6.2",
+    "youtube-transcript-api==0.6.3",
     "pytube==15.0.0",
 
     "extract_msg",

src/app.css

@@ -45,15 +45,15 @@ math {
 }
 
 .input-prose {
-	@apply prose dark:prose-invert prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
+	@apply prose dark:prose-invert prose-headings:font-semibold prose-hr:my-4 prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
 }
 
 .input-prose-sm {
-	@apply prose dark:prose-invert prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line text-sm;
+	@apply prose dark:prose-invert prose-headings:font-semibold prose-hr:my-4 prose-hr:border-gray-100 prose-hr:dark:border-gray-800 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line text-sm;
 }
 
 .markdown-prose {
-	@apply prose dark:prose-invert prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
+	@apply prose dark:prose-invert prose-headings:font-semibold prose-hr:my-4 prose-p:my-0 prose-img:my-1 prose-headings:my-1 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-ul:-my-0 prose-ol:-my-0 prose-li:-my-0 whitespace-pre-line;
 }
 
 .markdown a {
@@ -199,19 +199,103 @@ input[type='number'] {
 }
 
 .ProseMirror {
-	@apply h-full  min-h-fit max-h-full whitespace-pre-wrap;
+	@apply h-full min-h-fit max-h-full whitespace-pre-wrap;
 }
 
 .ProseMirror:focus {
 	outline: none;
 }
 
-.placeholder::after {
+.ProseMirror p.is-editor-empty:first-child::before {
 	content: attr(data-placeholder);
-	cursor: text;
+	float: left;
+	color: #adb5bd;
 	pointer-events: none;
 
-	float: left;
-
-	@apply absolute inset-0 z-0 text-gray-500;
+	@apply line-clamp-1 absolute;
+}
+
+.ai-autocompletion::after {
+	color: #a0a0a0;
+
+	content: attr(data-suggestion);
+	pointer-events: none;
+}
+
+.tiptap > pre > code {
+	border-radius: 0.4rem;
+	font-size: 0.85rem;
+	padding: 0.25em 0.3em;
+
+	@apply dark:bg-gray-800 bg-gray-100;
+}
+
+.tiptap > pre {
+	border-radius: 0.5rem;
+	font-family: 'JetBrainsMono', monospace;
+	margin: 1.5rem 0;
+	padding: 0.75rem 1rem;
+
+	@apply dark:bg-gray-800 bg-gray-100;
+}
+
+.tiptap p code {
+	color: #eb5757;
+	border-width: 0px;
+	padding: 3px 8px;
+	font-size: 0.8em;
+	font-weight: 600;
+	@apply rounded-md dark:bg-gray-800 bg-gray-100 mx-0.5;
+}
+
+/* Code styling */
+.hljs-comment,
+.hljs-quote {
+	color: #616161;
+}
+
+.hljs-variable,
+.hljs-template-variable,
+.hljs-attribute,
+.hljs-tag,
+.hljs-regexp,
+.hljs-link,
+.hljs-name,
+.hljs-selector-id,
+.hljs-selector-class {
+	color: #f98181;
+}
+
+.hljs-number,
+.hljs-meta,
+.hljs-built_in,
+.hljs-builtin-name,
+.hljs-literal,
+.hljs-type,
+.hljs-params {
+	color: #fbbc88;
+}
+
+.hljs-string,
+.hljs-symbol,
+.hljs-bullet {
+	color: #b9f18d;
+}
+
+.hljs-title,
+.hljs-section {
+	color: #faf594;
+}
+
+.hljs-keyword,
+.hljs-selector-tag {
+	color: #70cff8;
+}
+
+.hljs-emphasis {
+	font-style: italic;
+}
+
+.hljs-strong {
+	font-weight: 700;
 }

src/app.html

@@ -2,9 +2,12 @@
 <html lang="en">
 	<head>
 		<meta charset="utf-8" />
-		<link rel="icon" href="%sveltekit.assets%/favicon.png" />
-		<link rel="apple-touch-icon" href="%sveltekit.assets%/favicon.png" />
-		<link rel="manifest" href="%sveltekit.assets%/manifest.json" crossorigin="use-credentials" />
+		<link rel="icon" type="image/png" href="/favicon/favicon-96x96.png" sizes="96x96" />
+		<link rel="icon" type="image/svg+xml" href="/favicon/favicon.svg" />
+		<link rel="shortcut icon" href="/favicon/favicon.ico" />
+		<link rel="apple-touch-icon" sizes="180x180" href="/favicon/apple-touch-icon.png" />
+		<meta name="apple-mobile-web-app-title" content="Open WebUI" />
+		<link rel="manifest" href="/favicon/site.webmanifest" />
 		<meta
 			name="viewport"
 			content="width=device-width, initial-scale=1, maximum-scale=1, viewport-fit=cover"

src/lib/apis/configs/index.ts

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

src/lib/apis/index.ts

@@ -25,26 +25,6 @@ export const getModels = async (token: string = '', base: boolean = false) => {
 	}
 
 	let models = res?.data ?? [];
-	models = models
-		.filter((models) => models)
-		// Sort the models
-		.sort((a, b) => {
-			// Compare case-insensitively by name for models without position property
-			const lowerA = a.name.toLowerCase();
-			const lowerB = b.name.toLowerCase();
-
-			if (lowerA < lowerB) return -1;
-			if (lowerA > lowerB) return 1;
-
-			// If same case-insensitively, sort by original strings,
-			// lowercase will come before uppercase due to ASCII values
-			if (a.name < b.name) return -1;
-			if (a.name > b.name) return 1;
-
-			return 0; // They are equal
-		});
-
-	console.log(models);
 	return models;
 };
 
@@ -387,20 +367,15 @@ export const generateQueries = async (
 		throw error;
 	}
 
+	// Step 1: Safely extract the response string
+	const response = res?.choices[0]?.message?.content ?? '';
+
 	try {
-		// Step 1: Safely extract the response string
-		const response = res?.choices[0]?.message?.content ?? '';
+		const jsonStartIndex = response.indexOf('{');
+		const jsonEndIndex = response.lastIndexOf('}');
 
-		// Step 2: Attempt to fix common JSON format issues like single quotes
-		const sanitizedResponse = response.replace(/['‘’`]/g, '"'); // Convert single quotes to double quotes for valid JSON
-
-		// Step 3: Find the relevant JSON block within the response
-		const jsonStartIndex = sanitizedResponse.indexOf('{');
-		const jsonEndIndex = sanitizedResponse.lastIndexOf('}');
-
-		// Step 4: Check if we found a valid JSON block (with both `{` and `}`)
 		if (jsonStartIndex !== -1 && jsonEndIndex !== -1) {
-			const jsonResponse = sanitizedResponse.substring(jsonStartIndex, jsonEndIndex + 1);
+			const jsonResponse = response.substring(jsonStartIndex, jsonEndIndex + 1);
 
 			// Step 5: Parse the JSON block
 			const parsed = JSON.parse(jsonResponse);
@@ -413,12 +388,83 @@ export const generateQueries = async (
 			}
 		}
 
-		// If no valid JSON block found, return an empty array
-		return [];
+		// If no valid JSON block found, return response as is
+		return [response];
 	} catch (e) {
 		// Catch and safely return empty array on any parsing errors
 		console.error('Failed to parse response: ', e);
-		return [];
+		return [response];
+	}
+};
+
+export const generateAutoCompletion = async (
+	token: string = '',
+	model: string,
+	prompt: string,
+	messages?: object[],
+	type: string = 'search query'
+) => {
+	const controller = new AbortController();
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/task/auto/completions`, {
+		signal: controller.signal,
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			prompt: prompt,
+			...(messages && { messages: messages }),
+			type: type,
+			stream: false
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	const response = res?.choices[0]?.message?.content ?? '';
+
+	try {
+		const jsonStartIndex = response.indexOf('{');
+		const jsonEndIndex = response.lastIndexOf('}');
+
+		if (jsonStartIndex !== -1 && jsonEndIndex !== -1) {
+			const jsonResponse = response.substring(jsonStartIndex, jsonEndIndex + 1);
+
+			// Step 5: Parse the JSON block
+			const parsed = JSON.parse(jsonResponse);
+
+			// Step 6: If there's a "queries" key, return the queries array; otherwise, return an empty array
+			if (parsed && parsed.text) {
+				return parsed.text;
+			} else {
+				return '';
+			}
+		}
+
+		// If no valid JSON block found, return response as is
+		return response;
+	} catch (e) {
+		// Catch and safely return empty array on any parsing errors
+		console.error('Failed to parse response: ', e);
+		return response;
 	}
 };
 

src/lib/apis/models/index.ts

@@ -3,7 +3,7 @@ import { WEBUI_API_BASE_URL } from '$lib/constants';
 export const getModels = async (token: string = '') => {
 	let error = null;
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/models`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -97,7 +97,7 @@ export const getModelById = async (token: string, id: string) => {
 	const searchParams = new URLSearchParams();
 	searchParams.append('id', id);
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/models/id/${id}`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/model?${searchParams.toString()}`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',
@@ -132,7 +132,7 @@ export const toggleModelById = async (token: string, id: string) => {
 	const searchParams = new URLSearchParams();
 	searchParams.append('id', id);
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/models/id/${id}/toggle`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/model/toggle?${searchParams.toString()}`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -167,7 +167,7 @@ export const updateModelById = async (token: string, id: string, model: object)
 	const searchParams = new URLSearchParams();
 	searchParams.append('id', id);
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/models/id/${id}/update`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/model/update?${searchParams.toString()}`, {
 		method: 'POST',
 		headers: {
 			Accept: 'application/json',
@@ -203,7 +203,7 @@ export const deleteModelById = async (token: string, id: string) => {
 	const searchParams = new URLSearchParams();
 	searchParams.append('id', id);
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/models/id/${id}/delete`, {
+	const res = await fetch(`${WEBUI_API_BASE_URL}/models/model/delete?${searchParams.toString()}`, {
 		method: 'DELETE',
 		headers: {
 			Accept: 'application/json',

src/lib/apis/retrieval/index.ts

@@ -40,6 +40,7 @@ type ContentExtractConfigForm = {
 type YoutubeConfigForm = {
 	language: string[];
 	translation?: string | null;
+	proxy_url: string;
 };
 
 type RAGConfigForm = {

src/lib/apis/streaming/index.ts

@@ -5,7 +5,7 @@ type TextStreamUpdate = {
 	done: boolean;
 	value: string;
 	// eslint-disable-next-line @typescript-eslint/no-explicit-any
-	citations?: any;
+	sources?: any;
 	// eslint-disable-next-line @typescript-eslint/no-explicit-any
 	selectedModelId?: any;
 	error?: any;
@@ -67,8 +67,8 @@ async function* openAIStreamToIterator(
 				break;
 			}
 
-			if (parsedData.citations) {
-				yield { done: false, value: '', citations: parsedData.citations };
+			if (parsedData.sources) {
+				yield { done: false, value: '', sources: parsedData.sources };
 				continue;
 			}
 
@@ -98,7 +98,7 @@ async function* streamLargeDeltasAsRandomChunks(
 			yield textStreamUpdate;
 			return;
 		}
-		if (textStreamUpdate.citations) {
+		if (textStreamUpdate.sources) {
 			yield textStreamUpdate;
 			continue;
 		}

src/lib/components/admin/Functions.svelte

@@ -219,7 +219,7 @@
 </div>
 
 <div class="mb-5">
-	{#each filteredItems as func}
+	{#each filteredItems as func (func.id)}
 		<div
 			class=" flex space-x-4 cursor-pointer w-full px-3 py-2 dark:hover:bg-white/5 hover:bg-black/5 rounded-xl"
 		>

src/lib/components/admin/Settings/Connections/OpenAIConnection.svelte

@@ -60,7 +60,7 @@
 				/>
 
 				{#if pipeline}
-					<div class=" absolute top-2.5 right-2.5">
+					<div class=" absolute top-0.5 right-2.5">
 						<Tooltip content="Pipelines">
 							<svg
 								xmlns="http://www.w3.org/2000/svg"

src/lib/components/admin/Settings/Evaluations.svelte

@@ -5,6 +5,7 @@
 
 	const dispatch = createEventDispatcher();
 	import { getModels } from '$lib/apis';
+	import { getConfig, updateConfig } from '$lib/apis/evaluations';
 
 	import Switch from '$lib/components/common/Switch.svelte';
 	import Spinner from '$lib/components/common/Spinner.svelte';
@@ -12,7 +13,6 @@
 	import Plus from '$lib/components/icons/Plus.svelte';
 	import Model from './Evaluations/Model.svelte';
 	import ArenaModelModal from './Evaluations/ArenaModelModal.svelte';
-	import { getConfig, updateConfig } from '$lib/apis/evaluations';
 
 	const i18n = getContext('i18n');
 
@@ -27,6 +27,7 @@
 
 		if (config) {
 			toast.success('Settings saved successfully');
+			models.set(await getModels(localStorage.token));
 		}
 	};
 

src/lib/components/admin/Settings/Evaluations/ArenaModelModal.svelte

@@ -102,7 +102,7 @@
 			description = model.meta.description;
 			modelIds = model.meta.model_ids || [];
 			filterMode = model.meta?.filter_mode ?? 'include';
-			accessControl = model.meta?.access_control ?? {};
+			accessControl = 'access_control' in model.meta ? model.meta.access_control : {};
 		}
 	};
 
@@ -375,7 +375,7 @@
 					<div class="flex justify-end pt-3 text-sm font-medium gap-1.5">
 						{#if edit}
 							<button
-								class="px-3.5 py-1.5 text-sm font-medium dark:bg-black dark:hover:bg-gray-900 dark:text-white bg-white text-black hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center"
+								class="px-3.5 py-1.5 text-sm font-medium dark:bg-black dark:hover:bg-gray-950 dark:text-white bg-white text-black hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center"
 								type="button"
 								on:click={() => {
 									dispatch('delete', model);
@@ -387,7 +387,7 @@
 						{/if}
 
 						<button
-							class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center {loading
+							class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-950 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center {loading
 								? ' cursor-not-allowed'
 								: ''}"
 							type="submit"

src/lib/components/admin/Settings/Interface.svelte

@@ -24,6 +24,8 @@
 		TASK_MODEL: '',
 		TASK_MODEL_EXTERNAL: '',
 		TITLE_GENERATION_PROMPT_TEMPLATE: '',
+		ENABLE_AUTOCOMPLETE_GENERATION: true,
+		AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH: -1,
 		TAGS_GENERATION_PROMPT_TEMPLATE: '',
 		ENABLE_TAGS_GENERATION: true,
 		ENABLE_SEARCH_QUERY_GENERATION: true,
@@ -55,255 +57,207 @@
 	};
 </script>
 
-<form
-	class="flex flex-col h-full justify-between space-y-3 text-sm"
-	on:submit|preventDefault={() => {
-		updateInterfaceHandler();
-		dispatch('save');
-	}}
->
-	<div class="  overflow-y-scroll scrollbar-hidden h-full pr-1.5">
-		<div>
-			<div class=" mb-2.5 text-sm font-medium flex items-center">
-				<div class=" mr-1">{$i18n.t('Set Task Model')}</div>
-				<Tooltip
-					content={$i18n.t(
-						'A task model is used when performing tasks such as generating titles for chats and web search queries'
-					)}
-				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						fill="none"
-						viewBox="0 0 24 24"
-						stroke-width="1.5"
-						stroke="currentColor"
-						class="size-3.5"
+{#if taskConfig}
+	<form
+		class="flex flex-col h-full justify-between space-y-3 text-sm"
+		on:submit|preventDefault={() => {
+			updateInterfaceHandler();
+			dispatch('save');
+		}}
+	>
+		<div class="  overflow-y-scroll scrollbar-hidden h-full pr-1.5">
+			<div>
+				<div class=" mb-2.5 text-sm font-medium flex items-center">
+					<div class=" mr-1">{$i18n.t('Set Task Model')}</div>
+					<Tooltip
+						content={$i18n.t(
+							'A task model is used when performing tasks such as generating titles for chats and web search queries'
+						)}
 					>
-						<path
-							stroke-linecap="round"
-							stroke-linejoin="round"
-							d="m11.25 11.25.041-.02a.75.75 0 0 1 1.063.852l-.708 2.836a.75.75 0 0 0 1.063.853l.041-.021M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Zm-9-3.75h.008v.008H12V8.25Z"
-						/>
-					</svg>
-				</Tooltip>
-			</div>
-			<div class="flex w-full gap-2">
-				<div class="flex-1">
-					<div class=" text-xs mb-1">{$i18n.t('Local Models')}</div>
-					<select
-						class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
-						bind:value={taskConfig.TASK_MODEL}
-						placeholder={$i18n.t('Select a model')}
-					>
-						<option value="" selected>{$i18n.t('Current Model')}</option>
-						{#each $models.filter((m) => m.owned_by === 'ollama') as model}
-							<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
-								{model.name}
-							</option>
-						{/each}
-					</select>
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							fill="none"
+							viewBox="0 0 24 24"
+							stroke-width="1.5"
+							stroke="currentColor"
+							class="size-3.5"
+						>
+							<path
+								stroke-linecap="round"
+								stroke-linejoin="round"
+								d="m11.25 11.25.041-.02a.75.75 0 0 1 1.063.852l-.708 2.836a.75.75 0 0 0 1.063.853l.041-.021M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Zm-9-3.75h.008v.008H12V8.25Z"
+							/>
+						</svg>
+					</Tooltip>
+				</div>
+				<div class="flex w-full gap-2">
+					<div class="flex-1">
+						<div class=" text-xs mb-1">{$i18n.t('Local Models')}</div>
+						<select
+							class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+							bind:value={taskConfig.TASK_MODEL}
+							placeholder={$i18n.t('Select a model')}
+						>
+							<option value="" selected>{$i18n.t('Current Model')}</option>
+							{#each $models.filter((m) => m.owned_by === 'ollama') as model}
+								<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
+									{model.name}
+								</option>
+							{/each}
+						</select>
+					</div>
+
+					<div class="flex-1">
+						<div class=" text-xs mb-1">{$i18n.t('External Models')}</div>
+						<select
+							class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+							bind:value={taskConfig.TASK_MODEL_EXTERNAL}
+							placeholder={$i18n.t('Select a model')}
+						>
+							<option value="" selected>{$i18n.t('Current Model')}</option>
+							{#each $models as model}
+								<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
+									{model.name}
+								</option>
+							{/each}
+						</select>
+					</div>
 				</div>
 
-				<div class="flex-1">
-					<div class=" text-xs mb-1">{$i18n.t('External Models')}</div>
-					<select
-						class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
-						bind:value={taskConfig.TASK_MODEL_EXTERNAL}
-						placeholder={$i18n.t('Select a model')}
-					>
-						<option value="" selected>{$i18n.t('Current Model')}</option>
-						{#each $models as model}
-							<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
-								{model.name}
-							</option>
-						{/each}
-					</select>
-				</div>
-			</div>
-
-			<div class="mt-3">
-				<div class=" mb-2.5 text-xs font-medium">{$i18n.t('Title Generation Prompt')}</div>
-
-				<Tooltip
-					content={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
-					placement="top-start"
-				>
-					<Textarea
-						bind:value={taskConfig.TITLE_GENERATION_PROMPT_TEMPLATE}
-						placeholder={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
-					/>
-				</Tooltip>
-			</div>
-
-			<hr class=" dark:border-gray-850 my-3" />
-
-			<div class="my-3 flex w-full items-center justify-between">
-				<div class=" self-center text-xs font-medium">
-					{$i18n.t('Enable Tags Generation')}
-				</div>
-
-				<Switch bind:state={taskConfig.ENABLE_TAGS_GENERATION} />
-			</div>
-
-			{#if taskConfig.ENABLE_TAGS_GENERATION}
 				<div class="mt-3">
-					<div class=" mb-2.5 text-xs font-medium">{$i18n.t('Tags Generation Prompt')}</div>
+					<div class=" mb-2.5 text-xs font-medium">{$i18n.t('Title Generation Prompt')}</div>
 
 					<Tooltip
 						content={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
 						placement="top-start"
 					>
 						<Textarea
-							bind:value={taskConfig.TAGS_GENERATION_PROMPT_TEMPLATE}
+							bind:value={taskConfig.TITLE_GENERATION_PROMPT_TEMPLATE}
 							placeholder={$i18n.t(
 								'Leave empty to use the default prompt, or enter a custom prompt'
 							)}
 						/>
 					</Tooltip>
 				</div>
-			{/if}
 
-			<hr class=" dark:border-gray-850 my-3" />
+				<hr class=" border-gray-50 dark:border-gray-850 my-3" />
 
-			<div class="my-3 flex w-full items-center justify-between">
-				<div class=" self-center text-xs font-medium">
-					{$i18n.t('Enable Retrieval Query Generation')}
+				<div class="my-3 flex w-full items-center justify-between">
+					<div class=" self-center text-xs font-medium">
+						{$i18n.t('Autocomplete Generation')}
+					</div>
+
+					<Tooltip content={$i18n.t('Enable autocomplete generation for chat messages')}>
+						<Switch bind:state={taskConfig.ENABLE_AUTOCOMPLETE_GENERATION} />
+					</Tooltip>
 				</div>
 
-				<Switch bind:state={taskConfig.ENABLE_RETRIEVAL_QUERY_GENERATION} />
-			</div>
-
-			<div class="my-3 flex w-full items-center justify-between">
-				<div class=" self-center text-xs font-medium">
-					{$i18n.t('Enable Web Search Query Generation')}
-				</div>
-
-				<Switch bind:state={taskConfig.ENABLE_SEARCH_QUERY_GENERATION} />
-			</div>
-
-			<div class="">
-				<div class=" mb-2.5 text-xs font-medium">{$i18n.t('Query Generation Prompt')}</div>
-
-				<Tooltip
-					content={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
-					placement="top-start"
-				>
-					<Textarea
-						bind:value={taskConfig.QUERY_GENERATION_PROMPT_TEMPLATE}
-						placeholder={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
-					/>
-				</Tooltip>
-			</div>
-		</div>
-
-		<hr class=" dark:border-gray-850 my-3" />
-
-		<div class=" space-y-3 {banners.length > 0 ? ' mb-3' : ''}">
-			<div class="flex w-full justify-between">
-				<div class=" self-center text-sm font-semibold">
-					{$i18n.t('Banners')}
-				</div>
-
-				<button
-					class="p-1 px-3 text-xs flex rounded transition"
-					type="button"
-					on:click={() => {
-						if (banners.length === 0 || banners.at(-1).content !== '') {
-							banners = [
-								...banners,
-								{
-									id: uuidv4(),
-									type: '',
-									title: '',
-									content: '',
-									dismissible: true,
-									timestamp: Math.floor(Date.now() / 1000)
-								}
-							];
-						}
-					}}
-				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 20 20"
-						fill="currentColor"
-						class="w-4 h-4"
-					>
-						<path
-							d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
-						/>
-					</svg>
-				</button>
-			</div>
-			<div class="flex flex-col space-y-1">
-				{#each banners as banner, bannerIdx}
-					<div class=" flex justify-between">
-						<div class="flex flex-row flex-1 border rounded-xl dark:border-gray-800">
-							<select
-								class="w-fit capitalize rounded-xl py-2 px-4 text-xs bg-transparent outline-none"
-								bind:value={banner.type}
-								required
-							>
-								{#if banner.type == ''}
-									<option value="" selected disabled class="text-gray-900">{$i18n.t('Type')}</option
-									>
-								{/if}
-								<option value="info" class="text-gray-900">{$i18n.t('Info')}</option>
-								<option value="warning" class="text-gray-900">{$i18n.t('Warning')}</option>
-								<option value="error" class="text-gray-900">{$i18n.t('Error')}</option>
-								<option value="success" class="text-gray-900">{$i18n.t('Success')}</option>
-							</select>
-
-							<input
-								class="pr-5 py-1.5 text-xs w-full bg-transparent outline-none"
-								placeholder={$i18n.t('Content')}
-								bind:value={banner.content}
-							/>
-
-							<div class="relative top-1.5 -left-2">
-								<Tooltip content={$i18n.t('Dismissible')} className="flex h-fit items-center">
-									<Switch bind:state={banner.dismissible} />
-								</Tooltip>
-							</div>
+				{#if taskConfig.ENABLE_AUTOCOMPLETE_GENERATION}
+					<div class="mt-3">
+						<div class=" mb-2.5 text-xs font-medium">
+							{$i18n.t('Autocomplete Generation Input Max Length')}
 						</div>
 
-						<button
-							class="px-2"
-							type="button"
-							on:click={() => {
-								banners.splice(bannerIdx, 1);
-								banners = banners;
-							}}
+						<Tooltip
+							content={$i18n.t('Character limit for autocomplete generation input')}
+							placement="top-start"
 						>
-							<svg
-								xmlns="http://www.w3.org/2000/svg"
-								viewBox="0 0 20 20"
-								fill="currentColor"
-								class="w-4 h-4"
-							>
-								<path
-									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
-								/>
-							</svg>
-						</button>
+							<input
+								class="w-full outline-none bg-transparent"
+								bind:value={taskConfig.AUTOCOMPLETE_GENERATION_INPUT_MAX_LENGTH}
+								placeholder={$i18n.t('-1 for no limit, or a positive integer for a specific limit')}
+							/>
+						</Tooltip>
 					</div>
-				{/each}
-			</div>
-		</div>
+				{/if}
 
-		{#if $user.role === 'admin'}
-			<div class=" space-y-3">
-				<div class="flex w-full justify-between mb-2">
+				<hr class=" border-gray-50 dark:border-gray-850 my-3" />
+
+				<div class="my-3 flex w-full items-center justify-between">
+					<div class=" self-center text-xs font-medium">
+						{$i18n.t('Tags Generation')}
+					</div>
+
+					<Switch bind:state={taskConfig.ENABLE_TAGS_GENERATION} />
+				</div>
+
+				{#if taskConfig.ENABLE_TAGS_GENERATION}
+					<div class="mt-3">
+						<div class=" mb-2.5 text-xs font-medium">{$i18n.t('Tags Generation Prompt')}</div>
+
+						<Tooltip
+							content={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
+							placement="top-start"
+						>
+							<Textarea
+								bind:value={taskConfig.TAGS_GENERATION_PROMPT_TEMPLATE}
+								placeholder={$i18n.t(
+									'Leave empty to use the default prompt, or enter a custom prompt'
+								)}
+							/>
+						</Tooltip>
+					</div>
+				{/if}
+
+				<hr class=" border-gray-50 dark:border-gray-850 my-3" />
+
+				<div class="my-3 flex w-full items-center justify-between">
+					<div class=" self-center text-xs font-medium">
+						{$i18n.t('Retrieval Query Generation')}
+					</div>
+
+					<Switch bind:state={taskConfig.ENABLE_RETRIEVAL_QUERY_GENERATION} />
+				</div>
+
+				<div class="my-3 flex w-full items-center justify-between">
+					<div class=" self-center text-xs font-medium">
+						{$i18n.t('Web Search Query Generation')}
+					</div>
+
+					<Switch bind:state={taskConfig.ENABLE_SEARCH_QUERY_GENERATION} />
+				</div>
+
+				<div class="">
+					<div class=" mb-2.5 text-xs font-medium">{$i18n.t('Query Generation Prompt')}</div>
+
+					<Tooltip
+						content={$i18n.t('Leave empty to use the default prompt, or enter a custom prompt')}
+						placement="top-start"
+					>
+						<Textarea
+							bind:value={taskConfig.QUERY_GENERATION_PROMPT_TEMPLATE}
+							placeholder={$i18n.t(
+								'Leave empty to use the default prompt, or enter a custom prompt'
+							)}
+						/>
+					</Tooltip>
+				</div>
+			</div>
+
+			<hr class=" border-gray-50 dark:border-gray-850 my-3" />
+
+			<div class=" space-y-3 {banners.length > 0 ? ' mb-3' : ''}">
+				<div class="flex w-full justify-between">
 					<div class=" self-center text-sm font-semibold">
-						{$i18n.t('Default Prompt Suggestions')}
+						{$i18n.t('Banners')}
 					</div>
 
 					<button
 						class="p-1 px-3 text-xs flex rounded transition"
 						type="button"
 						on:click={() => {
-							if (promptSuggestions.length === 0 || promptSuggestions.at(-1).content !== '') {
-								promptSuggestions = [...promptSuggestions, { content: '', title: ['', ''] }];
+							if (banners.length === 0 || banners.at(-1).content !== '') {
+								banners = [
+									...banners,
+									{
+										id: uuidv4(),
+										type: '',
+										title: '',
+										content: '',
+										dismissible: true,
+										timestamp: Math.floor(Date.now() / 1000)
+									}
+								];
 							}
 						}}
 					>
@@ -319,40 +273,45 @@
 						</svg>
 					</button>
 				</div>
-				<div class="grid lg:grid-cols-2 flex-col gap-1.5">
-					{#each promptSuggestions as prompt, promptIdx}
-						<div
-							class=" flex border border-gray-100 dark:border-none dark:bg-gray-850 rounded-xl py-1.5"
-						>
-							<div class="flex flex-col flex-1 pl-1">
-								<div class="flex border-b border-gray-100 dark:border-gray-800 w-full">
-									<input
-										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r border-gray-100 dark:border-gray-800"
-										placeholder={$i18n.t('Title (e.g. Tell me a fun fact)')}
-										bind:value={prompt.title[0]}
-									/>
+				<div class="flex flex-col space-y-1">
+					{#each banners as banner, bannerIdx}
+						<div class=" flex justify-between">
+							<div class="flex flex-row flex-1 border rounded-xl dark:border-gray-800">
+								<select
+									class="w-fit capitalize rounded-xl py-2 px-4 text-xs bg-transparent outline-none"
+									bind:value={banner.type}
+									required
+								>
+									{#if banner.type == ''}
+										<option value="" selected disabled class="text-gray-900"
+											>{$i18n.t('Type')}</option
+										>
+									{/if}
+									<option value="info" class="text-gray-900">{$i18n.t('Info')}</option>
+									<option value="warning" class="text-gray-900">{$i18n.t('Warning')}</option>
+									<option value="error" class="text-gray-900">{$i18n.t('Error')}</option>
+									<option value="success" class="text-gray-900">{$i18n.t('Success')}</option>
+								</select>
 
-									<input
-										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r border-gray-100 dark:border-gray-800"
-										placeholder={$i18n.t('Subtitle (e.g. about the Roman Empire)')}
-										bind:value={prompt.title[1]}
-									/>
-								</div>
-
-								<textarea
-									class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r border-gray-100 dark:border-gray-800 resize-none"
-									placeholder={$i18n.t('Prompt (e.g. Tell me a fun fact about the Roman Empire)')}
-									rows="3"
-									bind:value={prompt.content}
+								<input
+									class="pr-5 py-1.5 text-xs w-full bg-transparent outline-none"
+									placeholder={$i18n.t('Content')}
+									bind:value={banner.content}
 								/>
+
+								<div class="relative top-1.5 -left-2">
+									<Tooltip content={$i18n.t('Dismissible')} className="flex h-fit items-center">
+										<Switch bind:state={banner.dismissible} />
+									</Tooltip>
+								</div>
 							</div>
 
 							<button
-								class="px-3"
+								class="px-2"
 								type="button"
 								on:click={() => {
-									promptSuggestions.splice(promptIdx, 1);
-									promptSuggestions = promptSuggestions;
+									banners.splice(bannerIdx, 1);
+									banners = banners;
 								}}
 							>
 								<svg
@@ -369,22 +328,103 @@
 						</div>
 					{/each}
 				</div>
-
-				{#if promptSuggestions.length > 0}
-					<div class="text-xs text-left w-full mt-2">
-						{$i18n.t('Adjusting these settings will apply changes universally to all users.')}
-					</div>
-				{/if}
 			</div>
-		{/if}
-	</div>
 
-	<div class="flex justify-end text-sm font-medium">
-		<button
-			class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full"
-			type="submit"
-		>
-			{$i18n.t('Save')}
-		</button>
-	</div>
-</form>
+			{#if $user.role === 'admin'}
+				<div class=" space-y-3">
+					<div class="flex w-full justify-between mb-2">
+						<div class=" self-center text-sm font-semibold">
+							{$i18n.t('Default Prompt Suggestions')}
+						</div>
+
+						<button
+							class="p-1 px-3 text-xs flex rounded transition"
+							type="button"
+							on:click={() => {
+								if (promptSuggestions.length === 0 || promptSuggestions.at(-1).content !== '') {
+									promptSuggestions = [...promptSuggestions, { content: '', title: ['', ''] }];
+								}
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
+								/>
+							</svg>
+						</button>
+					</div>
+					<div class="grid lg:grid-cols-2 flex-col gap-1.5">
+						{#each promptSuggestions as prompt, promptIdx}
+							<div
+								class=" flex border border-gray-100 dark:border-none dark:bg-gray-850 rounded-xl py-1.5"
+							>
+								<div class="flex flex-col flex-1 pl-1">
+									<div class="flex border-b border-gray-100 dark:border-gray-800 w-full">
+										<input
+											class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r border-gray-100 dark:border-gray-800"
+											placeholder={$i18n.t('Title (e.g. Tell me a fun fact)')}
+											bind:value={prompt.title[0]}
+										/>
+
+										<input
+											class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r border-gray-100 dark:border-gray-800"
+											placeholder={$i18n.t('Subtitle (e.g. about the Roman Empire)')}
+											bind:value={prompt.title[1]}
+										/>
+									</div>
+
+									<textarea
+										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r border-gray-100 dark:border-gray-800 resize-none"
+										placeholder={$i18n.t('Prompt (e.g. Tell me a fun fact about the Roman Empire)')}
+										rows="3"
+										bind:value={prompt.content}
+									/>
+								</div>
+
+								<button
+									class="px-3"
+									type="button"
+									on:click={() => {
+										promptSuggestions.splice(promptIdx, 1);
+										promptSuggestions = promptSuggestions;
+									}}
+								>
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 20 20"
+										fill="currentColor"
+										class="w-4 h-4"
+									>
+										<path
+											d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+										/>
+									</svg>
+								</button>
+							</div>
+						{/each}
+					</div>
+
+					{#if promptSuggestions.length > 0}
+						<div class="text-xs text-left w-full mt-2">
+							{$i18n.t('Adjusting these settings will apply changes universally to all users.')}
+						</div>
+					{/if}
+				</div>
+			{/if}
+		</div>
+
+		<div class="flex justify-end text-sm font-medium">
+			<button
+				class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full"
+				type="submit"
+			>
+				{$i18n.t('Save')}
+			</button>
+		</div>
+	</form>
+{/if}

src/lib/components/admin/Settings/Models.svelte

@@ -24,6 +24,8 @@
 	import ModelEditor from '$lib/components/workspace/Models/ModelEditor.svelte';
 	import { toast } from 'svelte-sonner';
 	import ConfirmDialog from '$lib/components/common/ConfirmDialog.svelte';
+	import Cog6 from '$lib/components/icons/Cog6.svelte';
+	import ConfigureModelsModal from './Models/ConfigureModelsModal.svelte';
 
 	let importFiles;
 	let modelsImportInputElement: HTMLInputElement;
@@ -35,12 +37,20 @@
 
 	let filteredModels = [];
 	let selectedModelId = null;
-	let showResetModal = false;
+
+	let showConfigModal = false;
 
 	$: if (models) {
-		filteredModels = models.filter(
-			(m) => searchValue === '' || m.name.toLowerCase().includes(searchValue.toLowerCase())
-		);
+		filteredModels = models
+			.filter((m) => searchValue === '' || m.name.toLowerCase().includes(searchValue.toLowerCase()))
+			.sort((a, b) => {
+				// // Check if either model is inactive and push them to the bottom
+				// if ((a.is_active ?? true) !== (b.is_active ?? true)) {
+				// 	return (b.is_active ?? true) - (a.is_active ?? true);
+				// }
+				// If both models' active states are the same, sort alphabetically
+				return a.name.localeCompare(b.name);
+			});
 	}
 
 	let searchValue = '';
@@ -114,12 +124,11 @@
 			}).catch((error) => {
 				return null;
 			});
-
-			await init();
 		} else {
 			await toggleModelById(localStorage.token, model.id);
 		}
 
+		await init();
 		_models.set(await getModels(localStorage.token));
 	};
 
@@ -128,18 +137,7 @@
 	});
 </script>
 
-<ConfirmDialog
-	title={$i18n.t('Delete All Models')}
-	message={$i18n.t('This will delete all models including custom models and cannot be undone.')}
-	bind:show={showResetModal}
-	onConfirm={async () => {
-		const res = deleteAllModels(localStorage.token);
-		if (res) {
-			toast.success($i18n.t('All models deleted successfully'));
-			init();
-		}
-	}}
-/>
+<ConfigureModelsModal bind:show={showConfigModal} {init} />
 
 {#if models !== null}
 	{#if selectedModelId === null}
@@ -154,17 +152,15 @@
 				</div>
 
 				<div>
-					<Tooltip content={$i18n.t('This will delete all models including custom models')}>
+					<Tooltip content={$i18n.t('Configure')}>
 						<button
 							class=" px-2.5 py-1 rounded-full flex gap-1 items-center"
 							type="button"
 							on:click={() => {
-								showResetModal = true;
+								showConfigModal = true;
 							}}
 						>
-							<div class="text-xs flex-shrink-0">
-								{$i18n.t('Reset')}
-							</div>
+							<Cog6 />
 						</button>
 					</Tooltip>
 				</div>
@@ -186,7 +182,7 @@
 
