Merge pull request #7896 from open-webui/dev

0.5.0

.dockerignore

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

.github/ISSUE_TEMPLATE/bug_report.md

@@ -8,6 +8,20 @@ assignees: ''
 
 # Bug Report
 
+## Important Notes
+
+- **Before submitting a bug report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.
+
+- **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.
+
+- **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
+
+- **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
+
+Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!
+
+---
+
 ## Installation Method
 
 [Describe the method you used to install the project, e.g., git clone, Docker, pip, etc.]

.github/ISSUE_TEMPLATE/feature_request.md

@@ -6,6 +6,22 @@ labels: ''
 assignees: ''
 ---
 
+# Feature Request
+
+## Important Notes
+
+- **Before submitting a report**: Please check the Issues or Discussions section to see if a similar issue or feature request has already been posted. It's likely we're already tracking it! If you’re unsure, start a discussion post first. This will help us efficiently focus on improving the project.
+
+- **Collaborate respectfully**: We value a constructive attitude, so please be mindful of your communication. If negativity is part of your approach, our capacity to engage may be limited. We’re here to help if you’re open to learning and communicating positively. Remember, Open WebUI is a volunteer-driven project managed by a single maintainer and supported by contributors who also have full-time jobs. We appreciate your time and ask that you respect ours.
+
+- **Contributing**: If you encounter an issue, we highly encourage you to submit a pull request or fork the project. We actively work to prevent contributor burnout to maintain the quality and continuity of Open WebUI.
+
+- **Bug reproducibility**: If a bug cannot be reproduced with a `:main` or `:dev` Docker setup, or a pip install with Python 3.11, it may require additional help from the community. In such cases, we will move it to the "issues" Discussions section due to our limited resources. We encourage the community to assist with these issues. Remember, it’s not that the issue doesn’t exist; we need your help!
+
+Note: Please remove the notes above when submitting your post. Thank you for your understanding and support!
+
+---
+
 **Is your feature request related to a problem? Please describe.**
 A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
 

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

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

.github/workflows/format-backend.yaml

@@ -23,7 +23,7 @@ jobs:
       - uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
 

.github/workflows/format-build-frontend.yaml

@@ -21,7 +21,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '20' # Or specify any other version you want to use
+          node-version: '22' # Or specify any other version you want to use
 
       - name: Install Dependencies
         run: npm install
@@ -48,7 +48,7 @@ jobs:
       - name: Setup Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '20'
+          node-version: '22'
 
       - name: Install Dependencies
         run: npm ci

.github/workflows/integration-test.yml

@@ -85,7 +85,7 @@ jobs:
   #     - uses: actions/checkout@v4
 
   #     - name: Set up Python
-  #       uses: actions/setup-python@v4
+  #       uses: actions/setup-python@v5
   #       with:
   #         python-version: ${{ matrix.python-version }}
 
@@ -182,6 +182,9 @@ jobs:
           WEBUI_SECRET_KEY: secret-key
           GLOBAL_LOG_LEVEL: debug
           DATABASE_URL: postgresql://postgres:postgres@localhost:5432/postgres
+          DATABASE_POOL_SIZE: 10
+          DATABASE_POOL_MAX_OVERFLOW: 10
+          DATABASE_POOL_TIMEOUT: 30
         run: |
           cd backend
           uvicorn open_webui.main:app --port "8081" --forwarded-allow-ips '*' &

.github/workflows/lint-backend.disabled

@@ -16,7 +16,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Use Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
       - name: Use Bun
         uses: oven-sh/setup-bun@v1
       - name: Install dependencies