 		<div class=" my-2 mb-5" id="model-list">
 			{#if models.length > 0}
-				{#each filteredModels as model (model.id)}
+				{#each filteredModels as model, modelIdx (model.id)}
 					<div
 						class=" flex space-x-4 cursor-pointer w-full px-3 py-2 dark:hover:bg-white/5 hover:bg-black/5 rounded-lg transition"
 						id="model-item-{model.id}"

src/lib/components/admin/Settings/Models/ConfigureModelsModal.svelte

@@ -0,0 +1,268 @@
+<script>
+	import { toast } from 'svelte-sonner';
+
+	import { createEventDispatcher, getContext, onMount } from 'svelte';
+	const i18n = getContext('i18n');
+	const dispatch = createEventDispatcher();
+
+	import { models } from '$lib/stores';
+	import { deleteAllModels } from '$lib/apis/models';
+
+	import Modal from '$lib/components/common/Modal.svelte';
+	import ConfirmDialog from '$lib/components/common/ConfirmDialog.svelte';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import ModelList from './ModelList.svelte';
+	import { getModelsConfig, setModelsConfig } from '$lib/apis/configs';
+	import Spinner from '$lib/components/common/Spinner.svelte';
+	import Minus from '$lib/components/icons/Minus.svelte';
+	import Plus from '$lib/components/icons/Plus.svelte';
+
+	export let show = false;
+	export let init = () => {};
+
+	let config = null;
+
+	let selectedModelId = '';
+	let defaultModelIds = [];
+	let modelIds = [];
+
+	let loading = false;
+	let showResetModal = false;
+
+	const submitHandler = async () => {
+		loading = true;
+
+		const res = await setModelsConfig(localStorage.token, {
+			DEFAULT_MODELS: defaultModelIds.join(','),
+			MODEL_ORDER_LIST: modelIds
+		});
+
+		if (res) {
+			toast.success($i18n.t('Models configuration saved successfully'));
+			init();
+			show = false;
+		} else {
+			toast.error($i18n.t('Failed to save models configuration'));
+		}
+
+		loading = false;
+	};
+
+	onMount(async () => {
+		config = await getModelsConfig(localStorage.token);
+
+		if (config?.DEFAULT_MODELS) {
+			defaultModelIds = (config?.DEFAULT_MODELS).split(',').filter((id) => id);
+		} else {
+			defaultModelIds = [];
+		}
+		const modelOrderList = config.MODEL_ORDER_LIST || [];
+		const allModelIds = $models.map((model) => model.id);
+
+		// Create a Set for quick lookup of ordered IDs
+		const orderedSet = new Set(modelOrderList);
+
+		modelIds = [
+			// Add all IDs from MODEL_ORDER_LIST that exist in allModelIds
+			...modelOrderList.filter((id) => orderedSet.has(id) && allModelIds.includes(id)),
+			// Add remaining IDs not in MODEL_ORDER_LIST, sorted alphabetically
+			...allModelIds.filter((id) => !orderedSet.has(id)).sort((a, b) => a.localeCompare(b))
+		];
+	});
+</script>
+
+<ConfirmDialog
+	title={$i18n.t('Reset All Models')}
+	message={$i18n.t('This will delete all models including custom models and cannot be undone.')}
+	bind:show={showResetModal}
+	onConfirm={async () => {
+		const res = deleteAllModels(localStorage.token);
+		if (res) {
+			toast.success($i18n.t('All models deleted successfully'));
+			init();
+		}
+	}}
+/>
+
+<Modal size="sm" bind:show>
+	<div>
+		<div class=" flex justify-between dark:text-gray-100 px-5 pt-4 pb-2">
+			<div class=" text-lg font-medium self-center font-primary">
+				{$i18n.t('Configure Models')}
+			</div>
+			<button
+				class="self-center"
+				on:click={() => {
+					show = false;
+				}}
+			>
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 20 20"
+					fill="currentColor"
+					class="w-5 h-5"
+				>
+					<path
+						d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+					/>
+				</svg>
+			</button>
+		</div>
+
+		<div class="flex flex-col md:flex-row w-full px-5 pb-4 md:space-x-4 dark:text-gray-200">
+			<div class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6">
+				{#if config}
+					<form
+						class="flex flex-col w-full"
+						on:submit|preventDefault={() => {
+							submitHandler();
+						}}
+					>
+						<div>
+							<div class="flex flex-col w-full">
+								<div class="mb-1 flex justify-between">
+									<div class="text-xs text-gray-500">{$i18n.t('Reorder Models')}</div>
+								</div>
+
+								<ModelList bind:modelIds />
+							</div>
+						</div>
+
+						<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
+
+						<div>
+							<div class="flex flex-col w-full">
+								<div class="mb-1 flex justify-between">
+									<div class="text-xs text-gray-500">{$i18n.t('Default Models')}</div>
+								</div>
+
+								{#if defaultModelIds.length > 0}
+									<div class="flex flex-col">
+										{#each defaultModelIds as modelId, modelIdx}
+											<div class=" flex gap-2 w-full justify-between items-center">
+												<div class=" text-sm flex-1 py-1 rounded-lg">
+													{$models.find((model) => model.id === modelId)?.name}
+												</div>
+												<div class="flex-shrink-0">
+													<button
+														type="button"
+														on:click={() => {
+															defaultModelIds = defaultModelIds.filter(
+																(_, idx) => idx !== modelIdx
+															);
+														}}
+													>
+														<Minus strokeWidth="2" className="size-3.5" />
+													</button>
+												</div>
+											</div>
+										{/each}
+									</div>
+								{:else}
+									<div class="text-gray-500 text-xs text-center py-2">
+										{$i18n.t('No models selected')}
+									</div>
+								{/if}
+
+								<hr class=" border-gray-100 dark:border-gray-700/10 my-2.5 w-full" />
+
+								<div class="flex items-center">
+									<select
+										class="w-full py-1 text-sm rounded-lg bg-transparent {selectedModelId
+											? ''
+											: 'text-gray-500'} placeholder:text-gray-300 dark:placeholder:text-gray-700 outline-none"
+										bind:value={selectedModelId}
+									>
+										<option value="">{$i18n.t('Select a model')}</option>
+										{#each $models as model}
+											<option value={model.id} class="bg-gray-50 dark:bg-gray-700"
+												>{model.name}</option
+											>
+										{/each}
+									</select>
+
+									<div>
+										<button
+											type="button"
+											on:click={() => {
+												if (selectedModelId === '') {
+													return;
+												}
+
+												if (defaultModelIds.includes(selectedModelId)) {
+													return;
+												}
+
+												defaultModelIds = [...defaultModelIds, selectedModelId];
+												selectedModelId = '';
+											}}
+										>
+											<Plus className="size-3.5" strokeWidth="2" />
+										</button>
+									</div>
+								</div>
+							</div>
+						</div>
+
+						<div class="flex justify-between pt-3 text-sm font-medium gap-1.5">
+							<Tooltip content={$i18n.t('This will delete all models including custom models')}>
+								<button
+									class="px-3.5 py-1.5 text-sm font-medium dark:bg-black dark:hover:bg-gray-950 dark:text-white bg-white text-black hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center"
+									type="button"
+									on:click={() => {
+										showResetModal = true;
+									}}
+								>
+									<!-- {$i18n.t('Delete All Models')} -->
+									{$i18n.t('Reset All Models')}
+								</button>
+							</Tooltip>
+
+							<button
+								class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full flex flex-row space-x-1 items-center {loading
+									? ' cursor-not-allowed'
+									: ''}"
+								type="submit"
+								disabled={loading}
+							>
+								{$i18n.t('Save')}
+
+								{#if loading}
+									<div class="ml-2 self-center">
+										<svg
+											class=" w-4 h-4"
+											viewBox="0 0 24 24"
+											fill="currentColor"
+											xmlns="http://www.w3.org/2000/svg"
+											><style>
+												.spinner_ajPY {
+													transform-origin: center;
+													animation: spinner_AtaB 0.75s infinite linear;
+												}
+												@keyframes spinner_AtaB {
+													100% {
+														transform: rotate(360deg);
+													}
+												}
+											</style><path
+												d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
+												opacity=".25"
+											/><path
+												d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
+												class="spinner_ajPY"
+											/></svg
+										>
+									</div>
+								{/if}
+							</button>
+						</div>
+					</form>
+				{:else}
+					<div>
+						<Spinner />
+					</div>
+				{/if}
+			</div>
+		</div>
+	</div>
+</Modal>

src/lib/components/admin/Settings/Models/ModelList.svelte

@@ -0,0 +1,58 @@
+<script lang="ts">
+	import Sortable from 'sortablejs';
+
+	import { createEventDispatcher, getContext, onMount } from 'svelte';
+	const i18n = getContext('i18n');
+
+	import { models } from '$lib/stores';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import EllipsisVertical from '$lib/components/icons/EllipsisVertical.svelte';
+
+	export let modelIds = [];
+
+	let sortable = null;
+	let modelListElement = null;
+
+	const positionChangeHandler = () => {
+		const modelList = Array.from(modelListElement.children).map((child) =>
+			child.id.replace('model-item-', '')
+		);
+
+		modelIds = modelList;
+	};
+
+	onMount(() => {
+		sortable = Sortable.create(modelListElement, {
+			animation: 150,
+			onUpdate: async (event) => {
+				positionChangeHandler();
+			}
+		});
+	});
+</script>
+
+{#if modelIds.length > 0}
+	<div class="flex flex-col -translate-x-1" bind:this={modelListElement}>
+		{#each modelIds as modelId, modelIdx (modelId)}
+			<div class=" flex gap-2 w-full justify-between items-center" id="model-item-{modelId}">
+				<Tooltip content={modelId} placement="top-start">
+					<div class="flex items-center gap-1">
+						<EllipsisVertical className="size-4 cursor-move" />
+
+						<div class=" text-sm flex-1 py-1 rounded-lg">
+							{#if $models.find((model) => model.id === modelId)}
+								{$models.find((model) => model.id === modelId).name}
+							{:else}
+								{modelId}
+							{/if}
+						</div>
+					</div>
+				</Tooltip>
+			</div>
+		{/each}
+	</div>
+{:else}
+	<div class="text-gray-500 text-xs text-center py-2">
+		{$i18n.t('No models found')}
+	</div>
+{/if}

src/lib/components/admin/Settings/WebSearch.svelte

@@ -16,6 +16,7 @@
 		'searxng',
 		'google_pse',
 		'brave',
+		'mojeek',
 		'serpstack',
 		'serper',
 		'serply',
@@ -28,13 +29,15 @@
 
 	let youtubeLanguage = 'en';
 	let youtubeTranslation = null;
+	let youtubeProxyUrl = '';
 
 	const submitHandler = async () => {
 		const res = await updateRAGConfig(localStorage.token, {
 			web: webConfig,
 			youtube: {
 				language: youtubeLanguage.split(',').map((lang) => lang.trim()),
-				translation: youtubeTranslation
+				translation: youtubeTranslation,
+				proxy_url: youtubeProxyUrl
 			}
 		});
 	};
@@ -47,6 +50,7 @@
 
 			youtubeLanguage = res.youtube.language.join(',');
 			youtubeTranslation = res.youtube.translation;
+			youtubeProxyUrl = res.youtube.proxy_url;
 		}
 	});
 </script>
@@ -151,6 +155,17 @@
 									bind:value={webConfig.search.brave_search_api_key}
 								/>
 							</div>
+						{:else if webConfig.search.engine === 'mojeek'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Mojeek Search API Key')}
+								</div>
+
+								<SensitiveInput
+									placeholder={$i18n.t('Enter Mojeek Search API Key')}
+									bind:value={webConfig.search.mojeek_search_api_key}
+								/>
+							</div>
 						{:else if webConfig.search.engine === 'serpstack'}
 							<div>
 								<div class=" self-center text-xs font-medium mb-1">
@@ -346,6 +361,21 @@
 						</div>
 					</div>
 				</div>
+
+				<div>
+					<div class=" py-0.5 flex w-full justify-between">
+						<div class=" w-20 text-xs font-medium self-center">{$i18n.t('Proxy URL')}</div>
+						<div class=" flex-1 self-center">
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+								type="text"
+								placeholder={$i18n.t('Enter proxy URL (e.g. https://user:password@host:port)')}
+								bind:value={youtubeProxyUrl}
+								autocomplete="off"
+							/>
+						</div>
+					</div>
+				</div>
 			</div>
 		{/if}
 	</div>

src/lib/components/admin/Users/UserList/UserChatsModal.svelte

@@ -9,13 +9,14 @@
 
 	import Modal from '$lib/components/common/Modal.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import Spinner from '$lib/components/common/Spinner.svelte';
 
 	const i18n = getContext('i18n');
 
 	export let show = false;
 	export let user;
 
-	let chats = [];
+	let chats = null;
 
 	const deleteChatHandler = async (chatId) => {
 		const res = await deleteChatById(localStorage.token, chatId).catch((error) => {
@@ -31,6 +32,8 @@
 				chats = await getChatListByUserId(localStorage.token, user.id);
 			}
 		})();
+	} else {
+		chats = null;
 	}
 
 	let sortKey = 'updated_at'; // default sort key
@@ -46,33 +49,32 @@
 </script>
 
 <Modal size="lg" bind:show>
-	<div>
-		<div class=" flex justify-between dark:text-gray-300 px-5 py-4">
-			<div class=" text-lg font-medium self-center capitalize">
-				{$i18n.t("{{user}}'s Chats", { user: user.name })}
-			</div>
-			<button
-				class="self-center"
-				on:click={() => {
-					show = false;
-				}}
-			>
-				<svg
-					xmlns="http://www.w3.org/2000/svg"
-					viewBox="0 0 20 20"
-					fill="currentColor"
-					class="w-5 h-5"
-				>
-					<path
-						d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
-					/>
-				</svg>
-			</button>
+	<div class=" flex justify-between dark:text-gray-300 px-5 pt-4">
+		<div class=" text-lg font-medium self-center capitalize">
+			{$i18n.t("{{user}}'s Chats", { user: user.name })}
 		</div>
-		<hr class=" dark:border-gray-850" />
+		<button
+			class="self-center"
+			on:click={() => {
+				show = false;
+			}}
+		>
+			<svg
+				xmlns="http://www.w3.org/2000/svg"
+				viewBox="0 0 20 20"
+				fill="currentColor"
+				class="w-5 h-5"
+			>
+				<path
+					d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+				/>
+			</svg>
+		</button>
+	</div>
 
-		<div class="flex flex-col md:flex-row w-full px-5 py-4 md:space-x-4 dark:text-gray-200">
-			<div class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6">
+	<div class="flex flex-col md:flex-row w-full px-5 pt-2 pb-4 md:space-x-4 dark:text-gray-200">
+		<div class=" flex flex-col w-full sm:flex-row sm:justify-center sm:space-x-6">
+			{#if chats}
 				{#if chats.length > 0}
 					<div class="text-left text-sm w-full mb-4 max-h-[22rem] overflow-y-scroll">
 						<div class="relative overflow-x-auto">
@@ -176,7 +178,9 @@
 						{$i18n.t('has no conversations.')}
 					</div>
 				{/if}
-			</div>
+			{:else}
+				<Spinner />
+			{/if}
 		</div>
 	</div>
 </Modal>

src/lib/components/chat/Chat.svelte

@@ -216,7 +216,7 @@
 				} else {
 					message.statusHistory = [data];
 				}
-			} else if (type === 'citation') {
+			} else if (type === 'source' || type === 'citation') {
 				if (data?.type === 'code_execution') {
 					// Code execution; update existing code execution by ID, or add new one.
 					if (!message?.code_executions) {
@@ -235,11 +235,11 @@
 
 					message.code_executions = message.code_executions;
 				} else {
-					// Regular citation.
-					if (message?.citations) {
-						message.citations.push(data);
+					// Regular source.
+					if (message?.sources) {
+						message.sources.push(data);
 					} else {
-						message.citations = [data];
+						message.sources = [data];
 					}
 				}
 			} else if (type === 'message') {
@@ -663,7 +663,8 @@
 				role: m.role,
 				content: m.content,
 				info: m.info ? m.info : undefined,
-				timestamp: m.timestamp
+				timestamp: m.timestamp,
+				...(m.sources ? { sources: m.sources } : {})
 			})),
 			chat_id: chatId,
 			session_id: $socket?.id,
@@ -716,7 +717,8 @@
 				role: m.role,
 				content: m.content,
 				info: m.info ? m.info : undefined,
-				timestamp: m.timestamp
+				timestamp: m.timestamp,
+				...(m.sources ? { sources: m.sources } : {})
 			})),
 			...(event ? { event: event } : {}),
 			chat_id: chatId,
@@ -886,11 +888,10 @@
 		await tick();
 
 		// Reset chat input textarea
-		const chatInputContainer = document.getElementById('chat-input-container');
+		const chatInputElement = document.getElementById('chat-input');
 
-		if (chatInputContainer) {
-			chatInputContainer.value = '';
-			chatInputContainer.style.height = '';
+		if (chatInputElement) {
+			chatInputElement.style.height = '';
 		}
 
 		const _files = JSON.parse(JSON.stringify(files));
@@ -1276,8 +1277,8 @@
 								console.log(line);
 								let data = JSON.parse(line);
 
-								if ('citations' in data) {
-									responseMessage.citations = data.citations;
+								if ('sources' in data) {
+									responseMessage.sources = data.sources;
 									// Only remove status if it was initially set
 									if (model?.info?.meta?.knowledge ?? false) {
 										responseMessage.statusHistory = responseMessage.statusHistory.filter(
@@ -1630,7 +1631,7 @@
 					const textStream = await createOpenAITextStream(res.body, $settings.splitLargeChunks);
 
 					for await (const update of textStream) {
-						const { value, done, citations, selectedModelId, error, usage } = update;
+						const { value, done, sources, selectedModelId, error, usage } = update;
 						if (error) {
 							await handleOpenAIError(error, null, model, responseMessage);
 							break;
@@ -1656,8 +1657,8 @@
 							continue;
 						}
 
-						if (citations) {
-							responseMessage.citations = citations;
+						if (sources) {
+							responseMessage.sources = sources;
 							// Only remove status if it was initially set
 							if (model?.info?.meta?.knowledge ?? false) {
 								responseMessage.statusHistory = responseMessage.statusHistory.filter(
@@ -1936,7 +1937,7 @@
 			if (res && res.ok && res.body) {
 				const textStream = await createOpenAITextStream(res.body, $settings.splitLargeChunks);
 				for await (const update of textStream) {
-					const { value, done, citations, error, usage } = update;
+					const { value, done, sources, error, usage } = update;
 					if (error || done) {
 						break;
 					}
@@ -1975,7 +1976,7 @@
 				}
 			);
 
-			return title;
+			return title ? title : (lastUserMessage?.content ?? 'New Chat');
 		} else {
 			return lastUserMessage?.content ?? 'New Chat';
 		}
@@ -2283,7 +2284,7 @@
 							</div>
 						</div>
 
-						<div class=" pb-[1.6rem]">
+						<div class=" pb-[1rem]">
 							<MessageInput
 								{history}
 								{selectedModels}
@@ -2308,15 +2309,19 @@
 								on:submit={async (e) => {
 									if (e.detail) {
 										await tick();
-										submitPrompt(e.detail.replaceAll('\n\n', '\n'));
+										submitPrompt(
+											($settings?.richTextInput ?? true)
+												? e.detail.replaceAll('\n\n', '\n')
+												: e.detail
+										);
 									}
 								}}
 							/>
 
 							<div
-								class="absolute bottom-1.5 text-xs text-gray-500 text-center line-clamp-1 right-0 left-0"
+								class="absolute bottom-1 text-xs text-gray-500 text-center line-clamp-1 right-0 left-0"
 							>
-								{$i18n.t('LLMs can make mistakes. Verify important information.')}
+								<!-- {$i18n.t('LLMs can make mistakes. Verify important information.')} -->
 							</div>
 						</div>
 					{:else}
@@ -2345,7 +2350,11 @@
 								on:submit={async (e) => {
 									if (e.detail) {
 										await tick();
-										submitPrompt(e.detail.replaceAll('\n\n', '\n'));
+										submitPrompt(
+											($settings?.richTextInput ?? true)
+												? e.detail.replaceAll('\n\n', '\n')
+												: e.detail
+										);
 									}
 								}}
 							/>

src/lib/components/chat/MessageInput.svelte

@@ -18,7 +18,7 @@
 		showControls
 	} from '$lib/stores';
 
-	import { blobToFile, findWordIndices } from '$lib/utils';
+	import { blobToFile, createMessagesList, findWordIndices } from '$lib/utils';
 	import { transcribeAudio } from '$lib/apis/audio';
 	import { uploadFile } from '$lib/apis/files';
 	import { getTools } from '$lib/apis/tools';
@@ -34,6 +34,8 @@
 	import Commands from './MessageInput/Commands.svelte';
 	import XMark from '../icons/XMark.svelte';
 	import RichTextInput from '../common/RichTextInput.svelte';
+	import { generateAutoCompletion } from '$lib/apis';
+	import { error, text } from '@sveltejs/kit';
 
 	const i18n = getContext('i18n');
 
@@ -47,6 +49,9 @@
 	export let atSelectedModel: Model | undefined;
 	export let selectedModels: [''];
 
+	let selectedModelIds = [];
+	$: selectedModelIds = atSelectedModel !== undefined ? [atSelectedModel.id] : selectedModels;
+
 	export let history;
 
 	export let prompt = '';
@@ -75,14 +80,6 @@
 		(model) => $models.find((m) => m.id === model)?.info?.meta?.capabilities?.vision ?? true
 	);
 
-	$: if (prompt) {
-		if (chatInputContainerElement) {
-			chatInputContainerElement.style.height = '';
-			chatInputContainerElement.style.height =
-				Math.min(chatInputContainerElement.scrollHeight, 200) + 'px';
-		}
-	}
-
 	const scrollToBottom = () => {
 		const element = document.getElementById('messages-container');
 		element.scrollTo({
@@ -274,8 +271,8 @@
 
 {#if loaded}
 	<div class="w-full font-primary">
-		<div class=" -mb-0.5 mx-auto inset-x-0 bg-transparent flex justify-center">
-			<div class="flex flex-col px-2.5 max-w-6xl w-full">
+		<div class=" mx-auto inset-x-0 bg-transparent flex justify-center">
+			<div class="flex flex-col px-3 max-w-6xl w-full">
 				<div class="relative">
 					{#if autoScroll === false && history?.currentId}
 						<div
@@ -308,7 +305,7 @@
 				<div class="w-full relative">
 					{#if atSelectedModel !== undefined || selectedToolIds.length > 0 || webSearchEnabled}
 						<div
-							class="px-4 pb-0.5 pt-1.5 text-left w-full flex flex-col absolute bottom-0 left-0 right-0 bg-gradient-to-t from-white dark:from-gray-900 z-10"
+							class="px-3 pb-0.5 pt-1.5 text-left w-full flex flex-col absolute bottom-0 left-0 right-0 bg-gradient-to-t from-white dark:from-gray-900 z-10"
 						>
 							{#if selectedToolIds.length > 0}
 								<div class="flex items-center justify-between w-full">
@@ -321,12 +318,22 @@
 												<span class="relative inline-flex rounded-full size-2 bg-yellow-500" />
 											</span>
 										</div>
-										<div class=" translate-y-[0.5px] line-clamp-1">
-											{selectedToolIds
-												.map((id) => {
-													return $tools ? $tools.find((tool) => tool.id === id)?.name : id;
-												})
-												.join(', ')}
+										<div class=" translate-y-[0.5px] text-ellipsis line-clamp-1 flex">
+											{#each selectedToolIds.map((id) => {
+												return $tools ? $tools.find((t) => t.id === id) : { id: id, name: id };
+											}) as tool, toolIdx (toolIdx)}
+												<Tooltip
+													content={tool?.meta?.description ?? ''}
+													className=" {toolIdx !== 0 ? 'pl-0.5' : ''} flex-shrink-0"
+													placement="top"
+												>
+													{tool.name}
+												</Tooltip>
+
+												{#if toolIdx !== selectedToolIds.length - 1}
+													<span>, </span>
+												{/if}
+											{/each}
 										</div>
 									</div>
 								</div>
@@ -403,7 +410,7 @@
 		</div>
 
 		<div class="{transparentBackground ? 'bg-transparent' : 'bg-white dark:bg-gray-900'} ">
-			<div class="max-w-6xl px-4 mx-auto inset-x-0">
+			<div class="max-w-6xl px-2.5 mx-auto inset-x-0">
 				<div class="">
 					<input
 						bind:this={filesInputElement}
@@ -455,7 +462,7 @@
 							}}
 						>
 							<div
-								class="flex-1 flex flex-col relative w-full rounded-3xl px-1.5 bg-gray-50 dark:bg-gray-850 dark:text-gray-100"
+								class="flex-1 flex flex-col relative w-full rounded-3xl px-1 bg-gray-50 dark:bg-gray-400/5 dark:text-gray-100"
 								dir={$settings?.chatDirection ?? 'LTR'}
 							>
 								{#if files.length > 0}
@@ -540,7 +547,7 @@
 								{/if}
 
 								<div class=" flex">
-									<div class=" ml-0.5 self-end mb-1.5 flex space-x-1">
+									<div class="ml-1 self-end mb-1.5 flex space-x-1">
 										<InputMenu
 											bind:webSearchEnabled
 											bind:selectedToolIds
@@ -555,18 +562,18 @@
 											}}
 										>
 											<button
-												class="bg-gray-50 hover:bg-gray-100 text-gray-800 dark:bg-gray-850 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-2 outline-none focus:outline-none"
+												class="bg-transparent hover:bg-white/80 text-gray-800 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-2 outline-none focus:outline-none"
 												type="button"
 												aria-label="More"
 											>
 												<svg
 													xmlns="http://www.w3.org/2000/svg"
-													viewBox="0 0 16 16"
+													viewBox="0 0 20 20"
 													fill="currentColor"
 													class="size-5"
 												>
 													<path
-														d="M8.75 3.75a.75.75 0 0 0-1.5 0v3.5h-3.5a.75.75 0 0 0 0 1.5h3.5v3.5a.75.75 0 0 0 1.5 0v-3.5h3.5a.75.75 0 0 0 0-1.5h-3.5v-3.5Z"
+														d="M10.75 4.75a.75.75 0 0 0-1.5 0v4.5h-4.5a.75.75 0 0 0 0 1.5h4.5v4.5a.75.75 0 0 0 1.5 0v-4.5h4.5a.75.75 0 0 0 0-1.5h-4.5v-4.5Z"
 													/>
 												</svg>
 											</button>
@@ -575,54 +582,46 @@
 
 									{#if $settings?.richTextInput ?? true}
 										<div
-											bind:this={chatInputContainerElement}
-											id="chat-input-container"
-											class="scrollbar-hidden text-left bg-gray-50 dark:bg-gray-850 dark:text-gray-100 outline-none w-full py-2.5 px-1 rounded-xl resize-none h-[48px] overflow-auto"
+											class="scrollbar-hidden text-left bg-transparent dark:text-gray-100 outline-none w-full py-2.5 px-1 rounded-xl resize-none h-fit max-h-80 overflow-auto"
 										>
 											<RichTextInput
 												bind:this={chatInputElement}
-												id="chat-input"
-												trim={true}
-												placeholder={placeholder ? placeholder : $i18n.t('Send a Message')}
-												largeTextAsFile={$settings?.largeTextAsFile ?? false}
 												bind:value={prompt}
+												id="chat-input"
+												messageInput={true}
 												shiftEnter={!$mobile ||
 													!(
 														'ontouchstart' in window ||
 														navigator.maxTouchPoints > 0 ||
 														navigator.msMaxTouchPoints > 0
 													)}
-												on:enter={async (e) => {
-													if (prompt !== '') {
-														dispatch('submit', prompt);
+												placeholder={placeholder ? placeholder : $i18n.t('Send a Message')}
+												largeTextAsFile={$settings?.largeTextAsFile ?? false}
+												autocomplete={true}
+												generateAutoCompletion={async (text) => {
+													if (selectedModelIds.length === 0 || !selectedModelIds.at(0)) {
+														toast.error($i18n.t('Please select a model first.'));
 													}
-												}}
-												on:input={async (e) => {
-													if (chatInputContainerElement) {
-														chatInputContainerElement.style.height = '';
-														chatInputContainerElement.style.height =
-															Math.min(chatInputContainerElement.scrollHeight, 200) + 'px';
-													}
-												}}
-												on:focus={async (e) => {
-													if (chatInputContainerElement) {
-														chatInputContainerElement.style.height = '';
-														chatInputContainerElement.style.height =
-															Math.min(chatInputContainerElement.scrollHeight, 200) + 'px';
-													}
-												}}
-												on:keypress={(e) => {
-													e = e.detail.event;
+
+													const res = await generateAutoCompletion(
+														localStorage.token,
+														selectedModelIds.at(0),
+														text,
+														history?.currentId
+															? createMessagesList(history, history.currentId)
+															: null
+													).catch((error) => {
+														console.log(error);
+
+														return null;
+													});
+
+													console.log(res);
+													return res;
 												}}
 												on:keydown={async (e) => {
 													e = e.detail.event;
 
-													if (chatInputContainerElement) {
-														chatInputContainerElement.style.height = '';
-														chatInputContainerElement.style.height =
-															Math.min(chatInputContainerElement.scrollHeight, 200) + 'px';
-													}
-
 													const isCtrlPressed = e.ctrlKey || e.metaKey; // metaKey is for Cmd key on Mac
 													const commandsContainerElement =
 														document.getElementById('commands-container');
@@ -662,50 +661,70 @@
 														editButton?.click();
 													}
 
-													if (commandsContainerElement && e.key === 'ArrowUp') {
-														e.preventDefault();
-														commandsElement.selectUp();
+													if (commandsContainerElement) {
+														if (commandsContainerElement && e.key === 'ArrowUp') {
+															e.preventDefault();
+															commandsElement.selectUp();
 
-														const commandOptionButton = [
-															...document.getElementsByClassName('selected-command-option-button')
-														]?.at(-1);
-														commandOptionButton.scrollIntoView({ block: 'center' });
-													}
-
-													if (commandsContainerElement && e.key === 'ArrowDown') {
-														e.preventDefault();
-														commandsElement.selectDown();
-
-														const commandOptionButton = [
-															...document.getElementsByClassName('selected-command-option-button')
-														]?.at(-1);
-														commandOptionButton.scrollIntoView({ block: 'center' });
-													}
-
-													if (commandsContainerElement && e.key === 'Enter') {
-														e.preventDefault();
-
-														const commandOptionButton = [
-															...document.getElementsByClassName('selected-command-option-button')
-														]?.at(-1);
-
-														if (e.shiftKey) {
-															prompt = `${prompt}\n`;
-														} else if (commandOptionButton) {
-															commandOptionButton?.click();
-														} else {
-															document.getElementById('send-message-button')?.click();
+															const commandOptionButton = [
+																...document.getElementsByClassName('selected-command-option-button')
+															]?.at(-1);
+															commandOptionButton.scrollIntoView({ block: 'center' });
 														}
-													}
 
-													if (commandsContainerElement && e.key === 'Tab') {
-														e.preventDefault();
+														if (commandsContainerElement && e.key === 'ArrowDown') {
+															e.preventDefault();
+															commandsElement.selectDown();
 
-														const commandOptionButton = [
-															...document.getElementsByClassName('selected-command-option-button')
-														]?.at(-1);
+															const commandOptionButton = [
+																...document.getElementsByClassName('selected-command-option-button')
+															]?.at(-1);
+															commandOptionButton.scrollIntoView({ block: 'center' });
+														}
 
-														commandOptionButton?.click();
+														if (commandsContainerElement && e.key === 'Tab') {
+															e.preventDefault();
+
+															const commandOptionButton = [
+																...document.getElementsByClassName('selected-command-option-button')
+															]?.at(-1);
+
+															commandOptionButton?.click();
+														}
+
+														if (commandsContainerElement && e.key === 'Enter') {
+															e.preventDefault();
+
+															const commandOptionButton = [
+																...document.getElementsByClassName('selected-command-option-button')
+															]?.at(-1);
+
+															if (commandOptionButton) {
+																commandOptionButton?.click();
+															} else {
+																document.getElementById('send-message-button')?.click();
+															}
+														}
+													} else {
+														if (
+															!$mobile ||
+															!(
+																'ontouchstart' in window ||
+																navigator.maxTouchPoints > 0 ||
+																navigator.msMaxTouchPoints > 0
+															)
+														) {
+															// Prevent Enter key from creating a new line
+															// Uses keyCode '13' for Enter key for chinese/japanese keyboards
+															if (e.keyCode === 13 && !e.shiftKey) {
+																e.preventDefault();
+															}
+
+															// Submit the prompt when Enter key is pressed
+															if (prompt !== '' && e.keyCode === 13 && !e.shiftKey) {
+																dispatch('submit', prompt);
+															}
+														}
 													}
 
 													if (e.key === 'Escape') {
@@ -888,7 +907,7 @@
 													}
 
 													e.target.style.height = '';
-													e.target.style.height = Math.min(e.target.scrollHeight, 200) + 'px';
+													e.target.style.height = Math.min(e.target.scrollHeight, 320) + 'px';
 												}
 
 												if (e.key === 'Escape') {
@@ -901,12 +920,11 @@
 											rows="1"
 											on:input={async (e) => {
 												e.target.style.height = '';
-												e.target.style.height = Math.min(e.target.scrollHeight, 200) + 'px';
-												user = null;
+												e.target.style.height = Math.min(e.target.scrollHeight, 320) + 'px';
 											}}
 											on:focus={async (e) => {
 												e.target.style.height = '';
-												e.target.style.height = Math.min(e.target.scrollHeight, 200) + 'px';
+												e.target.style.height = Math.min(e.target.scrollHeight, 320) + 'px';
 											}}
 											on:paste={async (e) => {
 												const clipboardData = e.clipboardData || window.clipboardData;
@@ -949,12 +967,12 @@
 										/>
 									{/if}
 
-									<div class="self-end mb-2 flex space-x-1 mr-1">
+									<div class="self-end mb-1.5 flex space-x-1 mr-1">
 										{#if !history?.currentId || history.messages[history.currentId]?.done == true}
 											<Tooltip content={$i18n.t('Record voice')}>
 												<button
 													id="voice-input-button"
-													class=" text-gray-600 dark:text-gray-300 hover:bg-gray-50 dark:hover:bg-gray-850 transition rounded-full p-1.5 mr-0.5 self-center"
+													class=" text-gray-600 dark:text-gray-300 hover:text-gray-700 dark:hover:text-gray-200 transition rounded-full p-1.5 mr-0.5 self-center"
 													type="button"
 													on:click={async () => {
 														try {
@@ -998,113 +1016,114 @@
 												</button>
 											</Tooltip>
 										{/if}
+
+										{#if !history.currentId || history.messages[history.currentId]?.done == true}
+											{#if prompt === ''}
+												<div class=" flex items-center">
+													<Tooltip content={$i18n.t('Call')}>
+														<button
+															class=" bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full p-2 self-center"
+															type="button"
+															on:click={async () => {
+																if (selectedModels.length > 1) {
+																	toast.error($i18n.t('Select only one model to call'));
+
+																	return;
+																}
+
+																if ($config.audio.stt.engine === 'web') {
+																	toast.error(
+																		$i18n.t(
+																			'Call feature is not supported when using Web STT engine'
+																		)
+																	);
+
+																	return;
+																}
+																// check if user has access to getUserMedia
+																try {
+																	let stream = await navigator.mediaDevices.getUserMedia({
+																		audio: true
+																	});
+																	// If the user grants the permission, proceed to show the call overlay
+
+																	if (stream) {
+																		const tracks = stream.getTracks();
+																		tracks.forEach((track) => track.stop());
+																	}
+
+																	stream = null;
+
+																	showCallOverlay.set(true);
+																	showControls.set(true);
+																} catch (err) {
+																	// If the user denies the permission or an error occurs, show an error message
+																	toast.error(
+																		$i18n.t('Permission denied when accessing media devices')
+																	);
+																}
+															}}
+															aria-label="Call"
+														>
+															<Headphone className="size-5" />
+														</button>
+													</Tooltip>
+												</div>
+											{:else}
+												<div class=" flex items-center">
+													<Tooltip content={$i18n.t('Send message')}>
+														<button
+															id="send-message-button"
+															class="{prompt !== ''
+																? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
+																: 'text-white bg-gray-200 dark:text-gray-900 dark:bg-gray-700 disabled'} transition rounded-full p-1.5 self-center"
+															type="submit"
+															disabled={prompt === ''}
+														>
+															<svg
+																xmlns="http://www.w3.org/2000/svg"
+																viewBox="0 0 16 16"
+																fill="currentColor"
+																class="size-6"
+															>
+																<path
+																	fill-rule="evenodd"
+																	d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
+																	clip-rule="evenodd"
+																/>
+															</svg>
+														</button>
+													</Tooltip>
+												</div>
+											{/if}
+										{:else}
+											<div class=" flex items-center">
+												<Tooltip content={$i18n.t('Stop')}>
+													<button
+														class="bg-white hover:bg-gray-100 text-gray-800 dark:bg-gray-700 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-1.5"
+														on:click={() => {
+															stopResponse();
+														}}
+													>
+														<svg
+															xmlns="http://www.w3.org/2000/svg"
+															viewBox="0 0 24 24"
+															fill="currentColor"
+															class="size-6"
+														>
+															<path
+																fill-rule="evenodd"
+																d="M2.25 12c0-5.385 4.365-9.75 9.75-9.75s9.75 4.365 9.75 9.75-4.365 9.75-9.75 9.75S2.25 17.385 2.25 12zm6-2.438c0-.724.588-1.312 1.313-1.312h4.874c.725 0 1.313.588 1.313 1.313v4.874c0 .725-.588 1.313-1.313 1.313H9.564a1.312 1.312 0 01-1.313-1.313V9.564z"
+																clip-rule="evenodd"
+															/>
+														</svg>
+													</button>
+												</Tooltip>
+											</div>
+										{/if}
 									</div>
 								</div>
 							</div>
-							<div class="flex items-end w-10">
-								{#if !history.currentId || history.messages[history.currentId]?.done == true}
-									{#if prompt === ''}
-										<div class=" flex items-center mb-1">
-											<Tooltip content={$i18n.t('Call')}>
-												<button
-													class=" text-gray-600 dark:text-gray-300 hover:bg-gray-50 dark:hover:bg-gray-850 transition rounded-full p-2 self-center"
-													type="button"
-													on:click={async () => {
-														if (selectedModels.length > 1) {
-															toast.error($i18n.t('Select only one model to call'));
-
-															return;
-														}
-
-														if ($config.audio.stt.engine === 'web') {
-															toast.error(
-																$i18n.t('Call feature is not supported when using Web STT engine')
-															);
-
-															return;
-														}
-														// check if user has access to getUserMedia
-														try {
-															let stream = await navigator.mediaDevices.getUserMedia({
-																audio: true
-															});
-															// If the user grants the permission, proceed to show the call overlay
-
-															if (stream) {
-																const tracks = stream.getTracks();
-																tracks.forEach((track) => track.stop());
-															}
-
-															stream = null;
-
-															showCallOverlay.set(true);
-															showControls.set(true);
-														} catch (err) {
-															// If the user denies the permission or an error occurs, show an error message
-															toast.error(
-																$i18n.t('Permission denied when accessing media devices')
-															);
-														}
-													}}
-													aria-label="Call"
-												>
-													<Headphone className="size-6" />
-												</button>
-											</Tooltip>
-										</div>
-									{:else}
-										<div class=" flex items-center mb-1">
-											<Tooltip content={$i18n.t('Send message')}>
-												<button
-													id="send-message-button"
-													class="{prompt !== ''
-														? 'bg-black text-white hover:bg-gray-900 dark:bg-white dark:text-black dark:hover:bg-gray-100 '
-														: 'text-white bg-gray-200 dark:text-gray-900 dark:bg-gray-700 disabled'} transition rounded-full p-1.5 m-0.5 self-center"
-													type="submit"
-													disabled={prompt === ''}
-												>
-													<svg
-														xmlns="http://www.w3.org/2000/svg"
-														viewBox="0 0 16 16"
-														fill="currentColor"
-														class="size-6"
-													>
-														<path
-															fill-rule="evenodd"
-															d="M8 14a.75.75 0 0 1-.75-.75V4.56L4.03 7.78a.75.75 0 0 1-1.06-1.06l4.5-4.5a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1-1.06 1.06L8.75 4.56v8.69A.75.75 0 0 1 8 14Z"
-															clip-rule="evenodd"
-														/>
-													</svg>
-												</button>
-											</Tooltip>
-										</div>
-									{/if}
-								{:else}
-									<div class=" flex items-center mb-1.5">
-										<Tooltip content={$i18n.t('Stop')}>
-											<button
-												class="bg-white hover:bg-gray-100 text-gray-800 dark:bg-gray-700 dark:text-white dark:hover:bg-gray-800 transition rounded-full p-1.5"
-												on:click={() => {
-													stopResponse();
-												}}
-											>
-												<svg
-													xmlns="http://www.w3.org/2000/svg"
-													viewBox="0 0 24 24"
-													fill="currentColor"
-													class="size-6"
-												>
-													<path
-														fill-rule="evenodd"
-														d="M2.25 12c0-5.385 4.365-9.75 9.75-9.75s9.75 4.365 9.75 9.75-4.365 9.75-9.75 9.75S2.25 17.385 2.25 12zm6-2.438c0-.724.588-1.312 1.313-1.312h4.874c.725 0 1.313.588 1.313 1.313v4.874c0 .725-.588 1.313-1.313 1.313H9.564a1.312 1.312 0 01-1.313-1.313V9.564z"
-														clip-rule="evenodd"
-													/>
-												</svg>
-											</button>
-										</Tooltip>
-									</div>
-								{/if}
-							</div>
 						</form>
 					{/if}
 				</div>

src/lib/components/chat/MessageInput/Commands.svelte

@@ -106,7 +106,7 @@
 	{:else}
 		<div
 			id="commands-container"
-			class="pl-3 pr-14 mb-3 text-left w-full absolute bottom-0 left-0 right-0 z-10"
+			class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 		>
 			<div class="flex w-full rounded-xl border border-gray-50 dark:border-gray-850">
 				<div

src/lib/components/chat/MessageInput/Commands/Knowledge.svelte

@@ -159,7 +159,7 @@
 {#if filteredItems.length > 0 || prompt.split(' ')?.at(0)?.substring(1).startsWith('http')}
 	<div
 		id="commands-container"
-		class="pl-3 pr-14 mb-3 text-left w-full absolute bottom-0 left-0 right-0 z-10"
+		class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 	>
 		<div class="flex w-full rounded-xl border border-gray-50 dark:border-gray-850">
 			<div

src/lib/components/chat/MessageInput/Commands/Models.svelte

@@ -68,7 +68,7 @@
 {#if filteredItems.length > 0}
 	<div
 		id="commands-container"
-		class="pl-3 pr-14 mb-3 text-left w-full absolute bottom-0 left-0 right-0 z-10"
+		class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 	>
 		<div class="flex w-full rounded-xl border border-gray-50 dark:border-gray-850">
 			<div

src/lib/components/chat/MessageInput/Commands/Prompts.svelte

@@ -137,7 +137,7 @@
 {#if filteredPrompts.length > 0}
 	<div
 		id="commands-container"
-		class="pl-3 pr-14 mb-3 text-left w-full absolute bottom-0 left-0 right-0 z-10"
+		class="px-2 mb-2 text-left w-full absolute bottom-0 left-0 right-0 z-10"
 	>
 		<div class="flex w-full rounded-xl border border-gray-50 dark:border-gray-850">
 			<div

src/lib/components/chat/Messages/Citations.svelte

@@ -7,9 +7,9 @@
 
 	const i18n = getContext('i18n');
 
-	export let citations = [];
+	export let sources = [];
 
-	let _citations = [];
+	let citations = [];
 	let showPercentage = false;
 	let showRelevance = true;
 
@@ -17,8 +17,8 @@
 	let selectedCitation: any = null;
 	let isCollapsibleOpen = false;
 
-	function calculateShowRelevance(citations: any[]) {
-		const distances = citations.flatMap((citation) => citation.distances ?? []);
+	function calculateShowRelevance(sources: any[]) {
+		const distances = sources.flatMap((citation) => citation.distances ?? []);
 		const inRange = distances.filter((d) => d !== undefined && d >= -1 && d <= 1).length;
 		const outOfRange = distances.filter((d) => d !== undefined && (d < -1 || d > 1)).length;
 
@@ -36,25 +36,31 @@
 		return true;
 	}
 
-	function shouldShowPercentage(citations: any[]) {
-		const distances = citations.flatMap((citation) => citation.distances ?? []);
+	function shouldShowPercentage(sources: any[]) {
+		const distances = sources.flatMap((citation) => citation.distances ?? []);
 		return distances.every((d) => d !== undefined && d >= -1 && d <= 1);
 	}
 
 	$: {
-		_citations = citations.reduce((acc, citation) => {
-			citation.document.forEach((document, index) => {
-				const metadata = citation.metadata?.[index];
-				const distance = citation.distances?.[index];
+		citations = sources.reduce((acc, source) => {
+			if (Object.keys(source).length === 0) {
+				return acc;
+			}
+
+			source.document.forEach((document, index) => {
+				const metadata = source.metadata?.[index];
+				const distance = source.distances?.[index];
+
+				// Within the same citation there could be multiple documents
 				const id = metadata?.source ?? 'N/A';
-				let source = citation?.source;
+				let _source = source?.source;
 
 				if (metadata?.name) {
-					source = { ...source, name: metadata.name };
+					_source = { ..._source, name: metadata.name };
 				}
 
 				if (id.startsWith('http://') || id.startsWith('https://')) {
-					source = { ...source, name: id, url: id };
+					_source = { ..._source, name: id, url: id };
 				}
 
 				const existingSource = acc.find((item) => item.id === id);
@@ -66,7 +72,7 @@
 				} else {
 					acc.push({
 						id: id,
-						source: source,
+						source: _source,
 						document: [document],
 						metadata: metadata ? [metadata] : [],
 						distances: distance !== undefined ? [distance] : undefined
@@ -76,8 +82,8 @@
 			return acc;
 		}, []);
 
-		showRelevance = calculateShowRelevance(_citations);
-		showPercentage = shouldShowPercentage(_citations);
+		showRelevance = calculateShowRelevance(citations);
+		showPercentage = shouldShowPercentage(citations);
 	}
 </script>
 
@@ -88,24 +94,27 @@
 	{showRelevance}
 />
 
-{#if _citations.length > 0}
+{#if citations.length > 0}
 	<div class=" py-0.5 -mx-0.5 w-full flex gap-1 items-center flex-wrap">
-		{#if _citations.length <= 3}
+		{#if citations.length <= 3}
 			<div class="flex text-xs font-medium">
-				{#each _citations as citation, idx}
+				{#each citations as citation, idx}
 					<button
-						class="no-toggle outline-none flex dark:text-gray-300 p-1 bg-gray-50 hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 transition rounded-xl max-w-96"
+						id={`source-${citation.source.name}`}
+						class="no-toggle outline-none flex dark:text-gray-300 p-1 bg-white dark:bg-gray-900 rounded-xl max-w-96"
 						on:click={() => {
 							showCitationModal = true;
 							selectedCitation = citation;
 						}}
 					>
-						{#if _citations.every((c) => c.distances !== undefined)}
+						{#if citations.every((c) => c.distances !== undefined)}
 							<div class="bg-gray-50 dark:bg-gray-800 rounded-full size-4">
 								{idx + 1}
 							</div>
 						{/if}
-						<div class="flex-1 mx-1 line-clamp-1 truncate">
+						<div
+							class="flex-1 mx-1 line-clamp-1 text-black/60 hover:text-black dark:text-white/60 dark:hover:text-white transition"
+						>
 							{citation.source.name}
 						</div>
 					</button>
@@ -120,7 +129,7 @@
 						<span class="whitespace-nowrap hidden sm:inline">{$i18n.t('References from')}</span>
 						<div class="flex items-center">
 							<div class="flex text-xs font-medium items-center">
-								{#each _citations.slice(0, 2) as citation, idx}
+								{#each citations.slice(0, 2) as citation, idx}
 									<button
 										class="no-toggle outline-none flex dark:text-gray-300 p-1 bg-gray-50 hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 transition rounded-xl max-w-96"
 										on:click={() => {
@@ -131,7 +140,7 @@
 											e.stopPropagation();
 										}}
 									>
-										{#if _citations.every((c) => c.distances !== undefined)}
+										{#if citations.every((c) => c.distances !== undefined)}
 											<div class="bg-gray-50 dark:bg-gray-800 rounded-full size-4">
 												{idx + 1}
 											</div>
@@ -145,7 +154,7 @@
 						</div>
 						<div class="flex items-center gap-1 whitespace-nowrap">
 							<span class="hidden sm:inline">{$i18n.t('and')}</span>
-							{_citations.length - 2}
+							{citations.length - 2}
 							<span>{$i18n.t('more')}</span>
 						</div>
 					</div>
@@ -159,7 +168,7 @@
 				</div>
 				<div slot="content">
 					<div class="flex text-xs font-medium">
-						{#each _citations as citation, idx}
+						{#each citations as citation, idx}
 							<button
 								class="no-toggle outline-none flex dark:text-gray-300 p-1 bg-gray-50 hover:bg-gray-100 dark:bg-gray-900 dark:hover:bg-gray-850 transition rounded-xl max-w-96"
 								on:click={() => {
@@ -167,7 +176,7 @@
 									selectedCitation = citation;
 								}}
 							>
-								{#if _citations.every((c) => c.distances !== undefined)}
+								{#if citations.every((c) => c.distances !== undefined)}
 									<div class="bg-gray-50 dark:bg-gray-800 rounded-full size-4">
 										{idx + 1}
 									</div>

src/lib/components/chat/Messages/CitationsModal.svelte

@@ -38,7 +38,9 @@
 			};
 		});
 		if (mergedDocuments.every((doc) => doc.distance !== undefined)) {
-			mergedDocuments.sort((a, b) => (a.distance ?? Infinity) - (b.distance ?? Infinity));
+			mergedDocuments = mergedDocuments.sort(
+				(a, b) => (b.distance ?? Infinity) - (a.distance ?? Infinity)
+			);
 		}
 	}
 </script>

src/lib/components/chat/Messages/ContentRenderer.svelte

@@ -7,13 +7,16 @@
 	import LightBlub from '$lib/components/icons/LightBlub.svelte';
 	import { chatId, mobile, showArtifacts, showControls, showOverview } from '$lib/stores';
 	import ChatBubble from '$lib/components/icons/ChatBubble.svelte';
+	import { stringify } from 'postcss';
 
 	export let id;
 	export let content;
 	export let model = null;
+	export let sources = null;
 
 	export let save = false;
 	export let floatingButtons = true;
+	export let onSourceClick = () => {};
 
 	let contentContainerElement;
 	let buttonsContainerElement;
@@ -129,6 +132,32 @@
 		{content}
 		{model}
 		{save}
+		sourceIds={(sources ?? []).reduce((acc, s) => {
+			let ids = [];
+			s.document.forEach((document, index) => {
+				const metadata = s.metadata?.[index];
+				const id = metadata?.source ?? 'N/A';
+
+				if (metadata?.name) {
+					ids.push(metadata.name);
+					return ids;
+				}
+
+				if (id.startsWith('http://') || id.startsWith('https://')) {
+					ids.push(id);
+				} else {
+					ids.push(s?.source?.name ?? id);
+				}
+
+				return ids;
+			});
+
+			acc = [...acc, ...ids];
+
+			// remove duplicates
+			return acc.filter((item, index) => acc.indexOf(item) === index);
+		}, [])}
+		{onSourceClick}
 		on:update={(e) => {
 			dispatch('update', e.detail);
 		}}

src/lib/components/chat/Messages/Error.svelte

@@ -4,9 +4,9 @@
 	export let content = '';
 </script>
 
-<div class="flex my-2 gap-2.5 border px-4 py-3 border-red-800 bg-red-800/30 rounded-lg">
+<div class="flex my-2 gap-2.5 border px-4 py-3 border-red-600/10 bg-red-600/10 rounded-lg">
 	<div class=" self-start mt-0.5">
-		<Info className="size-5" />
+		<Info className="size-5 text-red-700 dark:text-red-400" />
 	</div>
 
 	<div class=" self-center text-sm">

src/lib/components/chat/Messages/Markdown.svelte

@@ -16,6 +16,9 @@
 	export let model = null;
 	export let save = false;
 
+	export let sourceIds = [];
+	export let onSourceClick = () => {};
+
 	let tokens = [];
 
 	const options = {
@@ -28,7 +31,7 @@
 	$: (async () => {
 		if (content) {
 			tokens = marked.lexer(
-				replaceTokens(processResponseContent(content), model?.name, $user?.name)
+				replaceTokens(processResponseContent(content), sourceIds, model?.name, $user?.name)
 			);
 		}
 	})();
@@ -39,6 +42,7 @@
 		{tokens}
 		{id}
 		{save}
+		{onSourceClick}
 		on:update={(e) => {
 			dispatch('update', e.detail);
 		}}

src/lib/components/chat/Messages/Markdown/MarkdownInlineTokens.svelte

@@ -12,9 +12,11 @@
 
 	import Image from '$lib/components/common/Image.svelte';
 	import KatexRenderer from './KatexRenderer.svelte';
+	import Source from './Source.svelte';
 
 	export let id: string;
 	export let tokens: Token[];
+	export let onSourceClick: Function = () => {};
 </script>
 
 {#each tokens as token}
@@ -26,13 +28,15 @@
 			{@html html}
 		{:else if token.text.includes(`<iframe src="${WEBUI_BASE_URL}/api/v1/files/`)}
 			{@html `${token.text}`}
+		{:else if token.text.includes(`<source_id`)}
+			<Source {token} onClick={onSourceClick} />
 		{:else}
 			{token.text}
 		{/if}
 	{:else if token.type === 'link'}
 		{#if token.tokens}
 			<a href={token.href} target="_blank" rel="nofollow" title={token.title}>
-				<svelte:self id={`${id}-a`} tokens={token.tokens} />
+				<svelte:self id={`${id}-a`} tokens={token.tokens} {onSourceClick} />
 			</a>
 		{:else}
 			<a href={token.href} target="_blank" rel="nofollow" title={token.title}>{token.text}</a>
@@ -41,11 +45,11 @@
 		<Image src={token.href} alt={token.text} />
 	{:else if token.type === 'strong'}
 		<strong>
-			<svelte:self id={`${id}-strong`} tokens={token.tokens} />
+			<svelte:self id={`${id}-strong`} tokens={token.tokens} {onSourceClick} />
 		</strong>
 	{:else if token.type === 'em'}
 		<em>
-			<svelte:self id={`${id}-em`} tokens={token.tokens} />
+			<svelte:self id={`${id}-em`} tokens={token.tokens} {onSourceClick} />
 		</em>
 	{:else if token.type === 'codespan'}
 		<!-- svelte-ignore a11y-click-events-have-key-events -->
@@ -61,7 +65,7 @@
 		<br />
 	{:else if token.type === 'del'}
 		<del>
-			<svelte:self id={`${id}-del`} tokens={token.tokens} />
+			<svelte:self id={`${id}-del`} tokens={token.tokens} {onSourceClick} />
 		</del>
 	{:else if token.type === 'inlineKatex'}
 		{#if token.text}

src/lib/components/chat/Messages/Markdown/MarkdownTokens.svelte

@@ -25,6 +25,7 @@
 	export let top = true;
 
 	export let save = false;
+	export let onSourceClick: Function = () => {};
 
 	const headerComponent = (depth: number) => {
 		return 'h' + depth;
@@ -59,10 +60,10 @@
 <!-- {JSON.stringify(tokens)} -->
 {#each tokens as token, tokenIdx (tokenIdx)}
 	{#if token.type === 'hr'}
-		<hr />
+		<hr class=" border-gray-50 dark:border-gray-850" />
 	{:else if token.type === 'heading'}
 		<svelte:element this={headerComponent(token.depth)}>
-			<MarkdownInlineTokens id={`${id}-${tokenIdx}-h`} tokens={token.tokens} />
+			<MarkdownInlineTokens id={`${id}-${tokenIdx}-h`} tokens={token.tokens} {onSourceClick} />
 		</svelte:element>
 	{:else if token.type === 'code'}
 		{#if token.raw.includes('```')}
@@ -88,11 +89,9 @@
 		{/if}
 	{:else if token.type === 'table'}
 		<div class="relative w-full group">
-			<div
-				class="scrollbar-hidden relative whitespace-nowrap overflow-x-auto max-w-full rounded-lg"
-			>
+			<div class="scrollbar-hidden relative overflow-x-auto max-w-full rounded-lg">
 				<table
-					class="table-auto w-full text-sm text-left text-gray-500 dark:text-gray-400 max-w-full rounded-xl"
+					class=" w-full text-sm text-left text-gray-500 dark:text-gray-400 max-w-full rounded-xl"
 				>
 					<thead
 						class="text-xs text-gray-700 uppercase bg-gray-50 dark:bg-gray-850 dark:text-gray-400 border-none"
@@ -101,14 +100,17 @@
 							{#each token.header as header, headerIdx}
 								<th
 									scope="col"
-									class="!px-2 !py-1.5 cursor-pointer select-none border border-gray-50 dark:border-gray-850"
+									class="!px-3 !py-1.5 cursor-pointer select-none border border-gray-50 dark:border-gray-850"
 									style={token.align[headerIdx] ? '' : `text-align: ${token.align[headerIdx]}`}
 								>
-									<div class="flex gap-1.5 items-center">
-										<MarkdownInlineTokens
-											id={`${id}-${tokenIdx}-header-${headerIdx}`}
-											tokens={header.tokens}
-										/>
+									<div class="flex flex-col gap-1.5 text-left">
+										<div class="flex-shrink-0 break-normal">
+											<MarkdownInlineTokens
+												id={`${id}-${tokenIdx}-header-${headerIdx}`}
+												tokens={header.tokens}
+												{onSourceClick}
+											/>
+										</div>
 									</div>
 								</th>
 							{/each}
@@ -119,13 +121,14 @@
 							<tr class="bg-white dark:bg-gray-900 dark:border-gray-850 text-xs">
 								{#each row ?? [] as cell, cellIdx}
 									<td
-										class="!px-2 !py-1.5 font-medium text-gray-900 dark:text-white w-max border border-gray-50 dark:border-gray-850"
+										class="!px-3 !py-1.5 text-gray-900 dark:text-white w-max border border-gray-50 dark:border-gray-850"
 										style={token.align[cellIdx] ? '' : `text-align: ${token.align[cellIdx]}`}
 									>
-										<div class="flex">
+										<div class="flex flex-col break-normal">
 											<MarkdownInlineTokens
 												id={`${id}-${tokenIdx}-row-${rowIdx}-${cellIdx}`}
 												tokens={cell.tokens}
+												{onSourceClick}
 											/>
 										</div>
 									</td>
@@ -205,19 +208,27 @@
 		></iframe>
 	{:else if token.type === 'paragraph'}
 		<p>
-			<MarkdownInlineTokens id={`${id}-${tokenIdx}-p`} tokens={token.tokens ?? []} />
+			<MarkdownInlineTokens
+				id={`${id}-${tokenIdx}-p`}
+				tokens={token.tokens ?? []}
+				{onSourceClick}
+			/>
 		</p>
 	{:else if token.type === 'text'}
 		{#if top}
 			<p>
 				{#if token.tokens}
-					<MarkdownInlineTokens id={`${id}-${tokenIdx}-t`} tokens={token.tokens} />
+					<MarkdownInlineTokens id={`${id}-${tokenIdx}-t`} tokens={token.tokens} {onSourceClick} />
 				{:else}
 					{unescapeHtml(token.text)}
 				{/if}
 			</p>
 		{:else if token.tokens}
-			<MarkdownInlineTokens id={`${id}-${tokenIdx}-p`} tokens={token.tokens ?? []} />
+			<MarkdownInlineTokens
+				id={`${id}-${tokenIdx}-p`}
+				tokens={token.tokens ?? []}
+				{onSourceClick}
+			/>
 		{:else}
 			{unescapeHtml(token.text)}
 		{/if}

src/lib/components/chat/Messages/Markdown/Source.svelte

@@ -0,0 +1,25 @@
+<script lang="ts">
+	export let token;
+	export let onClick: Function = () => {};
+
+	let id = '';
+	function extractDataAttribute(input) {
+		// Use a regular expression to extract the value of the `data` attribute
+		const match = input.match(/data="([^"]*)"/);
+		// Check if a match was found and return the first captured group
+		return match ? match[1] : null;
+	}
+
+	$: id = extractDataAttribute(token.text);
+</script>
+
+<button
+	class="text-xs font-medium w-fit translate-y-[2px] px-2 py-0.5 dark:bg-white/5 dark:text-white/60 dark:hover:text-white bg-gray-50 text-black/60 hover:text-black transition rounded-lg"
+	on:click={() => {
+		onClick(id);
+	}}
+>
+	<span class="line-clamp-1">
+		{id}
+	</span>
+</button>

src/lib/components/chat/Messages/RateComment.svelte

@@ -38,6 +38,7 @@
 	let selectedReason = null;
 	let comment = '';
 
+	let detailedRating = null;
 	let selectedModel = null;
 
 	$: if (message?.annotation?.rating === 1) {
@@ -56,6 +57,7 @@
 		tags = (message?.annotation?.tags ?? []).map((tag) => ({
 			name: tag
 		}));
+		detailedRating = message?.annotation?.details?.rating ?? null;
 	};
 
 	onMount(() => {
@@ -79,7 +81,10 @@
 		dispatch('save', {
 			reason: selectedReason,
 			comment: comment,
-			tags: tags.map((tag) => tag.name)
+			tags: tags.map((tag) => tag.name),
+			details: {
+				rating: detailedRating
+			}
 		});
 
 		toast.success($i18n.t('Thanks for your feedback!'));
@@ -100,7 +105,9 @@
 	id="message-feedback-{message.id}"
 >
 	<div class="flex justify-between items-center">
-		<div class=" text-sm">{$i18n.t('Tell us more:')}</div>
+		<div class="text-sm font-medium">{$i18n.t('How would you rate this response?')}</div>
+
+		<!-- <div class=" text-sm">{$i18n.t('Tell us more:')}</div> -->
 
 		<button
 			on:click={() => {
@@ -120,53 +127,89 @@
 		</button>
 	</div>
 
-	{#if reasons.length > 0}
-		<div class="flex flex-wrap gap-1.5 text-sm mt-2.5">
-			{#each reasons as reason}
-				<button
-					class="px-3 py-0.5 border border-gray-50 dark:border-gray-850 hover:bg-gray-100 dark:hover:bg-gray-850 {selectedReason ===
-					reason
-						? 'bg-gray-200 dark:bg-gray-800'
-						: ''} transition rounded-lg"
-					on:click={() => {
-						selectedReason = reason;
-					}}
-				>
-					{#if reason === 'accurate_information'}
-						{$i18n.t('Accurate information')}
-					{:else if reason === 'followed_instructions_perfectly'}
-						{$i18n.t('Followed instructions perfectly')}
-					{:else if reason === 'showcased_creativity'}
-						{$i18n.t('Showcased creativity')}
-					{:else if reason === 'positive_attitude'}
-						{$i18n.t('Positive attitude')}
-					{:else if reason === 'attention_to_detail'}
-						{$i18n.t('Attention to detail')}
-					{:else if reason === 'thorough_explanation'}
-						{$i18n.t('Thorough explanation')}
-					{:else if reason === 'dont_like_the_style'}
-						{$i18n.t("Don't like the style")}
-					{:else if reason === 'too_verbose'}
-						{$i18n.t('Too verbose')}
-					{:else if reason === 'not_helpful'}
-						{$i18n.t('Not helpful')}
-					{:else if reason === 'not_factually_correct'}
-						{$i18n.t('Not factually correct')}
-					{:else if reason === 'didnt_fully_follow_instructions'}
-						{$i18n.t("Didn't fully follow instructions")}
-					{:else if reason === 'refused_when_it_shouldnt_have'}
-						{$i18n.t("Refused when it shouldn't have")}
-					{:else if reason === 'being_lazy'}
-						{$i18n.t('Being lazy')}
-					{:else if reason === 'other'}
-						{$i18n.t('Other')}
-					{:else}
-						{reason}
-					{/if}
-				</button>
-			{/each}
+	<div class="w-full flex justify-center">
+		<div class=" relative w-fit">
+			<div class="mt-1.5 w-fit flex gap-1 pb-5">
+				<!-- 1-10 scale -->
+				{#each Array.from({ length: 10 }).map((_, i) => i + 1) as rating}
+					<button
+						class="size-7 text-sm border border-gray-50 dark:border-gray-850 hover:bg-gray-50 dark:hover:bg-gray-850 {detailedRating ===
+						rating
+							? 'bg-gray-100 dark:bg-gray-800'
+							: ''} transition rounded-full disabled:cursor-not-allowed disabled:text-gray-500 disabled:bg-white disabled:dark:bg-gray-900"
+						on:click={() => {
+							detailedRating = rating;
+						}}
+						disabled={message?.annotation?.rating === -1 ? rating > 5 : rating < 6}
+					>
+						{rating}
+					</button>
+				{/each}
+			</div>
+
+			<div class="absolute bottom-0 left-0 right-0 flex justify-between text-xs">
+				<div>
+					1 - {$i18n.t('Awful')}
+				</div>
+
+				<div>
+					10 - {$i18n.t('Amazing')}
+				</div>
+			</div>
 		</div>
-	{/if}
+	</div>
+
+	<div>
+		{#if reasons.length > 0}
+			<div class="text-sm mt-1.5 font-medium">{$i18n.t('Why?')}</div>
+
+			<div class="flex flex-wrap gap-1.5 text-sm mt-1.5">
+				{#each reasons as reason}
+					<button
+						class="px-3 py-0.5 border border-gray-50 dark:border-gray-850 hover:bg-gray-50 dark:hover:bg-gray-850 {selectedReason ===
+						reason
+							? 'bg-gray-100 dark:bg-gray-800'
+							: ''} transition rounded-xl"
+						on:click={() => {
+							selectedReason = reason;
+						}}
+					>
+						{#if reason === 'accurate_information'}
+							{$i18n.t('Accurate information')}
+						{:else if reason === 'followed_instructions_perfectly'}
+							{$i18n.t('Followed instructions perfectly')}
+						{:else if reason === 'showcased_creativity'}
+							{$i18n.t('Showcased creativity')}
+						{:else if reason === 'positive_attitude'}
+							{$i18n.t('Positive attitude')}
+						{:else if reason === 'attention_to_detail'}
+							{$i18n.t('Attention to detail')}
+						{:else if reason === 'thorough_explanation'}
+							{$i18n.t('Thorough explanation')}
+						{:else if reason === 'dont_like_the_style'}
+							{$i18n.t("Don't like the style")}
+						{:else if reason === 'too_verbose'}
+							{$i18n.t('Too verbose')}
+						{:else if reason === 'not_helpful'}
+							{$i18n.t('Not helpful')}
+						{:else if reason === 'not_factually_correct'}
+							{$i18n.t('Not factually correct')}
+						{:else if reason === 'didnt_fully_follow_instructions'}
+							{$i18n.t("Didn't fully follow instructions")}
+						{:else if reason === 'refused_when_it_shouldnt_have'}
+							{$i18n.t("Refused when it shouldn't have")}
+						{:else if reason === 'being_lazy'}
+							{$i18n.t('Being lazy')}
+						{:else if reason === 'other'}
+							{$i18n.t('Other')}
+						{:else}
+							{reason}
+						{/if}
+					</button>
+				{/each}
+			</div>
+		{/if}
+	</div>
 
 	<div class="mt-2">
 		<textarea
@@ -195,7 +238,7 @@
 		</div>
 
 		<button
-			class=" bg-emerald-700 hover:bg-emerald-800 transition text-white text-sm font-medium rounded-xl px-3.5 py-1.5"
+			class="px-3.5 py-1.5 text-sm font-medium bg-black hover:bg-gray-900 text-white dark:bg-white dark:text-black dark:hover:bg-gray-100 transition rounded-full"
 			on:click={() => {
 				saveHandler();
 			}}

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -64,7 +64,7 @@
 		};
 		done: boolean;
 		error?: boolean | { content: string };
-		citations?: string[];
+		sources?: string[];
 		code_executions?: {
 			uuid: string;
 			name: string;
@@ -340,19 +340,16 @@
 
 	let feedbackLoading = false;
 
-	const feedbackHandler = async (
-		rating: number | null = null,
-		annotation: object | null = null
-	) => {
+	const feedbackHandler = async (rating: number | null = null, details: object | null = null) => {
 		feedbackLoading = true;
-		console.log('Feedback', rating, annotation);
+		console.log('Feedback', rating, details);
 
 		const updatedMessage = {
 			...message,
 			annotation: {
 				...(message?.annotation ?? {}),
 				...(rating !== null ? { rating: rating } : {}),
-				...(annotation ? annotation : {})
+				...(details ? details : {})
 			}
 		};
 
@@ -429,7 +426,7 @@
 
 		await tick();
 
-		if (!annotation) {
+		if (!details) {
 			showRateComment = true;
 
 			if (!updatedMessage.annotation?.tags) {
@@ -624,9 +621,18 @@
 									<ContentRenderer
 										id={message.id}
 										content={message.content}
+										sources={message.sources}
 										floatingButtons={message?.done}
 										save={!readOnly}
 										{model}
+										onSourceClick={(e) => {
+											console.log(e);
+											const sourceButton = document.getElementById(`source-${e}`);
+
+											if (sourceButton) {
+												sourceButton.click();
+											}
+										}}
 										on:update={(e) => {
 											const { raw, oldContent, newContent } = e.detail;
 
@@ -652,12 +658,12 @@
 									/>
 								{/if}
 
-								{#if message.error}
+								{#if message?.error}
 									<Error content={message?.error?.content ?? message.content} />
 								{/if}
 
-								{#if message.citations && (model?.info?.meta?.capabilities?.citations ?? true)}
-									<Citations citations={message.citations} />
+								{#if (message?.sources || message?.citations) && (model?.info?.meta?.capabilities?.citations ?? true)}
+									<Citations sources={message?.sources ?? message?.citations} />
 								{/if}
 
 								{#if message.code_executions}
@@ -1194,9 +1200,7 @@
 							bind:show={showRateComment}
 							on:save={async (e) => {
 								await feedbackHandler(null, {
-									tags: e.detail.tags,
-									comment: e.detail.comment,
-									reason: e.detail.reason
+									...e.detail
 								});
 							}}
 						/>

src/lib/components/chat/Messages/UserMessage.svelte

@@ -5,11 +5,7 @@
 
 	import { models, settings } from '$lib/stores';
 	import { user as _user } from '$lib/stores';
-	import {
-		copyToClipboard as _copyToClipboard,
-		processResponseContent,
-		replaceTokens
-	} from '$lib/utils';
+	import { copyToClipboard as _copyToClipboard } from '$lib/utils';
 
 	import Name from './Name.svelte';
 	import ProfileImage from './ProfileImage.svelte';

src/lib/components/chat/ModelSelector.svelte

@@ -5,9 +5,7 @@
 	import Selector from './ModelSelector/Selector.svelte';
 	import Tooltip from '../common/Tooltip.svelte';
 
-	import { setDefaultModels } from '$lib/apis/configs';
 	import { updateUserSettings } from '$lib/apis/users';
-
 	const i18n = getContext('i18n');
 
 	export let selectedModels = [''];

src/lib/components/chat/Settings/General.svelte

@@ -55,6 +55,7 @@
 		mirostat_tau: null,
 		top_k: null,
 		top_p: null,
+		min_p: null,
 		stop: null,
 		tfs_z: null,
 		num_ctx: null,
@@ -340,6 +341,7 @@
 						mirostat_tau: params.mirostat_tau !== null ? params.mirostat_tau : undefined,
 						top_k: params.top_k !== null ? params.top_k : undefined,
 						top_p: params.top_p !== null ? params.top_p : undefined,
+						min_p: params.min_p !== null ? params.min_p : undefined,
 						tfs_z: params.tfs_z !== null ? params.tfs_z : undefined,
 						num_ctx: params.num_ctx !== null ? params.num_ctx : undefined,
 						num_batch: params.num_batch !== null ? params.num_batch : undefined,

src/lib/components/common/Banner.svelte

@@ -2,6 +2,8 @@
 	import type { Banner } from '$lib/types';
 	import { onMount, createEventDispatcher } from 'svelte';
 	import { fade } from 'svelte/transition';
+	import DOMPurify from 'dompurify';
+	import { marked } from 'marked';
 
 	const dispatch = createEventDispatcher();
 
@@ -81,7 +83,7 @@
 				</div>
 
 				<div class="flex-1 text-xs text-gray-700 dark:text-white">
-					{banner.content}
+					{@html marked.parse(DOMPurify.sanitize(banner.content))}
 				</div>
 			</div>
 

src/lib/components/common/FileItem.svelte

@@ -5,6 +5,7 @@
 	import FileItemModal from './FileItemModal.svelte';
 	import GarbageBin from '../icons/GarbageBin.svelte';
 	import Spinner from './Spinner.svelte';
+	import Tooltip from './Tooltip.svelte';
 
 	const i18n = getContext('i18n');
 	const dispatch = createEventDispatcher();
@@ -18,6 +19,7 @@
 
 	export let item = null;
 	export let edit = false;
+	export let small = false;
 
 	export let name: string;
 	export let type: string;
@@ -31,7 +33,9 @@
 {/if}
 
 <button
-	class="relative group p-1.5 {className} flex items-center {colorClassName} rounded-2xl text-left"
+	class="relative group p-1.5 {className} flex items-center gap-1 {colorClassName} {small
+		? 'rounded-xl'
+		: 'rounded-2xl'} text-left"
 	type="button"
 	on:click={async () => {
 		if (item?.file?.data?.content) {
@@ -49,48 +53,66 @@
 		dispatch('click');
 	}}
 >
-	<div class="p-3 bg-black/20 dark:bg-white/10 text-white rounded-xl">
-		{#if !loading}
-			<svg
-				xmlns="http://www.w3.org/2000/svg"
-				viewBox="0 0 24 24"
-				fill="currentColor"
-				class=" size-5"
-			>
-				<path
-					fill-rule="evenodd"
-					d="M5.625 1.5c-1.036 0-1.875.84-1.875 1.875v17.25c0 1.035.84 1.875 1.875 1.875h12.75c1.035 0 1.875-.84 1.875-1.875V12.75A3.75 3.75 0 0 0 16.5 9h-1.875a1.875 1.875 0 0 1-1.875-1.875V5.25A3.75 3.75 0 0 0 9 1.5H5.625ZM7.5 15a.75.75 0 0 1 .75-.75h7.5a.75.75 0 0 1 0 1.5h-7.5A.75.75 0 0 1 7.5 15Zm.75 2.25a.75.75 0 0 0 0 1.5H12a.75.75 0 0 0 0-1.5H8.25Z"
-					clip-rule="evenodd"
-				/>
-				<path
-					d="M12.971 1.816A5.23 5.23 0 0 1 14.25 5.25v1.875c0 .207.168.375.375.375H16.5a5.23 5.23 0 0 1 3.434 1.279 9.768 9.768 0 0 0-6.963-6.963Z"
-				/>
-			</svg>
-		{:else}
-			<Spinner />
-		{/if}
-	</div>
-
-	<div class="flex flex-col justify-center -space-y-0.5 ml-1 px-2.5 w-full">
-		<div class=" dark:text-gray-100 text-sm font-medium line-clamp-1 mb-1">
-			{name}
-		</div>
-
-		<div class=" flex justify-between text-gray-500 text-xs line-clamp-1">
-			{#if type === 'file'}
-				{$i18n.t('File')}
-			{:else if type === 'doc'}
-				{$i18n.t('Document')}
-			{:else if type === 'collection'}
-				{$i18n.t('Collection')}
+	{#if !small}
+		<div class="p-3 bg-black/20 dark:bg-white/10 text-white rounded-xl">
+			{#if !loading}
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 24 24"
+					fill="currentColor"
+					class=" size-5"
+				>
+					<path
+						fill-rule="evenodd"
+						d="M5.625 1.5c-1.036 0-1.875.84-1.875 1.875v17.25c0 1.035.84 1.875 1.875 1.875h12.75c1.035 0 1.875-.84 1.875-1.875V12.75A3.75 3.75 0 0 0 16.5 9h-1.875a1.875 1.875 0 0 1-1.875-1.875V5.25A3.75 3.75 0 0 0 9 1.5H5.625ZM7.5 15a.75.75 0 0 1 .75-.75h7.5a.75.75 0 0 1 0 1.5h-7.5A.75.75 0 0 1 7.5 15Zm.75 2.25a.75.75 0 0 0 0 1.5H12a.75.75 0 0 0 0-1.5H8.25Z"
+						clip-rule="evenodd"
+					/>
+					<path
+						d="M12.971 1.816A5.23 5.23 0 0 1 14.25 5.25v1.875c0 .207.168.375.375.375H16.5a5.23 5.23 0 0 1 3.434 1.279 9.768 9.768 0 0 0-6.963-6.963Z"
+					/>
+				</svg>
 			{:else}
-				<span class=" capitalize line-clamp-1">{type}</span>
-			{/if}
-			{#if size}
-				<span class="capitalize">{formatFileSize(size)}</span>
+				<Spinner />
 			{/if}
 		</div>
-	</div>
+	{/if}
+
+	{#if !small}
+		<div class="flex flex-col justify-center -space-y-0.5 px-2.5 w-full">
+			<div class=" dark:text-gray-100 text-sm font-medium line-clamp-1 mb-1">
+				{name}
+			</div>
+
+			<div class=" flex justify-between text-gray-500 text-xs line-clamp-1">
+				{#if type === 'file'}
+					{$i18n.t('File')}
+				{:else if type === 'doc'}
+					{$i18n.t('Document')}
+				{:else if type === 'collection'}
+					{$i18n.t('Collection')}
+				{:else}
+					<span class=" capitalize line-clamp-1">{type}</span>
+				{/if}
+				{#if size}
+					<span class="capitalize">{formatFileSize(size)}</span>
+				{/if}
+			</div>
+		</div>
+	{:else}
+		<Tooltip content={name} className="flex flex-col w-full" placement="top-start">
+			<div class="flex flex-col justify-center -space-y-0.5 px-2.5 w-full">
+				<div class=" dark:text-gray-100 text-sm flex justify-between items-center">
+					{#if loading}
+						<div class=" shrink-0 mr-2">
+							<Spinner className="size-4" />
+						</div>
+					{/if}
+					<div class="font-medium line-clamp-1 flex-1">{name}</div>
+					<div class="text-gray-500 text-xs capitalize shrink-0">{formatFileSize(size)}</div>
+				</div>
+			</div>
+		</Tooltip>
+	{/if}
 
 	{#if dismissible}
 		<div class=" absolute -top-1 -right-1">

src/lib/components/common/Modal.svelte

@@ -6,7 +6,9 @@
 
 	export let show = true;
 	export let size = 'md';
-	export let className = 'bg-gray-50 dark:bg-gray-900  rounded-2xl';
+
+	export let containerClassName = 'p-3';
+	export let className = 'bg-gray-50 dark:bg-gray-900 rounded-2xl';
 
 	let modalElement = null;
 	let mounted = false;
@@ -65,7 +67,7 @@
 	<!-- svelte-ignore a11y-no-static-element-interactions -->
 	<div
 		bind:this={modalElement}
-		class="modal fixed top-0 right-0 left-0 bottom-0 bg-black/60 w-full h-screen max-h-[100dvh] flex justify-center z-[9999] overflow-hidden overscroll-contain"
+		class="modal fixed top-0 right-0 left-0 bottom-0 bg-black/60 w-full h-screen max-h-[100dvh] {containerClassName} flex justify-center z-[9999] overflow-y-auto overscroll-contain"
 		in:fade={{ duration: 10 }}
 		on:mousedown={() => {
 			show = false;
@@ -74,7 +76,7 @@
 		<div
 			class=" m-auto max-w-full {sizeToWidth(size)} {size !== 'full'
 				? 'mx-2'
-				: ''} shadow-3xl max-h-[100dvh] overflow-y-auto scrollbar-hidden {className}"
+				: ''} shadow-3xl min-h-fit scrollbar-hidden {className}"
 			in:flyAndScale
 			on:mousedown={(e) => {
 				e.stopPropagation();

src/lib/components/common/RichTextInput.svelte

@@ -1,241 +1,55 @@
 <script lang="ts">
-	import { onDestroy, onMount } from 'svelte';
+	import { marked } from 'marked';
+	import TurndownService from 'turndown';
+	const turndownService = new TurndownService({
+		codeBlockStyle: 'fenced',
+		headingStyle: 'atx'
+	});
+	turndownService.escape = (string) => string;
+
+	import { onMount, onDestroy } from 'svelte';
 	import { createEventDispatcher } from 'svelte';
 	const eventDispatch = createEventDispatcher();
 
-	import { EditorState, Plugin, TextSelection } from 'prosemirror-state';
-	import { EditorView, Decoration, DecorationSet } from 'prosemirror-view';
-	import { undo, redo, history } from 'prosemirror-history';
-	import {
-		schema,
-		defaultMarkdownParser,
-		MarkdownParser,
-		defaultMarkdownSerializer
-	} from 'prosemirror-markdown';
+	import { EditorState, Plugin, PluginKey, TextSelection } from 'prosemirror-state';
+	import { Decoration, DecorationSet } from 'prosemirror-view';
+
+	import { Editor } from '@tiptap/core';
+
+	import { AIAutocompletion } from './RichTextInput/AutoCompletion.js';
+
+	import CodeBlockLowlight from '@tiptap/extension-code-block-lowlight';
+	import Placeholder from '@tiptap/extension-placeholder';
+	import Highlight from '@tiptap/extension-highlight';
+	import Typography from '@tiptap/extension-typography';
+	import StarterKit from '@tiptap/starter-kit';
+	import { all, createLowlight } from 'lowlight';
 
-	import {
-		inputRules,
-		wrappingInputRule,
-		textblockTypeInputRule,
-		InputRule
-	} from 'prosemirror-inputrules'; // Import input rules
-	import { splitListItem, liftListItem, sinkListItem } from 'prosemirror-schema-list'; // Import from prosemirror-schema-list
-	import { keymap } from 'prosemirror-keymap';
-	import { baseKeymap, chainCommands } from 'prosemirror-commands';
-	import { DOMParser, DOMSerializer, Schema, Fragment } from 'prosemirror-model';
 	import { PASTED_TEXT_CHARACTER_LIMIT } from '$lib/constants';
 
+	// create a lowlight instance with all languages loaded
+	const lowlight = createLowlight(all);
+
 	export let className = 'input-prose';
+	export let placeholder = 'Type here...';
+	export let value = '';
+	export let id = '';
+
+	export let preserveBreaks = false;
+	export let generateAutoCompletion: Function = async () => null;
+	export let autocomplete = false;
+	export let messageInput = false;
 	export let shiftEnter = false;
 	export let largeTextAsFile = false;
 
-	export let id = '';
-	export let value = '';
-	export let placeholder = 'Type here...';
-	export let trim = false;
+	let element;
+	let editor;
 
-	let element: HTMLElement; // Element where ProseMirror will attach
-	let state;
-	let view;
-
-	// Plugin to add placeholder when the content is empty
-	function placeholderPlugin(placeholder: string) {
-		return new Plugin({
-			props: {
-				decorations(state) {
-					const doc = state.doc;
-					if (
-						doc.childCount === 1 &&
-						doc.firstChild.isTextblock &&
-						doc.firstChild?.textContent === ''
-					) {
-						// If there's nothing in the editor, show the placeholder decoration
-						const decoration = Decoration.node(0, doc.content.size, {
-							'data-placeholder': placeholder,
-							class: 'placeholder'
-						});
-						return DecorationSet.create(doc, [decoration]);
-					}
-					return DecorationSet.empty;
-				}
-			}
-		});
-	}
-
-	function unescapeMarkdown(text: string): string {
-		return text
-			.replace(/\\([\\`*{}[\]()#+\-.!_>])/g, '$1') // unescape backslashed characters
-			.replace(/&amp;/g, '&')
-			.replace(/</g, '<')
-			.replace(/>/g, '>')
-			.replace(/&quot;/g, '"')
-			.replace(/&#39;/g, "'");
-	}
-
-	// Custom parsing rule that creates proper paragraphs for newlines and empty lines
-	function markdownToProseMirrorDoc(markdown: string) {
-		// Split the markdown into lines
-		const lines = markdown.split('\n\n');
-
-		// Create an array to hold our paragraph nodes
-		const paragraphs = [];
-
-		// Process each line
-		lines.forEach((line) => {
-			if (line.trim() === '') {
-				// For empty lines, create an empty paragraph
-				paragraphs.push(schema.nodes.paragraph.create());
-			} else {
-				// For non-empty lines, parse as usual
-				const doc = defaultMarkdownParser.parse(line);
-				// Extract the content of the parsed document
-				doc.content.forEach((node) => {
-					paragraphs.push(node);
-				});
-			}
-		});
-
-		// Create a new document with these paragraphs
-		return schema.node('doc', null, paragraphs);
-	}
-
-	// Create a custom serializer for paragraphs
-	// Custom paragraph serializer to preserve newlines for empty paragraphs (empty block).
-	function serializeParagraph(state, node: Node) {
-		const content = node.textContent.trim();
-
-		// If the paragraph is empty, just add an empty line.
-		if (content === '') {
-			state.write('\n\n');
-		} else {
-			state.renderInline(node);
-			state.closeBlock(node);
-		}
-	}
-
-	const customMarkdownSerializer = new defaultMarkdownSerializer.constructor(
-		{
-			...defaultMarkdownSerializer.nodes,
-
-			paragraph: (state, node) => {
-				serializeParagraph(state, node); // Use custom paragraph serialization
-			}
-
-			// Customize other block formats if needed
-		},
-
-		// Copy marks directly from the original serializer (or customize them if necessary)
-		defaultMarkdownSerializer.marks
-	);
-
-	// Utility function to convert ProseMirror content back to markdown text
-	function serializeEditorContent(doc) {
-		const markdown = customMarkdownSerializer.serialize(doc);
-		if (trim) {
-			return unescapeMarkdown(markdown).trim();
-		} else {
-			return unescapeMarkdown(markdown);
-		}
-	}
-
-	// ---- Input Rules ----
-	// Input rule for heading (e.g., # Headings)
-	function headingRule(schema) {
-		return textblockTypeInputRule(/^(#{1,6})\s$/, schema.nodes.heading, (match) => ({
-			level: match[1].length
-		}));
-	}
-
-	// Input rule for bullet list (e.g., `- item`)
-	function bulletListRule(schema) {
-		return wrappingInputRule(/^\s*([-+*])\s$/, schema.nodes.bullet_list);
-	}
-
-	// Input rule for ordered list (e.g., `1. item`)
-	function orderedListRule(schema) {
-		return wrappingInputRule(/^(\d+)\.\s$/, schema.nodes.ordered_list, (match) => ({
-			order: +match[1]
-		}));
-	}
-
-	// Custom input rules for Bold/Italic (using * or _)
-	function markInputRule(regexp: RegExp, markType: any) {
-		return new InputRule(regexp, (state, match, start, end) => {
-			const { tr } = state;
-			if (match) {
-				tr.replaceWith(start, end, schema.text(match[1], [markType.create()]));
-			}
-			return tr;
-		});
-	}
-
-	function boldRule(schema) {
-		return markInputRule(/(?<=^|\s)\*([^*]+)\*(?=\s|$)/, schema.marks.strong);
-	}
-
-	function italicRule(schema) {
-		// Using lookbehind and lookahead to prevent the space from being consumed
-		return markInputRule(/(?<=^|\s)_([^*_]+)_(?=\s|$)/, schema.marks.em);
-	}
-
-	// Initialize Editor State and View
-	function afterSpacePress(state, dispatch) {
-		// Get the position right after the space was naturally inserted by the browser.
-		let { from, to, empty } = state.selection;
-
-		if (dispatch && empty) {
-			let tr = state.tr;
-
-			// Check for any active marks at `from - 1` (the space we just inserted)
-			const storedMarks = state.storedMarks || state.selection.$from.marks();
-
-			const hasBold = storedMarks.some((mark) => mark.type === state.schema.marks.strong);
-			const hasItalic = storedMarks.some((mark) => mark.type === state.schema.marks.em);
-
-			// Remove marks from the space character (marks applied to the space character will be marked as false)
-			if (hasBold) {
-				tr = tr.removeMark(from - 1, from, state.schema.marks.strong);
-			}
-			if (hasItalic) {
-				tr = tr.removeMark(from - 1, from, state.schema.marks.em);
-			}
-
-			// Dispatch the resulting transaction to update the editor state
-			dispatch(tr);
-		}
-
-		return true;
-	}
-
-	function toggleMark(markType) {
-		return (state, dispatch) => {
-			const { from, to } = state.selection;
-			if (state.doc.rangeHasMark(from, to, markType)) {
-				if (dispatch) dispatch(state.tr.removeMark(from, to, markType));
-				return true;
-			} else {
-				if (dispatch) dispatch(state.tr.addMark(from, to, markType.create()));
-				return true;
-			}
-		};
-	}
-
-	function isInList(state) {
-		const { $from } = state.selection;
-		return (
-			$from.parent.type === schema.nodes.paragraph && $from.node(-1).type === schema.nodes.list_item
-		);
-	}
-
-	function isEmptyListItem(state) {
-		const { $from } = state.selection;
-		return isInList(state) && $from.parent.content.size === 0 && $from.node(-1).childCount === 1;
-	}
-
-	function exitList(state, dispatch) {
-		return liftListItem(schema.nodes.list_item)(state, dispatch);
-	}
+	const options = {
+		throwOnError: false
+	};
 
+	// Function to find the next template in the document
 	function findNextTemplate(doc, from = 0) {
 		const patterns = [
 			{ start: '[', end: ']' },
@@ -270,6 +84,7 @@
 		return result;
 	}
 
+	// Function to select the next template in the document
 	function selectNextTemplate(state, dispatch) {
 		const { doc, selection } = state;
 		const from = selection.to;
@@ -290,220 +105,254 @@
 		return false;
 	}
 
-	// Replace tabs with four spaces
-	function handleTabIndentation(text: string): string {
-		// Replace each tab character with four spaces
-		return text.replace(/\t/g, '    ');
-	}
+	export const setContent = (content) => {
+		editor.commands.setContent(content);
+	};
 