CHANGELOG.md

@@ -5,6 +5,321 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.5.0] - 2024-12-25
+
+### Added
+
+- **💬 True Asynchronous Chat Support**: Create chats, navigate away, and return anytime with responses ready. Ideal for reasoning models and multi-agent workflows, enhancing multitasking like never before.
+- **🔔 Chat Completion Notifications**: Never miss a completed response. Receive instant in-UI notifications when a chat finishes in a non-active tab, keeping you updated while you work elsewhere.
+- **🌐 Notification Webhook Integration**: Get alerts via webhooks even when your tab is closed! Configure your webhook URL in Settings > Account and receive timely updates for long-running chats or external integration needs.
+- **📚 Channels (Beta)**: Explore Discord/Slack-style chat rooms designed for real-time collaboration between users and AIs. Build bots for channels and unlock asynchronous communication for proactive multi-agent workflows. Opt-in via Admin Settings > General. A Comprehensive Bot SDK tutorial (https://github.com/open-webui/bot) is incoming, so stay tuned!
+- **🖼️ Client-Side Image Compression**: Now compress images before upload (Settings > Interface), saving bandwidth and improving performance seamlessly.
+- **🛠️ OAuth Management for User Groups**: Enable group-level management via OAuth integration for enhanced control and scalability in collaborative environments.
+- **✅ Structured Output for Ollama**: Pass structured data output directly to Ollama, unlocking new possibilities for streamlined automation and precise data handling.
+- **📜 Offline Swagger Documentation**: Developer-friendly Swagger API docs are now available offline, ensuring full accessibility wherever you are.
+- **📸 Quick Screen Capture Button**: Effortlessly capture your screen with a single click from the message input menu.
+- **🌍 i18n Updates**: Improved and refined translations across several languages, including Ukrainian, German, Brazilian Portuguese, Catalan, and more, ensuring a seamless global user experience.
+
+### Fixed
+
+- **📋 Table Export to CSV**: Resolved issues with CSV export where headers were missing or errors occurred due to values with commas, ensuring smooth and reliable data handling.
+- **🔓 BYPASS_MODEL_ACCESS_CONTROL**: Fixed an issue where users could see models but couldn’t use them with 'BYPASS_MODEL_ACCESS_CONTROL=True', restoring proper functionality for environments leveraging this setting.
+
+### Changed
+
+- **💡 API Key Authentication Restriction**: Narrowed API key auth permissions to '/api/models' and '/api/chat/completions' for enhanced security and better API governance.
+- **⚙️ Backend Overhaul for Performance**: Major backend restructuring; a heads-up that some "Functions" using internal variables may face compatibility issues. Moving forward, websocket support is mandatory to ensure Open WebUI operates seamlessly.
+
+### Removed
+
+- **⚠️ Legacy Functionality Clean-Up**: Deprecated outdated backend systems that were non-essential or overlapped with newer implementations, allowing for a leaner, more efficient platform.
+
+## [0.4.8] - 2024-12-07
+
+### Added
+
+- **🔓 Bypass Model Access Control**: Introduced the 'BYPASS_MODEL_ACCESS_CONTROL' environment variable. Easily bypass model access controls for user roles when access control isn't required, simplifying workflows for trusted environments.
+- **📝 Markdown in Banners**: Now supports markdown for banners, enabling richer, more visually engaging announcements.
+- **🌐 Internationalization Updates**: Enhanced translations across multiple languages, further improving accessibility and global user experience.
+- **🎨 Styling Enhancements**: General UI style refinements for a cleaner and more polished interface.
+- **📋 Rich Text Reliability**: Improved the reliability and stability of rich text input across chats for smoother interactions.
+
+### Fixed
+
+- **💡 Tailwind Build Issue**: Resolved a breaking bug caused by Tailwind, ensuring smoother builds and overall system reliability.
+- **📚 Knowledge Collection Query Fix**: Addressed API endpoint issues with querying knowledge collections, ensuring accurate and reliable information retrieval.
+
+## [0.4.7] - 2024-12-01
+
+### Added
+
+- **✨ Prompt Input Auto-Completion**: Type a prompt and let AI intelligently suggest and complete your inputs. Simply press 'Tab' or swipe right on mobile to confirm. Available only with Rich Text Input (default setting). Disable via Admin Settings for full control.
+- **🌍 Improved Translations**: Enhanced localization for multiple languages, ensuring a more polished and accessible experience for international users.
+
+### Fixed
+
+- **🛠️ Tools Export Issue**: Resolved a critical issue where exporting tools wasn’t functioning, restoring seamless export capabilities.
+- **🔗 Model ID Registration**: Fixed an issue where model IDs weren’t registering correctly in the model editor, ensuring reliable model setup and tracking.
+- **🖋️ Textarea Auto-Expansion**: Corrected a bug where textareas didn’t expand automatically on certain browsers, improving usability for multi-line inputs.
+- **🔧 Ollama Embed Endpoint**: Addressed the /ollama/embed endpoint malfunction, ensuring consistent performance and functionality.
+
+### Changed
+
+- **🎨 Knowledge Base Styling**: Refined knowledge base visuals for a cleaner, more modern look, laying the groundwork for further enhancements in upcoming releases.
+
+## [0.4.6] - 2024-11-26
+
+### Added
+
+- **🌍 Enhanced Translations**: Various language translations improved to make the WebUI more accessible and user-friendly worldwide.
+
+### Fixed
+
+- **✏️ Textarea Shifting Bug**: Resolved the issue where the textarea shifted unexpectedly, ensuring a smoother typing experience.