-	onMount(() => {
-		const initialDoc = markdownToProseMirrorDoc(value || ''); // Convert the initial content
+	const selectTemplate = () => {
+		if (value !== '') {
+			// After updating the state, try to find and select the next template
+			setTimeout(() => {
+				const templateFound = selectNextTemplate(editor.view.state, editor.view.dispatch);
+				if (!templateFound) {
+					// If no template found, set cursor at the end
+					const endPos = editor.view.state.doc.content.size;
+					editor.view.dispatch(
+						editor.view.state.tr.setSelection(TextSelection.create(editor.view.state.doc, endPos))
+					);
+				}
+			}, 0);
+		}
+	};
 
-		state = EditorState.create({
-			doc: initialDoc,
-			schema,
-			plugins: [
-				history(),
-				placeholderPlugin(placeholder),
-				inputRules({
-					rules: [
-						headingRule(schema), // Handle markdown-style headings (# H1, ## H2, etc.)
-						bulletListRule(schema), // Handle `-` or `*` input to start bullet list
-						orderedListRule(schema), // Handle `1.` input to start ordered list
-						boldRule(schema), // Bold input rule
-						italicRule(schema) // Italic input rule
-					]
+	onMount(async () => {
+		console.log(value);
+
+		if (preserveBreaks) {
+			turndownService.addRule('preserveBreaks', {
+				filter: 'br', // Target <br> elements
+				replacement: function (content) {
+					return '<br/>';
+				}
+			});
+		}
+
+		async function tryParse(value, attempts = 3, interval = 100) {
+			try {
+				// Try parsing the value
+				return marked.parse(value.replaceAll(`\n<br/>`, `<br/>`), {
+					breaks: false
+				});
+			} catch (error) {
+				// If no attempts remain, fallback to plain text
+				if (attempts <= 1) {
+					return value;
+				}
+				// Wait for the interval, then retry
+				await new Promise((resolve) => setTimeout(resolve, interval));
+				return tryParse(value, attempts - 1, interval); // Recursive call
+			}
+		}
+
+		// Usage example
+		let content = await tryParse(value);
+
+		editor = new Editor({
+			element: element,
+			extensions: [
+				StarterKit,
+				CodeBlockLowlight.configure({
+					lowlight
 				}),
-				keymap({
-					...baseKeymap,
-					'Mod-z': undo,
-					'Mod-y': redo,
-					Enter: (state, dispatch, view) => {
-						if (shiftEnter) {
-							eventDispatch('enter');
-							return true;
-						}
-						return chainCommands(
-							(state, dispatch, view) => {
-								if (isEmptyListItem(state)) {
-									return exitList(state, dispatch);
-								}
-								return false;
-							},
-							(state, dispatch, view) => {
-								if (isInList(state)) {
-									return splitListItem(schema.nodes.list_item)(state, dispatch);
-								}
-								return false;
-							},
-							baseKeymap.Enter
-						)(state, dispatch, view);
-					},
+				Highlight,
+				Typography,
+				Placeholder.configure({ placeholder }),
+				...(autocomplete
+					? [
+							AIAutocompletion.configure({
+								generateCompletion: async (text) => {
+									if (text.trim().length === 0) {
+										return null;
+									}
 
-					'Shift-Enter': (state, dispatch, view) => {
-						if (shiftEnter) {
-							return chainCommands(
-								(state, dispatch, view) => {
-									if (isEmptyListItem(state)) {
-										return exitList(state, dispatch);
+									const suggestion = await generateAutoCompletion(text).catch(() => null);
+									if (!suggestion || suggestion.trim().length === 0) {
+										return null;
 									}
-									return false;
-								},
-								(state, dispatch, view) => {
-									if (isInList(state)) {
-										return splitListItem(schema.nodes.list_item)(state, dispatch);
-									}
-									return false;
-								},
-								baseKeymap.Enter
-							)(state, dispatch, view);
-						} else {
-							return baseKeymap.Enter(state, dispatch, view);
+
+									return suggestion;
+								}
+							})
+						]
+					: [])
+			],
+			content: content,
+			autofocus: messageInput ? true : false,
+			onTransaction: () => {
+				// force re-render so `editor.isActive` works as expected
+				editor = editor;
+				const newValue = turndownService
+					.turndown(
+						(preserveBreaks
+							? editor.getHTML().replace(/<p><\/p>/g, '<br/>')
+							: editor.getHTML()
+						).replace(/ {2,}/g, (m) => m.replace(/ /g, '\u00a0'))
+					)
+					.replace(/\u00a0/g, ' ');
+
+				if (value !== newValue) {
+					value = newValue;
+
+					// check if the node is paragraph as well
+					if (editor.isActive('paragraph')) {
+						if (value === '') {
+							editor.commands.clearContent();
 						}
+					}
+				}
+			},
+			editorProps: {
+				attributes: { id },
+				handleDOMEvents: {
+					focus: (view, event) => {
+						eventDispatch('focus', { event });
 						return false;
 					},
-
-					// Prevent default tab navigation and provide indent/outdent behavior inside lists:
-					Tab: chainCommands((state, dispatch, view) => {
-						const { $from } = state.selection;
-						if (isInList(state)) {
-							return sinkListItem(schema.nodes.list_item)(state, dispatch);
-						} else {
-							return selectNextTemplate(state, dispatch);
-						}
-						return true; // Prevent Tab from moving the focus
-					}),
-					'Shift-Tab': (state, dispatch, view) => {
-						const { $from } = state.selection;
-						if (isInList(state)) {
-							return liftListItem(schema.nodes.list_item)(state, dispatch);
-						}
-						return true; // Prevent Shift-Tab from moving the focus
+					keyup: (view, event) => {
+						eventDispatch('keyup', { event });
+						return false;
 					},
-					'Mod-b': toggleMark(schema.marks.strong),
-					'Mod-i': toggleMark(schema.marks.em)
-				})
-			]
-		});
-
-		view = new EditorView(element, {
-			state,
-			dispatchTransaction(transaction) {
-				// Update editor state
-				let newState = view.state.apply(transaction);
-				view.updateState(newState);
-
-				value = serializeEditorContent(newState.doc); // Convert ProseMirror content to markdown text
-				eventDispatch('input', { value });
-			},
-			handleDOMEvents: {
-				focus: (view, event) => {
-					eventDispatch('focus', { event });
-					return false;
-				},
-				keypress: (view, event) => {
-					eventDispatch('keypress', { event });
-					return false;
-				},
-				keydown: (view, event) => {
-					eventDispatch('keydown', { event });
-					return false;
-				},
-				paste: (view, event) => {
-					if (event.clipboardData) {
-						// Extract plain text from clipboard and paste it without formatting
-						const plainText = event.clipboardData.getData('text/plain');
-						if (plainText) {
-							if (largeTextAsFile) {
-								if (plainText.length > PASTED_TEXT_CHARACTER_LIMIT) {
-									// Dispatch paste event to parent component
-									eventDispatch('paste', { event });
+					keydown: (view, event) => {
+						if (messageInput) {
+							// Handle Tab Key
+							if (event.key === 'Tab') {
+								const handled = selectNextTemplate(view.state, view.dispatch);
+								if (handled) {
 									event.preventDefault();
 									return true;
 								}
 							}
 
-							const modifiedText = handleTabIndentation(plainText);
-							console.log(modifiedText);
+							if (event.key === 'Enter') {
+								// Check if the current selection is inside a structured block (like codeBlock or list)
+								const { state } = view;
+								const { $head } = state.selection;
 
-							// Replace the current selection with the plain text content
-							const tr = view.state.tr.replaceSelectionWith(
-								view.state.schema.text(modifiedText),
-								false
+								// Recursive function to check ancestors for specific node types
+								function isInside(nodeTypes: string[]): boolean {
+									let currentNode = $head;
+									while (currentNode) {
+										if (nodeTypes.includes(currentNode.parent.type.name)) {
+											return true;
+										}
+										if (!currentNode.depth) break; // Stop if we reach the top
+										currentNode = state.doc.resolve(currentNode.before()); // Move to the parent node
+									}
+									return false;
+								}
+
+								const isInCodeBlock = isInside(['codeBlock']);
+								const isInList = isInside(['listItem', 'bulletList', 'orderedList']);
+								const isInHeading = isInside(['heading']);
+
+								if (isInCodeBlock || isInList || isInHeading) {
+									// Let ProseMirror handle the normal Enter behavior
+									return false;
+								}
+							}
+
+							// Handle shift + Enter for a line break
+							if (shiftEnter) {
+								if (event.key === 'Enter' && event.shiftKey && !event.ctrlKey && !event.metaKey) {
+									editor.commands.setHardBreak(); // Insert a hard break
+									view.dispatch(view.state.tr.scrollIntoView()); // Move viewport to the cursor
+									event.preventDefault();
+									return true;
+								}
+							}
+						}
+						eventDispatch('keydown', { event });
+						return false;
+					},
+					paste: (view, event) => {
+						if (event.clipboardData) {
+							// Extract plain text from clipboard and paste it without formatting
+							const plainText = event.clipboardData.getData('text/plain');
+							if (plainText) {
+								if (largeTextAsFile) {
+									if (plainText.length > PASTED_TEXT_CHARACTER_LIMIT) {
+										// Dispatch paste event to parent component
+										eventDispatch('paste', { event });
+										event.preventDefault();
+										return true;
+									}
+								}
+								return false;
+							}
+
+							// Check if the pasted content contains image files
+							const hasImageFile = Array.from(event.clipboardData.files).some((file) =>
+								file.type.startsWith('image/')
 							);
-							view.dispatch(tr.scrollIntoView());
-							event.preventDefault(); // Prevent the default paste behavior
-							return true;
+
+							// Check for image in dataTransfer items (for cases where files are not available)
+							const hasImageItem = Array.from(event.clipboardData.items).some((item) =>
+								item.type.startsWith('image/')
+							);
+							if (hasImageFile) {
+								// If there's an image, dispatch the event to the parent
+								eventDispatch('paste', { event });
+								event.preventDefault();
+								return true;
+							}
+
+							if (hasImageItem) {
+								// If there's an image item, dispatch the event to the parent
+								eventDispatch('paste', { event });
+								event.preventDefault();
+								return true;
+							}
 						}
 
-						// Check if the pasted content contains image files
-						const hasImageFile = Array.from(event.clipboardData.files).some((file) =>
-							file.type.startsWith('image/')
-						);
-
-						// Check for image in dataTransfer items (for cases where files are not available)
-						const hasImageItem = Array.from(event.clipboardData.items).some((item) =>
-							item.type.startsWith('image/')
-						);
-						if (hasImageFile) {
-							// If there's an image, dispatch the event to the parent
-							eventDispatch('paste', { event });
-							event.preventDefault();
-							return true;
-						}
-
-						if (hasImageItem) {
-							// If there's an image item, dispatch the event to the parent
-							eventDispatch('paste', { event });
-							event.preventDefault();
-							return true;
-						}
+						// For all other cases (text, formatted text, etc.), let ProseMirror handle it
+						view.dispatch(view.state.tr.scrollIntoView()); // Move viewport to the cursor after pasting
+						return false;
 					}
-
-					// For all other cases (text, formatted text, etc.), let ProseMirror handle it
-					return false;
-				},
-				// Handle space input after browser has completed it
-				keyup: (view, event) => {
-					if (event.key === ' ' && event.code === 'Space') {
-						afterSpacePress(view.state, view.dispatch);
-					}
-					return false;
 				}
-			},
-			attributes: { id }
+			}
 		});
-	});
 
-	// Reinitialize the editor if the value is externally changed (i.e. when `value` is updated)
-	$: if (view && value !== serializeEditorContent(view.state.doc)) {
-		const newDoc = markdownToProseMirrorDoc(value || '');
-
-		const newState = EditorState.create({
-			doc: newDoc,
-			schema,
-			plugins: view.state.plugins,
-			selection: TextSelection.atEnd(newDoc) // This sets the cursor at the end
-		});
-		view.updateState(newState);
-
-		if (value !== '') {
-			// After updating the state, try to find and select the next template
-			setTimeout(() => {
-				const templateFound = selectNextTemplate(view.state, view.dispatch);
-				if (!templateFound) {
-					// If no template found, set cursor at the end
-					const endPos = view.state.doc.content.size;
-					view.dispatch(view.state.tr.setSelection(TextSelection.create(view.state.doc, endPos)));
-				}
-			}, 0);
+		if (messageInput) {
+			selectTemplate();
 		}
-	}
-
-	// Destroy ProseMirror instance on unmount
-	onDestroy(() => {
-		view?.destroy();
 	});
+
+	onDestroy(() => {
+		if (editor) {
+			editor.destroy();
+		}
+	});
+
+	// Update the editor content if the external `value` changes
+	$: if (
+		editor &&
+		value !==
+			turndownService
+				.turndown(
+					(preserveBreaks
+						? editor.getHTML().replace(/<p><\/p>/g, '<br/>')
+						: editor.getHTML()
+					).replace(/ {2,}/g, (m) => m.replace(/ /g, '\u00a0'))
+				)
+				.replace(/\u00a0/g, ' ')
+	) {
+		editor.commands.setContent(
+			marked.parse(value.replaceAll(`\n<br/>`, `<br/>`), {
+				breaks: false
+			})
+		); // Update editor content
+		selectTemplate();
+	}
 </script>
 
-<div bind:this={element} class="relative w-full min-w-full h-full min-h-fit {className}"></div>
+<div bind:this={element} class="relative w-full min-w-full h-full min-h-fit {className}" />

src/lib/components/common/RichTextInput/AutoCompletion.js

@@ -0,0 +1,278 @@
+/*
+Here we initialize the plugin with keyword mapping.
+Intended to handle user interactions seamlessly.
+
+Observe the keydown events for proactive suggestions.
+Provide a mechanism for accepting AI suggestions.
+Evaluate each input change with debounce logic.
+Next, we implement touch and mouse interactions.
+
+Anchor the user experience to intuitive behavior.
+Intelligently reset suggestions on new input.
+*/
+
+import { Extension } from '@tiptap/core';
+import { Plugin, PluginKey } from 'prosemirror-state';
+
+export const AIAutocompletion = Extension.create({
+	name: 'aiAutocompletion',
+
+	addOptions() {
+		return {
+			generateCompletion: () => Promise.resolve(''),
+			debounceTime: 1000
+		};
+	},
+
+	addGlobalAttributes() {
+		return [
+			{
+				types: ['paragraph'],
+				attributes: {
+					class: {
+						default: null,
+						parseHTML: (element) => element.getAttribute('class'),
+						renderHTML: (attributes) => {
+							if (!attributes.class) return {};
+							return { class: attributes.class };
+						}
+					},
+					'data-prompt': {
+						default: null,
+						parseHTML: (element) => element.getAttribute('data-prompt'),
+						renderHTML: (attributes) => {
+							if (!attributes['data-prompt']) return {};
+							return { 'data-prompt': attributes['data-prompt'] };
+						}
+					},
+					'data-suggestion': {
+						default: null,
+						parseHTML: (element) => element.getAttribute('data-suggestion'),
+						renderHTML: (attributes) => {
+							if (!attributes['data-suggestion']) return {};
+							return { 'data-suggestion': attributes['data-suggestion'] };
+						}
+					}
+				}
+			}
+		];
+	},
+
+	addProseMirrorPlugins() {
+		let debounceTimer = null;
+		let loading = false;
+
+		let touchStartX = 0;
+		let touchStartY = 0;
+
+		return [
+			new Plugin({
+				key: new PluginKey('aiAutocompletion'),
+				props: {
+					handleKeyDown: (view, event) => {
+						const { state, dispatch } = view;
+						const { selection } = state;
+						const { $head } = selection;
+
+						if ($head.parent.type.name !== 'paragraph') return false;
+
+						const node = $head.parent;
+
+						if (event.key === 'Tab') {
+							// if (!node.attrs['data-suggestion']) {
+							//   // Generate completion
+							//   if (loading) return true
+							//   loading = true
+							//   const prompt = node.textContent
+							//   this.options.generateCompletion(prompt).then(suggestion => {
+							//     if (suggestion && suggestion.trim() !== '') {
+							//       dispatch(state.tr.setNodeMarkup($head.before(), null, {
+							//         ...node.attrs,
+							//         class: 'ai-autocompletion',
+							//         'data-prompt': prompt,
+							//         'data-suggestion': suggestion,
+							//       }))
+							//     }
+							//     // If suggestion is empty or null, do nothing
+							//   }).finally(() => {
+							//     loading = false
+							//   })
+							// }
+
+							if (node.attrs['data-suggestion']) {
+								// Accept suggestion
+								const suggestion = node.attrs['data-suggestion'];
+								dispatch(
+									state.tr.insertText(suggestion, $head.pos).setNodeMarkup($head.before(), null, {
+										...node.attrs,
+										class: null,
+										'data-prompt': null,
+										'data-suggestion': null
+									})
+								);
+								return true;
+							}
+						} else {
+							if (node.attrs['data-suggestion']) {
+								// Reset suggestion on any other key press
+								dispatch(
+									state.tr.setNodeMarkup($head.before(), null, {
+										...node.attrs,
+										class: null,
+										'data-prompt': null,
+										'data-suggestion': null
+									})
+								);
+							}
+
+							// Start debounce logic for AI generation only if the cursor is at the end of the paragraph
+							if (selection.empty && $head.pos === $head.end()) {
+								// Set up debounce for AI generation
+								if (this.options.debounceTime !== null) {
+									clearTimeout(debounceTimer);
+
+									// Capture current position
+									const currentPos = $head.before();
+
+									debounceTimer = setTimeout(() => {
+										const newState = view.state;
+										const newSelection = newState.selection;
+										const newNode = newState.doc.nodeAt(currentPos);
+
+										// Check if the node still exists and is still a paragraph
+										if (
+											newNode &&
+											newNode.type.name === 'paragraph' &&
+											newSelection.$head.pos === newSelection.$head.end() &&
+											newSelection.$head.pos === currentPos + newNode.nodeSize - 1
+										) {
+											const prompt = newNode.textContent;
+
+											if (prompt.trim() !== '') {
+												if (loading) return true;
+												loading = true;
+												this.options
+													.generateCompletion(prompt)
+													.then((suggestion) => {
+														if (suggestion && suggestion.trim() !== '') {
+															if (
+																view.state.selection.$head.pos === view.state.selection.$head.end()
+															) {
+																view.dispatch(
+																	newState.tr.setNodeMarkup(currentPos, null, {
+																		...newNode.attrs,
+																		class: 'ai-autocompletion',
+																		'data-prompt': prompt,
+																		'data-suggestion': suggestion
+																	})
+																);
+															}
+														}
+													})
+													.finally(() => {
+														loading = false;
+													});
+											}
+										}
+									}, this.options.debounceTime);
+								}
+							}
+						}
+						return false;
+					},
+					handleDOMEvents: {
+						touchstart: (view, event) => {
+							touchStartX = event.touches[0].clientX;
+							touchStartY = event.touches[0].clientY;
+							return false;
+						},
+						touchend: (view, event) => {
+							const touchEndX = event.changedTouches[0].clientX;
+							const touchEndY = event.changedTouches[0].clientY;
+
+							const deltaX = touchEndX - touchStartX;
+							const deltaY = touchEndY - touchStartY;
+
+							// Check if the swipe was primarily horizontal and to the right
+							if (Math.abs(deltaX) > Math.abs(deltaY) && deltaX > 50) {
+								const { state, dispatch } = view;
+								const { selection } = state;
+								const { $head } = selection;
+								const node = $head.parent;
+
+								if (node.type.name === 'paragraph' && node.attrs['data-suggestion']) {
+									const suggestion = node.attrs['data-suggestion'];
+									dispatch(
+										state.tr.insertText(suggestion, $head.pos).setNodeMarkup($head.before(), null, {
+											...node.attrs,
+											class: null,
+											'data-prompt': null,
+											'data-suggestion': null
+										})
+									);
+									return true;
+								}
+							}
+							return false;
+						},
+						// Add mousedown behavior
+						// mouseup: (view, event) => {
+						// 	const { state, dispatch } = view;
+						// 	const { selection } = state;
+						// 	const { $head } = selection;
+						// 	const node = $head.parent;
+
+						// 	// Reset debounce timer on mouse click
+						// 	clearTimeout(debounceTimer);
+
+						// 	// If a suggestion exists and the cursor moves, remove the suggestion
+						// 	if (
+						// 		node.type.name === 'paragraph' &&
+						// 		node.attrs['data-suggestion'] &&
+						// 		view.state.selection.$head.pos !== view.state.selection.$head.end()
+						// 	) {
+						// 		dispatch(
+						// 			state.tr.setNodeMarkup($head.before(), null, {
+						// 				...node.attrs,
+						// 				class: null,
+						// 				'data-prompt': null,
+						// 				'data-suggestion': null
+						// 			})
+						// 		);
+						// 	}
+
+						// 	return false;
+						// }
+						mouseup: (view, event) => {
+							const { state, dispatch } = view;
+
+							// Reset debounce timer on mouse click
+							clearTimeout(debounceTimer);
+
+							// Iterate over all nodes in the document
+							const tr = state.tr;
+							state.doc.descendants((node, pos) => {
+								if (node.type.name === 'paragraph' && node.attrs['data-suggestion']) {
+									// Remove suggestion from this paragraph
+									tr.setNodeMarkup(pos, null, {
+										...node.attrs,
+										class: null,
+										'data-prompt': null,
+										'data-suggestion': null
+									});
+								}
+							});
+
+							// Apply the transaction if any changes were made
+							if (tr.docChanged) {
+								dispatch(tr);
+							}
+
+							return false;
+						}
+					}
+				}
+			})
+		];
+	}
+});

src/lib/components/common/Textarea.svelte

@@ -3,42 +3,65 @@
 
 	export let value = '';
 	export let placeholder = '';
-
-	export let rows = 1;
-	export let required = false;
-
 	export let className =
 		'w-full rounded-lg px-3 py-2 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none resize-none h-full';
 
 	let textareaElement;
 
-	onMount(async () => {
-		await tick();
-		if (textareaElement) {
-			await tick();
-			setTimeout(adjustHeight, 0);
+	$: if (textareaElement) {
+		if (textareaElement.innerText !== value && value !== '') {
+			textareaElement.innerText = value ?? '';
 		}
-	});
-
-	$: if (value) {
-		setTimeout(adjustHeight, 0);
 	}
 
-	const adjustHeight = () => {
-		if (textareaElement) {
-			textareaElement.style.height = '';
-			textareaElement.style.height = `${textareaElement.scrollHeight}px`;
-		}
-	};
+	// Adjust height on mount and after setting the element.
+	onMount(async () => {
+		await tick();
+	});
+
+	// Handle paste event to ensure only plaintext is pasted
+	function handlePaste(event: ClipboardEvent) {
+		event.preventDefault(); // Prevent the default paste action
+		const clipboardData = event.clipboardData?.getData('text/plain'); // Get plaintext from clipboard
+
+		// Insert plaintext into the textarea
+		document.execCommand('insertText', false, clipboardData);
+	}
 </script>
 
-<textarea
+<div
+	contenteditable="true"
 	bind:this={textareaElement}
-	bind:value
-	{placeholder}
-	on:input={adjustHeight}
-	on:focus={adjustHeight}
-	class={className}
-	{rows}
-	{required}
+	class="{className} whitespace-pre-wrap relative {value
+		? !value.trim()
+			? 'placeholder'
+			: ''
+		: 'placeholder'}"
+	style="field-sizing: content; -moz-user-select: text !important;"
+	on:input={() => {
+		const text = textareaElement.innerText;
+		if (text === '\n') {
+			value = '';
+			return;
+		}
+
+		value = text;
+	}}
+	on:paste={handlePaste}
+	data-placeholder={placeholder}
 />
+
+<style>
+	.placeholder::before {
+		/* abolute */
+		position: absolute;
+		content: attr(data-placeholder);
+		color: #adb5bd;
+		overflow: hidden;
+		display: -webkit-box;
+		-webkit-box-orient: vertical;
+		-webkit-line-clamp: 1;
+		pointer-events: none;
+		touch-action: none;
+	}
+</style>

src/lib/components/layout/Navbar.svelte

@@ -115,6 +115,20 @@
 							</div>
 						</button>
 					</Menu>
+				{:else if $mobile}
+					<Tooltip content={$i18n.t('Controls')}>
+						<button
+							class=" flex cursor-pointer px-2 py-2 rounded-xl hover:bg-gray-50 dark:hover:bg-gray-850 transition"
+							on:click={async () => {
+								await showControls.set(!$showControls);
+							}}
+							aria-label="Controls"
+						>
+							<div class=" m-auto self-center">
+								<AdjustmentsHorizontal className=" size-5" strokeWidth="0.5" />
+							</div>
+						</button>
+					</Tooltip>
 				{/if}
 
 				{#if !$mobile}

src/lib/components/workspace/Knowledge.svelte

@@ -165,12 +165,14 @@
 						<div class="mt-3 flex justify-between">
 							<div class="text-xs text-gray-500">
 								<Tooltip
-									content={item?.user?.email}
+									content={item?.user?.email ?? $i18n.t('Deleted User')}
 									className="flex shrink-0"
 									placement="top-start"
 								>
 									{$i18n.t('By {{name}}', {
-										name: capitalizeFirstLetter(item?.user?.name ?? item?.user?.email)
+										name: capitalizeFirstLetter(
+											item?.user?.name ?? item?.user?.email ?? $i18n.t('Deleted User')
+										)
 									})}
 								</Tooltip>
 							</div>

src/lib/components/workspace/Knowledge/KnowledgeBase.svelte

@@ -68,7 +68,7 @@
 	let inputFiles = null;
 
 	let filteredItems = [];
-	$: if (knowledge) {
+	$: if (knowledge && knowledge.files) {
 		fuse = new Fuse(knowledge.files, {
 			keys: ['meta.name', 'meta.description']
 		});
@@ -446,7 +446,13 @@
 
 	const onDragOver = (e) => {
 		e.preventDefault();
-		dragged = true;
+
+		// Check if a file is being draggedOver.
+		if (e.dataTransfer?.types?.includes('Files')) {
+			dragged = true;
+		} else {
+			dragged = false;
+		}
 	};
 
 	const onDragLeave = () => {
@@ -457,15 +463,17 @@
 		e.preventDefault();
 		dragged = false;
 
-		if (e.dataTransfer?.files) {
-			const inputFiles = e.dataTransfer?.files;
+		if (e.dataTransfer?.types?.includes('Files')) {
+			if (e.dataTransfer?.files) {
+				const inputFiles = e.dataTransfer?.files;
 
-			if (inputFiles && inputFiles.length > 0) {
-				for (const file of inputFiles) {
-					await uploadFileHandler(file);
+				if (inputFiles && inputFiles.length > 0) {
+					for (const file of inputFiles) {
+						await uploadFileHandler(file);
+					}
+				} else {
+					toast.error($i18n.t(`File not found.`));
 				}
-			} else {
-				toast.error($i18n.t(`File not found.`));
 			}
 		}
 	};
@@ -600,7 +608,7 @@
 	}}
 />
 
-<div class="flex flex-col w-full h-full max-h-[100dvh] translate-y-1" id="collection-container">
+<div class="flex flex-col w-full translate-y-1" id="collection-container">
 	{#if id && knowledge}
 		<AccessControlModal
 			bind:show={showAccessControlModal}
@@ -657,228 +665,205 @@
 			</div>
 		</div>
 
-		<div class="flex flex-row flex-1 h-full max-h-full pb-2.5">
-			<PaneGroup direction="horizontal">
-				<Pane
-					bind:pane
-					defaultSize={minSize}
-					collapsible={true}
-					maxSize={50}
-					{minSize}
-					class="h-full"
-					onExpand={() => {
-						showSidepanel = true;
-					}}
-					onCollapse={() => {
-						showSidepanel = false;
-					}}
-				>
-					<div
-						class="{largeScreen ? 'flex-shrink-0' : 'flex-1'}
-						flex
-						py-2
-						rounded-2xl
-						border
-						border-gray-50
-						h-full
-						dark:border-gray-850"
-					>
-						<div class=" flex flex-col w-full space-x-2 rounded-lg h-full">
-							<div class="w-full h-full flex flex-col">
-								<div class=" px-3">
-									<div class="flex py-1">
-										<div class=" self-center ml-1 mr-3">
-											<svg
-												xmlns="http://www.w3.org/2000/svg"
-												viewBox="0 0 20 20"
-												fill="currentColor"
-												class="w-4 h-4"
-											>
-												<path
-													fill-rule="evenodd"
-													d="M9 3.5a5.5 5.5 0 100 11 5.5 5.5 0 000-11zM2 9a7 7 0 1112.452 4.391l3.328 3.329a.75.75 0 11-1.06 1.06l-3.329-3.328A7 7 0 012 9z"
-													clip-rule="evenodd"
-												/>
-											</svg>
-										</div>
-										<input
-											class=" w-full text-sm pr-4 py-1 rounded-r-xl outline-none bg-transparent"
-											bind:value={query}
-											placeholder={$i18n.t('Search Collection')}
-											on:focus={() => {
-												selectedFileId = null;
-											}}
-										/>
-
-										<div>
-											<AddContentMenu
-												on:upload={(e) => {
-													if (e.detail.type === 'directory') {
-														uploadDirectoryHandler();
-													} else if (e.detail.type === 'text') {
-														showAddTextContentModal = true;
-													} else {
-														document.getElementById('files-input').click();
-													}
-												}}
-												on:sync={(e) => {
-													showSyncConfirmModal = true;
-												}}
-											/>
-										</div>
-									</div>
-								</div>
-
-								{#if filteredItems.length > 0}
-									<div class=" flex overflow-y-auto h-full w-full scrollbar-hidden text-xs">
-										<Files
-											files={filteredItems}
-											{selectedFileId}
-											on:click={(e) => {
-												selectedFileId = selectedFileId === e.detail ? null : e.detail;
-											}}
-											on:delete={(e) => {
-												console.log(e.detail);
-
-												selectedFileId = null;
-												deleteFileHandler(e.detail);
-											}}
-										/>
-									</div>
-								{:else}
-									<div
-										class="m-auto flex flex-col justify-center text-center text-gray-500 text-xs"
-									>
-										<div>
-											{$i18n.t('No content found')}
-										</div>
-
-										<div class="mx-12 mt-2 text-center text-gray-200 dark:text-gray-700">
-											{$i18n.t('Drag and drop a file to upload or select a file to view')}
-										</div>
-									</div>
-								{/if}
-							</div>
-						</div>
-					</div>
-				</Pane>
-
-				{#if largeScreen}
-					<PaneResizer class="relative flex w-2 items-center justify-center bg-background group">
-						<div class="z-10 flex h-7 w-5 items-center justify-center rounded-sm">
-							<EllipsisVertical className="size-4 invisible group-hover:visible" />
-						</div>
-					</PaneResizer>
-					<Pane>
-						<div class="flex-1 flex justify-start h-full max-h-full">
-							{#if selectedFile}
-								<div class=" flex flex-col w-full h-full max-h-full ml-2.5">
-									<div class="flex-shrink-0 mb-2 flex items-center">
-										{#if !showSidepanel}
-											<div class="-translate-x-2">
-												<button
-													class="w-full text-left text-sm p-1.5 rounded-lg dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-gray-850"
-													on:click={() => {
-														pane.expand();
-													}}
-												>
-													<ChevronLeft strokeWidth="2.5" />
-												</button>
-											</div>
-										{/if}
-
-										<div class=" flex-1 text-2xl font-medium">
-											<a
-												class="hover:text-gray-500 hover:dark:text-gray-100 hover:underline flex-grow line-clamp-1"
-												href={selectedFile.id ? `/api/v1/files/${selectedFile.id}/content` : '#'}
-												target="_blank"
-											>
-												{selectedFile?.meta?.name}
-											</a>
-										</div>
-
-										<div>
-											<button
-												class="self-center w-fit text-sm py-1 px-2.5 dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-white/5 rounded-lg"
-												on:click={() => {
-													updateFileContentHandler();
-												}}
-											>
-												{$i18n.t('Save')}
-											</button>
-										</div>
-									</div>
-
-									<div
-										class=" flex-1 w-full h-full max-h-full text-sm bg-transparent outline-none overflow-y-auto scrollbar-hidden"
-									>
-										{#key selectedFile.id}
-											<RichTextInput
-												className="input-prose-sm"
-												bind:value={selectedFile.data.content}
-												placeholder={$i18n.t('Add content here')}
-											/>
-										{/key}
-									</div>
-								</div>
-							{:else}
-								<div></div>
-							{/if}
-						</div>
-					</Pane>
-				{:else if !largeScreen && selectedFileId !== null}
-					<Drawer
-						className="h-full"
-						show={selectedFileId !== null}
-						on:close={() => {
-							selectedFileId = null;
-						}}
-					>
-						<div class="flex flex-col justify-start h-full max-h-full p-2">
-							<div class=" flex flex-col w-full h-full max-h-full">
-								<div class="flex-shrink-0 mt-1 mb-2 flex items-center">
-									<div class="mr-2">
+		<div class="flex flex-row flex-1 h-full max-h-full pb-2.5 gap-3">
+			{#if largeScreen}
+				<div class="flex-1 flex justify-start w-full h-full max-h-full">
+					{#if selectedFile}
+						<div class=" flex flex-col w-full h-full max-h-full">
+							<div class="flex-shrink-0 mb-2 flex items-center">
+								{#if !showSidepanel}
+									<div class="-translate-x-2">
 										<button
 											class="w-full text-left text-sm p-1.5 rounded-lg dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-gray-850"
 											on:click={() => {
-												selectedFileId = null;
+												pane.expand();
 											}}
 										>
 											<ChevronLeft strokeWidth="2.5" />
 										</button>
 									</div>
-									<div class=" flex-1 text-xl line-clamp-1">
-										{selectedFile?.meta?.name}
-									</div>
+								{/if}
 
-									<div>
-										<button
-											class="self-center w-fit text-sm py-1 px-2.5 dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-white/5 rounded-lg"
-											on:click={() => {
-												updateFileContentHandler();
-											}}
-										>
-											{$i18n.t('Save')}
-										</button>
-									</div>
+								<div class=" flex-1 text-xl font-medium">
+									<a
+										class="hover:text-gray-500 hover:dark:text-gray-100 hover:underline flex-grow line-clamp-1"
+										href={selectedFile.id ? `/api/v1/files/${selectedFile.id}/content` : '#'}
+										target="_blank"
+									>
+										{selectedFile?.meta?.name}
+									</a>
 								</div>
 
-								<div
-									class=" flex-1 w-full h-full max-h-full py-2.5 px-3.5 rounded-lg text-sm bg-transparent overflow-y-auto scrollbar-hidden"
-								>
-									{#key selectedFile.id}
-										<RichTextInput
-											className="input-prose-sm"
-											bind:value={selectedFile.data.content}
-											placeholder={$i18n.t('Add content here')}
+								<div>
+									<button
+										class="self-center w-fit text-sm py-1 px-2.5 dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-white/5 rounded-lg"
+										on:click={() => {
+											updateFileContentHandler();
+										}}
+									>
+										{$i18n.t('Save')}
+									</button>
+								</div>
+							</div>
+
+							<div
+								class=" flex-1 w-full h-full max-h-full text-sm bg-transparent outline-none overflow-y-auto scrollbar-hidden"
+							>
+								{#key selectedFile.id}
+									<RichTextInput
+										className="input-prose-sm"
+										bind:value={selectedFile.data.content}
+										placeholder={$i18n.t('Add content here')}
+										preserveBreaks={true}
+									/>
+								{/key}
+							</div>
+						</div>
+					{:else}
+						<div class="h-full flex w-full">
+							<div class="m-auto text-xs text-center text-gray-200 dark:text-gray-700">
+								{$i18n.t('Drag and drop a file to upload or select a file to view')}
+							</div>
+						</div>
+					{/if}
+				</div>
+			{:else if !largeScreen && selectedFileId !== null}
+				<Drawer
+					className="h-full"
+					show={selectedFileId !== null}
+					on:close={() => {
+						selectedFileId = null;
+					}}
+				>
+					<div class="flex flex-col justify-start h-full max-h-full p-2">
+						<div class=" flex flex-col w-full h-full max-h-full">
+							<div class="flex-shrink-0 mt-1 mb-2 flex items-center">
+								<div class="mr-2">
+									<button
+										class="w-full text-left text-sm p-1.5 rounded-lg dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-gray-850"
+										on:click={() => {
+											selectedFileId = null;
+										}}
+									>
+										<ChevronLeft strokeWidth="2.5" />
+									</button>
+								</div>
+								<div class=" flex-1 text-xl line-clamp-1">
+									{selectedFile?.meta?.name}
+								</div>
+
+								<div>
+									<button
+										class="self-center w-fit text-sm py-1 px-2.5 dark:text-gray-300 dark:hover:text-white hover:bg-black/5 dark:hover:bg-white/5 rounded-lg"
+										on:click={() => {
+											updateFileContentHandler();
+										}}
+									>
+										{$i18n.t('Save')}
+									</button>
+								</div>
+							</div>
+
+							<div
+								class=" flex-1 w-full h-full max-h-full py-2.5 px-3.5 rounded-lg text-sm bg-transparent overflow-y-auto scrollbar-hidden"
+							>
+								{#key selectedFile.id}
+									<RichTextInput
+										className="input-prose-sm"
+										bind:value={selectedFile.data.content}
+										placeholder={$i18n.t('Add content here')}
+										preserveBreaks={true}
+									/>
+								{/key}
+							</div>
+						</div>
+					</div>
+				</Drawer>
+			{/if}
+
+			<div
+				class="{largeScreen ? 'flex-shrink-0 w-72 max-w-72' : 'flex-1'}
+			flex
+			py-2
+			rounded-2xl
+			border
+			border-gray-50
+			h-full
+			dark:border-gray-850"
+			>
+				<div class=" flex flex-col w-full space-x-2 rounded-lg h-full">
+					<div class="w-full h-full flex flex-col">
+						<div class=" px-3">
+							<div class="flex mb-0.5">
+								<div class=" self-center ml-1 mr-3">
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 20 20"
+										fill="currentColor"
+										class="w-4 h-4"
+									>
+										<path
+											fill-rule="evenodd"
+											d="M9 3.5a5.5 5.5 0 100 11 5.5 5.5 0 000-11zM2 9a7 7 0 1112.452 4.391l3.328 3.329a.75.75 0 11-1.06 1.06l-3.329-3.328A7 7 0 012 9z"
+											clip-rule="evenodd"
 										/>
-									{/key}
+									</svg>
+								</div>
+								<input
+									class=" w-full text-sm pr-4 py-1 rounded-r-xl outline-none bg-transparent"
+									bind:value={query}
+									placeholder={$i18n.t('Search Collection')}
+									on:focus={() => {
+										selectedFileId = null;
+									}}
+								/>
+
+								<div>
+									<AddContentMenu
+										on:upload={(e) => {
+											if (e.detail.type === 'directory') {
+												uploadDirectoryHandler();
+											} else if (e.detail.type === 'text') {
+												showAddTextContentModal = true;
+											} else {
+												document.getElementById('files-input').click();
+											}
+										}}
+										on:sync={(e) => {
+											showSyncConfirmModal = true;
+										}}
+									/>
 								</div>
 							</div>
 						</div>
-					</Drawer>
-				{/if}
-			</PaneGroup>
+
+						{#if filteredItems.length > 0}
+							<div class=" flex overflow-y-auto h-full w-full scrollbar-hidden text-xs">
+								<Files
+									small
+									files={filteredItems}
+									{selectedFileId}
+									on:click={(e) => {
+										selectedFileId = selectedFileId === e.detail ? null : e.detail;
+									}}
+									on:delete={(e) => {
+										console.log(e.detail);
+
+										selectedFileId = null;
+										deleteFileHandler(e.detail);
+									}}
+								/>
+							</div>
+						{:else}
+							<div class="my-3 flex flex-col justify-center text-center text-gray-500 text-xs">
+								<div>
+									{$i18n.t('No content found')}
+								</div>
+							</div>
+						{/if}
+					</div>
+				</div>
+			</div>
 		</div>
 	{:else}
 		<Spinner />

src/lib/components/workspace/Knowledge/KnowledgeBase/AddTextContentModal.svelte

@@ -20,7 +20,7 @@
 	let voiceInput = false;
 </script>
 
-<Modal size="full" className="h-full bg-white dark:bg-gray-900" bind:show>
+<Modal size="full" containerClassName="" className="h-full bg-white dark:bg-gray-900" bind:show>
 	<div class="absolute top-0 right-0 p-5">
 		<button
 			class="self-center dark:text-white"
@@ -67,7 +67,11 @@
 					</div>
 
 					<div class=" flex-1 w-full h-full">
-						<RichTextInput bind:value={content} placeholder={$i18n.t('Write something...')} />
+						<RichTextInput
+							bind:value={content}
+							placeholder={$i18n.t('Write something...')}
+							preserveBreaks={true}
+						/>
 					</div>
 				</div>
 			</div>
@@ -77,7 +81,7 @@
 			>
 				<div class="">
 					{#if voiceInput}
-						<div class=" max-w-full w-64">
+						<div class=" max-w-full w-full">
 							<VoiceRecording
 								bind:recording={voiceInput}
 								className="p-1"

src/lib/components/workspace/Knowledge/KnowledgeBase/Files.svelte

@@ -6,6 +6,8 @@
 
 	export let selectedFileId = null;
 	export let files = [];
+
+	export let small = false;
 </script>
 
 <div class=" max-h-full flex flex-col w-full">
@@ -16,6 +18,7 @@
 				colorClassName="{selectedFileId === file.id
 					? ' bg-gray-50 dark:bg-gray-850'
 					: 'bg-transparent'} hover:bg-gray-50 dark:hover:bg-gray-850 transition"
+				{small}
 				{file}
 				name={file?.name ?? file?.meta?.name}
 				type="file"

src/lib/components/workspace/Models.svelte

@@ -279,10 +279,16 @@
 
 				<div class="flex justify-between items-center -mb-0.5 px-0.5">
 					<div class=" text-xs mt-0.5">
-						<Tooltip content={model?.user?.email} className="flex shrink-0" placement="top-start">
+						<Tooltip
+							content={model?.user?.email ?? $i18n.t('Deleted User')}
+							className="flex shrink-0"
+							placement="top-start"
+						>
 							<div class="shrink-0 text-gray-500">
 								{$i18n.t('By {{name}}', {
-									name: capitalizeFirstLetter(model?.user?.name ?? model?.user?.email)
+									name: capitalizeFirstLetter(
+										model?.user?.name ?? model?.user?.email ?? $i18n.t('Deleted User')
+									)
 								})}
 							</div>
 						</Tooltip>

src/lib/components/workspace/Models/ModelEditor.svelte

@@ -15,6 +15,7 @@
 	import { getKnowledgeBases } from '$lib/apis/knowledge';
 	import AccessControl from '../common/AccessControl.svelte';
 	import { stringify } from 'postcss';
+	import { toast } from 'svelte-sonner';
 
 	const i18n = getContext('i18n');
 