+- **⚙️ Model Configuration Modal**: Fixed the issue where the models configuration modal introduced in 0.4.5 wasn’t working for some users.
+- **🔍 Legacy Query Support**: Restored functionality for custom query generation in RAG when using legacy prompts, ensuring both default and custom templates now work seamlessly.
+- **⚡ Improved General Reliability**: Various minor fixes improve platform stability and ensure a smoother overall experience across workflows.
+
+## [0.4.5] - 2024-11-26
+
+### Added
+
+- **🎨 Model Order/Defaults Reintroduced**: Brought back the ability to set model order and default models, now configurable via Admin Settings > Models > Configure (Gear Icon).
+
+### Fixed
+
+- **🔍 Query Generation Issue**: Resolved an error in web search query generation, enhancing search accuracy and ensuring smoother search workflows.
+- **📏 Textarea Auto Height Bug**: Fixed a layout issue where textarea input height was shifting unpredictably, particularly when editing system prompts.
+- **🔑 Ollama Authentication**: Corrected an issue with Ollama’s authorization headers, guaranteeing reliable authentication across all endpoints.
+- **⚙️ Missing Min_P Save**: Resolved an issue where the 'min_p' parameter was not being saved in configurations.
+- **🛠️ Tools Description**: Fixed a key issue that omitted tool descriptions in tools payload.
+
+## [0.4.4] - 2024-11-22
+
+### Added
+
+- **🌐 Translation Updates**: Refreshed Catalan, Brazilian Portuguese, German, and Ukrainian translations, further enhancing the platform's accessibility and improving the experience for international users.
+
+### Fixed
+
+- **📱 Mobile Controls Visibility**: Resolved an issue where the controls button was not displaying on the new chats page for mobile users, ensuring smoother navigation and functionality on smaller screens.
+- **📷 LDAP Profile Image Issue**: Fixed an LDAP integration bug related to profile images, ensuring seamless authentication and a reliable login experience for users.
+- **⏳ RAG Query Generation Issue**: Addressed a significant problem where RAG query generation occurred unnecessarily without attached files, drastically improving speed and reducing delays during chat completions.
+
+### Changed
+
+- **⚙️ Legacy Event Emitter Support**: Reintroduced compatibility with legacy "citation" types for event emitters in tools and functions, providing smoother workflows and broader tool support for users.
+
+## [0.4.3] - 2024-11-21
+
+### Added
+
+- **📚 Inline Citations for RAG Results**: Get seamless inline citations for Retrieval-Augmented Generation (RAG) responses using the default RAG prompt. Note: This feature only supports newly uploaded files, improving traceability and providing source clarity.
+- **🎨 Better Rich Text Input Support**: Enjoy smoother and more reliable rich text formatting for chats, enhancing communication quality.
+- **⚡ Faster Model Retrieval**: Implemented caching optimizations for faster model loading, providing a noticeable speed boost across workflows. Further improvements are on the way!
+
+### Fixed
+
+- **🔗 Pipelines Feature Restored**: Resolved a critical issue that previously prevented Pipelines from functioning, ensuring seamless workflows.
+- **✏️ Missing Suffix Field in Ollama Form**: Added the missing "suffix" field to the Ollama generate form, enhancing customization options.
+
+### Changed
+
+- **🗂️ Renamed "Citations" to "Sources"**: Improved clarity and consistency by renaming the "citations" field to "sources" in messages.
+
+## [0.4.2] - 2024-11-20
+
+### Fixed
+
+- **📁 Knowledge Files Visibility Issue**: Resolved the bug preventing individual files in knowledge collections from displaying when referenced with '#'.
+- **🔗 OpenAI Endpoint Prefix**: Fixed the issue where certain OpenAI connections that deviate from the official API spec weren’t working correctly with prefixes.
+- **⚔️ Arena Model Access Control**: Corrected an issue where arena model access control settings were not being saved.
+- **🔧 Usage Capability Selector**: Fixed the broken usage capabilities selector in the model editor.
+
+## [0.4.1] - 2024-11-19
+
+### Added
+
+- **📊 Enhanced Feedback System**: Introduced a detailed 1-10 rating scale for feedback alongside thumbs up/down, preparing for more precise model fine-tuning and improving feedback quality.
+- **ℹ️ Tool Descriptions on Hover**: Easily access tool descriptions by hovering over the message input, providing a smoother workflow with more context when utilizing tools.
+
+### Fixed
+
+- **🗑️ Graceful Handling of Deleted Users**: Resolved an issue where deleted users caused workspace items (models, knowledge, prompts, tools) to fail, ensuring reliable workspace loading.
+- **🔑 API Key Creation**: Fixed an issue preventing users from creating new API keys, restoring secure and seamless API management.
+- **🔗 HTTPS Proxy Fix**: Corrected HTTPS proxy issues affecting the '/api/v1/models/' endpoint, ensuring smoother, uninterrupted model management.
+
+## [0.4.0] - 2024-11-19
+
+### Added
+
+- **👥 User Groups**: You can now create and manage user groups, making user organization seamless.
+- **🔐 Group-Based Access Control**: Set granular access to models, knowledge, prompts, and tools based on user groups, allowing for more controlled and secure environments.
+- **🛠️ Group-Based User Permissions**: Easily manage workspace permissions. Grant users the ability to upload files, delete, edit, or create temporary chats, as well as define their ability to create models, knowledge, prompts, and tools.
+- **🔑 LDAP Support**: Newly introduced LDAP authentication adds robust security and scalability to user management.