@@ -68,7 +69,9 @@
 		}
 	};
 
-	let params = {};
+	let params = {
+		system: ''
+	};
 	let capabilities = {
 		vision: true,
 		usage: undefined,
@@ -101,6 +104,14 @@
 		info.id = id;
 		info.name = name;
 
+		if (id === '') {
+			toast.error('Model ID is required.');
+		}
+
+		if (name === '') {
+			toast.error('Model Name is required.');
+		}
+
 		info.access_control = accessControl;
 		info.meta.capabilities = capabilities;
 
@@ -210,9 +221,6 @@
 				}
 			});
 			capabilities = { ...capabilities, ...(model?.meta?.capabilities ?? {}) };
-			if (model?.owned_by === 'openai') {
-				capabilities.usage = false;
-			}
 
 			if ('access_control' in model) {
 				accessControl = model.access_control;
@@ -320,6 +328,7 @@
 						info.meta.profile_image_url = compressedSrc;
 
 						inputFiles = null;
+						filesInputElement.value = '';
 					};
 				};
 
@@ -348,7 +357,7 @@
 				<div class="self-center md:self-start flex justify-center my-2 flex-shrink-0">
 					<div class="self-center">
 						<button
-							class="rounded-2xl flex flex-shrink-0 items-center {info.meta.profile_image_url !==
+							class="rounded-xl flex flex-shrink-0 items-center {info.meta.profile_image_url !==
 							'/static/favicon.png'
 								? 'bg-transparent'
 								: 'bg-white'} shadow-xl group relative"
@@ -361,13 +370,13 @@
 								<img
 									src={info.meta.profile_image_url}
 									alt="model profile"
-									class="rounded-lg size-72 md:size-60 object-cover shrink-0"
+									class="rounded-xl size-72 md:size-60 object-cover shrink-0"
 								/>
 							{:else}
 								<img
 									src="/static/favicon.png"
 									alt="model profile"
-									class=" rounded-lg size-72 md:size-60 object-cover shrink-0"
+									class=" rounded-xl size-72 md:size-60 object-cover shrink-0"
 								/>
 							{/if}
 
@@ -396,6 +405,18 @@
 								class="absolute top-0 bottom-0 left-0 right-0 bg-white dark:bg-black rounded-lg opacity-0 group-hover:opacity-20 transition"
 							></div>
 						</button>
+
+						<div class="flex w-full mt-1 justify-end">
+							<button
+								class="px-2 py-1 text-gray-500 rounded-lg text-xs"
+								on:click={() => {
+									info.meta.profile_image_url = '/static/favicon.png';
+								}}
+								type="button"
+							>
+								Reset Image</button
+							>
+						</div>
 					</div>
 				</div>
 
@@ -413,12 +434,11 @@
 						</div>
 
 						<div class="flex-1">
-							<!-- <div class=" text-sm font-semibold">{$i18n.t('Model ID')}*</div> -->
 							<div>
 								<input
 									class="text-xs w-full bg-transparent text-gray-500 outline-none"
 									placeholder={$i18n.t('Model ID')}
-									value={id}
+									bind:value={id}
 									disabled={edit}
 									required
 								/>

src/lib/components/workspace/Prompts.svelte

@@ -155,13 +155,15 @@
 
 						<div class=" text-xs px-0.5">
 							<Tooltip
-								content={prompt?.user?.email}
+								content={prompt?.user?.email ?? $i18n.t('Deleted User')}
 								className="flex shrink-0"
 								placement="top-start"
 							>
 								<div class="shrink-0 text-gray-500">
 									{$i18n.t('By {{name}}', {
-										name: capitalizeFirstLetter(prompt?.user?.name ?? prompt?.user?.email)
+										name: capitalizeFirstLetter(
+											prompt?.user?.name ?? prompt?.user?.email ?? $i18n.t('Deleted User')
+										)
 									})}
 								</div>
 							</Tooltip>

src/lib/components/workspace/Tools.svelte

@@ -251,12 +251,14 @@
 
 								<div class="text-xs text-gray-500 shrink-0">
 									<Tooltip
-										content={tool?.user?.email}
+										content={tool?.user?.email ?? $i18n.t('Deleted User')}
 										className="flex shrink-0"
 										placement="top-start"
 									>
 										{$i18n.t('By {{name}}', {
-											name: capitalizeFirstLetter(tool?.user?.name ?? tool?.user?.email)
+											name: capitalizeFirstLetter(
+												tool?.user?.name ?? tool?.user?.email ?? $i18n.t('Deleted User')
+											)
 										})}
 									</Tooltip>
 								</div>

src/lib/i18n/locales/ar-BH/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' أو '-1' لا توجد انتهاء",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "( `sh webui.sh --api`مثال)",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "هل تملك حساب ؟",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "مساعد",
 	"and": "و",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "النسخ التلقائي للاستجابة إلى الحافظة",
 	"Auto-playback response": "استجابة التشغيل التلقائي",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 الرابط الرئيسي",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 الرابط مطلوب",
 	"Available list": "",
 	"available!": "متاح",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "خلف",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "تغير الباسورد",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "المحادثة",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "الطلبات المتزامنة",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "تأكيد كلمة المرور",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "(SentenceTransformers) الإفتراضي",
 	"Default Model": "النموذج الافتراضي",
 	"Default model updated": "الإفتراضي تحديث الموديل",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "الإفتراضي Prompt الاقتراحات",
@@ -234,6 +242,7 @@
 	"Delete User": "حذف المستخدم",
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} حذف",
 	"Deleted {{name}}": "حذف {{name}}",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "وصف",
 	"Didn't fully follow instructions": "لم أتبع التعليمات بشكل كامل",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "تضمين محرك النموذج",
 	"Embedding model set to \"{{embedding_model}}\"": "تم تعيين نموذج التضمين على \"{{embedding_model}}\"",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "تمكين مشاركة المجتمع",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "تفعيل عمليات التسجيل الجديدة",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "تمكين بحث الويب",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "تأكد من أن ملف CSV الخاص بك يتضمن 4 أعمدة بهذا الترتيب: Name, Email, Password, Role.",
@@ -326,7 +333,9 @@
 	"Enter language codes": "أدخل كود اللغة",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "(e.g. {{modelTag}}) أدخل الموديل تاق",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "(e.g. 50) أدخل عدد الخطوات",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "أدخل النتيجة",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "فشل في إنشاء مفتاح API.",
 	"Failed to read clipboard contents": "فشل في قراءة محتويات الحافظة",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "فبراير",
@@ -449,6 +459,7 @@
 	"Hide": "أخفاء",
 	"Host": "",
 	"How can I help you today?": "كيف استطيع مساعدتك اليوم؟",
+	"How would you rate this response?": "",
 	"Hybrid Search": "البحث الهجين",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "محتوى الملف النموذجي",
 	"Models": "الموديلات",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "المزيد",
 	"Name": "الأسم",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "لا توجد نتايج",
 	"No search query generated": "لم يتم إنشاء استعلام بحث",
 	"No source available": "لا يوجد مصدر متاح",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "موقف ايجابي",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "مطالبات",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Ollama.com \"{{searchValue}}\" أسحب من ",
 	"Pull a model from Ollama.com": "Ollama.com سحب الموديل من ",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "إزالة",
 	"Remove Model": "حذف الموديل",
 	"Rename": "إعادة تسمية",
+	"Reorder Models": "",
 	"Repeat Last N": "N كرر آخر",
 	"Request Mode": "وضع الطلب",
 	"Reranking Model": "إعادة تقييم النموذج",
 	"Reranking model disabled": "تم تعطيل نموذج إعادة الترتيب",
 	"Reranking model set to \"{{reranking_model}}\"": "تم ضبط نموذج إعادة الترتيب على \"{{reranking_model}}\"",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "منصب",
@@ -829,6 +848,7 @@
 	"System": "النظام",
 	"System Instructions": "",
 	"System Prompt": "محادثة النظام",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -971,6 +991,7 @@
 	"Web Loader Settings": "Web تحميل اعدادات",
 	"Web Search": "بحث الويب",
 	"Web Search Engine": "محرك بحث الويب",
+	"Web Search Query Generation": "",
 	"Webhook URL": "Webhook الرابط",
 	"WebUI Settings": "WebUI اعدادات",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -981,6 +1002,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/bg-BG/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' или '-1' за неограничен срок.",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "(например `sh webui.sh --api`)",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "Вече имате акаунт? ",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "асистент",
 	"and": "и",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "Аувтоматично копиране на отговор в клипборда",
 	"Auto-playback response": "Аувтоматично възпроизвеждане на Отговора",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 Базов URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 Базов URL е задължителен.",
 	"Available list": "",
 	"available!": "наличен!",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "Назад",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "Промяна на Парола",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "Чат",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "Едновременни искания",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "Потвърди Парола",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "По подразбиране (SentenceTransformers)",
 	"Default Model": "Модел по подразбиране",
 	"Default model updated": "Моделът по подразбиране е обновен",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "Промпт Предложения по подразбиране",
@@ -234,6 +242,7 @@
 	"Delete User": "Изтриване на потребител",
 	"Deleted {{deleteModelTag}}": "Изтрито {{deleteModelTag}}",
 	"Deleted {{name}}": "Изтрито {{име}}",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "Описание",
 	"Didn't fully follow instructions": "Не следва инструкциите",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "Модел за вграждане",
 	"Embedding model set to \"{{embedding_model}}\"": "Модел за вграждане е настроен на \"{{embedding_model}}\"",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "Разрешаване на споделяне в общност",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "Вклюване на Нови Потребители",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "Разрешаване на търсене в уеб",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "Уверете се, че вашият CSV файл включва 4 колони в следния ред: Име, Имейл, Парола, Роля.",
@@ -326,7 +333,9 @@
 	"Enter language codes": "Въведете кодове на езика",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "Въведете таг на модел (напр. {{modelTag}})",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "Въведете брой стъпки (напр. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "Въведете оценка",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "Неуспешно създаване на API ключ.",
 	"Failed to read clipboard contents": "Грешка при четене на съдържанието от клипборда",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "Февруари",
@@ -449,6 +459,7 @@
 	"Hide": "Скрий",
 	"Host": "",
 	"How can I help you today?": "Как мога да ви помогна днес?",
+	"How would you rate this response?": "",
 	"Hybrid Search": "Hybrid Search",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "Съдържание на модфайл",
 	"Models": "Модели",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "Повече",
 	"Name": "Име",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "Няма намерени резултати",
 	"No search query generated": "Не е генерирана заявка за търсене",
 	"No source available": "Няма наличен източник",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "Позитивна ативност",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "Промптове",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Извади \"{{searchValue}}\" от Ollama.com",
 	"Pull a model from Ollama.com": "Издърпайте модел от Ollama.com",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "Изтриване",
 	"Remove Model": "Изтриване на модела",
 	"Rename": "Преименуване",
+	"Reorder Models": "",
 	"Repeat Last N": "Repeat Last N",
 	"Request Mode": "Request Mode",
 	"Reranking Model": "Reranking Model",
 	"Reranking model disabled": "Reranking model disabled",
 	"Reranking model set to \"{{reranking_model}}\"": "Reranking model set to \"{{reranking_model}}\"",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "Роля",
@@ -825,6 +844,7 @@
 	"System": "Система",
 	"System Instructions": "",
 	"System Prompt": "Системен Промпт",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -967,6 +987,7 @@
 	"Web Loader Settings": "Настройки за зареждане на уеб",
 	"Web Search": "Търсене в уеб",
 	"Web Search Engine": "Уеб търсачка",
+	"Web Search Query Generation": "",
 	"Webhook URL": "Уебхук URL",
 	"WebUI Settings": "WebUI Настройки",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,6 +998,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/bn-BD/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' অথবা অনির্দিষ্টকাল মেয়াদের জন্য '-1' ",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "(যেমন `sh webui.sh --api`)",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "আগে থেকেই একাউন্ট আছে?",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "একটা এসিস্ট্যান্ট",
 	"and": "এবং",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "রেসপন্সগুলো স্বয়ংক্রিভাবে ক্লিপবোর্ডে কপি হবে",
 	"Auto-playback response": "রেসপন্স অটো-প্লেব্যাক",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 বেজ ইউআরএল",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 বেজ ইউআরএল আবশ্যক",
 	"Available list": "",
 	"available!": "উপলব্ধ!",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "পেছনে",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "পাসওয়ার্ড পরিবর্তন করুন",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "চ্যাট",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "সমকালীন অনুরোধ",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "পাসওয়ার্ড নিশ্চিত করুন",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "ডিফল্ট (SentenceTransformers)",
 	"Default Model": "ডিফল্ট মডেল",
 	"Default model updated": "ডিফল্ট মডেল আপডেট হয়েছে",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "ডিফল্ট প্রম্পট সাজেশন",
@@ -234,6 +242,7 @@
 	"Delete User": "ইউজার মুছে ফেলুন",
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} মুছে ফেলা হয়েছে",
 	"Deleted {{name}}": "{{name}} মোছা হয়েছে",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "বিবরণ",
 	"Didn't fully follow instructions": "ইনস্ট্রাকশন সম্পূর্ণ অনুসরণ করা হয়নি",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "ইমেজ ইমেবডিং মডেল ইঞ্জিন",
 	"Embedding model set to \"{{embedding_model}}\"": "ইমেজ ইমেবডিং মডেল সেট করা হয়েছে - \"{{embedding_model}}\"",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "সম্প্রদায় শেয়ারকরণ সক্ষম করুন",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "নতুন সাইনআপ চালু করুন",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "ওয়েব অনুসন্ধান সক্ষম করুন",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "আপনার সিএসভি ফাইলটিতে এই ক্রমে 4 টি কলাম অন্তর্ভুক্ত রয়েছে তা নিশ্চিত করুন: নাম, ইমেল, পাসওয়ার্ড, ভূমিকা।.",
@@ -326,7 +333,9 @@
 	"Enter language codes": "ল্যাঙ্গুয়েজ কোড লিখুন",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "মডেল ট্যাগ লিখুন (e.g. {{modelTag}})",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "ধাপের সংখ্যা দিন (যেমন: 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "স্কোর দিন",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "API Key তৈরি করা যায়নি।",
 	"Failed to read clipboard contents": "ক্লিপবোর্ডের বিষয়বস্তু পড়া সম্ভব হয়নি",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "ফেব্রুয়ারি",
@@ -449,6 +459,7 @@
 	"Hide": "লুকান",
 	"Host": "",
 	"How can I help you today?": "আপনাকে আজ কিভাবে সাহায্য করতে পারি?",
+	"How would you rate this response?": "",
 	"Hybrid Search": "হাইব্রিড অনুসন্ধান",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "মডেলফাইল কনটেন্ট",
 	"Models": "মডেলসমূহ",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "আরো",
 	"Name": "নাম",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "কোন ফলাফল পাওয়া যায়নি",
 	"No search query generated": "কোনও অনুসন্ধান ক্যোয়ারী উত্পন্ন হয়নি",
 	"No source available": "কোন উৎস পাওয়া যায়নি",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "পজিটিভ আক্রমণ",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "প্রম্পটসমূহ",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Ollama.com থেকে \"{{searchValue}}\" টানুন",
 	"Pull a model from Ollama.com": "Ollama.com থেকে একটি টেনে আনুন আনুন",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "রিমুভ করুন",
 	"Remove Model": "মডেল রিমুভ করুন",
 	"Rename": "রেনেম",
+	"Reorder Models": "",
 	"Repeat Last N": "রিপিট Last N",
 	"Request Mode": "রিকোয়েস্ট মোড",
 	"Reranking Model": "রির্যাক্টিং মডেল",
 	"Reranking model disabled": "রির্যাক্টিং মডেল নিষ্ক্রিয় করা",
 	"Reranking model set to \"{{reranking_model}}\"": "রির ্যাঙ্কিং মডেল \"{{reranking_model}}\" -এ সেট করা আছে",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "পদবি",
@@ -825,6 +844,7 @@
 	"System": "সিস্টেম",
 	"System Instructions": "",
 	"System Prompt": "সিস্টেম প্রম্পট",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -967,6 +987,7 @@
 	"Web Loader Settings": "ওয়েব লোডার সেটিংস",
 	"Web Search": "ওয়েব অনুসন্ধান",
 	"Web Search Engine": "ওয়েব সার্চ ইঞ্জিন",
+	"Web Search Query Generation": "",
 	"Webhook URL": "ওয়েবহুক URL",
 	"WebUI Settings": "WebUI সেটিংসমূহ",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,6 +998,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/ca-ES/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "-1 per a cap límit, o un nombre positiu per a un límit específic",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' o '-1' perquè no caduqui mai.",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "(p. ex. `sh webui.sh --api --api-auth username_password`)",
 	"(e.g. `sh webui.sh --api`)": "(p. ex. `sh webui.sh --api`)",
@@ -11,9 +12,9 @@
 	"A task model is used when performing tasks such as generating titles for chats and web search queries": "Un model de tasca s'utilitza quan es realitzen tasques com ara generar títols per a xats i consultes de cerca per a la web",
 	"a user": "un usuari",
 	"About": "Sobre",
-	"Access": "",
-	"Access Control": "",
-	"Accessible to all users": "",
+	"Access": "Accés",
+	"Access Control": "Control d'accés",
+	"Accessible to all users": "Accessible a tots els usuaris",
 	"Account": "Compte",
 	"Account Activation Pending": "Activació del compte pendent",
 	"Accurate information": "Informació precisa",
@@ -30,14 +31,14 @@
 	"Add content here": "Afegir contingut aquí",
 	"Add custom prompt": "Afegir una indicació personalitzada",
 	"Add Files": "Afegir arxius",
-	"Add Group": "",
+	"Add Group": "Afegir grup",
 	"Add Memory": "Afegir memòria",
 	"Add Model": "Afegir un model",
 	"Add Tag": "Afegir etiqueta",
 	"Add Tags": "Afegir etiquetes",
 	"Add text content": "Afegir contingut de text",
 	"Add User": "Afegir un usuari",
-	"Add User Group": "",
+	"Add User Group": "Afegir grup d'usuaris",
 	"Adjusting these settings will apply changes universally to all users.": "Si ajustes aquesta preferència, els canvis s'aplicaran de manera universal a tots els usuaris.",
 	"admin": "administrador",
 	"Admin": "Administrador",
@@ -48,17 +49,18 @@
 	"Advanced Params": "Paràmetres avançats",
 	"All chats": "Tots els xats",
 	"All Documents": "Tots els documents",
-	"All models deleted successfully": "",
-	"Allow Chat Delete": "",
+	"All models deleted successfully": "Tots els models s'han eliminat correctament",
+	"Allow Chat Delete": "Permetre eliminar el xat",
 	"Allow Chat Deletion": "Permetre la supressió del xat",
-	"Allow Chat Edit": "",
-	"Allow File Upload": "",
+	"Allow Chat Edit": "Permetre editar el xat",
+	"Allow File Upload": "Permetre la pujada d'arxius",
 	"Allow non-local voices": "Permetre veus no locals",
 	"Allow Temporary Chat": "Permetre el xat temporal",
 	"Allow User Location": "Permetre la ubicació de l'usuari",
 	"Allow Voice Interruption in Call": "Permetre la interrupció de la veu en una trucada",
 	"Already have an account?": "Ja tens un compte?",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "Alternativa al top_p, i pretén garantir un equilibri de qualitat i varietat. El paràmetre p representa la probabilitat mínima que es consideri un token, en relació amb la probabilitat del token més probable. Per exemple, amb p=0,05 i el token més probable amb una probabilitat de 0,9, es filtren els logits amb un valor inferior a 0,045. (Per defecte: 0.0)",
+	"Amazing": "Al·lucinant",
 	"an assistant": "un assistent",
 	"and": "i",
 	"and {{COUNT}} more": "i {{COUNT}} més",
@@ -69,7 +71,7 @@
 	"API keys": "Claus de l'API",
 	"Application DN": "DN d'aplicació",
 	"Application DN Password": "Contrasenya del DN d'aplicació",
-	"applies to all users with the \"user\" role": "",
+	"applies to all users with the \"user\" role": "s'aplica a tots els usuaris amb el rol \"usuari\"",
 	"April": "Abril",
 	"Archive": "Arxiu",
 	"Archive All Chats": "Arxiva tots els xats",
@@ -89,12 +91,15 @@
 	"Authenticate": "Autenticar",
 	"Auto-Copy Response to Clipboard": "Copiar la resposta automàticament al porta-retalls",
 	"Auto-playback response": "Reproduir la resposta automàticament",
+	"Autocomplete Generation": "Generació automàtica",
+	"Autocomplete Generation Input Max Length": "Entrada màxima de la generació automàtica",
 	"Automatic1111": "Automatic1111",
 	"AUTOMATIC1111 Api Auth String": "Cadena d'autenticació de l'API d'AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL": "URL Base d'AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "Es requereix l'URL Base d'AUTOMATIC1111.",
 	"Available list": "Llista de disponibles",
 	"available!": "disponible!",
+	"Awful": "Terrible",
 	"Azure AI Speech": "Azure AI Speech",
 	"Azure Region": "Regió d'Azure",
 	"Back": "Enrere",
@@ -107,7 +112,7 @@
 	"Bing Search V7 Endpoint": "Punt de connexió a Bing Search V7",
 	"Bing Search V7 Subscription Key": "Clau de subscripció a Bing Search V7",
 	"Brave Search API Key": "Clau API de Brave Search",
-	"By {{name}}": "",
+	"By {{name}}": "Per {{name}}",
 	"Bypass SSL verification for Websites": "Desactivar la verificació SSL per a l'accés a Internet",
 	"Call": "Trucada",
 	"Call feature is not supported when using Web STT engine": "La funció de trucada no s'admet quan s'utilitza el motor Web STT",
@@ -117,6 +122,7 @@
 	"Certificate Path": "Camí del certificat",
 	"Change Password": "Canviar la contrasenya",
 	"Character": "Personatge",
+	"Character limit for autocomplete generation input": "Límit de caràcters per a l'entrada de generació automàtica",
 	"Chart new frontiers": "Traça noves fronteres",
 	"Chat": "Xat",
 	"Chat Background Image": "Imatge de fons del xat",
@@ -124,7 +130,7 @@
 	"Chat Controls": "Controls de xat",
 	"Chat direction": "Direcció del xat",
 	"Chat Overview": "Vista general del xat",
-	"Chat Permissions": "",
+	"Chat Permissions": "Permisos del xat",
 	"Chat Tags Auto-Generation": "Generació automàtica d'etiquetes del xat",
 	"Chats": "Xats",
 	"Check Again": "Comprovar-ho de nou",
@@ -155,7 +161,7 @@
 	"Code execution": "Execució de codi",
 	"Code formatted successfully": "Codi formatat correctament",
 	"Collection": "Col·lecció",
-	"Color": "",
+	"Color": "Color",
 	"ComfyUI": "ComfyUI",
 	"ComfyUI Base URL": "URL base de ComfyUI",
 	"ComfyUI Base URL is required.": "L'URL base de ComfyUI és obligatòria.",
@@ -165,6 +171,7 @@
 	"Completions": "Completaments",
 	"Concurrent Requests": "Peticions simultànies",
 	"Configure": "Configurar",
+	"Configure Models": "Configurar models",
 	"Confirm": "Confirmar",
 	"Confirm Password": "Confirmar la contrasenya",
 	"Confirm your action": "Confirma la teva acció",
@@ -189,12 +196,12 @@
 	"Copy Link": "Copiar l'enllaç",
 	"Copy to clipboard": "Copiar al porta-retalls",
 	"Copying to clipboard was successful!": "La còpia al porta-retalls s'ha realitzat correctament",
-	"Create": "",
+	"Create": "Crear",
 	"Create a knowledge base": "Crear una base de coneixement",
 	"Create a model": "Crear un model",
 	"Create Account": "Crear un compte",
 	"Create Admin Account": "Crear un compte d'Administrador",
-	"Create Group": "",
+	"Create Group": "Crear grup",
 	"Create Knowledge": "Crear Coneixement",
 	"Create new key": "Crear una nova clau",
 	"Create new secret key": "Crear una nova clau secreta",
@@ -213,8 +220,9 @@
 	"Default (SentenceTransformers)": "Per defecte (SentenceTransformers)",
 	"Default Model": "Model per defecte",
 	"Default model updated": "Model per defecte actualitzat",
-	"Default permissions": "",
-	"Default permissions updated successfully": "",
+	"Default Models": "Models per defecte",
+	"Default permissions": "Permisos per defecte",
+	"Default permissions updated successfully": "Permisos per defecte actualitzats correctament",
 	"Default Prompt Suggestions": "Suggeriments d'indicació per defecte",
 	"Default to 389 or 636 if TLS is enabled": "Per defecte 389 o 636 si TLS està habilitat",
 	"Default to ALL": "Per defecte TOTS",
@@ -222,7 +230,7 @@
 	"Delete": "Eliminar",
 	"Delete a model": "Eliminar un model",
 	"Delete All Chats": "Eliminar tots els xats",
-	"Delete All Models": "",
+	"Delete All Models": "Eliminar tots els models",
 	"Delete chat": "Eliminar xat",
 	"Delete Chat": "Eliminar xat",
 	"Delete chat?": "Eliminar el xat?",
@@ -234,6 +242,7 @@
 	"Delete User": "Eliminar usuari",
 	"Deleted {{deleteModelTag}}": "S'ha eliminat {{deleteModelTag}}",
 	"Deleted {{name}}": "S'ha eliminat {{name}}",
+	"Deleted User": "Usuari eliminat",
 	"Describe your knowledge base and objectives": "Descriu la teva base de coneixement i objectius",
 	"Description": "Descripció",
 	"Didn't fully follow instructions": "No s'han seguit les instruccions completament",
@@ -248,10 +257,10 @@
 	"Discover, download, and explore custom tools": "Descobrir, descarregar i explorar eines personalitzades",
 	"Discover, download, and explore model presets": "Descobrir, descarregar i explorar models preconfigurats",
 	"Dismissible": "Descartable",
-	"Display": "",
+	"Display": "Mostrar",
 	"Display Emoji in Call": "Mostrar emojis a la trucada",
 	"Display the username instead of You in the Chat": "Mostrar el nom d'usuari en lloc de 'Tu' al xat",
-	"Displays citations in the response": "",
+	"Displays citations in the response": "Mostra les referències a la resposta",
 	"Dive into knowledge": "Aprofundir en el coneixement",
 	"Do not install functions from sources you do not fully trust.": "No instal·lis funcions de fonts en què no confiïs plenament.",
 	"Do not install tools from sources you do not fully trust.": "No instal·lis eines de fonts en què no confiïs plenament.",
@@ -267,23 +276,23 @@
 	"Download": "Descarregar",
 	"Download canceled": "Descàrrega cancel·lada",
 	"Download Database": "Descarregar la base de dades",
-	"Drag and drop a file to upload or select a file to view": "",
+	"Drag and drop a file to upload or select a file to view": "Arrossegar un arxiu per pujar o escull un arxiu a veure",
 	"Draw": "Dibuixar",
 	"Drop any files here to add to the conversation": "Deixa qualsevol arxiu aquí per afegir-lo a la conversa",
 	"e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.": "p. ex. '30s','10m'. Les unitats de temps vàlides són 's', 'm', 'h'.",
 	"e.g. A filter to remove profanity from text": "p. ex. Un filtre per eliminar paraules malsonants del text",
 	"e.g. My Filter": "p. ex. El meu filtre",
-	"e.g. My Tools": "",
+	"e.g. My Tools": "p. ex. Les meves eines",
 	"e.g. my_filter": "p. ex. els_meus_filtres",
-	"e.g. my_tools": "",
-	"e.g. Tools for performing various operations": "",
+	"e.g. my_tools": "p. ex. les_meves_eines",
+	"e.g. Tools for performing various operations": "p. ex. Eines per dur a terme operacions",
 	"Edit": "Editar",
 	"Edit Arena Model": "Editar model de l'Arena",
 	"Edit Connection": "Editar la connexió",
-	"Edit Default Permissions": "",
+	"Edit Default Permissions": "Editar el permisos per defecte",
 	"Edit Memory": "Editar la memòria",
 	"Edit User": "Editar l'usuari",
-	"Edit User Group": "",
+	"Edit User Group": "Editar el grup d'usuaris",
 	"ElevenLabs": "ElevenLabs",
 	"Email": "Correu electrònic",
 	"Embark on adventures": "Embarcar en aventures",
@@ -291,17 +300,15 @@
 	"Embedding Model": "Model d'incrustació",
 	"Embedding Model Engine": "Motor de model d'incrustació",
 	"Embedding model set to \"{{embedding_model}}\"": "Model d'incrustació configurat a \"{{embedding_model}}\"",
-	"Enable API Key Auth": "",
+	"Enable API Key Auth": "Activar l'autenticació amb clau API",
+	"Enable autocomplete generation for chat messages": "Activar la generació automàtica per als missatges del xat",
 	"Enable Community Sharing": "Activar l'ús compartit amb la comunitat",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "Activar el bloqueig de memòria (mlock) per evitar que les dades del model s'intercanviïn fora de la memòria RAM. Aquesta opció bloqueja el conjunt de pàgines de treball del model a la memòria RAM, assegurant-se que no s'intercanviaran al disc. Això pot ajudar a mantenir el rendiment evitant errors de pàgina i garantint un accés ràpid a les dades.",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "Activar l'assignació de memòria (mmap) per carregar les dades del model. Aquesta opció permet que el sistema utilitzi l'emmagatzematge en disc com a extensió de la memòria RAM tractant els fitxers de disc com si estiguessin a la memòria RAM. Això pot millorar el rendiment del model permetent un accés més ràpid a les dades. Tanmateix, és possible que no funcioni correctament amb tots els sistemes i pot consumir una quantitat important d'espai en disc.",
 	"Enable Message Rating": "Permetre la qualificació de missatges",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "Activar el mostreig de Mirostat per controlar la perplexitat. (Per defecte: 0, 0 = Inhabilitat, 1 = Mirostat, 2 = Mirostat 2.0)",
 	"Enable New Sign Ups": "Permetre nous registres",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "Activar la generació d'etiquetes",
 	"Enable Web Search": "Activar la cerca web",
-	"Enable Web Search Query Generation": "Activa la generació de consultes de cerca web",
 	"Enabled": "Habilitat",
 	"Engine": "Motor",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "Assegura't que els teus fitxers CSV inclouen 4 columnes en aquest ordre: Nom, Correu electrònic, Contrasenya, Rol.",
@@ -326,7 +333,9 @@
 	"Enter language codes": "Introdueix els codis de llenguatge",
 	"Enter Model ID": "Introdueix l'identificador del model",
 	"Enter model tag (e.g. {{modelTag}})": "Introdueix l'etiqueta del model (p. ex. {{modelTag}})",
+	"Enter Mojeek Search API Key": "Introdueix la clau API de Mojeek Search",
 	"Enter Number of Steps (e.g. 50)": "Introdueix el nombre de passos (p. ex. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "Entra l'URL (p. ex. https://user:password@host:port)",
 	"Enter Sampler (e.g. Euler a)": "Introdueix el mostrejador (p.ex. Euler a)",
 	"Enter Scheduler (e.g. Karras)": "Entra el programador (p.ex. Karras)",
 	"Enter Score": "Introdueix la puntuació",
@@ -371,7 +380,7 @@
 	"Export Config to JSON File": "Exportar la configuració a un arxiu JSON",
 	"Export Functions": "Exportar funcions",
 	"Export Models": "Exportar els models",
-	"Export Presets": "",
+	"Export Presets": "Exportar les configuracions",
 	"Export Prompts": "Exportar les indicacions",
 	"Export to CSV": "Exportar a CSV",
 	"Export Tools": "Exportar les eines",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "No s'ha pogut afegir l'arxiu.",
 	"Failed to create API Key.": "No s'ha pogut crear la clau API.",
 	"Failed to read clipboard contents": "No s'ha pogut llegir el contingut del porta-retalls",
+	"Failed to save models configuration": "No s'ha pogut desar la configuració dels models",
 	"Failed to update settings": "No s'han pogut actualitzar les preferències",
 	"Failed to upload file.": "No s'ha pogut pujar l'arxiu.",
 	"February": "Febrer",
@@ -432,11 +442,11 @@
 	"Good Response": "Bona resposta",
 	"Google PSE API Key": "Clau API PSE de Google",
 	"Google PSE Engine Id": "Identificador del motor PSE de Google",
-	"Group created successfully": "",
-	"Group deleted successfully": "",
-	"Group Description": "",
-	"Group Name": "",
-	"Group updated successfully": "",
+	"Group created successfully": "El grup s'ha creat correctament",
+	"Group deleted successfully": "El grup s'ha eliminat correctament",
+	"Group Description": "Descripció del grup",
+	"Group Name": "Nom del grup",
+	"Group updated successfully": "Grup actualitzat correctament",
 	"Groups": "Grups",
 	"h:mm a": "h:mm a",
 	"Haptic Feedback": "Retorn hàptic",
@@ -444,11 +454,12 @@
 	"Hello, {{name}}": "Hola, {{name}}",
 	"Help": "Ajuda",
 	"Help us create the best community leaderboard by sharing your feedback history!": "Ajuda'ns a crear la millor taula de classificació de la comunitat compartint el teu historial de comentaris!",
-	"Hex Color": "",
-	"Hex Color - Leave empty for default color": "",
+	"Hex Color": "Color hexadecimal",
+	"Hex Color - Leave empty for default color": "Color hexadecimal - Deixar buit per a color per defecte",
 	"Hide": "Amaga",
 	"Host": "Servidor",
 	"How can I help you today?": "Com et puc ajudar avui?",
+	"How would you rate this response?": "Com avaluaries aquesta resposta?",
 	"Hybrid Search": "Cerca híbrida",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "Afirmo que he llegit i entenc les implicacions de la meva acció. Soc conscient dels riscos associats a l'execució de codi arbitrari i he verificat la fiabilitat de la font.",
 	"ID": "ID",
@@ -461,7 +472,7 @@
 	"Import Config from JSON File": "Importar la configuració des d'un arxiu JSON",
 	"Import Functions": "Importar funcions",
 	"Import Models": "Importar models",
-	"Import Presets": "",
+	"Import Presets": "Importar configuracions",
 	"Import Prompts": "Importar indicacions",
 	"Import Tools": "Importar eines",
 	"Include": "Incloure",
@@ -488,7 +499,7 @@
 	"Key": "Clau",
 	"Keyboard shortcuts": "Dreceres de teclat",
 	"Knowledge": "Coneixement",
-	"Knowledge Access": "",
+	"Knowledge Access": "Accés al coneixement",
 	"Knowledge created successfully.": "Coneixement creat correctament.",
 	"Knowledge deleted successfully.": "Coneixement eliminat correctament.",
 	"Knowledge reset successfully.": "Coneixement restablert correctament.",
@@ -518,7 +529,7 @@
 	"Make sure to export a workflow.json file as API format from ComfyUI.": "Assegura't d'exportar un fitxer workflow.json com a format API des de ComfyUI.",
 	"Manage": "Gestionar",
 	"Manage Arena Models": "Gestionar els models de l'Arena",
-	"Manage Ollama": "",
+	"Manage Ollama": "Gestionar Ollama",
 	"Manage Ollama API Connections": "Gestionar les connexions a l'API d'Ollama",
 	"Manage OpenAI API Connections": "Gestionar les connexions a l'API d'OpenAI",
 	"Manage Pipelines": "Gestionar les Pipelines",
@@ -554,17 +565,19 @@
 	"Model accepts image inputs": "El model accepta entrades d'imatge",
 	"Model created successfully!": "Model creat correctament",
 	"Model filesystem path detected. Model shortname is required for update, cannot continue.": "S'ha detectat el camí del sistema de fitxers del model. És necessari un nom curt del model per actualitzar, no es pot continuar.",
-	"Model Filtering": "",
+	"Model Filtering": "Filtrat de models",
 	"Model ID": "Identificador del model",
 	"Model IDs": "Identificadors del model",
 	"Model Name": "Nom del model",
 	"Model not selected": "Model no seleccionat",
 	"Model Params": "Paràmetres del model",
-	"Model Permissions": "",
+	"Model Permissions": "Permisos dels models",
 	"Model updated successfully": "Model actualitzat correctament",
 	"Modelfile Content": "Contingut del Modelfile",
 	"Models": "Models",
-	"Models Access": "",
+	"Models Access": "Accés als models",
+	"Models configuration saved successfully": "La configuració dels models s'ha desat correctament",
+	"Mojeek Search API Key": "Clau API de Mojeek Search",
 	"more": "més",
 	"More": "Més",
 	"Name": "Nom",
@@ -578,15 +591,16 @@
 	"No feedbacks found": "No s'han trobat comentaris",
 	"No file selected": "No s'ha escollit cap fitxer",
 	"No files found.": "No s'han trobat arxius.",
-	"No groups with access, add a group to grant access": "",
+	"No groups with access, add a group to grant access": "No hi ha cap grup amb accés, afegeix un grup per concedir accés",
 	"No HTML, CSS, or JavaScript content found.": "No s'ha trobat contingut HTML, CSS o JavaScript.",
 	"No knowledge found": "No s'ha trobat Coneixement",
-	"No model IDs": "",
+	"No model IDs": "No hi ha IDs de model",
 	"No models found": "No s'han trobat models",
+	"No models selected": "No s'ha seleccionat cap model",
 	"No results found": "No s'han trobat resultats",
 	"No search query generated": "No s'ha generat cap consulta",
 	"No source available": "Sense font disponible",
-	"No users were found.": "",
+	"No users were found.": "No s'han trobat usuaris",
 	"No valves to update": "No hi ha cap Valve per actualitzar",
 	"None": "Cap",
 	"Not factually correct": "No és clarament correcte",
@@ -611,7 +625,7 @@
 	"Only alphanumeric characters and hyphens are allowed": "Només es permeten caràcters alfanumèrics i guions",
 	"Only alphanumeric characters and hyphens are allowed in the command string.": "Només es permeten caràcters alfanumèrics i guions en la comanda.",
 	"Only collections can be edited, create a new knowledge base to edit/add documents.": "Només es poden editar col·leccions, crea una nova base de coneixement per editar/afegir documents.",
-	"Only select users and groups with permission can access": "",
+	"Only select users and groups with permission can access": "Només hi poden accedir usuaris i grups seleccionats amb permís",
 	"Oops! Looks like the URL is invalid. Please double-check and try again.": "Ui! Sembla que l'URL no és vàlida. Si us plau, revisa-la i torna-ho a provar.",
 	"Oops! There are files still uploading. Please wait for the upload to complete.": "Ui! Encara hi ha fitxers pujant-se. Si us plau, espera que finalitzi la càrrega.",
 	"Oops! There was an error in the previous response.": "Ui! Hi ha hagut un error a la resposta anterior.",
@@ -629,21 +643,21 @@
 	"OpenAI API settings updated": "Configuració de l'API d'OpenAI actualitzada",
 	"OpenAI URL/Key required.": "URL/Clau d'OpenAI requerides.",
 	"or": "o",
-	"Organize your users": "",
+	"Organize your users": "Organitza els teus usuaris",
 	"Other": "Altres",
 	"OUTPUT": "SORTIDA",
 	"Output format": "Format de sortida",
 	"Overview": "Vista general",
 	"page": "pàgina",
 	"Password": "Contrasenya",
-	"Paste Large Text as File": "",
+	"Paste Large Text as File": "Enganxa un text llarg com a fitxer",
 	"PDF document (.pdf)": "Document PDF (.pdf)",
 	"PDF Extract Images (OCR)": "Extreu imatges del PDF (OCR)",
 	"pending": "pendent",
 	"Permission denied when accessing media devices": "Permís denegat en accedir a dispositius multimèdia",
 	"Permission denied when accessing microphone": "Permís denegat en accedir al micròfon",
 	"Permission denied when accessing microphone: {{error}}": "Permís denegat en accedir al micròfon: {{error}}",
-	"Permissions": "",
+	"Permissions": "Permisos",
 	"Personalization": "Personalització",
 	"Pin": "Fixar",
 	"Pinned": "Fixat",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "Si us plau, revisa els següents avisos amb cura:",
 	"Please enter a prompt": "Si us plau, entra una indicació",
 	"Please fill in all fields.": "Emplena tots els camps, si us plau.",
+	"Please select a model first.": "Si us plau, selecciona un model primer",
 	"Please select a reason": "Si us plau, selecciona una raó",
 	"Port": "Port",
 	"Positive attitude": "Actitud positiva",
@@ -668,14 +683,15 @@
 	"Profile Image": "Imatge de perfil",
 	"Prompt (e.g. Tell me a fun fact about the Roman Empire)": "Indicació (p.ex. Digues-me quelcom divertit sobre l'Imperi Romà)",
 	"Prompt Content": "Contingut de la indicació",
-	"Prompt created successfully": "",
+	"Prompt created successfully": "Indicació creada correctament",
 	"Prompt suggestions": "Suggeriments d'indicacions",
-	"Prompt updated successfully": "",
+	"Prompt updated successfully": "Indicació actualitzada correctament",
 	"Prompts": "Indicacions",
-	"Prompts Access": "",
+	"Prompts Access": "Accés a les indicacions",
+	"Proxy URL": "URL del proxy",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Obtenir \"{{searchValue}}\" de Ollama.com",
 	"Pull a model from Ollama.com": "Obtenir un model d'Ollama.com",
-	"Query Generation Prompt": "",
+	"Query Generation Prompt": "Indicació per a generació de consulta",
 	"Query Params": "Paràmetres de consulta",
 	"RAG Template": "Plantilla RAG",
 	"Rating": "Valoració",
@@ -693,17 +709,20 @@
 	"Remove": "Eliminar",
 	"Remove Model": "Eliminar el model",
 	"Rename": "Canviar el nom",
+	"Reorder Models": "Reordenar els models",
 	"Repeat Last N": "Repeteix els darrers N",
 	"Request Mode": "Mode de sol·licitud",
 	"Reranking Model": "Model de reavaluació",
 	"Reranking model disabled": "Model de reavaluació desactivat",
 	"Reranking model set to \"{{reranking_model}}\"": "Model de reavaluació establert a \"{{reranking_model}}\"",
 	"Reset": "Restableix",
+	"Reset All Models": "Restablir tots els models",
 	"Reset Upload Directory": "Restableix el directori de pujades",
 	"Reset Vector Storage/Knowledge": "Restableix el Repositori de vectors/Coneixement",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "Les notifications de resposta no es poden activar perquè els permisos del lloc web han estat rebutjats. Comprova les preferències del navegador per donar l'accés necessari.",
 	"Response splitting": "Divisió de la resposta",
 	"Result": "Resultat",
+	"Retrieval Query Generation": "Generació de consultes Retrieval",
 	"Rich Text Input for Chat": "Entrada de text ric per al xat",
 	"RK": "RK",
 	"Role": "Rol",
@@ -749,7 +768,7 @@
 	"Select a base model": "Seleccionar un model base",
 	"Select a engine": "Seleccionar un motor",
 	"Select a function": "Seleccionar una funció",
-	"Select a group": "",
+	"Select a group": "Seleccionar un grup",
 	"Select a model": "Seleccionar un model",
 	"Select a pipeline": "Seleccionar una Pipeline",
 	"Select a pipeline url": "Seleccionar l'URL d'una Pipeline",
@@ -772,7 +791,7 @@
 	"Set as default": "Establir com a predeterminat",
 	"Set CFG Scale": "Establir l'escala CFG",
 	"Set Default Model": "Establir el model predeterminat",
-	"Set embedding model": "",
+	"Set embedding model": "Establir el model d'incrustació",
 	"Set embedding model (e.g. {{model}})": "Establir el model d'incrustació (p.ex. {{model}})",
 	"Set Image Size": "Establir la mida de la image",
 	"Set reranking model (e.g. {{model}})": "Establir el model de reavaluació (p.ex. {{model}})",
@@ -826,6 +845,7 @@
 	"System": "Sistema",
 	"System Instructions": "Instruccions de sistema",
 	"System Prompt": "Indicació del Sistema",
+	"Tags Generation": "Generació d'etiquetes",
 	"Tags Generation Prompt": "Indicació per a la generació d'etiquetes",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "El mostreig sense cua s'utilitza per reduir l'impacte de tokens menys probables de la sortida. Un valor més alt (p. ex., 2,0) reduirà més l'impacte, mentre que un valor d'1,0 desactiva aquesta configuració. (per defecte: 1)",
 	"Tap to interrupt": "Prem per interrompre",
@@ -860,8 +880,8 @@
 	"This response was generated by \"{{model}}\"": "Aquesta resposta l'ha generat el model \"{{model}}\"",
 	"This will delete": "Això eliminarà",
 	"This will delete <strong>{{NAME}}</strong> and <strong>all its contents</strong>.": "Això eliminarà <strong>{{NAME}}</strong> i <strong>tots els continguts</strong>.",
-	"This will delete all models including custom models": "",
-	"This will delete all models including custom models and cannot be undone.": "",
+	"This will delete all models including custom models": "Això eliminarà tots els models incloent els personalitzats",
+	"This will delete all models including custom models and cannot be undone.": "Això eliminarà tots els models incloent els personalitzats i no es pot desfer",
 	"This will reset the knowledge base and sync all files. Do you wish to continue?": "Això restablirà la base de coneixement i sincronitzarà tots els fitxers. Vols continuar?",
 	"Thorough explanation": "Explicació en detall",
 	"Tika": "Tika",
@@ -891,13 +911,13 @@
 	"Too verbose": "Massa explicit",
 	"Tool created successfully": "Eina creada correctament",
 	"Tool deleted successfully": "Eina eliminada correctament",
-	"Tool Description": "",
-	"Tool ID": "",
+	"Tool Description": "Descripció de l'eina",
+	"Tool ID": "ID de l'eina",
 	"Tool imported successfully": "Eina importada correctament",
-	"Tool Name": "",
+	"Tool Name": "Nom de l'eina",
 	"Tool updated successfully": "Eina actualitzada correctament",
 	"Tools": "Eines",
-	"Tools Access": "",
+	"Tools Access": "Accés a les eines",
 	"Tools are a function calling system with arbitrary code execution": "Les eines són un sistema de crida a funcions amb execució de codi arbitrari",
 	"Tools have a function calling system that allows arbitrary code execution": "Les eines disposen d'un sistema de crida a funcions que permet execució de codi arbitrari",
 	"Tools have a function calling system that allows arbitrary code execution.": "Les eines disposen d'un sistema de crida a funcions que permet execució de codi arbitrari.",
@@ -937,7 +957,7 @@
 	"URL Mode": "Mode URL",
 	"Use '#' in the prompt input to load and include your knowledge.": "Utilitza '#' a l'entrada de la indicació per carregar i incloure els teus coneixements.",
 	"Use Gravatar": "Utilitzar Gravatar",
-	"Use groups to group your users and assign permissions.": "",
+	"Use groups to group your users and assign permissions.": "Utilitza grups per agrupar els usuaris i assignar permisos.",
 	"Use Initials": "Utilitzar inicials",
 	"use_mlock (Ollama)": "use_mlock (Ollama)",
 	"use_mmap (Ollama)": "use_mmap (Ollama)",
@@ -956,18 +976,19 @@
 	"variable to have them replaced with clipboard content.": "variable per tenir-les reemplaçades amb el contingut del porta-retalls.",
 	"Version": "Versió",
 	"Version {{selectedVersion}} of {{totalVersions}}": "Versió {{selectedVersion}} de {{totalVersions}}",
-	"Visibility": "",
+	"Visibility": "Visibilitat",
 	"Voice": "Veu",
 	"Voice Input": "Entrada de veu",
 	"Warning": "Avís",
 	"Warning:": "Avís:",
-	"Warning: Enabling this will allow users to upload arbitrary code on the server.": "",
+	"Warning: Enabling this will allow users to upload arbitrary code on the server.": "Avís: Habilitar això permetrà als usuaris penjar codi arbitrari al servidor.",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Avís: Si s'actualitza o es canvia el model d'incrustació, s'hauran de tornar a importar tots els documents.",
 	"Web": "Web",
 	"Web API": "Web API",
 	"Web Loader Settings": "Preferències del carregador web",
 	"Web Search": "Cerca la web",
 	"Web Search Engine": "Motor de cerca de la web",
+	"Web Search Query Generation": "Generació de consultes per a la cerca de la web",
 	"Webhook URL": "URL del webhook",
 	"WebUI Settings": "Preferències de WebUI",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "WebUI farà peticions a \"{{url}}/api/chat\"",
@@ -978,11 +999,12 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "Quan està activat, el model respondrà a cada missatge de xat en temps real, generant una resposta tan bon punt l'usuari envia un missatge. Aquest mode és útil per a aplicacions de xat en directe, però pot afectar el rendiment en maquinari més lent.",
 	"wherever you are": "allà on estiguis",
 	"Whisper (Local)": "Whisper (local)",
+	"Why?": "Per què?",
 	"Widescreen Mode": "Mode de pantalla ampla",
 	"Won": "Ha guanyat",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "Funciona juntament amb top-k. Un valor més alt (p. ex., 0,95) donarà lloc a un text més divers, mentre que un valor més baix (p. ex., 0,5) generarà un text més concentrat i conservador. (Per defecte: 0,9)",
 	"Workspace": "Espai de treball",
-	"Workspace Permissions": "",
+	"Workspace Permissions": "Permisos de l'espai de treball",
 	"Write a prompt suggestion (e.g. Who are you?)": "Escriu una suggerència d'indicació (p. ex. Qui ets?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Escriu un resum en 50 paraules que resumeixi [tema o paraula clau].",
 	"Write something...": "Escriu quelcom...",
@@ -992,7 +1014,7 @@
 	"You can only chat with a maximum of {{maxCount}} file(s) at a time.": "Només pots xatejar amb un màxim de {{maxCount}} fitxers alhora.",
 	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "Pots personalitzar les teves interaccions amb els models de llenguatge afegint memòries mitjançant el botó 'Gestiona' que hi ha a continuació, fent-les més útils i adaptades a tu.",
 	"You cannot upload an empty file.": "No es pot pujar un ariux buit.",
-	"You do not have permission to upload files.": "",
+	"You do not have permission to upload files.": "No tens permisos per pujar arxius.",
 	"You have no archived conversations.": "No tens converses arxivades.",
 	"You have shared this chat": "Has compartit aquest xat",
 	"You're a helpful assistant.": "Ets un assistent útil.",