+- **🌐 Enhanced OpenAI-Compatible Connections**: Added prefix ID support to avoid model ID clashes, with explicit model ID support for APIs lacking '/models' endpoint support, ensuring smooth operation with custom setups.
+- **🔐 Ollama API Key Support**: Now manage credentials for Ollama when set behind proxies, including the option to utilize prefix ID for proper distinction across multiple Ollama instances.
+- **🔄 Connection Enable/Disable Toggle**: Easily enable or disable individual OpenAI and Ollama connections as needed.
+- **🎨 Redesigned Model Workspace**: Freshly redesigned to improve usability for managing models across users and groups.
+- **🎨 Redesigned Prompt Workspace**: A fresh UI to conveniently organize and manage prompts.
+- **🧩 Sorted Functions Workspace**: Functions are now automatically categorized by type (Action, Filter, Pipe), streamlining management.
+- **💻 Redesigned Collaborative Workspace**: Enhanced support for multiple users contributing to models, knowledge, prompts, or tools, improving collaboration.
+- **🔧 Auto-Selected Tools in Model Editor**: Tools enabled through the model editor are now automatically selected, whereas previously it only gave users the option to enable the tool, reducing manual steps and enhancing efficiency.
+- **🔔 Web Search & Tools Indicator**: A clear indication now shows when web search or tools are active, reducing confusion.
+- **🔑 Toggle API Key Auth**: Tighten security by easily enabling or disabling API key authentication option for Open WebUI.
+- **🗂️ Agentic Retrieval**: Improve RAG accuracy via smart pre-processing of chat history to determine the best queries before retrieval.
+- **📁 Large Text as File Option**: Optionally convert large pasted text into a file upload, keeping the chat interface cleaner.
+- **🗂️ Toggle Citations for Models**: Ability to disable citations has been introduced in the model editor.
+- **🔍 User Settings Search**: Quickly search for settings fields, improving ease of use and navigation.
+- **🗣️ Experimental SpeechT5 TTS**: Local SpeechT5 support added for improved text-to-speech capabilities.
+- **🔄 Unified Reset for Models**: A one-click option has been introduced to reset and remove all models from the Admin Settings.
+- **🛠️ Initial Setup Wizard**: The setup process now explicitly informs users that they are creating an admin account during the first-time setup, ensuring clarity. Previously, users encountered the login page right away without this distinction.
+- **🌐 Enhanced Translations**: Several language translations, including Ukrainian, Norwegian, and Brazilian Portuguese, were refined for better localization.
+
+### Fixed
+
+- **🎥 YouTube Video Attachments**: Fixed issues preventing proper loading and attachment of YouTube videos as files.
+- **🔄 Shared Chat Update**: Corrected issues where shared chats were not updating, improving collaboration consistency.
+- **🔍 DuckDuckGo Rate Limit Fix**: Addressed issues with DuckDuckGo search integration, enhancing search stability and performance when operating within rate limits.
+- **🧾 Citations Relevance Fix**: Adjusted the relevance percentage calculation for citations, so that Open WebUI properly reflect the accuracy of a retrieved document in RAG, ensuring users get clearer insights into sources.
+- **🔑 Jina Search API Key Requirement**: Added the option to input an API key for Jina Search, ensuring smooth functionality as keys are now mandatory.
+
+### Changed
+
+- **🛠️ Functions Moved to Admin Panel**: As Functions operate as advanced plugins, they are now accessible from the Admin Panel instead of the workspace.
+- **🛠️ Manage Ollama Connections**: The "Models" section in Admin Settings has been relocated to Admin Settings > "Connections" > Ollama Connections. You can now manage Ollama instances via a dedicated "Manage Ollama" modal from "Connections", streamlining the setup and configuration of Ollama models.
+- **📊 Base Models in Admin Settings**: Admins can now find all base models, both connections or functions, in the "Models" Admin setting. Global model accessibility can be enabled or disabled here. Models are private by default, requiring explicit permission assignment for user access.
+- **📌 Sticky Model Selection for New Chats**: The model chosen from a previous chat now persists when creating a new chat. If you click "New Chat" again from the new chat page, it will revert to your default model.
+- **🎨 Design Refactoring**: Overall design refinements across the platform have been made, providing a more cohesive and polished user experience.
+
+### Removed
+
+- **📂 Model List Reordering**: Temporarily removed and will be reintroduced in upcoming user group settings improvements.
+- **⚙️ Default Model Setting**: Removed the ability to set a default model for users, will be reintroduced with user group settings in the future.
+
+## [0.3.35] - 2024-10-26
+
+### Added
+
+- **🌐 Translation Update**: Added translation labels in the SearchInput and CreateCollection components and updated Brazilian Portuguese translation (pt-BR)
+- **📁 Robust File Handling**: Enhanced file input handling for chat. If the content extraction fails or is empty, users will now receive a clear warning, preventing silent failures and ensuring you always know what's happening with your uploads.
+- **🌍 New Language Support**: Introduced Hungarian translations and updated French translations, expanding the platform's language accessibility for a more global user base.
+
+### Fixed
+
+- **📚 Knowledge Base Loading Issue**: Resolved a critical bug where the Knowledge Base was not loading, ensuring smooth access to your stored documents and improving information retrieval in RAG-enhanced workflows.
+- **🛠️ Tool Parameters Issue**: Fixed an error where tools were not functioning correctly when required parameters were missing, ensuring reliable tool performance and more efficient task completions.
+- **🔗 Merged Response Loss in Multi-Model Chats**: Addressed an issue where responses in multi-model chat workflows were being deleted after follow-up queries, improving consistency and ensuring smoother interactions across models.
+
+## [0.3.34] - 2024-10-26
+
+### Added
+
+- **🔧 Feedback Export Enhancements**: Feedback history data can now be exported to JSON, allowing for seamless integration in RLHF processing and further analysis.
+- **🗂️ Embedding Model Lazy Loading**: Search functionality for leaderboard reranking is now more efficient, as embedding models are lazy-loaded only when needed, optimizing performance.
+- **🎨 Rich Text Input Toggle**: Users can now switch back to legacy textarea input for chat if they prefer simpler text input, though rich text is still the default until deprecation.
+- **🛠️ Improved Tool Calling Mechanism**: Enhanced method for parsing and calling tools, improving the reliability and robustness of tool function calls.
+- **🌐 Globalization Enhancements**: Updates to internationalization (i18n) support, further refining multi-language compatibility and accuracy.
+
+### Fixed
+
+- **🖥️ Folder Rename Fix for Firefox**: Addressed a persistent issue where users could not rename folders by pressing enter in Firefox, now ensuring seamless folder management across browsers.
+- **🔠 Tiktoken Model Text Splitter Issue**: Resolved an issue where the tiktoken text splitter wasn’t working in Docker installations, restoring full functionality for tokenized text editing.
+- **💼 S3 File Upload Issue**: Fixed a problem affecting S3 file uploads, ensuring smooth operations for those who store files on cloud storage.
+- **🔒 Strict-Transport-Security Crash**: Resolved a crash when setting the Strict-Transport-Security (HSTS) header, improving stability and security enhancements.
+- **🚫 OIDC Boolean Access Fix**: Addressed an issue with boolean values not being accessed correctly during OIDC logins, ensuring login reliability.
+- **⚙️ Rich Text Paste Behavior**: Refined paste behavior in rich text input to make it smoother and more intuitive when pasting various content types.
+- **🔨 Model Exclusion for Arena Fix**: Corrected the filter function that was not properly excluding models from the arena, improving model management.
+- **🏷️ "Tags Generation Prompt" Fix**: Addressed an issue preventing custom "tags generation prompts" from registering properly, ensuring custom prompt work seamlessly.
+
+## [0.3.33] - 2024-10-24
+
+### Added
+
+- **🏆 Evaluation Leaderboard**: Easily track your performance through a new leaderboard system where your ratings contribute to a real-time ranking based on the Elo system. Sibling responses (regenerations, many model chats) are required for your ratings to count in the leaderboard. Additionally, you can opt-in to share your feedback history and be part of the community-wide leaderboard. Expect further improvements as we refine the algorithm—help us build the best community leaderboard!
+- **⚔️ Arena Model Evaluation**: Enable blind A/B testing of models directly from Admin Settings > Evaluation for a true side-by-side comparison. Ideal for pinpointing the best model for your needs.
+- **🎯 Topic-Based Leaderboard**: Discover more accurate rankings with experimental topic-based reranking, which adjusts leaderboard standings based on tag similarity in feedback. Get more relevant insights based on specific topics!
+- **📁 Folders Support for Chats**: Organize your chats better by grouping them into folders. Drag and drop chats between folders and export them seamlessly for easy sharing or analysis.
+- **📤 Easy Chat Import via Drag & Drop**: Save time by simply dragging and dropping chat exports (JSON) directly onto the sidebar to import them into your workspace—streamlined, efficient, and intuitive!
+- **📚 Enhanced Knowledge Collection**: Now, you can reference individual files from a knowledge collection—ideal for more precise Retrieval-Augmented Generations (RAG) queries and document analysis.
+- **🏷️ Enhanced Tagging System**: Tags now take up less space! Utilize the new 'tag:' query system to manage, search, and organize your conversations more effectively without cluttering the interface.
+- **🧠 Auto-Tagging for Chats**: Your conversations are now automatically tagged for improved organization, mirroring the efficiency of auto-generated titles.
+- **🔍 Backend Chat Query System**: Chat filtering has become more efficient, now handled through the backend\*\* instead of your browser, improving search performance and accuracy.
+- **🎮 Revamped Playground**: Experience a refreshed and optimized Playground for smoother testing, tweaks, and experimentation of your models and tools.
+- **🧩 Token-Based Text Splitter**: Introducing token-based text splitting (tiktoken), giving you more precise control over how text is processed. Previously, only character-based splitting was available.
+- **🔢 Ollama Batch Embeddings**: Leverage new batch embedding support for improved efficiency and performance with Ollama embedding models.
+- **🔍 Enhanced Add Text Content Modal**: Enjoy a cleaner, more intuitive workflow for adding and curating knowledge content with an upgraded input modal from our Knowledge workspace.
+- **🖋️ Rich Text Input for Chats**: Make your chat inputs more dynamic with support for rich text formatting. Your conversations just got a lot more polished and professional.
+- **⚡ Faster Whisper Model Configurability**: Customize your local faster whisper model directly from the WebUI.
+- **☁️ Experimental S3 Support**: Enable stateless WebUI instances with S3 support, greatly enhancing scalability and balancing heavy workloads.