src/lib/i18n/locales/ceb-PH/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' o '-1' para walay expiration.",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "(pananglitan `sh webui.sh --api`)",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "Naa na kay account ?",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "usa ka katabang",
 	"and": "Ug",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "Awtomatikong kopya sa tubag sa clipboard",
 	"Auto-playback response": "Autoplay nga tubag",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "Base URL AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "Ang AUTOMATIC1111 base URL gikinahanglan.",
 	"Available list": "",
 	"available!": "magamit!",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "Balik",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "Usba ang password",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "Panaghisgot",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "Kumpirma ang password",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "",
 	"Default Model": "",
 	"Default model updated": "Gi-update nga default template",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "Default nga prompt nga mga sugyot",
@@ -234,6 +242,7 @@
 	"Delete User": "",
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} gipapas",
 	"Deleted {{name}}": "",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "Deskripsyon",
 	"Didn't fully follow instructions": "",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "",
 	"Embedding model set to \"{{embedding_model}}\"": "",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "I-enable ang bag-ong mga rehistro",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "",
@@ -326,7 +333,9 @@
 	"Enter language codes": "",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "Pagsulod sa template tag (e.g. {{modelTag}})",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "Pagsulod sa gidaghanon sa mga lakang (e.g. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "Napakyas sa pagbasa sa sulod sa clipboard",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "",
@@ -449,6 +459,7 @@
 	"Hide": "Tagoa",
 	"Host": "",
 	"How can I help you today?": "Unsaon nako pagtabang kanimo karon?",
+	"How would you rate this response?": "",
 	"Hybrid Search": "",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "Mga sulod sa template file",
 	"Models": "Mga modelo",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "",
 	"Name": "Ngalan",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "Walay tinubdan nga anaa",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "Mga aghat",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "",
 	"Pull a model from Ollama.com": "Pagkuha ug template gikan sa Ollama.com",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "",
 	"Remove Model": "",
 	"Rename": "",
+	"Reorder Models": "",
 	"Repeat Last N": "Balika ang katapusang N",
 	"Request Mode": "Query mode",
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "Papel",
@@ -825,6 +844,7 @@
 	"System": "Sistema",
 	"System Instructions": "",
 	"System Prompt": "Madasig nga Sistema",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -967,6 +987,7 @@
 	"Web Loader Settings": "",
 	"Web Search": "",
 	"Web Search Engine": "",
+	"Web Search Query Generation": "",
 	"Webhook URL": "",
 	"WebUI Settings": "Mga Setting sa WebUI",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,6 +998,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/cs-CZ/translation.json

@@ -1,67 +1,69 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' nebo '-1' pro žádné vypršení platnosti.",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "(např. `sh webui.sh --api --api-auth username_password`)",
 	"(e.g. `sh webui.sh --api`)": "(např. `sh webui.sh --api`)",
 	"(latest)": "Nejnovější",
 	"{{ models }}": "{{ models }}",
 	"{{user}}'s Chats": "{{user}}'s konverzace",
-	"{{webUIName}} Backend Required": "Požadováno {{webUIName}} Backend",
-	"*Prompt node ID(s) are required for image generation": "*ID (ID) uzlu pro generování obrázků jsou vyžadována.",
+	"{{webUIName}} Backend Required": "Požadován {{webUIName}} Backend",
+	"*Prompt node ID(s) are required for image generation": "*Jsou vyžadovány IDs pro prompt node pro generování obrázků",
 	"A new version (v{{LATEST_VERSION}}) is now available.": "Nová verze (v{{LATEST_VERSION}}) je nyní k dispozici.",
 	"A task model is used when performing tasks such as generating titles for chats and web search queries": "Model úloh se používá při provádění úloh, jako je generování názvů pro chaty a vyhledávací dotazy na webu.",
 	"a user": "uživatel",
 	"About": "O programu",
-	"Access": "",
+	"Access": "Přístup",
 	"Access Control": "",
-	"Accessible to all users": "",
+	"Accessible to all users": "Přístupné pro všecny uživatele",
 	"Account": "Účet",
 	"Account Activation Pending": "Čeká na aktivaci účtu",
 	"Accurate information": "Přesné informace",
 	"Actions": "Akce",
-	"Activate this command by typing \"/{{COMMAND}}\" to chat input.": "",
+	"Activate this command by typing \"/{{COMMAND}}\" to chat input.": "Aktivujte tenhle příkaz napsáním \"/{{COMMAND}}\" do chat inputu",
 	"Active Users": "Aktivní uživatelé",
 	"Add": "Přidat",
-	"Add a model ID": "",
+	"Add a model ID": "Přidat ID modelu",
 	"Add a short description about what this model does": "Přidejte krátký popis toho, co tento model dělá.",
 	"Add a tag": "Přidat štítek",
-	"Add Arena Model": "Přidat model Arena",
-	"Add Connection": "",
+	"Add Arena Model": "Přidat Arena model",
+	"Add Connection": "Přidat připojení",
 	"Add Content": "Přidat obsah",
 	"Add content here": "Přidat obsah zde",
-	"Add custom prompt": "Přidání vlastního výzvy",
+	"Add custom prompt": "Přidání vlastního promptu",
 	"Add Files": "Přidat soubory",
-	"Add Group": "",
-	"Add Memory": "Přidání paměti",
+	"Add Group": "Přidat skupinu",
+	"Add Memory": "Přidat paměť",
 	"Add Model": "Přidat model",
 	"Add Tag": "Přidat štítek",
-	"Add Tags": "Přidat značky",
+	"Add Tags": "Přidat štítky",
 	"Add text content": "Přidejte textový obsah",
 	"Add User": "Přidat uživatele",
-	"Add User Group": "",
+	"Add User Group": "Přidatg skupinu uživatelů",
 	"Adjusting these settings will apply changes universally to all users.": "Úprava těchto nastavení se projeví univerzálně u všech uživatelů.",
-	"admin": "Správce",
-	"Admin": "Ahoj! Jak ti mohu pomoci?",
-	"Admin Panel": "Administrační panel",
-	"Admin Settings": "Nastavení administrátora",
+	"admin": "amin",
+	"Admin": "Admin",
+	"Admin Panel": "Adminis panel",
+	"Admin Settings": "Nastavení admina",
 	"Admins have access to all tools at all times; users need tools assigned per model in the workspace.": "Administrátoři mají přístup ke všem nástrojům kdykoliv; uživatelé potřebují mít nástroje přiřazené podle modelu ve workspace.",
 	"Advanced Parameters": "Pokročilé parametry",
 	"Advanced Params": "Pokročilé parametry",
 	"All chats": "Všechny chaty",
 	"All Documents": "Všechny dokumenty",
-	"All models deleted successfully": "",
-	"Allow Chat Delete": "",
+	"All models deleted successfully": "Všechny modely úspěšně odstráněny",
+	"Allow Chat Delete": "Povolit odstranění chatu",
 	"Allow Chat Deletion": "Povolit odstranění chatu",
-	"Allow Chat Edit": "",
-	"Allow File Upload": "",
+	"Allow Chat Edit": "Povolit úpravu chatu",
+	"Allow File Upload": "Povolit nahrávat soubory",
 	"Allow non-local voices": "Povolit ne-místní hlasy",
 	"Allow Temporary Chat": "Povolit dočasný chat",
 	"Allow User Location": "Povolit uživatelskou polohu",
 	"Allow Voice Interruption in Call": "Povolit přerušení hlasu při hovoru",
 	"Already have an account?": "Už máte účet?",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "asistent",
 	"and": "a",
-	"and {{COUNT}} more": "a {{COUNT}} dalších",
+	"and {{COUNT}} more": "a {{COUNT}} další/ch",
 	"and create a new shared link.": "a vytvořit nový sdílený odkaz.",
 	"API Base URL": "Základní URL adresa API",
 	"API Key": "Klíč API",
@@ -76,8 +78,8 @@
 	"Archived Chats": "Archivované chaty",
 	"archived-chat-export": "",
 	"Are you sure you want to unarchive all archived chats?": "",
-	"Are you sure?": "Ano, jsem si jistý.",
-	"Arena Models": "Modely Arena",
+	"Are you sure?": "Jste si jistý?",
+	"Arena Models": "Arena modely",
 	"Artifacts": "Artefakty",
 	"Ask a question": "Zeptejte se na otázku",
 	"Assistant": "Ano, jak vám mohu pomoci?",
@@ -86,24 +88,27 @@
 	"Attribute for Username": "",
 	"Audio": "Zvuk",
 	"August": "Srpen",
-	"Authenticate": "",
+	"Authenticate": "Autentikace",
 	"Auto-Copy Response to Clipboard": "Automatické kopírování odpovědi do schránky",
 	"Auto-playback response": "Automatická odpověď při přehrávání",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "Automatic1111",
 	"AUTOMATIC1111 Api Auth String": "AUTOMATIC1111 Api Auth String",
 	"AUTOMATIC1111 Base URL": "Výchozí URL pro AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "Vyžaduje se základní URL pro AUTOMATIC1111.",
 	"Available list": "Dostupný seznam",
 	"available!": "k dispozici!",
+	"Awful": "",
 	"Azure AI Speech": "Azure AI syntéza řeči",
 	"Azure Region": "Azure oblast",
 	"Back": "Zpět",
 	"Bad Response": "Špatná odezva",
 	"Banners": "Bannery",
-	"Base Model (From)": "Základní model (Z)",
-	"Batch Size (num_batch)": "Velikost dávky (num_batch)",
+	"Base Model (From)": "Základní model (z)",
+	"Batch Size (num_batch)": "Batch size (num_batch)",
 	"before": "před",
-	"Being lazy": "Být líný",
+	"Being lazy": "",
 	"Bing Search V7 Endpoint": "",
 	"Bing Search V7 Subscription Key": "",
 	"Brave Search API Key": "Klíč API pro Brave Search",
@@ -112,11 +117,12 @@
 	"Call": "Volání",
 	"Call feature is not supported when using Web STT engine": "Funkce pro volání není podporována při použití Web STT engine.",
 	"Camera": "Kamera",
-	"Cancel": "Zrušit.",
+	"Cancel": "Zrušit",
 	"Capabilities": "Schopnosti",
 	"Certificate Path": "",
-	"Change Password": "Změna hesla",
+	"Change Password": "Změnit heslo",
 	"Character": "Znak",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "Chat",
 	"Chat Background Image": "Obrázek pozadí chatu",
@@ -131,9 +137,9 @@
 	"Check for updates": "Zkontrolovat aktualizace",
 	"Checking for updates...": "Kontrola aktualizací...",
 	"Choose a model before saving...": "Vyberte model před uložením...",
-	"Chunk Overlap": "Překrytí bloků",
-	"Chunk Params": "Parametry chunků",
-	"Chunk Size": "Velikost bloku",
+	"Chunk Overlap": "",
+	"Chunk Params": "",
+	"Chunk Size": "",
 	"Ciphers": "",
 	"Citation": "Odkaz",
 	"Clear memory": "Vymazat paměť",
@@ -154,8 +160,8 @@
 	"Close": "Zavřít",
 	"Code execution": "Provádění kódu",
 	"Code formatted successfully": "Kód byl úspěšně naformátován.",
-	"Collection": "Sbírka",
-	"Color": "",
+	"Collection": "",
+	"Color": "Barva",
 	"ComfyUI": "ComfyUI.",
 	"ComfyUI Base URL": "Základní URL ComfyUI",
 	"ComfyUI Base URL is required.": "Je vyžadována základní URL pro ComfyUI.",
@@ -164,7 +170,8 @@
 	"Command": "Příkaz",
 	"Completions": "Doplnění",
 	"Concurrent Requests": "Současné požadavky",
-	"Configure": "",
+	"Configure": "Konfigurovat",
+	"Configure Models": "Konfigurovat modely",
 	"Confirm": "Potvrdit",
 	"Confirm Password": "Potvrzení hesla",
 	"Confirm your action": "Potvrďte svoji akci",
@@ -189,13 +196,13 @@
 	"Copy Link": "Kopírovat odkaz",
 	"Copy to clipboard": "Kopírovat do schránky",
 	"Copying to clipboard was successful!": "Kopírování do schránky bylo úspěšné!",
-	"Create": "",
-	"Create a knowledge base": "",
+	"Create": "Vytvořit",
+	"Create a knowledge base": "Vytvořit knowledge base",
 	"Create a model": "Vytvořte model",
 	"Create Account": "Vytvořit účet",
-	"Create Admin Account": "",
-	"Create Group": "",
-	"Create Knowledge": "Vytvořit znalosti",
+	"Create Admin Account": "Vytvořit admin účet",
+	"Create Group": "Vytvořit skupinu",
+	"Create Knowledge": "Vytvořit knowledge",
 	"Create new key": "Vytvořit nový klíč",
 	"Create new secret key": "Vytvořte nový tajný klíč",
 	"Created at": "Vytvořeno dne",
@@ -213,8 +220,9 @@
 	"Default (SentenceTransformers)": "Výchozí (SentenceTransformers)",
 	"Default Model": "Výchozí model",
 	"Default model updated": "Výchozí model aktualizován.",
-	"Default permissions": "",
-	"Default permissions updated successfully": "",
+	"Default Models": "Výchozí modely",
+	"Default permissions": "Výchozí povolení",
+	"Default permissions updated successfully": "Výchozí povolení úspěšne aktualizovány",
 	"Default Prompt Suggestions": "Výchozí návrhy promptů",
 	"Default to 389 or 636 if TLS is enabled": "",
 	"Default to ALL": "",
@@ -228,23 +236,24 @@
 	"Delete chat?": "Smazat konverzaci?",
 	"Delete folder?": "Smazat složku?",
 	"Delete function?": "Funkce pro odstranění?",
-	"Delete prompt?": "Smazat výzvu?",
+	"Delete prompt?": "Smazat prompt?",
 	"delete this link": "smazat tento odkaz",
 	"Delete tool?": "Odstranit nástroj?",
 	"Delete User": "Smazat uživatele",
 	"Deleted {{deleteModelTag}}": "Smazáno {{deleteModelTag}}",
 	"Deleted {{name}}": "Smazáno {{name}}",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "Popis",
 	"Didn't fully follow instructions": "Nenásledovali jste přesně všechny instrukce.",
 	"Disabled": "Zakázáno",
 	"Discover a function": "Objevit funkci",
 	"Discover a model": "Objevte model",
-	"Discover a prompt": "Objevte výzvu",
+	"Discover a prompt": "Objevte prompt",
 	"Discover a tool": "Objevte nástroj",
 	"Discover wonders": "",
 	"Discover, download, and explore custom functions": "Objevujte, stahujte a zkoumejte vlastní funkce",
-	"Discover, download, and explore custom prompts": "Objevte, stáhněte a prozkoumejte vlastní výzvy.",
+	"Discover, download, and explore custom prompts": "Objevte, stáhněte a prozkoumejte vlastní prompty.",
 	"Discover, download, and explore custom tools": "Objevujte, stahujte a prozkoumávejte vlastní nástroje",
 	"Discover, download, and explore model presets": "Objevte, stáhněte a prozkoumejte přednastavení modelů",
 	"Dismissible": "Odstranitelné",
@@ -287,21 +296,19 @@
 	"ElevenLabs": "ElevenLabs",
 	"Email": "E-mail",
 	"Embark on adventures": "",
-	"Embedding Batch Size": "Velikost dávky pro vkládání",
+	"Embedding Batch Size": "",
 	"Embedding Model": "Vkládací model (Embedding Model)",
-	"Embedding Model Engine": "Model zabudovaný motor",
+	"Embedding Model Engine": "",
 	"Embedding model set to \"{{embedding_model}}\"": "Model vkládání nastaven na \"{{embedding_model}}\"",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "Povolit sdílení komunity",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "Povolit hodnocení zpráv",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "Povolit nové registrace",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "Povolit webové vyhledávání",
-	"Enable Web Search Query Generation": "Povolit generování dotazů pro webové vyhledávání",
 	"Enabled": "Povoleno",
 	"Engine": "Engine",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "Ujistěte se, že váš CSV soubor obsahuje 4 sloupce v tomto pořadí: Name, Email, Password, Role.",
@@ -326,7 +333,9 @@
 	"Enter language codes": "Zadejte kódy jazyků",
 	"Enter Model ID": "Zadejte ID modelu",
 	"Enter model tag (e.g. {{modelTag}})": "Zadejte označení modelu (např. {{modelTag}})",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "Zadejte počet kroků (např. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "Zadejte vzorkovač (např. Euler a)",
 	"Enter Scheduler (e.g. Karras)": "Zadejte plánovač (např. Karras)",
 	"Enter Score": "Zadejte skóre",
@@ -341,7 +350,7 @@
 	"Enter server label": "",
 	"Enter server port": "",
 	"Enter stop sequence": "Zadejte ukončovací sekvenci",
-	"Enter system prompt": "Vložte systémovou výzvu",
+	"Enter system prompt": "Vložte systémový prompt",
 	"Enter Tavily API Key": "Zadejte API klíč Tavily",
 	"Enter Tika Server URL": "Zadejte URL serveru Tika",
 	"Enter Top K": "Zadejte horní K",
@@ -372,13 +381,14 @@
 	"Export Functions": "Exportovat funkce",
 	"Export Models": "Export modelů",
 	"Export Presets": "",
-	"Export Prompts": "Exportovat výzvy",
+	"Export Prompts": "Exportovat prompty",
 	"Export to CSV": "",
 	"Export Tools": "Exportní nástroje",
 	"External Models": "Externí modely",
 	"Failed to add file.": "Nepodařilo se přidat soubor.",
 	"Failed to create API Key.": "Nepodařilo se vytvořit API klíč.",
 	"Failed to read clipboard contents": "Nepodařilo se přečíst obsah schránky",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "Nepodařilo se aktualizovat nastavení",
 	"Failed to upload file.": "Nepodařilo se nahrát soubor.",
 	"February": "Únor",
@@ -449,6 +459,7 @@
 	"Hide": "Schovej",
 	"Host": "",
 	"How can I help you today?": "Jak vám mohu dnes pomoci?",
+	"How would you rate this response?": "",
 	"Hybrid Search": "Hybridní vyhledávání",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "Beru na vědomí, že jsem si přečetl a chápu důsledky svých činů. Jsem si vědom rizik spojených s vykonáváním libovolného kódu a ověřil jsem důvěryhodnost zdroje.",
 	"ID": "ID",
@@ -521,7 +532,7 @@
 	"Manage Ollama": "",
 	"Manage Ollama API Connections": "",
 	"Manage OpenAI API Connections": "",
-	"Manage Pipelines": "Správa potrubí",
+	"Manage Pipelines": "Správa pipelines",
 	"March": "Březen",
 	"Max Tokens (num_predict)": "Maximální počet tokenů (num_predict)",
 	"Max Upload Count": "Maximální počet nahrání",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "Obsah souboru modelfile",
 	"Models": "Modely",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "více",
 	"More": "Více",
 	"Name": "Jméno",
@@ -583,6 +596,7 @@
 	"No knowledge found": "Nebyly nalezeny žádné znalosti",
 	"No model IDs": "",
 	"No models found": "Nebyly nalezeny žádné modely",
+	"No models selected": "",
 	"No results found": "Nebyly nalezeny žádné výsledky",
 	"No search query generated": "Nebyl vygenerován žádný vyhledávací dotaz.",
 	"No source available": "Není k dispozici žádný zdroj.",
@@ -648,16 +662,17 @@
 	"Pin": "Kolík",
 	"Pinned": "Připnuto",
 	"Pioneer insights": "",
-	"Pipeline deleted successfully": "Potrubí bylo úspěšně odstraněno.",
+	"Pipeline deleted successfully": "Pipeline byla úspěšně odstraněna",
 	"Pipeline downloaded successfully": "Kanál byl úspěšně stažen",
-	"Pipelines": "Potrubí (Pipelines)",
+	"Pipelines": "",
 	"Pipelines Not Detected": "Přenosové kanály nebyly detekovány",
-	"Pipelines Valves": "Potrubní ventily",
+	"Pipelines Valves": "",
 	"Plain text (.txt)": "Čistý text (.txt)",
-	"Playground": "Hřiště",
+	"Playground": "",
 	"Please carefully review the following warnings:": "Prosím, pečlivě si přečtěte následující upozornění:",
 	"Please enter a prompt": "Prosím, zadejte zadání.",
 	"Please fill in all fields.": "Prosím, vyplňte všechna pole.",
+	"Please select a model first.": "",
 	"Please select a reason": "Prosím vyberte důvod",
 	"Port": "",
 	"Positive attitude": "Pozitivní přístup",
@@ -666,13 +681,14 @@
 	"Previous 30 days": "Předchozích 30 dnů",
 	"Previous 7 days": "Předchozích 7 dní",
 	"Profile Image": "Profilový obrázek",
-	"Prompt (e.g. Tell me a fun fact about the Roman Empire)": "Výzva (např. Řekni mi zábavný fakt o Římské říši)",
-	"Prompt Content": "Obsah výzvy",
+	"Prompt (e.g. Tell me a fun fact about the Roman Empire)": "Prompt (např. Řekni mi zábavný fakt o Římské říši)",
+	"Prompt Content": "Obsah promptu",
 	"Prompt created successfully": "",
 	"Prompt suggestions": "Návrhy výzev",
 	"Prompt updated successfully": "",
-	"Prompts": "Výzvy",
+	"Prompts": "Prompty",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Stáhněte \"{{searchValue}}\" z Ollama.com",
 	"Pull a model from Ollama.com": "Stáhněte model z Ollama.com",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "Odebrat",
 	"Remove Model": "Odebrat model",
 	"Rename": "Přejmenovat",
+	"Reorder Models": "",
 	"Repeat Last N": "Opakovat posledních N",
 	"Request Mode": "Režim žádosti",
 	"Reranking Model": "Model pro přehodnocení pořadí",
 	"Reranking model disabled": "Přeřazovací model je deaktivován",
 	"Reranking model set to \"{{reranking_model}}\"": "Model pro přeřazení nastaven na \"{{reranking_model}}\"",
 	"Reset": "režim Reset",
+	"Reset All Models": "",
 	"Reset Upload Directory": "Resetovat adresář nahrávání",
 	"Reset Vector Storage/Knowledge": "Resetování úložiště vektorů/znalostí",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "Oznámení o odpovědích nelze aktivovat, protože oprávnění webu byla zamítnuta. Navštivte nastavení svého prohlížeče a udělte potřebný přístup.",
 	"Response splitting": "Rozdělení odpovědi",
 	"Result": "Výsledek",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "Vstup pro chat ve formátu Rich Text",
 	"RK": "RK",
 	"Role": "Funkci",
@@ -748,14 +767,14 @@
 	"See what's new": "Podívejte se, co je nového",
 	"Seed": "Semínko",
 	"Select a base model": "Vyberte základní model",
-	"Select a engine": "Vyberte motor",
+	"Select a engine": "Vyberte engine",
 	"Select a function": "Vyberte funkci",
 	"Select a group": "",
 	"Select a model": "Vyberte model",
-	"Select a pipeline": "Vyberte si potrubí (pipeline)",
+	"Select a pipeline": "Vyberte pipeline",
 	"Select a pipeline url": "Vyberte URL adresu kanálu",
 	"Select a tool": "Vyberte nástroj",
-	"Select Engine": "Vyberte motor",
+	"Select Engine": "Vyberte engine",
 	"Select Knowledge": "Vybrat znalosti",
 	"Select model": "Vyberte model",
 	"Select only one model to call": "Vyberte pouze jeden model, který chcete použít",
@@ -825,20 +844,21 @@
 	"Support this plugin:": "Podpořte tento plugin:",
 	"Sync directory": "Synchronizovat adresář",
 	"System": "System",
-	"System Instructions": "Pokyny systému",
-	"System Prompt": "Systémová výzva",
-	"Tags Generation Prompt": "Výzva pro generování značek",
+	"System Instructions": "",
+	"System Prompt": "Systémový prompt",
+	"Tags Generation": "",
+	"Tags Generation Prompt": "Prompt pro generování značek",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "Klepněte pro přerušení",
 	"Tavily API Key": "Klíč API pro Tavily",
 	"Tell us more:": "Řekněte nám více.",
-	"Temperature": "Teplota",
+	"Temperature": "",
 	"Template": "Šablona",
 	"Temporary Chat": "Dočasný chat",
 	"Text Splitter": "Rozdělovač textu",
 	"Text-to-Speech Engine": "Stroj pro převod textu na řeč",
 	"Tfs Z": "Tfs Z",
-	"Thanks for your feedback!": "Děkuji za vaši zpětnou vazbu!",
+	"Thanks for your feedback!": "Děkujeme za vaši zpětnou vazbu!",
 	"The Application Account DN you bind with for search": "",
 	"The base to search for users": "",
 	"The batch size determines how many text requests are processed together at once. A higher batch size can increase the performance and speed of the model, but it also requires more memory.  (Default: 512)": "",
@@ -859,7 +879,7 @@
 	"This option sets the maximum number of tokens the model can generate in its response. Increasing this limit allows the model to provide longer answers, but it may also increase the likelihood of unhelpful or irrelevant content being generated.  (Default: 128)": "",
 	"This option will delete all existing files in the collection and replace them with newly uploaded files.": "Tato volba odstraní všechny existující soubory ve sbírce a nahradí je nově nahranými soubory.",
 	"This response was generated by \"{{model}}\"": "Tato odpověď byla vygenerována pomocí \"{{model}}\"",
-	"This will delete": "Tím se odstraní",
+	"This will delete": "Tohle odstraní",
 	"This will delete <strong>{{NAME}}</strong> and <strong>all its contents</strong>.": "Tímto dojde k odstranění <strong>{{NAME}}</strong> a <strong>všech jeho obsahů</strong>.",
 	"This will delete all models including custom models": "",
 	"This will delete all models including custom models and cannot be undone.": "",
@@ -873,16 +893,16 @@
 	"Title (e.g. Tell me a fun fact)": "Název (např. Řekni mi zajímavost)",
 	"Title Auto-Generation": "Automatické generování názvu",
 	"Title cannot be an empty string.": "Název nemůže být prázdným řetězcem.",
-	"Title Generation Prompt": "Generování názvu výzvy",
+	"Title Generation Prompt": "Generování názvu promptu",
 	"TLS": "",
 	"To access the available model names for downloading,": "Pro získání dostupných názvů modelů ke stažení,",
 	"To access the GGUF models available for downloading,": "Pro přístup k modelům GGUF dostupným pro stažení,",
 	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "Pro přístup k WebUI se prosím obraťte na administrátora. Administrátoři mohou spravovat stavy uživatelů z Admin Panelu.",
-	"To attach knowledge base here, add them to the \"Knowledge\" workspace first.": "Chcete-li zde připojit znalostní databázi, nejprve ji přidejte do pracovního prostoru \"Knowledge\".",
+	"To attach knowledge base here, add them to the \"Knowledge\" workspace first.": "Chcete-li zde připojit znalostní databázi, nejprve ji přidejte do workspace \"Knowledge\".",
 	"To protect your privacy, only ratings, model IDs, tags, and metadata are shared from your feedback—your chat logs remain private and are not included.": "Aby byla chráněna vaše soukromí, z vaší zpětné vazby jsou sdílena pouze hodnocení, ID modelů, značky a metadata – vaše chatové záznamy zůstávají soukromé a nejsou zahrnuty.",
 	"To select actions here, add them to the \"Functions\" workspace first.": "Chcete-li zde vybrat akce, nejprve je přidejte do pracovní plochy \"Functions\".",
-	"To select filters here, add them to the \"Functions\" workspace first.": "Chcete-li zde vybrat filtry, nejprve je přidejte do pracovního prostoru „Functions“.",
-	"To select toolkits here, add them to the \"Tools\" workspace first.": "Chcete-li zde vybrat nástroje, přidejte je nejprve do pracovního prostoru \"Tools\".",
+	"To select filters here, add them to the \"Functions\" workspace first.": "Chcete-li zde vybrat filtry, nejprve je přidejte do workspace „Functions“.",
+	"To select toolkits here, add them to the \"Tools\" workspace first.": "Chcete-li zde vybrat nástroje, přidejte je nejprve do workspace \"Tools\".",
 	"Toast notifications for new updates": "Oznámení ve formě toastů pro nové aktualizace",
 	"Today": "Dnes",
 	"Toggle settings": "Přepnout nastavení",
@@ -893,7 +913,7 @@
 	"Tool created successfully": "Nástroj byl úspěšně vytvořen.",
 	"Tool deleted successfully": "Nástroj byl úspěšně smazán.",
 	"Tool Description": "",
-	"Tool ID": "",
+	"Tool ID": "ID nástroje",
 	"Tool imported successfully": "Nástroj byl úspěšně importován",
 	"Tool Name": "",
 	"Tool updated successfully": "Nástroj byl úspěšně aktualizován.",
@@ -913,7 +933,7 @@
 	"Type Hugging Face Resolve (Download) URL": "Zadejte URL pro úspěšné stažení z Hugging Face.",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Jejda! Došlo k problému s připojením k poskytovateli {{provider}}.",
 	"UI": "UI",
-	"Unarchive All": "",
+	"Unarchive All": "Odarchivovat všechny",
 	"Unarchive All Archived Chats": "",
 	"Unarchive Chat": "",
 	"Unlock mysteries": "",
@@ -932,7 +952,7 @@
 	"Upload directory": "Nahrát adresář",
 	"Upload files": "Nahrát soubory",
 	"Upload Files": "Nahrát soubory",
-	"Upload Pipeline": "Nahrát potrubí",
+	"Upload Pipeline": "Nahrát pipeline",
 	"Upload Progress": "Průběh nahrávání",
 	"URL": "",
 	"URL Mode": "Režim URL",
@@ -945,7 +965,7 @@
 	"user": "uživatel",
 	"User": "Uživatel",
 	"User location successfully retrieved.": "Umístění uživatele bylo úspěšně získáno.",
-	"Username": "",
+	"Username": "Uživatelské jméno",
 	"Users": "Uživatelé",
 	"Using the default arena model with all models. Click the plus button to add custom models.": "Použití výchozího modelu arény se všemi modely. Kliknutím na tlačítko plus přidejte vlastní modely.",
 	"Utilize": "Využít",
@@ -957,7 +977,7 @@
 	"variable to have them replaced with clipboard content.": "proměnnou, aby byl jejich obsah nahrazen obsahem schránky.",
 	"Version": "Verze",
 	"Version {{selectedVersion}} of {{totalVersions}}": "Verze {{selectedVersion}} z {{totalVersions}}",
-	"Visibility": "",
+	"Visibility": "Viditelnost",
 	"Voice": "Hlas",
 	"Voice Input": "Hlasový vstup",
 	"Warning": "Varování",
@@ -969,6 +989,7 @@
 	"Web Loader Settings": "Nastavení Web Loaderu",
 	"Web Search": "Vyhledávání na webu",
 	"Web Search Engine": "Webový vyhledávač",
+	"Web Search Query Generation": "",
 	"Webhook URL": "Webhook URL",
 	"WebUI Settings": "Nastavení WebUI",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,16 +998,17 @@
 	"What are you working on?": "",
 	"What’s New in": "Co je nového v",
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
-	"wherever you are": "",
+	"wherever you are": "kdekoliv jste",
 	"Whisper (Local)": "Whisper (Lokálně)",
+	"Why?": "Proč?",
 	"Widescreen Mode": "Režim širokoúhlého zobrazení",
 	"Won": "Vyhrál",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",
-	"Workspace": "Pracovní prostor",
+	"Workspace": "",
 	"Workspace Permissions": "",
 	"Write a prompt suggestion (e.g. Who are you?)": "Navrhněte dotaz (např. Kdo jsi?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Napište shrnutí na 50 slov, které shrnuje [téma nebo klíčové slovo].",
-	"Write something...": "Napiš něco...",
+	"Write something...": "Napište něco...",
 	"Write your model template content here": "",
 	"Yesterday": "Včera",
 	"You": "Vy",
@@ -1001,5 +1023,5 @@
 	"Your account status is currently pending activation.": "Stav vašeho účtu je nyní čekající na aktivaci.",
 	"Your entire contribution will go directly to the plugin developer; Open WebUI does not take any percentage. However, the chosen funding platform might have its own fees.": "Váš celý příspěvek půjde přímo vývojáři pluginu; Open WebUI si nebere žádné procento. Vybraná platforma pro financování však může mít vlastní poplatky.",
 	"Youtube": "YouTube",
-	"Youtube Loader Settings": "Nastavení Stahovače YouTube"
+	"Youtube Loader Settings": "Nastavení YouTube loaderu"
 }

src/lib/i18n/locales/da-DK/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' eller '-1' for ingen udløb",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "(f.eks. `sh webui.sh --api --api-auth username_password`)",
 	"(e.g. `sh webui.sh --api`)": "(f.eks. `sh webui.sh --api`)",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "Tillad afbrydelser i stemme i opkald",
 	"Already have an account?": "Har du allerede en profil?",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "en assistent",
 	"and": "og",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "Automatisk kopiering af svar til udklipsholder",
 	"Auto-playback response": "Automatisk afspil svar",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "Automatic1111",
 	"AUTOMATIC1111 Api Auth String": "AUTOMATIC1111 Api Auth String",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 Base URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 Base URL er påkrævet.",
 	"Available list": "Tilgængelige lister",
 	"available!": "tilgængelig!",
+	"Awful": "",
 	"Azure AI Speech": "Azure AI Speech",
 	"Azure Region": "Azure Region",
 	"Back": "Tilbage",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "Skift password",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "Chat",
 	"Chat Background Image": "Chat baggrundsbillede",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "Concurrent requests",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "Bekræft",
 	"Confirm Password": "Bekræft password",
 	"Confirm your action": "Bekræft din handling",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "Standard (SentenceTransformers)",
 	"Default Model": "Standard model",
 	"Default model updated": "Standard model opdateret",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "Standardforslag til prompt",
@@ -234,6 +242,7 @@
 	"Delete User": "Slet bruger",
 	"Deleted {{deleteModelTag}}": "Slettede {{deleteModelTag}}",
 	"Deleted {{name}}": "Slettede {{name}}",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "Beskrivelse",
 	"Didn't fully follow instructions": "Fulgte ikke instruktioner",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "Embedding Model engine",
 	"Embedding model set to \"{{embedding_model}}\"": "Embedding model sat til \"{{embedding_model}}\"",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "Aktiver deling til Community",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "Aktiver rating af besked",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "Aktiver nye signups",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "Aktiver websøgning",
-	"Enable Web Search Query Generation": "Aktiver query generation med websøgning",
 	"Enabled": "Aktiveret",
 	"Engine": "engine",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "Sørg for at din CSV-fil indeholder 4 kolonner in denne rækkefølge: Name, Email, Password, Role.",
@@ -326,7 +333,9 @@
 	"Enter language codes": "Indtast sprogkoder",
 	"Enter Model ID": "Indtast model-ID",
 	"Enter model tag (e.g. {{modelTag}})": "Indtast modelmærke (f.eks. {{modelTag}})",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "Indtast antal trin (f.eks. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "Indtast sampler (f.eks. Euler a)",
 	"Enter Scheduler (e.g. Karras)": "Indtast scheduler (f.eks. Karras)",
 	"Enter Score": "Indtast score",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "Kunne ikke oprette API-nøgle.",
 	"Failed to read clipboard contents": "Kunne ikke læse indholdet af udklipsholderen",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "Kunne ikke opdatere indstillinger",
 	"Failed to upload file.": "Kunne ikke uploade fil.",
 	"February": "Februar",
@@ -449,6 +459,7 @@
 	"Hide": "Skjul",
 	"Host": "",
 	"How can I help you today?": "Hvordan kan jeg hjælpe dig i dag?",
+	"How would you rate this response?": "",
 	"Hybrid Search": "Hybrid søgning",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "Jeg anerkender, at jeg har læst og forstået konsekvenserne af min handling. Jeg er opmærksom på de risici, der er forbundet med at udføre vilkårlig kode, og jeg har verificeret kildens troværdighed.",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "Modelfilindhold",
 	"Models": "Modeller",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "Mere",
 	"Name": "Navn",
@@ -583,6 +596,7 @@
 	"No knowledge found": "Ingen viden fundet",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "Ingen resultater fundet",
 	"No search query generated": "Ingen søgeforespørgsel genereret",
 	"No source available": "Ingen kilde tilgængelig",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "Gennemgå omhyggeligt følgende advarsler:",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "Udfyld alle felter.",
+	"Please select a model first.": "",
 	"Please select a reason": "Vælg en årsag",
 	"Port": "",
 	"Positive attitude": "Positiv holdning",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "Prompts",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "Hent \"{{searchValue}}\" fra Ollama.com",
 	"Pull a model from Ollama.com": "Hent en model fra Ollama.com",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "Fjern",
 	"Remove Model": "Fjern model",
 	"Rename": "Omdøb",
+	"Reorder Models": "",
 	"Repeat Last N": "Gentag sidste N",
 	"Request Mode": "Forespørgselstilstand",
 	"Reranking Model": "Omarrangeringsmodel",
 	"Reranking model disabled": "Omarrangeringsmodel deaktiveret",
 	"Reranking model set to \"{{reranking_model}}\"": "Omarrangeringsmodel sat til \"{{reranking_model}}\"",
 	"Reset": "Nulstil",
+	"Reset All Models": "",
 	"Reset Upload Directory": "Nulstil uploadmappe",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "Svarnotifikationer kan ikke aktiveres, da webstedets tilladelser er blevet nægtet. Besøg dine browserindstillinger for at give den nødvendige adgang.",
 	"Response splitting": "Svaropdeling",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "Rolle",
@@ -825,6 +844,7 @@
 	"System": "System",
 	"System Instructions": "",
 	"System Prompt": "Systemprompt",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "Tryk for at afbryde",
@@ -967,6 +987,7 @@
 	"Web Loader Settings": "Web Loader-indstillinger",
 	"Web Search": "Websøgning",
 	"Web Search Engine": "Websøgemaskine",
+	"Web Search Query Generation": "",
 	"Webhook URL": "Webhook-URL",
 	"WebUI Settings": "WebUI-indstillinger",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,6 +998,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "Whisper (lokal)",
+	"Why?": "",
 	"Widescreen Mode": "Widescreen-tilstand",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/de-DE/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' oder '-1' für keine Ablaufzeit.",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "(z. B. `sh webui.sh --api --api-auth username_password`)",
 	"(e.g. `sh webui.sh --api`)": "(z. B. `sh webui.sh --api`)",
@@ -11,33 +12,33 @@
 	"A task model is used when performing tasks such as generating titles for chats and web search queries": "Aufgabenmodelle können Unterhaltungstitel oder Websuchanfragen generieren.",
 	"a user": "ein Benutzer",
 	"About": "Über",
-	"Access": "",
-	"Access Control": "",
-	"Accessible to all users": "",
+	"Access": "Zugang",
+	"Access Control": "Zugangskontrolle",
+	"Accessible to all users": "Für alle Benutzer zugänglich",
 	"Account": "Konto",
 	"Account Activation Pending": "Kontoaktivierung ausstehend",
 	"Accurate information": "Präzise Information(en)",
 	"Actions": "Aktionen",
-	"Activate this command by typing \"/{{COMMAND}}\" to chat input.": "",
+	"Activate this command by typing \"/{{COMMAND}}\" to chat input.": "Aktivieren Sie diesen Befehl, indem Sie \"/{{COMMAND}}\" in die Chat-Eingabe eingeben.",
 	"Active Users": "Aktive Benutzer",
 	"Add": "Hinzufügen",
-	"Add a model ID": "",
+	"Add a model ID": "Modell-ID hinzufügen",
 	"Add a short description about what this model does": "Fügen Sie eine kurze Beschreibung über dieses Modell hinzu",
 	"Add a tag": "Tag hinzufügen",
 	"Add Arena Model": "Arena-Modell hinzufügen",
-	"Add Connection": "",
+	"Add Connection": "Verbindung hinzufügen",
 	"Add Content": "Inhalt hinzufügen",
 	"Add content here": "Inhalt hier hinzufügen",
 	"Add custom prompt": "Benutzerdefinierten Prompt hinzufügen",
 	"Add Files": "Dateien hinzufügen",
-	"Add Group": "",
+	"Add Group": "Gruppe hinzufügen",
 	"Add Memory": "Erinnerung hinzufügen",
 	"Add Model": "Modell hinzufügen",
 	"Add Tag": "Tag hinzufügen",
 	"Add Tags": "Tags hinzufügen",
 	"Add text content": "Textinhalt hinzufügen",
 	"Add User": "Benutzer hinzufügen",
-	"Add User Group": "",
+	"Add User Group": "Benutzergruppe hinzufügen",
 	"Adjusting these settings will apply changes universally to all users.": "Das Anpassen dieser Einstellungen wird Änderungen universell auf alle Benutzer anwenden.",
 	"admin": "Administrator",
 	"Admin": "Administrator",
@@ -48,17 +49,18 @@
 	"Advanced Params": "Erweiterte Parameter",
 	"All chats": "Alle Unterhaltungen",
 	"All Documents": "Alle Dokumente",
-	"All models deleted successfully": "",
-	"Allow Chat Delete": "",
+	"All models deleted successfully": "Alle Modelle erfolgreich gelöscht",
+	"Allow Chat Delete": "Löschen von Unterhaltungen erlauben",
 	"Allow Chat Deletion": "Löschen von Unterhaltungen erlauben",
-	"Allow Chat Edit": "",
-	"Allow File Upload": "",
+	"Allow Chat Edit": "Bearbeiten von Unterhaltungen erlauben",
+	"Allow File Upload": "Hochladen von Dateien erlauben",
 	"Allow non-local voices": "Nicht-lokale Stimmen erlauben",
 	"Allow Temporary Chat": "Temporäre Unterhaltungen erlauben",
 	"Allow User Location": "Standort freigeben",
 	"Allow Voice Interruption in Call": "Unterbrechung durch Stimme im Anruf zulassen",
 	"Already have an account?": "Haben Sie bereits einen Account?",
-	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "Alternative zu top_p und zielt darauf ab, ein Gleichgewicht zwischen Qualität und Vielfalt zu gewährleisten. Der Parameter p repräsentiert die Mindestwahrscheinlichkeit für ein Token, um berücksichtigt zu werden, relativ zur Wahrscheinlichkeit des wahrscheinlichsten Tokens. Zum Beispiel, bei p=0.05 und das wahrscheinlichste Token hat eine Wahrscheinlichkeit von 0.9, werden Logits mit einem Wert von weniger als 0.045 herausgefiltert. (Standard: 0.0)",
+	"Amazing": "Fantastisch",
 	"an assistant": "ein Assistent",
 	"and": "und",
 	"and {{COUNT}} more": "und {{COUNT}} mehr",
@@ -67,15 +69,15 @@
 	"API Key": "API-Schlüssel",
 	"API Key created.": "API-Schlüssel erstellt.",
 	"API keys": "API-Schlüssel",
-	"Application DN": "",
-	"Application DN Password": "",
-	"applies to all users with the \"user\" role": "",
+	"Application DN": "Anwendungs-DN",
+	"Application DN Password": "Anwendungs-DN-Passwort",
+	"applies to all users with the \"user\" role": "gilt für alle Benutzer mit der Rolle \"Benutzer\"",
 	"April": "April",
 	"Archive": "Archivieren",
 	"Archive All Chats": "Alle Unterhaltungen archivieren",
 	"Archived Chats": "Archivierte Unterhaltungen",
-	"archived-chat-export": "",
-	"Are you sure you want to unarchive all archived chats?": "",
+	"archived-chat-export": "archivierter-chat-export",
+	"Are you sure you want to unarchive all archived chats?": "Sind Sie sicher, dass Sie alle archivierten Unterhaltungen wiederherstellen möchten?",
 	"Are you sure?": "Sind Sie sicher?",
 	"Arena Models": "Arena-Modelle",
 	"Artifacts": "Artefakte",
@@ -83,18 +85,21 @@
 	"Assistant": "Assistent",
 	"Attach file": "Datei anhängen",
 	"Attention to detail": "Aufmerksamkeit für Details",
-	"Attribute for Username": "",
+	"Attribute for Username": "Attribut für Benutzername",
 	"Audio": "Audio",
 	"August": "August",
-	"Authenticate": "",
+	"Authenticate": "Authentifizieren",
 	"Auto-Copy Response to Clipboard": "Antwort automatisch in die Zwischenablage kopieren",
 	"Auto-playback response": "Antwort automatisch abspielen",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "Automatic1111",
 	"AUTOMATIC1111 Api Auth String": "AUTOMATIC1111-API-Authentifizierungszeichenfolge",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111-Basis-URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111-Basis-URL ist erforderlich.",
 	"Available list": "Verfügbare Liste",
 	"available!": "Verfügbar!",
+	"Awful": "Schrecklich",
 	"Azure AI Speech": "Azure AI Speech",
 	"Azure Region": "Azure-Region",
 	"Back": "Zurück",
@@ -104,27 +109,28 @@
 	"Batch Size (num_batch)": "Stapelgröße (num_batch)",
 	"before": "bereits geteilt",
 	"Being lazy": "Faulheit",
-	"Bing Search V7 Endpoint": "",
-	"Bing Search V7 Subscription Key": "",
+	"Bing Search V7 Endpoint": "Bing Search V7-Endpunkt",
+	"Bing Search V7 Subscription Key": "Bing Search V7-Abonnement-Schlüssel",
 	"Brave Search API Key": "Brave Search API-Schlüssel",
-	"By {{name}}": "",
+	"By {{name}}": "Von {{name}}",
 	"Bypass SSL verification for Websites": "SSL-Überprüfung für Webseiten umgehen",
 	"Call": "Anrufen",
 	"Call feature is not supported when using Web STT engine": "Die Anruffunktion wird nicht unterstützt, wenn die Web-STT-Engine verwendet wird.",
 	"Camera": "Kamera",
 	"Cancel": "Abbrechen",
 	"Capabilities": "Fähigkeiten",
-	"Certificate Path": "",
+	"Certificate Path": "Zertifikatpfad",
 	"Change Password": "Passwort ändern",
 	"Character": "Zeichen",
-	"Chart new frontiers": "",
+	"Character limit for autocomplete generation input": "",
+	"Chart new frontiers": "Neue Wege beschreiten",
 	"Chat": "Gespräch",
 	"Chat Background Image": "Hintergrundbild des Unterhaltungsfensters",
 	"Chat Bubble UI": "Chat Bubble UI",
 	"Chat Controls": "Chat-Steuerung",
 	"Chat direction": "Textrichtung",
 	"Chat Overview": "Unterhaltungsübersicht",
-	"Chat Permissions": "",
+	"Chat Permissions": "Unterhaltungsberechtigungen",
 	"Chat Tags Auto-Generation": "Automatische Generierung von Unterhaltungstags",
 	"Chats": "Unterhaltungen",
 	"Check Again": "Erneut überprüfen",
@@ -134,11 +140,11 @@
 	"Chunk Overlap": "Blocküberlappung",
 	"Chunk Params": "Blockparameter",
 	"Chunk Size": "Blockgröße",
-	"Ciphers": "",
+	"Ciphers": "Verschlüsselungen",
 	"Citation": "Zitate",
 	"Clear memory": "Alle Erinnerungen entfernen",
-	"click here": "",
-	"Click here for filter guides.": "",
+	"click here": "hier klicken",
+	"Click here for filter guides.": "Klicken Sie hier für Filteranleitungen.",
 	"Click here for help.": "Klicken Sie hier für Hilfe.",
 	"Click here to": "Klicken Sie hier, um",
 	"Click here to download user import template file.": "Klicken Sie hier, um die Vorlage für den Benutzerimport herunterzuladen.",
@@ -155,7 +161,7 @@
 	"Code execution": "Codeausführung",
 	"Code formatted successfully": "Code erfolgreich formatiert",
 	"Collection": "Kollektion",
-	"Color": "",
+	"Color": "Farbe",
 	"ComfyUI": "ComfyUI",
 	"ComfyUI Base URL": "ComfyUI-Basis-URL",
 	"ComfyUI Base URL is required.": "ComfyUI-Basis-URL wird benötigt.",
@@ -164,7 +170,8 @@
 	"Command": "Befehl",
 	"Completions": "Vervollständigungen",
 	"Concurrent Requests": "Anzahl gleichzeitiger Anfragen",
-	"Configure": "",
+	"Configure": "Konfigurieren",
+	"Configure Models": "",
 	"Confirm": "Bestätigen",
 	"Confirm Password": "Passwort bestätigen",
 	"Confirm your action": "Bestätigen Sie Ihre Aktion.",
@@ -175,11 +182,11 @@
 	"Context Length": "Kontextlänge",
 	"Continue Response": "Antwort fortsetzen",
 	"Continue with {{provider}}": "Mit {{provider}} fortfahren",
-	"Continue with Email": "",
-	"Continue with LDAP": "",
+	"Continue with Email": "Mit Email fortfahren",
+	"Continue with LDAP": "Mit LDAP fortfahren",
 	"Control how message text is split for TTS requests. 'Punctuation' splits into sentences, 'paragraphs' splits into paragraphs, and 'none' keeps the message as a single string.": "Kontrollieren Sie, wie Nachrichtentext für TTS-Anfragen aufgeteilt wird. 'Punctuation' teilt in Sätze auf, 'paragraphs' teilt in Absätze auf und 'none' behält die Nachricht als einzelnen String.",
 	"Controls": "Steuerung",
-	"Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)": "",
+	"Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0)": "Kontrolliert das Gleichgewicht zwischen Kohärenz und Vielfalt des Ausgabetextes. Ein niedrigerer Wert führt zu fokussierterem und kohärenterem Text. (Standard: 5.0)",
 	"Copied": "Kopiert",
 	"Copied shared chat URL to clipboard!": "Freigabelink in die Zwischenablage kopiert!",
 	"Copied to clipboard": "In die Zwischenablage kopiert",
@@ -189,12 +196,12 @@
 	"Copy Link": "Link kopieren",
 	"Copy to clipboard": "In die Zwischenablage kopieren",
 	"Copying to clipboard was successful!": "Das Kopieren in die Zwischenablage war erfolgreich!",
-	"Create": "",
-	"Create a knowledge base": "",
-	"Create a model": "Ein Modell erstellen",
+	"Create": "Erstellen",
+	"Create a knowledge base": "Wissensspeicher erstellen",
+	"Create a model": "Modell erstellen",
 	"Create Account": "Konto erstellen",
-	"Create Admin Account": "",
-	"Create Group": "",
+	"Create Admin Account": "Administrator-Account erstellen",
+	"Create Group": "Gruppe erstellen",
 	"Create Knowledge": "Wissen erstellen",
 	"Create new key": "Neuen Schlüssel erstellen",
 	"Create new secret key": "Neuen API-Schlüssel erstellen",
@@ -213,16 +220,17 @@
 	"Default (SentenceTransformers)": "Standard (SentenceTransformers)",
 	"Default Model": "Standardmodell",
 	"Default model updated": "Standardmodell aktualisiert",
-	"Default permissions": "",
-	"Default permissions updated successfully": "",
+	"Default Models": "",
+	"Default permissions": "Standardberechtigungen",
+	"Default permissions updated successfully": "Standardberechtigungen erfolgreich aktualisiert",
 	"Default Prompt Suggestions": "Prompt-Vorschläge",
-	"Default to 389 or 636 if TLS is enabled": "",
-	"Default to ALL": "",
+	"Default to 389 or 636 if TLS is enabled": "Standardmäßig auf 389 oder 636 setzen, wenn TLS aktiviert ist",
+	"Default to ALL": "Standardmäßig auf ALLE setzen",
 	"Default User Role": "Standardbenutzerrolle",
 	"Delete": "Löschen",
 	"Delete a model": "Ein Modell löschen",
 	"Delete All Chats": "Alle Unterhaltungen löschen",
-	"Delete All Models": "",
+	"Delete All Models": "Alle Modelle löschen",
 	"Delete chat": "Unterhaltung löschen",
 	"Delete Chat": "Unterhaltung löschen",
 	"Delete chat?": "Unterhaltung löschen?",
@@ -234,7 +242,8 @@
 	"Delete User": "Benutzer löschen",
 	"Deleted {{deleteModelTag}}": "{{deleteModelTag}} gelöscht",
 	"Deleted {{name}}": "{{name}} gelöscht",
-	"Describe your knowledge base and objectives": "",
+	"Deleted User": "Benutzer gelöscht",
+	"Describe your knowledge base and objectives": "Beschreibe deinen Wissensspeicher und deine Ziele",
 	"Description": "Beschreibung",
 	"Didn't fully follow instructions": "Nicht genau den Answeisungen gefolgt",
 	"Disabled": "Deaktiviert",
@@ -242,17 +251,17 @@
 	"Discover a model": "Entdecken Sie weitere Modelle",
 	"Discover a prompt": "Entdecken Sie weitere Prompts",
 	"Discover a tool": "Entdecken Sie weitere Werkzeuge",
-	"Discover wonders": "",
+	"Discover wonders": "Entdecken Sie Wunder",
 	"Discover, download, and explore custom functions": "Entdecken und beziehen Sie benutzerdefinierte Funktionen",
 	"Discover, download, and explore custom prompts": "Entdecken und beziehen Sie benutzerdefinierte Prompts",
 	"Discover, download, and explore custom tools": "Entdecken und beziehen Sie benutzerdefinierte Werkzeuge",
 	"Discover, download, and explore model presets": "Entdecken und beziehen Sie benutzerdefinierte Modellvorlagen",
 	"Dismissible": "ausblendbar",
-	"Display": "",
+	"Display": "Anzeigen",
 	"Display Emoji in Call": "Emojis im Anruf anzeigen",
 	"Display the username instead of You in the Chat": "Soll \"Sie\" durch Ihren Benutzernamen ersetzt werden?",
-	"Displays citations in the response": "",
-	"Dive into knowledge": "",
+	"Displays citations in the response": "Zeigt Zitate in der Antwort an",
+	"Dive into knowledge": "Tauchen Sie in das Wissen ein",
 	"Do not install functions from sources you do not fully trust.": "Installieren Sie keine Funktionen aus Quellen, denen Sie nicht vollständig vertrauen.",
 	"Do not install tools from sources you do not fully trust.": "Installieren Sie keine Werkzeuge aus Quellen, denen Sie nicht vollständig vertrauen.",
 	"Document": "Dokument",
@@ -267,53 +276,51 @@
 	"Download": "Exportieren",
 	"Download canceled": "Exportierung abgebrochen",
 	"Download Database": "Datenbank exportieren",
-	"Drag and drop a file to upload or select a file to view": "",
+	"Drag and drop a file to upload or select a file to view": "Ziehen Sie eine Datei zum Hochladen oder wählen Sie eine Datei zum Anzeigen aus",
 	"Draw": "Zeichnen",
 	"Drop any files here to add to the conversation": "Ziehen Sie beliebige Dateien hierher, um sie der Unterhaltung hinzuzufügen",
 	"e.g. '30s','10m'. Valid time units are 's', 'm', 'h'.": "z. B. '30s','10m'. Gültige Zeiteinheiten sind 's', 'm', 'h'.",
-	"e.g. A filter to remove profanity from text": "",
-	"e.g. My Filter": "",
-	"e.g. My Tools": "",
-	"e.g. my_filter": "",
-	"e.g. my_tools": "",
-	"e.g. Tools for performing various operations": "",
+	"e.g. A filter to remove profanity from text": "z. B. Ein Filter, um Schimpfwörter aus Text zu entfernen",
+	"e.g. My Filter": "z. B. Mein Filter",
+	"e.g. My Tools": "z. B. Meine Werkzeuge",
+	"e.g. my_filter": "z. B. mein_filter",
+	"e.g. my_tools": "z. B. meine_werkzeuge",
+	"e.g. Tools for performing various operations": "z. B. Werkzeuge für verschiedene Operationen",
 	"Edit": "Bearbeiten",
 	"Edit Arena Model": "Arena-Modell bearbeiten",
-	"Edit Connection": "",
-	"Edit Default Permissions": "",
+	"Edit Connection": "Verbindung bearbeiten",
+	"Edit Default Permissions": "Standardberechtigungen bearbeiten",
 	"Edit Memory": "Erinnerungen bearbeiten",
 	"Edit User": "Benutzer bearbeiten",
-	"Edit User Group": "",
+	"Edit User Group": "Benutzergruppe bearbeiten",
 	"ElevenLabs": "ElevenLabs",
 	"Email": "E-Mail",
-	"Embark on adventures": "",
+	"Embark on adventures": "Abenteuer erleben",
 	"Embedding Batch Size": "Embedding-Stapelgröße",
 	"Embedding Model": "Embedding-Modell",
 	"Embedding Model Engine": "Embedding-Modell-Engine",
 	"Embedding model set to \"{{embedding_model}}\"": "Embedding-Modell auf \"{{embedding_model}}\" gesetzt",
-	"Enable API Key Auth": "",
+	"Enable API Key Auth": "API-Schlüssel-Authentifizierung aktivieren",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "Community-Freigabe aktivieren",
-	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
-	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
+	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "Aktiviere Memory Locking (mlock), um zu verhindern, dass Modelldaten aus dem RAM ausgelagert werden. Diese Option sperrt die Arbeitsseiten des Modells im RAM, um sicherzustellen, dass sie nicht auf die Festplatte ausgelagert werden. Dies kann die Leistung verbessern, indem Page Faults vermieden und ein schneller Datenzugriff sichergestellt werden.",
+	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "Aktiviere Memory Mapping (mmap), um Modelldaten zu laden. Diese Option ermöglicht es dem System, den Festplattenspeicher als Erweiterung des RAM zu verwenden, indem Festplattendateien so behandelt werden, als ob sie im RAM wären. Dies kann die Modellleistung verbessern, indem ein schnellerer Datenzugriff ermöglicht wird. Es kann jedoch nicht auf allen Systemen korrekt funktionieren und einen erheblichen Teil des Festplattenspeichers beanspruchen.",
 	"Enable Message Rating": "Nachrichtenbewertung aktivieren",
-	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
+	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "Mirostat Sampling zur Steuerung der Perplexität aktivieren. (Standard: 0, 0 = Deaktiviert, 1 = Mirostat, 2 = Mirostat 2.0)",
 	"Enable New Sign Ups": "Registrierung erlauben",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "Websuche aktivieren",
-	"Enable Web Search Query Generation": "Websuchanfragen-Generierung aktivieren",
 	"Enabled": "Aktiviert",
 	"Engine": "Engine",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "Stellen Sie sicher, dass Ihre CSV-Datei 4 Spalten in dieser Reihenfolge enthält: Name, E-Mail, Passwort, Rolle.",
 	"Enter {{role}} message here": "Geben Sie die {{role}}-Nachricht hier ein",
 	"Enter a detail about yourself for your LLMs to recall": "Geben Sie ein Detail über sich selbst ein, das Ihre Sprachmodelle (LLMs) sich merken sollen",
 	"Enter api auth string (e.g. username:password)": "Geben Sie die API-Authentifizierungszeichenfolge ein (z. B. Benutzername:Passwort)",
-	"Enter Application DN": "",
-	"Enter Application DN Password": "",
-	"Enter Bing Search V7 Endpoint": "",
-	"Enter Bing Search V7 Subscription Key": "",
+	"Enter Application DN": "Geben Sie die Anwendungs-DN ein",
+	"Enter Application DN Password": "Geben Sie das Anwendungs-DN-Passwort ein",
+	"Enter Bing Search V7 Endpoint": "Geben Sie den Bing Search V7-Endpunkt ein",
+	"Enter Bing Search V7 Subscription Key": "Geben Sie den Bing Search V7-Abonnement-Schlüssel ein",
 	"Enter Brave Search API Key": "Geben Sie den Brave Search API-Schlüssel ein",
-	"Enter certificate path": "",
+	"Enter certificate path": "Geben Sie den Zertifikatpfad ein",
 	"Enter CFG Scale (e.g. 7.0)": "Geben Sie die CFG-Skala ein (z. B. 7.0)",
 	"Enter Chunk Overlap": "Geben Sie die Blocküberlappung ein",
 	"Enter Chunk Size": "Geben Sie die Blockgröße ein",
@@ -322,24 +329,26 @@
 	"Enter Google PSE API Key": "Geben Sie den Google PSE-API-Schlüssel ein",
 	"Enter Google PSE Engine Id": "Geben Sie die Google PSE-Engine-ID ein",
 	"Enter Image Size (e.g. 512x512)": "Geben Sie die Bildgröße ein (z. B. 512x512)",
-	"Enter Jina API Key": "",
+	"Enter Jina API Key": "Geben Sie den Jina-API-Schlüssel ein",
 	"Enter language codes": "Geben Sie die Sprachcodes ein",
 	"Enter Model ID": "Geben Sie die Modell-ID ein",
-	"Enter model tag (e.g. {{modelTag}})": "Gebn Sie den Model-Tag ein",
+	"Enter model tag (e.g. {{modelTag}})": "Geben Sie den Model-Tag ein",
+	"Enter Mojeek Search API Key": "Geben Sie den Mojeek Search API-Schlüssel ein",
 	"Enter Number of Steps (e.g. 50)": "Geben Sie die Anzahl an Schritten ein (z. B. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "Geben Sie den Sampler ein (z. B. Euler a)",
 	"Enter Scheduler (e.g. Karras)": "Geben Sie den Scheduler ein (z. B. Karras)",
 	"Enter Score": "Punktzahl eingeben",
 	"Enter SearchApi API Key": "Geben Sie den SearchApi-API-Schlüssel ein",
 	"Enter SearchApi Engine": "Geben Sie die SearchApi-Engine ein",
 	"Enter Searxng Query URL": "Geben Sie die Searxng-Abfrage-URL ein",
-	"Enter Seed": "",
+	"Enter Seed": "Geben Sie den Seed ein",
 	"Enter Serper API Key": "Geben Sie den Serper-API-Schlüssel ein",
 	"Enter Serply API Key": "Geben Sie den",
 	"Enter Serpstack API Key": "Geben Sie den Serpstack-API-Schlüssel ein",
-	"Enter server host": "",
-	"Enter server label": "",
-	"Enter server port": "",
+	"Enter server host": "Geben Sie den Server-Host ein",
+	"Enter server label": "Geben Sie das Server-Label ein",
+	"Enter server port": "Geben Sie den Server-Port ein",
 	"Enter stop sequence": "Stop-Sequenz eingeben",
 	"Enter system prompt": "Systemprompt eingeben",
 	"Enter Tavily API Key": "Geben Sie den Tavily-API-Schlüssel ein",
@@ -352,38 +361,39 @@
 	"Enter your message": "Geben Sie Ihre Nachricht ein",
 	"Enter Your Password": "Geben Sie Ihr Passwort ein",
 	"Enter Your Role": "Geben Sie Ihre Rolle ein",
-	"Enter Your Username": "",
+	"Enter Your Username": "Geben Sie Ihren Benutzernamen ein",
 	"Error": "Fehler",
 	"ERROR": "FEHLER",
 	"Evaluations": "Evaluationen",
-	"Example: (&(objectClass=inetOrgPerson)(uid=%s))": "",
-	"Example: ALL": "",
-	"Example: ou=users,dc=foo,dc=example": "",
-	"Example: sAMAccountName or uid or userPrincipalName": "",
+	"Example: (&(objectClass=inetOrgPerson)(uid=%s))": "Beispiel: (&(objectClass=inetOrgPerson)(uid=%s))",
+	"Example: ALL": "Beispiel: ALL",
+	"Example: ou=users,dc=foo,dc=example": "Beispiel: ou=users,dc=foo,dc=example",
+	"Example: sAMAccountName or uid or userPrincipalName": "Beispiel: sAMAccountName or uid or userPrincipalName",
 	"Exclude": "Ausschließen",
 	"Experimental": "Experimentell",
-	"Explore the cosmos": "",
+	"Explore the cosmos": "Erforschen Sie das Universum",
 	"Export": "Exportieren",
-	"Export All Archived Chats": "",
+	"Export All Archived Chats": "Alle archivierten Unterhaltungen exportieren",
 	"Export All Chats (All Users)": "Alle Unterhaltungen exportieren (alle Benutzer)",
 	"Export chat (.json)": "Unterhaltung exportieren (.json)",
 	"Export Chats": "Unterhaltungen exportieren",
 	"Export Config to JSON File": "Exportiere Konfiguration als JSON-Datei",
 	"Export Functions": "Funktionen exportieren",
 	"Export Models": "Modelle exportieren",
-	"Export Presets": "",
+	"Export Presets": "Voreinstellungen exportieren",
 	"Export Prompts": "Prompts exportieren",
-	"Export to CSV": "",
+	"Export to CSV": "Als CSV exportieren",
 	"Export Tools": "Werkzeuge exportieren",
 	"External Models": "Externe Modelle",
 	"Failed to add file.": "Fehler beim Hinzufügen der Datei.",
 	"Failed to create API Key.": "Fehler beim Erstellen des API-Schlüssels.",
 	"Failed to read clipboard contents": "Fehler beim Abruf der Zwischenablage",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "Fehler beim Aktualisieren der Einstellungen",
 	"Failed to upload file.": "Fehler beim Hochladen der Datei.",
 	"February": "Februar",
 	"Feedback History": "Feedback-Verlauf",
-	"Feedbacks": "",
+	"Feedbacks": "Feedbacks",
 	"Feel free to add specific details": "Fühlen Sie sich frei, spezifische Details hinzuzufügen",
 	"File": "Datei",
 	"File added successfully.": "Datei erfolgreich hinzugefügt.",
@@ -404,18 +414,18 @@
 	"Folder name cannot be empty.": "Ordnername darf nicht leer sein.",
 	"Folder name updated successfully": "Ordnername erfolgreich aktualisiert",
 	"Followed instructions perfectly": "Anweisungen perfekt befolgt",
-	"Forge new paths": "",
+	"Forge new paths": "Neue Wege beschreiten",
 	"Form": "Formular",
 	"Format your variables using brackets like this:": "Formatieren Sie Ihre Variablen mit Klammern, wie hier:",
 	"Frequency Penalty": "Frequenzstrafe",
 	"Function": "Funktion",
 	"Function created successfully": "Funktion erfolgreich erstellt",
 	"Function deleted successfully": "Funktion erfolgreich gelöscht",
-	"Function Description": "",
-	"Function ID": "",
+	"Function Description": "Funktionsbeschreibung",
+	"Function ID": "Funktions-ID",
 	"Function is now globally disabled": "Die Funktion ist jetzt global deaktiviert",
 	"Function is now globally enabled": "Die Funktion ist jetzt global aktiviert",
-	"Function Name": "",
+	"Function Name": "Funktionsname",
 	"Function updated successfully": "Funktion erfolgreich aktualisiert",
 	"Functions": "Funktionen",
 	"Functions allow arbitrary code execution": "Funktionen ermöglichen die Ausführung beliebigen Codes",
@@ -426,33 +436,34 @@
 	"Generate Image": "Bild erzeugen",
 	"Generating search query": "Suchanfrage wird erstellt",
 	"Generation Info": "Generierungsinformationen",
-	"Get started": "",
-	"Get started with {{WEBUI_NAME}}": "",
+	"Get started": "Loslegen",
+	"Get started with {{WEBUI_NAME}}": "Loslegen mit {{WEBUI_NAME}}",
 	"Global": "Global",
 	"Good Response": "Gute Antwort",
 	"Google PSE API Key": "Google PSE-API-Schlüssel",
 	"Google PSE Engine Id": "Google PSE-Engine-ID",
-	"Group created successfully": "",
-	"Group deleted successfully": "",
-	"Group Description": "",
-	"Group Name": "",
-	"Group updated successfully": "",
-	"Groups": "",
+	"Group created successfully": "Gruppe erfolgreich erstellt",
+	"Group deleted successfully": "Gruppe erfolgreich gelöscht",
+	"Group Description": "Gruppenbeschreibung",
+	"Group Name": "Gruppenname",
+	"Group updated successfully": "Gruppe erfolgreich aktualisiert",
+	"Groups": "Gruppen",
 	"h:mm a": "h:mm a",
 	"Haptic Feedback": "Haptisches Feedback",
 	"has no conversations.": "hat keine Unterhaltungen.",
 	"Hello, {{name}}": "Hallo, {{name}}",
 	"Help": "Hilfe",
 	"Help us create the best community leaderboard by sharing your feedback history!": "Helfen Sie uns, die beste Community-Bestenliste zu erstellen, indem Sie Ihren Feedback-Verlauf teilen!",
-	"Hex Color": "",
-	"Hex Color - Leave empty for default color": "",
+	"Hex Color": "Hex-Farbe",
+	"Hex Color - Leave empty for default color": "Hex-Farbe - Leer lassen für Standardfarbe",
 	"Hide": "Verbergen",
-	"Host": "",
+	"Host": "Host",
 	"How can I help you today?": "Wie kann ich Ihnen heute helfen?",
+	"How would you rate this response?": "Wie würden Sie diese Antwort bewerten?",
 	"Hybrid Search": "Hybride Suche",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "Ich bestätige, dass ich gelesen habe und die Auswirkungen meiner Aktion verstehe. Mir sind die Risiken bewusst, die mit der Ausführung beliebigen Codes verbunden sind, und ich habe die Vertrauenswürdigkeit der Quelle überprüft.",
 	"ID": "ID",
-	"Ignite curiosity": "",
+	"Ignite curiosity": "Neugier entfachen",
 	"Image Generation (Experimental)": "Bildgenerierung (experimentell)",
 	"Image Generation Engine": "Bildgenerierungs-Engine",
 	"Image Settings": "Bildeinstellungen",
@@ -461,13 +472,13 @@
 	"Import Config from JSON File": "Konfiguration aus JSON-Datei importieren",
 	"Import Functions": "Funktionen importieren",
 	"Import Models": "Modelle importieren",
-	"Import Presets": "",
+	"Import Presets": "Voreinstellungen importieren",
 	"Import Prompts": "Prompts importieren",
 	"Import Tools": "Werkzeuge importieren",
 	"Include": "Einschließen",
 	"Include `--api-auth` flag when running stable-diffusion-webui": "Fügen Sie beim Ausführen von stable-diffusion-webui die Option `--api-auth` hinzu",
 	"Include `--api` flag when running stable-diffusion-webui": "Fügen Sie beim Ausführen von stable-diffusion-webui die Option `--api` hinzu",
-	"Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)": "",
+	"Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1)": "Beeinflusst, wie schnell der Algorithmus auf Feedback aus dem generierten Text reagiert. Eine niedrigere Lernrate führt zu langsameren Anpassungen, während eine höhere Lernrate den Algorithmus reaktionsschneller macht. (Standard: 0.1)",
 	"Info": "Info",
 	"Input commands": "Eingabebefehle",
 	"Install from Github URL": "Installiere von der Github-URL",
@@ -476,7 +487,7 @@
 	"Invalid file format.": "Ungültiges Dateiformat.",
 	"Invalid Tag": "Ungültiger Tag",
 	"January": "Januar",
-	"Jina API Key": "",
+	"Jina API Key": "Jina-API-Schlüssel",
 	"join our Discord for help.": "Treten Sie unserem Discord bei, um Hilfe zu erhalten.",
 	"JSON": "JSON",
 	"JSON Preview": "JSON-Vorschau",
@@ -485,31 +496,31 @@
 	"JWT Expiration": "JWT-Ablauf",
 	"JWT Token": "JWT-Token",
 	"Keep Alive": "Verbindung aufrechterhalten",
-	"Key": "",
+	"Key": "Schlüssel",
 	"Keyboard shortcuts": "Tastenkombinationen",
 	"Knowledge": "Wissen",
-	"Knowledge Access": "",
+	"Knowledge Access": "Wissenszugriff",
 	"Knowledge created successfully.": "Wissen erfolgreich erstellt.",
 	"Knowledge deleted successfully.": "Wissen erfolgreich gelöscht.",
 	"Knowledge reset successfully.": "Wissen erfolgreich zurückgesetzt.",
 	"Knowledge updated successfully": "Wissen erfolgreich aktualisiert",
-	"Label": "",
+	"Label": "Label",
 	"Landing Page Mode": "Startseitenmodus",
 	"Language": "Sprache",
 	"Last Active": "Zuletzt aktiv",
 	"Last Modified": "Zuletzt bearbeitet",
-	"LDAP": "",
-	"LDAP server updated": "",
+	"LDAP": "LDAP",
+	"LDAP server updated": "LDAP-Server aktualisiert",
 	"Leaderboard": "Bestenliste",
 	"Leave empty for unlimited": "Leer lassen für unbegrenzt",
-	"Leave empty to include all models from \"{{URL}}/api/tags\" endpoint": "",
-	"Leave empty to include all models from \"{{URL}}/models\" endpoint": "",
+	"Leave empty to include all models from \"{{URL}}/api/tags\" endpoint": "Leer lassen, um alle Modelle vom \"{{URL}}/api/tags\"-Endpunkt einzuschließen",
+	"Leave empty to include all models from \"{{URL}}/models\" endpoint": "Leer lassen, um alle Modelle vom \"{{URL}}/models\"-Endpunkt einzuschließen",
 	"Leave empty to include all models or select specific models": "Leer lassen, um alle Modelle einzuschließen oder spezifische Modelle auszuwählen",
 	"Leave empty to use the default prompt, or enter a custom prompt": "Leer lassen, um den Standardprompt zu verwenden, oder geben Sie einen benutzerdefinierten Prompt ein",
 	"Light": "Hell",
 	"Listening...": "Höre zu...",
 	"LLMs can make mistakes. Verify important information.": "LLMs können Fehler machen. Überprüfe wichtige Informationen.",
-	"Local": "",
+	"Local": "Lokal",
 	"Local Models": "Lokale Modelle",
 	"Lost": "Verloren",
 	"LTR": "LTR",
@@ -518,9 +529,9 @@
 	"Make sure to export a workflow.json file as API format from ComfyUI.": "Stellen Sie sicher, dass sie eine workflow.json-Datei im API-Format von ComfyUI exportieren.",
 	"Manage": "Verwalten",
 	"Manage Arena Models": "Arena-Modelle verwalten",
-	"Manage Ollama": "",
-	"Manage Ollama API Connections": "",
-	"Manage OpenAI API Connections": "",
+	"Manage Ollama": "Ollama verwalten",
+	"Manage Ollama API Connections": "Ollama-API-Verbindungen verwalten",
+	"Manage OpenAI API Connections": "OpenAI-API-Verbindungen verwalten",
 	"Manage Pipelines": "Pipelines verwalten",
 	"March": "März",
 	"Max Tokens (num_predict)": "Maximale Tokenanzahl (num_predict)",
@@ -554,21 +565,23 @@
 	"Model accepts image inputs": "Modell akzeptiert Bileingaben",
 	"Model created successfully!": "Modell erfolgreich erstellt!",
 	"Model filesystem path detected. Model shortname is required for update, cannot continue.": "Modell-Dateisystempfad erkannt. Modellkurzname ist für das Update erforderlich, Fortsetzung nicht möglich.",
-	"Model Filtering": "",
+	"Model Filtering": "Modellfilterung",
 	"Model ID": "Modell-ID",
-	"Model IDs": "",
+	"Model IDs": "Modell-IDs",
 	"Model Name": "Modell-Name",
 	"Model not selected": "Modell nicht ausgewählt",
-	"Model Params": "Modell-Params",
-	"Model Permissions": "",
+	"Model Params": "Modell-Parameter",
+	"Model Permissions": "Modellberechtigungen",
 	"Model updated successfully": "Modell erfolgreich aktualisiert",
 	"Modelfile Content": "Modelfile-Inhalt",
 	"Models": "Modelle",
-	"Models Access": "",
+	"Models Access": "Modell-Zugriff",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "Mojeek Search API-Schlüssel",
 	"more": "mehr",
 	"More": "Mehr",
 	"Name": "Name",
-	"Name your knowledge base": "",
+	"Name your knowledge base": "Benennen Sie Ihren Wissensspeicher",
 	"New Chat": "Neue Unterhaltung",
 	"New folder": "Neuer Ordner",
 	"New Password": "Neues Passwort",
@@ -578,15 +591,16 @@
 	"No feedbacks found": "Kein Feedback gefunden",
 	"No file selected": "Keine Datei ausgewählt",
 	"No files found.": "Keine Dateien gefunden.",
-	"No groups with access, add a group to grant access": "",
+	"No groups with access, add a group to grant access": "Keine Gruppen mit Zugriff, fügen Sie eine Gruppe hinzu, um Zugriff zu gewähren",
 	"No HTML, CSS, or JavaScript content found.": "Keine HTML-, CSS- oder JavaScript-Inhalte gefunden.",
 	"No knowledge found": "Kein Wissen gefunden",
-	"No model IDs": "",
+	"No model IDs": "Keine Modell-IDs",
 	"No models found": "Keine Modelle gefunden",
+	"No models selected": "",
 	"No results found": "Keine Ergebnisse gefunden",
 	"No search query generated": "Keine Suchanfrage generiert",
 	"No source available": "Keine Quelle verfügbar",
-	"No users were found.": "",
+	"No users were found.": "Keine Benutzer gefunden.",
 	"No valves to update": "Keine Valves zum Aktualisieren",
 	"None": "Nichts",
 	"Not factually correct": "Nicht sachlich korrekt",
@@ -605,13 +619,13 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama-API",
 	"Ollama API disabled": "Ollama-API deaktiviert",
-	"Ollama API settings updated": "",
+	"Ollama API settings updated": "Ollama-API-Einstellungen aktualisiert",
 	"Ollama Version": "Ollama-Version",
 	"On": "Ein",
-	"Only alphanumeric characters and hyphens are allowed": "",
+	"Only alphanumeric characters and hyphens are allowed": "Nur alphanumerische Zeichen und Bindestriche sind erlaubt",
 	"Only alphanumeric characters and hyphens are allowed in the command string.": "In der Befehlszeichenfolge sind nur alphanumerische Zeichen und Bindestriche erlaubt.",
 	"Only collections can be edited, create a new knowledge base to edit/add documents.": "Nur Sammlungen können bearbeitet werden. Erstellen Sie eine neue Wissensbasis, um Dokumente zu bearbeiten/hinzuzufügen.",
-	"Only select users and groups with permission can access": "",
+	"Only select users and groups with permission can access": "Nur ausgewählte Benutzer und Gruppen mit Berechtigung können darauf zugreifen",
 	"Oops! Looks like the URL is invalid. Please double-check and try again.": "Hoppla! Es scheint, dass die URL ungültig ist. Bitte überprüfen Sie diese und versuchen Sie es erneut.",
 	"Oops! There are files still uploading. Please wait for the upload to complete.": "Hoppla! Es werden noch Dateien hochgeladen. Bitte warten Sie, bis der Upload abgeschlossen ist.",
 	"Oops! There was an error in the previous response.": "Hoppla! Es gab einen Fehler in der vorherigen Antwort.",
@@ -620,34 +634,34 @@
 	"Open in full screen": "Im Vollbildmodus öffnen",
 	"Open new chat": "Neuen Chat öffnen",
 	"Open WebUI uses faster-whisper internally.": "Open WebUI verwendet intern faster-whisper.",
-	"Open WebUI uses SpeechT5 and CMU Arctic speaker embeddings.": "",
+	"Open WebUI uses SpeechT5 and CMU Arctic speaker embeddings.": "Open WebUI verwendet SpeechT5 und CMU Arctic-Sprecher-Embeddings.",
 	"Open WebUI version (v{{OPEN_WEBUI_VERSION}}) is lower than required version (v{{REQUIRED_VERSION}})": "Die installierte Open-WebUI-Version (v{{OPEN_WEBUI_VERSION}}) ist niedriger als die erforderliche Version (v{{REQUIRED_VERSION}})",
 	"OpenAI": "OpenAI",
 	"OpenAI API": "OpenAI-API",
 	"OpenAI API Config": "OpenAI-API-Konfiguration",
 	"OpenAI API Key is required.": "OpenAI-API-Schlüssel erforderlich.",
-	"OpenAI API settings updated": "",
+	"OpenAI API settings updated": "OpenAI-API-Einstellungen aktualisiert",
 	"OpenAI URL/Key required.": "OpenAI-URL/Schlüssel erforderlich.",
 	"or": "oder",
-	"Organize your users": "",
+	"Organize your users": "Organisieren Sie Ihre Benutzer",
 	"Other": "Andere",
 	"OUTPUT": "AUSGABE",
 	"Output format": "Ausgabeformat",
 	"Overview": "Übersicht",
 	"page": "Seite",
 	"Password": "Passwort",
-	"Paste Large Text as File": "",
+	"Paste Large Text as File": "Großen Text als Datei einfügen",
 	"PDF document (.pdf)": "PDF-Dokument (.pdf)",
 	"PDF Extract Images (OCR)": "Text von Bildern aus PDFs extrahieren (OCR)",
 	"pending": "ausstehend",
 	"Permission denied when accessing media devices": "Zugriff auf Mediengeräte verweigert",
 	"Permission denied when accessing microphone": "Zugriff auf das Mikrofon verweigert",
 	"Permission denied when accessing microphone: {{error}}": "Zugriff auf das Mikrofon verweigert: {{error}}",
-	"Permissions": "",
+	"Permissions": "Berechtigungen",
 	"Personalization": "Personalisierung",
 	"Pin": "Anheften",
 	"Pinned": "Angeheftet",
-	"Pioneer insights": "",
+	"Pioneer insights": "Bahnbrechende Erkenntnisse",
 	"Pipeline deleted successfully": "Pipeline erfolgreich gelöscht",
 	"Pipeline downloaded successfully": "Pipeline erfolgreich heruntergeladen",
 	"Pipelines": "Pipelines",
@@ -658,24 +672,26 @@
 	"Please carefully review the following warnings:": "Bitte überprüfen Sie die folgenden Warnungen sorgfältig:",
 	"Please enter a prompt": "Bitte geben Sie einen Prompt ein",
 	"Please fill in all fields.": "Bitte füllen Sie alle Felder aus.",
+	"Please select a model first.": "",
 	"Please select a reason": "Bitte wählen Sie einen Grund aus",
-	"Port": "",
+	"Port": "Port",
 	"Positive attitude": "Positive Einstellung",
-	"Prefix ID": "",
-	"Prefix ID is used to avoid conflicts with other connections by adding a prefix to the model IDs - leave empty to disable": "",
+	"Prefix ID": "Präfix-ID",
+	"Prefix ID is used to avoid conflicts with other connections by adding a prefix to the model IDs - leave empty to disable": "Prefix-ID wird verwendet, um Konflikte mit anderen Verbindungen zu vermeiden, indem ein Präfix zu den Modell-IDs hinzugefügt wird - leer lassen, um zu deaktivieren",
 	"Previous 30 days": "Vorherige 30 Tage",
 	"Previous 7 days": "Vorherige 7 Tage",
 	"Profile Image": "Profilbild",
 	"Prompt (e.g. Tell me a fun fact about the Roman Empire)": "Prompt (z. B. \"Erzähle mir eine interessante Tatsache über das Römische Reich\")",
 	"Prompt Content": "Prompt-Inhalt",
-	"Prompt created successfully": "",
+	"Prompt created successfully": "Prompt erfolgreich erstellt",
 	"Prompt suggestions": "Prompt-Vorschläge",
-	"Prompt updated successfully": "",
+	"Prompt updated successfully": "Prompt erfolgreich aktualisiert",
 	"Prompts": "Prompts",
-	"Prompts Access": "",
+	"Prompts Access": "Prompt-Zugriff",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "\"{{searchValue}}\" von Ollama.com beziehen",
 	"Pull a model from Ollama.com": "Modell von Ollama.com beziehen",
-	"Query Generation Prompt": "",
+	"Query Generation Prompt": "Abfragegenerierungsprompt",
 	"Query Params": "Abfrageparameter",
 	"RAG Template": "RAG-Vorlage",
 	"Rating": "Bewertung",
@@ -683,7 +699,7 @@
 	"Read Aloud": "Vorlesen",
 	"Record voice": "Stimme aufnehmen",
 	"Redirecting you to OpenWebUI Community": "Sie werden zur OpenWebUI-Community weitergeleitet",
-	"Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)": "",
+	"Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)": "Reduziert die Wahrscheinlichkeit, Unsinn zu generieren. Ein höherer Wert (z.B. 100) liefert vielfältigere Antworten, während ein niedrigerer Wert (z.B. 10) konservativer ist. (Standard: 40)",
 	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "Beziehen Sie sich auf sich selbst als \"Benutzer\" (z. B. \"Benutzer lernt Spanisch\")",
 	"References from": "Referenzen aus",
 	"Refused when it shouldn't have": "Abgelehnt, obwohl es nicht hätte abgelehnt werden sollen",
@@ -693,17 +709,20 @@
 	"Remove": "Entfernen",
 	"Remove Model": "Modell entfernen",
 	"Rename": "Umbenennen",
+	"Reorder Models": "",
 	"Repeat Last N": "Wiederhole die letzten N",
 	"Request Mode": "Anforderungsmodus",
 	"Reranking Model": "Reranking-Modell",
 	"Reranking model disabled": "Reranking-Modell deaktiviert",
 	"Reranking model set to \"{{reranking_model}}\"": "Reranking-Modell \"{{reranking_model}}\" fesgelegt",
 	"Reset": "Zurücksetzen",
+	"Reset All Models": "",
 	"Reset Upload Directory": "Upload-Verzeichnis zurücksetzen",
 	"Reset Vector Storage/Knowledge": "Vektorspeicher/Wissen zurücksetzen",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "Benachrichtigungen können nicht aktiviert werden, da die Website-Berechtigungen abgelehnt wurden. Bitte besuchen Sie Ihre Browser-Einstellungen, um den erforderlichen Zugriff zu gewähren.",
 	"Response splitting": "Antwortaufteilung",
 	"Result": "Ergebnis",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "Rich-Text-Eingabe für Unterhaltungen",
 	"RK": "RK",
 	"Role": "Rolle",
@@ -722,18 +741,18 @@
 	"Scroll to bottom when switching between branches": "Beim Wechsel zwischen Branches nach unten scrollen",
 	"Search": "Suchen",
 	"Search a model": "Modell suchen",
-	"Search Base": "",
+	"Search Base": "Suchbasis",
 	"Search Chats": "Unterhaltungen durchsuchen...",
 	"Search Collection": "Sammlung durchsuchen",
-	"Search Filters": "",
+	"Search Filters": "Suchfilter",
 	"search for tags": "nach Tags suchen",
 	"Search Functions": "Funktionen durchsuchen...",
 	"Search Knowledge": "Wissen durchsuchen",
 	"Search Models": "Modelle durchsuchen...",
-	"Search options": "",
+	"Search options": "Suchoptionen",
 	"Search Prompts": "Prompts durchsuchen...",
 	"Search Result Count": "Anzahl der Suchergebnisse",
-	"Search the web": "",
+	"Search the web": "Im Web suchen",
 	"Search Tools": "Werkzeuge durchsuchen...",
 	"SearchApi API Key": "SearchApi-API-Schlüssel",
 	"SearchApi Engine": "SearchApi-Engine",
@@ -748,7 +767,7 @@
 	"Select a base model": "Wählen Sie ein Basismodell",
 	"Select a engine": "Wählen Sie eine Engine",
 	"Select a function": "Wählen Sie eine Funktion",
-	"Select a group": "",
+	"Select a group": "Wählen Sie eine Gruppe",
 	"Select a model": "Wählen Sie ein Modell",
 	"Select a pipeline": "Wählen Sie eine Pipeline",
 	"Select a pipeline url": "Wählen Sie eine Pipeline-URL",
@@ -771,7 +790,7 @@
 	"Set as default": "Als Standard festlegen",
 	"Set CFG Scale": "CFG-Skala festlegen",
 	"Set Default Model": "Standardmodell festlegen",
-	"Set embedding model": "",
+	"Set embedding model": "Einbettungsmodell festlegen",
 	"Set embedding model (e.g. {{model}})": "Einbettungsmodell festlegen (z. B. {{model}})",
 	"Set Image Size": "Bildgröße festlegen",
 	"Set reranking model (e.g. {{model}})": "Rerankingmodell festlegen (z. B. {{model}})",
@@ -779,29 +798,29 @@
 	"Set Scheduler": "Scheduler festlegen",
 	"Set Steps": "Schrittgröße festlegen",
 	"Set Task Model": "Aufgabenmodell festlegen",
-	"Set the number of GPU devices used for computation. This option controls how many GPU devices (if available) are used to process incoming requests. Increasing this value can significantly improve performance for models that are optimized for GPU acceleration but may also consume more power and GPU resources.": "",
-	"Set the number of worker threads used for computation. This option controls how many threads are used to process incoming requests concurrently. Increasing this value can improve performance under high concurrency workloads but may also consume more CPU resources.": "",
+	"Set the number of GPU devices used for computation. This option controls how many GPU devices (if available) are used to process incoming requests. Increasing this value can significantly improve performance for models that are optimized for GPU acceleration but may also consume more power and GPU resources.": "Legt die Anzahl der für die Berechnung verwendeten GPU-Geräte fest. Diese Option steuert, wie viele GPU-Geräte (falls verfügbar) zur Verarbeitung eingehender Anfragen verwendet werden. Eine Erhöhung dieses Wertes kann die Leistung für Modelle, die für GPU-Beschleunigung optimiert sind, erheblich verbessern, kann jedoch auch mehr Strom und GPU-Ressourcen verbrauchen.",
+	"Set the number of worker threads used for computation. This option controls how many threads are used to process incoming requests concurrently. Increasing this value can improve performance under high concurrency workloads but may also consume more CPU resources.": "Legt die Anzahl der für die Berechnung verwendeten GPU-Geräte fest. Diese Option steuert, wie viele GPU-Geräte (falls verfügbar) zur Verarbeitung eingehender Anfragen verwendet werden. Eine Erhöhung dieses Wertes kann die Leistung für Modelle, die für GPU-Beschleunigung optimiert sind, erheblich verbessern, kann jedoch auch mehr Strom und GPU-Ressourcen verbrauchen.",
 	"Set Voice": "Stimme festlegen",
 	"Set whisper model": "Whisper-Modell festlegen",
-	"Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)": "",
-	"Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)": "",
-	"Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: random)": "",
-	"Sets the size of the context window used to generate the next token. (Default: 2048)": "",
-	"Sets the stop sequences to use. When this pattern is encountered, the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile.": "",
+	"Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx)": "Legt fest, wie weit das Modell zurückblicken soll, um Wiederholungen zu verhindern. (Standard: 64, 0 = deaktiviert, -1 = num_ctx)",
+	"Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)": "Legt fest, wie stark Wiederholungen bestraft werden sollen. Ein höherer Wert (z.B. 1.5) bestraft Wiederholungen stärker, während ein niedrigerer Wert (z.B. 0.9) nachsichtiger ist. (Standard: 1.1)",
+	"Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: random)": "Legt den Zufallszahlengenerator-Seed für die Generierung fest. Wenn dieser auf eine bestimmte Zahl gesetzt wird, erzeugt das Modell denselben Text für denselben Prompt. (Standard: zufällig)",
+	"Sets the size of the context window used to generate the next token. (Default: 2048)": "Legt die Größe des Kontextfensters fest, das zur Generierung des nächsten Tokens verwendet wird. (Standard: 2048)",
+	"Sets the stop sequences to use. When this pattern is encountered, the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile.": "Legt die zu verwendenden Stoppsequenzen fest. Wenn dieses Muster erkannt wird, stoppt das LLM die Textgenerierung und gibt zurück. Mehrere Stoppmuster können festgelegt werden, indem mehrere separate Stopp-Parameter in einer Modelldatei angegeben werden.",
 	"Settings": "Einstellungen",
 	"Settings saved successfully!": "Einstellungen erfolgreich gespeichert!",
 	"Share": "Teilen",
 	"Share Chat": "Unterhaltung teilen",
 	"Share to OpenWebUI Community": "Mit OpenWebUI Community teilen",
 	"Show": "Anzeigen",
-	"Show \"What's New\" modal on login": "",
+	"Show \"What's New\" modal on login": "\"Was gibt's Neues\"-Modal beim Anmelden anzeigen",
 	"Show Admin Details in Account Pending Overlay": "Admin-Details im Account-Pending-Overlay anzeigen",
 	"Show shortcuts": "Verknüpfungen anzeigen",
 	"Show your support!": "Zeigen Sie Ihre Unterstützung!",
 	"Showcased creativity": "Kreativität gezeigt",
 	"Sign in": "Anmelden",
 	"Sign in to {{WEBUI_NAME}}": "Bei {{WEBUI_NAME}} anmelden",
-	"Sign in to {{WEBUI_NAME}} with LDAP": "",
+	"Sign in to {{WEBUI_NAME}} with LDAP": "Bei {{WEBUI_NAME}} mit LDAP anmelden",
 	"Sign Out": "Abmelden",
 	"Sign up": "Registrieren",
 	"Sign up to {{WEBUI_NAME}}": "Bei {{WEBUI_NAME}} registrieren",
@@ -825,8 +844,9 @@
 	"System": "System",
 	"System Instructions": "Systemanweisungen",
 	"System Prompt": "System-Prompt",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "Prompt für Tag-Generierung",
-	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
+	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "Tail-Free Sampling wird verwendet, um den Einfluss weniger wahrscheinlicher Tokens auf die Ausgabe zu reduzieren. Ein höherer Wert (z.B. 2.0) reduziert den Einfluss stärker, während ein Wert von 1.0 diese Einstellung deaktiviert. (Standard: 1)",
 	"Tap to interrupt": "Zum Unterbrechen tippen",
 	"Tavily API Key": "Tavily-API-Schlüssel",
 	"Tell us more:": "Erzähl uns mehr",
@@ -837,30 +857,30 @@
 	"Text-to-Speech Engine": "Text-zu-Sprache-Engine",
 	"Tfs Z": "Tfs Z",
 	"Thanks for your feedback!": "Danke für Ihr Feedback!",
-	"The Application Account DN you bind with for search": "",
-	"The base to search for users": "",
-	"The batch size determines how many text requests are processed together at once. A higher batch size can increase the performance and speed of the model, but it also requires more memory.  (Default: 512)": "",
+	"The Application Account DN you bind with for search": "Der Anwendungs-Konto-DN, mit dem Sie für die Suche binden",
+	"The base to search for users": "Die Basis, in der nach Benutzern gesucht wird",
+	"The batch size determines how many text requests are processed together at once. A higher batch size can increase the performance and speed of the model, but it also requires more memory.  (Default: 512)": "Die Batch-Größe bestimmt, wie viele Textanfragen gleichzeitig verarbeitet werden. Eine größere Batch-Größe kann die Leistung und Geschwindigkeit des Modells erhöhen, erfordert jedoch auch mehr Speicher. (Standard: 512)",
 	"The developers behind this plugin are passionate volunteers from the community. If you find this plugin helpful, please consider contributing to its development.": "Die Entwickler hinter diesem Plugin sind leidenschaftliche Freiwillige aus der Community. Wenn Sie dieses Plugin hilfreich finden, erwägen Sie bitte, zu seiner Entwicklung beizutragen.",
 	"The evaluation leaderboard is based on the Elo rating system and is updated in real-time.": "Die Bewertungs-Bestenliste basiert auf dem Elo-Bewertungssystem und wird in Echtzeit aktualisiert.",
-	"The LDAP attribute that maps to the username that users use to sign in.": "",
+	"The LDAP attribute that maps to the username that users use to sign in.": "Das LDAP-Attribut, das dem Benutzernamen zugeordnet ist, den Benutzer zum Anmelden verwenden.",
 	"The leaderboard is currently in beta, and we may adjust the rating calculations as we refine the algorithm.": "Die Bestenliste befindet sich derzeit in der Beta-Phase, und es ist möglich, dass wir die Bewertungsberechnungen anpassen, während wir den Algorithmus verfeinern.",
 	"The maximum file size in MB. If the file size exceeds this limit, the file will not be uploaded.": "Die maximale Dateigröße in MB. Wenn die Dateigröße dieses Limit überschreitet, wird die Datei nicht hochgeladen.",
 	"The maximum number of files that can be used at once in chat. If the number of files exceeds this limit, the files will not be uploaded.": "Die maximale Anzahl von Dateien, die gleichzeitig in der Unterhaltung verwendet werden können. Wenn die Anzahl der Dateien dieses Limit überschreitet, werden die Dateien nicht hochgeladen.",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "Die Punktzahl sollte ein Wert zwischen 0,0 (0 %) und 1,0 (100 %) sein.",
-	"The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)": "",
+	"The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8)": "Die Temperatur des Modells. Eine Erhöhung der Temperatur führt dazu, dass das Modell kreativer antwortet. (Standard: 0,8)",
 	"Theme": "Design",
 	"Thinking...": "Denke nach...",
 	"This action cannot be undone. Do you wish to continue?": "Diese Aktion kann nicht rückgängig gemacht werden. Möchten Sie fortfahren?",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Dies stellt sicher, dass Ihre wertvollen Unterhaltungen sicher in Ihrer Backend-Datenbank gespeichert werden. Vielen Dank!",
 	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "Dies ist eine experimentelle Funktion, sie funktioniert möglicherweise nicht wie erwartet und kann jederzeit geändert werden.",
-	"This option controls how many tokens are preserved when refreshing the context. For example, if set to 2, the last 2 tokens of the conversation context will be retained. Preserving context can help maintain the continuity of a conversation, but it may reduce the ability to respond to new topics. (Default: 24)": "",
-	"This option sets the maximum number of tokens the model can generate in its response. Increasing this limit allows the model to provide longer answers, but it may also increase the likelihood of unhelpful or irrelevant content being generated.  (Default: 128)": "",
+	"This option controls how many tokens are preserved when refreshing the context. For example, if set to 2, the last 2 tokens of the conversation context will be retained. Preserving context can help maintain the continuity of a conversation, but it may reduce the ability to respond to new topics. (Default: 24)": "Diese Option steuert, wie viele Tokens beim Aktualisieren des Kontexts beibehalten werden. Wenn sie beispielsweise auf 2 gesetzt ist, werden die letzten 2 Tokens des Gesprächskontexts beibehalten. Das Beibehalten des Kontexts kann helfen, die Kontinuität eines Gesprächs aufrechtzuerhalten, kann jedoch die Fähigkeit verringern, auf neue Themen zu reagieren. (Standard: 24)",
+	"This option sets the maximum number of tokens the model can generate in its response. Increasing this limit allows the model to provide longer answers, but it may also increase the likelihood of unhelpful or irrelevant content being generated.  (Default: 128)": "Diese Option legt die maximale Anzahl von Tokens fest, die das Modell in seiner Antwort generieren kann. Eine Erhöhung dieses Limits ermöglicht es dem Modell, längere Antworten zu geben, kann jedoch auch die Wahrscheinlichkeit erhöhen, dass unhilfreicher oder irrelevanter Inhalt generiert wird. (Standard: 128)",
 	"This option will delete all existing files in the collection and replace them with newly uploaded files.": "Diese Option löscht alle vorhandenen Dateien in der Sammlung und ersetzt sie durch neu hochgeladene Dateien.",
 	"This response was generated by \"{{model}}\"": "Diese Antwort wurde von \"{{model}}\" generiert",
 	"This will delete": "Dies löscht",
 	"This will delete <strong>{{NAME}}</strong> and <strong>all its contents</strong>.": "Dies löscht <strong>{{NAME}}</strong> und <strong>alle Inhalte</strong>.",
-	"This will delete all models including custom models": "",
-	"This will delete all models including custom models and cannot be undone.": "",
+	"This will delete all models including custom models": "Dies wird alle Modelle einschließlich benutzerdefinierter Modelle löschen",
+	"This will delete all models including custom models and cannot be undone.": "Dies wird alle Modelle einschließlich benutzerdefinierter Modelle löschen und kann nicht rückgängig gemacht werden.",
 	"This will reset the knowledge base and sync all files. Do you wish to continue?": "Dadurch wird die Wissensdatenbank zurückgesetzt und alle Dateien synchronisiert. Möchten Sie fortfahren?",
 	"Thorough explanation": "Ausführliche Erklärung",
 	"Tika": "Tika",
@@ -872,7 +892,7 @@
 	"Title Auto-Generation": "Unterhaltungstitel automatisch generieren",
 	"Title cannot be an empty string.": "Titel darf nicht leer sein.",
 	"Title Generation Prompt": "Prompt für Titelgenerierung",
-	"TLS": "",
+	"TLS": "TLS",
 	"To access the available model names for downloading,": "Um auf die verfügbaren Modellnamen zuzugreifen,",
 	"To access the GGUF models available for downloading,": "Um auf die verfügbaren GGUF-Modelle zuzugreifen,",
 	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "Um auf das WebUI zugreifen zu können, wenden Sie sich bitte an einen Administrator. Administratoren können den Benutzerstatus über das Admin-Panel verwalten.",
@@ -890,19 +910,19 @@
 	"Too verbose": "Zu ausführlich",
 	"Tool created successfully": "Werkzeug erfolgreich erstellt",
 	"Tool deleted successfully": "Werkzeug erfolgreich gelöscht",
-	"Tool Description": "",
-	"Tool ID": "",
+	"Tool Description": "Werkzeugbeschreibung",
+	"Tool ID": "Werkzeug-ID",
 	"Tool imported successfully": "Werkzeug erfolgreich importiert",
-	"Tool Name": "",
+	"Tool Name": "Werkzeugname",
 	"Tool updated successfully": "Werkzeug erfolgreich aktualisiert",
 	"Tools": "Werkzeuge",
-	"Tools Access": "",
+	"Tools Access": "Werkzeugzugriff",
 	"Tools are a function calling system with arbitrary code execution": "Wekzeuge sind ein Funktionssystem mit beliebiger Codeausführung",
 	"Tools have a function calling system that allows arbitrary code execution": "Werkezuge verfügen über ein Funktionssystem, das die Ausführung beliebigen Codes ermöglicht",
 	"Tools have a function calling system that allows arbitrary code execution.": "Werkzeuge verfügen über ein Funktionssystem, das die Ausführung beliebigen Codes ermöglicht.",
 	"Top K": "Top K",
 	"Top P": "Top P",
-	"Transformers": "",
+	"Transformers": "Transformers",
 	"Trouble accessing Ollama?": "Probleme beim Zugriff auf Ollama?",
 	"TTS Model": "TTS-Modell",
 	"TTS Settings": "TTS-Einstellungen",
@@ -911,12 +931,12 @@
 	"Type Hugging Face Resolve (Download) URL": "Geben Sie die Hugging Face Resolve-URL ein",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Ups! Es gab ein Problem bei der Verbindung mit {{provider}}.",
 	"UI": "Oberfläche",
-	"Unarchive All": "",
-	"Unarchive All Archived Chats": "",
-	"Unarchive Chat": "",
-	"Unlock mysteries": "",
+	"Unarchive All": "Alle wiederherstellen",
+	"Unarchive All Archived Chats": "Alle archivierten Unterhaltungen wiederherstellen",
+	"Unarchive Chat": "Unterhaltung wiederherstellen",
+	"Unlock mysteries": "Geheimnisse entsperren",
 	"Unpin": "Lösen",
-	"Unravel secrets": "",
+	"Unravel secrets": "Geheimnisse lüften",
 	"Untagged": "Ungetaggt",
 	"Update": "Aktualisieren",
 	"Update and Copy Link": "Aktualisieren und Link kopieren",
@@ -932,18 +952,18 @@
 	"Upload Files": "Datei(en) hochladen",
 	"Upload Pipeline": "Pipeline hochladen",
 	"Upload Progress": "Hochladefortschritt",
-	"URL": "",
+	"URL": "URL",
 	"URL Mode": "URL-Modus",
 	"Use '#' in the prompt input to load and include your knowledge.": "Nutzen Sie '#' in der Prompt-Eingabe, um Ihr Wissen zu laden und einzuschließen.",
 	"Use Gravatar": "Gravatar verwenden",
-	"Use groups to group your users and assign permissions.": "",
+	"Use groups to group your users and assign permissions.": "Nutzen Sie Gruppen, um Ihre Benutzer zu gruppieren und Berechtigungen zuzuweisen.",
 	"Use Initials": "Initialen verwenden",
 	"use_mlock (Ollama)": "use_mlock (Ollama)",
 	"use_mmap (Ollama)": "use_mmap (Ollama)",
 	"user": "Benutzer",
 	"User": "Benutzer",
 	"User location successfully retrieved.": "Benutzerstandort erfolgreich ermittelt.",
-	"Username": "",
+	"Username": "Benutzername",
 	"Users": "Benutzer",
 	"Using the default arena model with all models. Click the plus button to add custom models.": "Verwendung des Standard-Arena-Modells mit allen Modellen. Klicken Sie auf die Plus-Schaltfläche, um benutzerdefinierte Modelle hinzuzufügen.",
 	"Utilize": "Verwende",
@@ -955,43 +975,45 @@
 	"variable to have them replaced with clipboard content.": "Variable, um den Inhalt der Zwischenablage beim Nutzen des Prompts zu ersetzen.",
 	"Version": "Version",
 	"Version {{selectedVersion}} of {{totalVersions}}": "Version {{selectedVersion}} von {{totalVersions}}",
-	"Visibility": "",
+	"Visibility": "Sichtbarkeit",
 	"Voice": "Stimme",
 	"Voice Input": "Spracheingabe",
 	"Warning": "Warnung",
 	"Warning:": "Warnung:",
-	"Warning: Enabling this will allow users to upload arbitrary code on the server.": "",
+	"Warning: Enabling this will allow users to upload arbitrary code on the server.": "Warnung: Wenn Sie dies aktivieren, können Benutzer beliebigen Code auf dem Server hochladen.",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Warnung: Wenn Sie das Einbettungsmodell aktualisieren oder ändern, müssen Sie alle Dokumente erneut importieren.",
 	"Web": "Web",
 	"Web API": "Web-API",
 	"Web Loader Settings": "Web Loader Einstellungen",
 	"Web Search": "Websuche",
 	"Web Search Engine": "Suchmaschine",
+	"Web Search Query Generation": "",
 	"Webhook URL": "Webhook URL",
 	"WebUI Settings": "WebUI-Einstellungen",
-	"WebUI will make requests to \"{{url}}/api/chat\"": "",
-	"WebUI will make requests to \"{{url}}/chat/completions\"": "",
-	"What are you trying to achieve?": "",
-	"What are you working on?": "",
+	"WebUI will make requests to \"{{url}}/api/chat\"": "WebUI wird Anfragen an \"{{url}}/api/chat\" senden",
+	"WebUI will make requests to \"{{url}}/chat/completions\"": "WebUI wird Anfragen an \"{{url}}/chat/completions\" senden",
+	"What are you trying to achieve?": "Was versuchen Sie zu erreichen?",
+	"What are you working on?": "Woran arbeiten Sie?",
 	"What’s New in": "Neuigkeiten von",
-	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
-	"wherever you are": "",
+	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "Wenn aktiviert, antwortet das Modell in Echtzeit auf jede Chat-Nachricht und generiert eine Antwort, sobald der Benutzer eine Nachricht sendet. Dieser Modus ist nützlich für Live-Chat-Anwendungen, kann jedoch die Leistung auf langsamerer Hardware beeinträchtigen.",
+	"wherever you are": "wo immer Sie sind",
 	"Whisper (Local)": "Whisper (lokal)",
+	"Why?": "Warum?",
 	"Widescreen Mode": "Breitbildmodus",
 	"Won": "Gewonnen",
-	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",
+	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "Funktioniert zusammen mit top-k. Ein höherer Wert (z.B. 0,95) führt zu vielfältigerem Text, während ein niedrigerer Wert (z.B. 0,5) fokussierteren und konservativeren Text erzeugt. (Standard: 0,9)",
 	"Workspace": "Arbeitsbereich",
-	"Workspace Permissions": "",
+	"Workspace Permissions": "Arbeitsbereichsberechtigungen",
 	"Write a prompt suggestion (e.g. Who are you?)": "Schreiben Sie einen Promptvorschlag (z. B. Wer sind Sie?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Schreibe eine kurze Zusammenfassung in 50 Wörtern, die [Thema oder Schlüsselwort] zusammenfasst.",
 	"Write something...": "Schreiben Sie etwas...",
-	"Write your model template content here": "",
+	"Write your model template content here": "Schreiben Sie hier Ihren Modellvorlageninhalt",
 	"Yesterday": "Gestern",
 	"You": "Sie",
 	"You can only chat with a maximum of {{maxCount}} file(s) at a time.": "Sie können nur mit maximal {{maxCount}} Datei(en) gleichzeitig chatten.",
 	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "Personalisieren Sie Interaktionen mit LLMs, indem Sie über die Schaltfläche \"Verwalten\" Erinnerungen hinzufügen.",
 	"You cannot upload an empty file.": "Sie können keine leere Datei hochladen.",
-	"You do not have permission to upload files.": "",
+	"You do not have permission to upload files.": "Sie haben keine Berechtigung zum Hochladen von Dateien.",
 	"You have no archived conversations.": "Du hast keine archivierten Unterhaltungen.",
 	"You have shared this chat": "Sie haben diese Unterhaltung geteilt",
 	"You're a helpful assistant.": "Du bist ein hilfreicher Assistent.",