+- **🔕 Disable Update Toast**: Now you can streamline your workspace even further—choose to disable update notifications for a more focused experience.
+- **🌟 RAG Citation Relevance Percentage**: Easily assess citation accuracy with the addition of relevance percentages in RAG results.
+- **⚙️ Mermaid Copy Button**: Mermaid diagrams now come with a handy copy button, simplifying the extraction and use of diagram contents directly in your workflow.
+- **🎨 UI Redesign**: Major interface redesign that will make navigation smoother, keep your focus where it matters, and ensure a modern look.
+
+### Fixed
+
+- **🎙️ Voice Note Mic Stopping Issue**: Fixed the issue where the microphone stayed active after ending a voice note recording, ensuring your audio workflow runs smoothly.
+
+### Removed
+
+- **👋 Goodbye Sidebar Tags**: Sidebar tag clutter is gone. We’ve shifted tag buttons to more effective query-based tag filtering for a sleeker, more agile interface.
+
+## [0.3.32] - 2024-10-06
+
+### Added
+
+- **🔢 Workspace Enhancements**: Added a display count for models, prompts, tools, and functions in the workspace, providing a clear overview and easier management.
+
+### Fixed
+
+- **🖥️ Web and YouTube Attachment Fix**: Resolved an issue where attaching web links and YouTube videos was malfunctioning, ensuring seamless integration and display within chats.
+- **📞 Call Mode Activation on Landing Page**: Fixed a bug where call mode was not operational from the landing page.
+
+### Changed
+
+- **🔄 URL Parameter Refinement**: Updated the 'tool_ids' URL parameter to 'tools' or 'tool-ids' for more intuitive and consistent user experience.
+- **🎨 Floating Buttons Styling Update**: Refactored the styling of floating buttons to intelligently adjust to the left side when there isn't enough room on the right, improving interface usability and aesthetic.
+- **🔧 Enhanced Accessibility for Floating Buttons**: Implemented the ability to close floating buttons with the 'Esc' key, making workflow smoother and more efficient for users navigating via keyboard.
+- **🖇️ Updated Information URL**: Information URLs now direct users to a general release page rather than a version-specific URL, ensuring access to the latest and relevant details all in one place.
+- **📦 Library Dependencies Update**: Upgraded dependencies to ensure compatibility and performance optimization for pip installs.
+
+## [0.3.31] - 2024-10-06
+
+### Added
+
+- **📚 Knowledge Feature**: Reimagined documents feature, now more performant with a better UI for enhanced organization; includes streamlined API integration for Retrieval-Augmented Generation (RAG). Detailed documentation forthcoming: https://docs.openwebui.com/
+- **🌐 New Landing Page**: Freshly designed landing page; toggle between the new UI and the classic chat UI from Settings > Interface for a personalized experience.
+- **📁 Full Document Retrieval Mode**: Toggle between full document retrieval or traditional snippets by clicking on the file item. This mode enhances document capabilities and supports comprehensive tasks like summarization by utilizing the entire content instead of RAG.
+- **📄 Extracted File Content Display**: View extracted content directly by clicking on the file item, simplifying file analysis.
+- **🎨 Artifacts Feature**: Render web content and SVGs directly in the interface, supporting quick iterations and live changes.
+- **🖊️ Editable Code Blocks**: Supercharged code blocks now allow live editing directly in the LLM response, with live reloads supported by artifacts.
+- **🔧 Code Block Enhancements**: Introduced a floating copy button in code blocks to facilitate easier code copying without scrolling.
+- **🔍 SVG Pan/Zoom**: Enhanced interaction with SVG images, including Mermaid diagrams, via new pan and zoom capabilities.
+- **🔍 Text Select Quick Actions**: New floating buttons appear when text is highlighted in LLM responses, offering deeper interactions like "Ask a Question" or "Explain".
+- **🗃️ Database Pool Configuration**: Enhanced database handling to support scalable user growth.
+- **🔊 Experimental Audio Compression**: Compress audio files to navigate around the 25MB limit for OpenAI's speech-to-text processing.
+- **🔍 Query Embedding**: Adjusted embedding behavior to enhance system performance by not repeating query embedding.
+- **💾 Lazy Load Optimizations**: Implemented lazy loading of large dependencies to minimize initial memory usage, boosting performance.
+- **🍏 Apple Touch Icon Support**: Optimizes the display of icons for web bookmarks on Apple mobile devices.
+- **🔽 Expandable Content Markdown Support**: Introducing 'details', 'summary' tag support for creating expandable content sections in markdown, facilitating cleaner, organized documentation and interactive content display.
+
+### Fixed
+
+- **🔘 Action Button Issue**: Resolved a bug where action buttons were not functioning, enhancing UI reliability.
+- **🔄 Multi-Model Chat Loop**: Fixed an infinite loop issue in multi-model chat environments, ensuring smoother chat operations.
+- **📄 Chat PDF/TXT Export Issue**: Resolved problems with exporting chat logs to PDF and TXT formats.
+- **🔊 Call to Text-to-Speech Issues**: Rectified problems with text-to-speech functions to improve audio interactions.
+
+### Changed
+
+- **⚙️ Endpoint Renaming**: Renamed 'rag' endpoints to 'retrieval' for clearer function description.
+- **🎨 Styling and Interface Updates**: Multiple refinements across the platform to enhance visual appeal and user interaction.
+
+### Removed
+
+- **🗑️ Deprecated 'DOCS_DIR'**: Removed the outdated 'docs_dir' variable in favor of more direct file management solutions, with direct file directory syncing and API uploads for a more integrated experience.
+
 ## [0.3.30] - 2024-09-26
 