src/lib/i18n/locales/dg-DG/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "'s', 'm', 'h', 'd', 'w' or '-1' for no expire. Much permanent, very wow.",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "(such e.g. `sh webui.sh --api`)",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "Such account exists?",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "such assistant",
 	"and": "and",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "Copy Bark Auto Bark",
 	"Auto-playback response": "Auto-playback response",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 Base URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 Base URL is required.",
 	"Available list": "",
 	"available!": "available! So excite!",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "Back",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "Change Password",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "Chat",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "Confirm Password",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "",
 	"Default Model": "",
 	"Default model updated": "Default model much updated",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "Default Prompt Suggestions",
@@ -234,6 +242,7 @@
 	"Delete User": "",
 	"Deleted {{deleteModelTag}}": "Deleted {{deleteModelTag}}",
 	"Deleted {{name}}": "",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "Description",
 	"Didn't fully follow instructions": "",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "",
 	"Embedding model set to \"{{embedding_model}}\"": "",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "Enable New Bark Ups",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "",
@@ -326,7 +333,9 @@
 	"Enter language codes": "",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "Enter model doge tag (e.g. {{modelTag}})",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "Enter Number of Steps (e.g. 50)",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "Failed to read clipboard borks",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "",
@@ -449,6 +459,7 @@
 	"Hide": "Hide",
 	"Host": "",
 	"How can I help you today?": "How can I halp u today?",
+	"How would you rate this response?": "",
 	"Hybrid Search": "",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "Modelfile Content",
 	"Models": "Wowdels",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "",
 	"Name": "Name",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "No source available",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "Promptos",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "",
 	"Pull a model from Ollama.com": "Pull a wowdel from Ollama.com",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "",
 	"Remove Model": "",
 	"Rename": "",
+	"Reorder Models": "",
 	"Repeat Last N": "Repeat Last N",
 	"Request Mode": "Request Bark",
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "Role",
@@ -827,6 +846,7 @@
 	"System": "System very system",
 	"System Instructions": "",
 	"System Prompt": "System Prompt much prompt",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -969,6 +989,7 @@
 	"Web Loader Settings": "",
 	"Web Search": "",
 	"Web Search Engine": "",
+	"Web Search Query Generation": "",
 	"Webhook URL": "",
 	"WebUI Settings": "WebUI Settings much settings",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -979,6 +1000,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/en-GB/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "",
 	"and": "",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "",
 	"Auto-playback response": "",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "",
 	"AUTOMATIC1111 Base URL is required.": "",
 	"Available list": "",
 	"available!": "",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "",
 	"Default Model": "",
 	"Default model updated": "",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "",
@@ -234,6 +242,7 @@
 	"Delete User": "",
 	"Deleted {{deleteModelTag}}": "",
 	"Deleted {{name}}": "",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "",
 	"Didn't fully follow instructions": "",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "",
 	"Embedding model set to \"{{embedding_model}}\"": "",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "",
@@ -326,7 +333,9 @@
 	"Enter language codes": "",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "",
@@ -449,6 +459,7 @@
 	"Hide": "",
 	"Host": "",
 	"How can I help you today?": "",
+	"How would you rate this response?": "",
 	"Hybrid Search": "",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "",
 	"Models": "",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "",
 	"Name": "",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "",
 	"Pull a model from Ollama.com": "",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "",
 	"Remove Model": "",
 	"Rename": "",
+	"Reorder Models": "",
 	"Repeat Last N": "",
 	"Request Mode": "",
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "",
@@ -825,6 +844,7 @@
 	"System": "",
 	"System Instructions": "",
 	"System Prompt": "",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -967,6 +987,7 @@
 	"Web Loader Settings": "",
 	"Web Search": "",
 	"Web Search Engine": "",
+	"Web Search Query Generation": "",
 	"Webhook URL": "",
 	"WebUI Settings": "",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,6 +998,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",

src/lib/i18n/locales/en-US/translation.json

@@ -1,4 +1,5 @@
 {
+	"-1 for no limit, or a positive integer for a specific limit": "",
 	"'s', 'm', 'h', 'd', 'w' or '-1' for no expiration.": "",
 	"(e.g. `sh webui.sh --api --api-auth username_password`)": "",
 	"(e.g. `sh webui.sh --api`)": "",
@@ -59,6 +60,7 @@
 	"Allow Voice Interruption in Call": "",
 	"Already have an account?": "",
 	"Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0)": "",
+	"Amazing": "",
 	"an assistant": "",
 	"and": "",
 	"and {{COUNT}} more": "",
@@ -89,12 +91,15 @@
 	"Authenticate": "",
 	"Auto-Copy Response to Clipboard": "",
 	"Auto-playback response": "",
+	"Autocomplete Generation": "",
+	"Autocomplete Generation Input Max Length": "",
 	"Automatic1111": "",
 	"AUTOMATIC1111 Api Auth String": "",
 	"AUTOMATIC1111 Base URL": "",
 	"AUTOMATIC1111 Base URL is required.": "",
 	"Available list": "",
 	"available!": "",
+	"Awful": "",
 	"Azure AI Speech": "",
 	"Azure Region": "",
 	"Back": "",
@@ -117,6 +122,7 @@
 	"Certificate Path": "",
 	"Change Password": "",
 	"Character": "",
+	"Character limit for autocomplete generation input": "",
 	"Chart new frontiers": "",
 	"Chat": "",
 	"Chat Background Image": "",
@@ -165,6 +171,7 @@
 	"Completions": "",
 	"Concurrent Requests": "",
 	"Configure": "",
+	"Configure Models": "",
 	"Confirm": "",
 	"Confirm Password": "",
 	"Confirm your action": "",
@@ -213,6 +220,7 @@
 	"Default (SentenceTransformers)": "",
 	"Default Model": "",
 	"Default model updated": "",
+	"Default Models": "",
 	"Default permissions": "",
 	"Default permissions updated successfully": "",
 	"Default Prompt Suggestions": "",
@@ -234,6 +242,7 @@
 	"Delete User": "",
 	"Deleted {{deleteModelTag}}": "",
 	"Deleted {{name}}": "",
+	"Deleted User": "",
 	"Describe your knowledge base and objectives": "",
 	"Description": "",
 	"Didn't fully follow instructions": "",
@@ -292,16 +301,14 @@
 	"Embedding Model Engine": "",
 	"Embedding model set to \"{{embedding_model}}\"": "",
 	"Enable API Key Auth": "",
+	"Enable autocomplete generation for chat messages": "",
 	"Enable Community Sharing": "",
 	"Enable Memory Locking (mlock) to prevent model data from being swapped out of RAM. This option locks the model's working set of pages into RAM, ensuring that they will not be swapped out to disk. This can help maintain performance by avoiding page faults and ensuring fast data access.": "",
 	"Enable Memory Mapping (mmap) to load model data. This option allows the system to use disk storage as an extension of RAM by treating disk files as if they were in RAM. This can improve model performance by allowing for faster data access. However, it may not work correctly with all systems and can consume a significant amount of disk space.": "",
 	"Enable Message Rating": "",
 	"Enable Mirostat sampling for controlling perplexity. (Default: 0, 0 = Disabled, 1 = Mirostat, 2 = Mirostat 2.0)": "",
 	"Enable New Sign Ups": "",
-	"Enable Retrieval Query Generation": "",
-	"Enable Tags Generation": "",
 	"Enable Web Search": "",
-	"Enable Web Search Query Generation": "",
 	"Enabled": "",
 	"Engine": "",
 	"Ensure your CSV file includes 4 columns in this order: Name, Email, Password, Role.": "",
@@ -326,7 +333,9 @@
 	"Enter language codes": "",
 	"Enter Model ID": "",
 	"Enter model tag (e.g. {{modelTag}})": "",
+	"Enter Mojeek Search API Key": "",
 	"Enter Number of Steps (e.g. 50)": "",
+	"Enter proxy URL (e.g. https://user:password@host:port)": "",
 	"Enter Sampler (e.g. Euler a)": "",
 	"Enter Scheduler (e.g. Karras)": "",
 	"Enter Score": "",
@@ -379,6 +388,7 @@
 	"Failed to add file.": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "",
+	"Failed to save models configuration": "",
 	"Failed to update settings": "",
 	"Failed to upload file.": "",
 	"February": "",
@@ -449,6 +459,7 @@
 	"Hide": "",
 	"Host": "",
 	"How can I help you today?": "",
+	"How would you rate this response?": "",
 	"Hybrid Search": "",
 	"I acknowledge that I have read and I understand the implications of my action. I am aware of the risks associated with executing arbitrary code and I have verified the trustworthiness of the source.": "",
 	"ID": "",
@@ -565,6 +576,8 @@
 	"Modelfile Content": "",
 	"Models": "",
 	"Models Access": "",
+	"Models configuration saved successfully": "",
+	"Mojeek Search API Key": "",
 	"more": "",
 	"More": "",
 	"Name": "",
@@ -583,6 +596,7 @@
 	"No knowledge found": "",
 	"No model IDs": "",
 	"No models found": "",
+	"No models selected": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "",
@@ -658,6 +672,7 @@
 	"Please carefully review the following warnings:": "",
 	"Please enter a prompt": "",
 	"Please fill in all fields.": "",
+	"Please select a model first.": "",
 	"Please select a reason": "",
 	"Port": "",
 	"Positive attitude": "",
@@ -673,6 +688,7 @@
 	"Prompt updated successfully": "",
 	"Prompts": "",
 	"Prompts Access": "",
+	"Proxy URL": "",
 	"Pull \"{{searchValue}}\" from Ollama.com": "",
 	"Pull a model from Ollama.com": "",
 	"Query Generation Prompt": "",
@@ -693,17 +709,20 @@
 	"Remove": "",
 	"Remove Model": "",
 	"Rename": "",
+	"Reorder Models": "",
 	"Repeat Last N": "",
 	"Request Mode": "",
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
 	"Reset": "",
+	"Reset All Models": "",
 	"Reset Upload Directory": "",
 	"Reset Vector Storage/Knowledge": "",
 	"Response notifications cannot be activated as the website permissions have been denied. Please visit your browser settings to grant the necessary access.": "",
 	"Response splitting": "",
 	"Result": "",
+	"Retrieval Query Generation": "",
 	"Rich Text Input for Chat": "",
 	"RK": "",
 	"Role": "",
@@ -825,6 +844,7 @@
 	"System": "",
 	"System Instructions": "",
 	"System Prompt": "",
+	"Tags Generation": "",
 	"Tags Generation Prompt": "",
 	"Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1)": "",
 	"Tap to interrupt": "",
@@ -967,6 +987,7 @@
 	"Web Loader Settings": "",
 	"Web Search": "",
 	"Web Search Engine": "",
+	"Web Search Query Generation": "",
 	"Webhook URL": "",
 	"WebUI Settings": "",
 	"WebUI will make requests to \"{{url}}/api/chat\"": "",
@@ -977,6 +998,7 @@
 	"When enabled, the model will respond to each chat message in real-time, generating a response as soon as the user sends a message. This mode is useful for live chat applications, but may impact performance on slower hardware.": "",
 	"wherever you are": "",
 	"Whisper (Local)": "",
+	"Why?": "",
 	"Widescreen Mode": "",
 	"Won": "",
 	"Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)": "",