 ### Fixed

CODE_OF_CONDUCT.md

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

Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1
 # Initialize device type args
-# use build args in the docker build commmand with --build-arg="BUILDARG=true"
+# use build args in the docker build command with --build-arg="BUILDARG=true"
 ARG USE_CUDA=false
 ARG USE_OLLAMA=false
 # Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
@@ -11,13 +11,17 @@ ARG USE_CUDA_VER=cu121
 # IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
 ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
 ARG USE_RERANKING_MODEL=""
+
+# Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
+ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
+
 ARG BUILD_HASH=dev-build
 # Override at your own risk - non-root configurations are untested
 ARG UID=0
 ARG GID=0
 
 ######## WebUI frontend ########
-FROM --platform=$BUILDPLATFORM node:21-alpine3.19 as build
+FROM --platform=$BUILDPLATFORM node:22-alpine3.20 AS build
 ARG BUILD_HASH
 
 WORKDIR /app
@@ -30,7 +34,7 @@ ENV APP_BUILD_HASH=${BUILD_HASH}
 RUN npm run build
 
 ######## WebUI backend ########
-FROM python:3.11-slim-bookworm as base
+FROM python:3.11-slim-bookworm AS base
 
 # Use args
 ARG USE_CUDA
@@ -72,6 +76,10 @@ ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
     RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
     SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
 
+## Tiktoken model settings ##
+ENV TIKTOKEN_ENCODING_NAME="cl100k_base" \
+    TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken"
+
 ## Hugging Face download cache ##
 ENV HF_HOME="/app/backend/data/cache/embedding/models"
 
@@ -82,7 +90,7 @@ ENV HF_HOME="/app/backend/data/cache/embedding/models"
 
 WORKDIR /app/backend
 
-ENV HOME /root
+ENV HOME=/root
 # Create user and group if not root
 RUN if [ $UID -ne 0 ]; then \
     if [ $GID -ne 0 ]; then \
@@ -131,11 +139,13 @@ RUN pip3 install uv && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     else \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     fi; \
     chown -R $UID:$GID /app/backend/data/
 
@@ -161,6 +171,6 @@ USER $UID:$GID
 
 ARG BUILD_HASH
 ENV WEBUI_BUILD_VERSION=${BUILD_HASH}
-ENV DOCKER true
+ENV DOCKER=true
 
 CMD [ "bash", "start.sh"]

README.md

@@ -1,4 +1,4 @@
-# Open WebUI (Formerly Ollama WebUI) 👋
+# Open WebUI 👋
 
 ![GitHub stars](https://img.shields.io/github/stars/open-webui/open-webui?style=social)
 ![GitHub forks](https://img.shields.io/github/forks/open-webui/open-webui?style=social)
@@ -21,7 +21,7 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 🤝 **Ollama/OpenAI API Integration**: Effortlessly integrate OpenAI-compatible APIs for versatile conversations alongside Ollama models. Customize the OpenAI API URL to link with **LMStudio, GroqCloud, Mistral, OpenRouter, and more**.
 
-- 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
+- 🛡️ **Granular Permissions and User Groups**: By allowing administrators to create detailed user roles and permissions, we ensure a secure user environment. This granularity not only enhances security but also allows for customized user experiences, fostering a sense of ownership and responsibility amongst users.
 
 - 📱 **Responsive Design**: Enjoy a seamless experience across Desktop PC, Laptop, and Mobile devices.
 
@@ -37,7 +37,7 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 📚 **Local RAG Integration**: Dive into the future of chat interactions with groundbreaking Retrieval Augmented Generation (RAG) support. This feature seamlessly integrates document interactions into your chat experience. You can load documents directly into the chat or add files to your document library, effortlessly accessing them using the `#` command before a query.
 
-- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, `serper`, `Serply`, `DuckDuckGo`, `TavilySearch` and `SearchApi` and inject the results directly into your chat experience.
+- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, `serper`, `Serply`, `DuckDuckGo`, `TavilySearch`, `SearchApi` and `Bing` and inject the results directly into your chat experience.
 
 - 🌐 **Web Browsing Capability**: Seamlessly integrate websites into your chat experience using the `#` command followed by a URL. This feature allows you to incorporate web content directly into your conversations, enhancing the richness and depth of your interactions.
 
@@ -49,6 +49,8 @@ Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-
 
 - 🌐🌍 **Multilingual Support**: Experience Open WebUI in your preferred language with our internationalization (i18n) support. Join us in expanding our supported languages! We're actively seeking contributors!
 
+- 🧩 **Pipelines, Open WebUI Plugin Support**: Seamlessly integrate custom logic and Python libraries into Open WebUI using [Pipelines Plugin Framework](https://github.com/open-webui/pipelines). Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. [Examples](https://github.com/open-webui/pipelines/tree/main/examples) include **Function Calling**, User **Rate Limiting** to control access, **Usage Monitoring** with tools like Langfuse, **Live Translation with LibreTranslate** for multilingual support, **Toxic Message Filtering** and much more.
+
 - 🌟 **Continuous Updates**: We are committed to improving Open WebUI with regular updates, fixes, and new features.
 
 Want to learn more about Open WebUI's features? Check out our [Open WebUI documentation](https://docs.openwebui.com/features) for a comprehensive overview!
@@ -106,7 +108,7 @@ This will start the Open WebUI server, which you can access at [http://localhost
   docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=https://example.com -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
   ```
 
-  - **To run Open WebUI with Nvidia GPU support**, use this command:
+- **To run Open WebUI with Nvidia GPU support**, use this command:
 
   ```bash
   docker run -d -p 3000:8080 --gpus all --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:cuda
@@ -170,7 +172,7 @@ docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/wa
 
 In the last part of the command, replace `open-webui` with your container name if it is different.
 
-Check our Migration Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/migration/).
+Check our Migration Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/tutorials/migration/).
 
 ### Using the Dev Branch 🌙
 
@@ -187,18 +189,6 @@ docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui --a
 
 Discover upcoming features on our roadmap in the [Open WebUI Documentation](https://docs.openwebui.com/roadmap/).
 
-## Supporters ✨
-
-A big shoutout to our amazing supporters who's helping to make this project possible! 🙏
-
-### Platinum Sponsors 🤍
-
-- We're looking for Sponsors!
-
-### Acknowledgments
-
-Special thanks to [Prof. Lawrence Kim](https://www.lhkim.com/) and [Prof. Nick Vincent](https://www.nickmvincent.com/) for their invaluable support and guidance in shaping this project into a research endeavor. Grateful for your mentorship throughout the journey! 🙌
-
 ## License 📜
 
 This project is licensed under the [MIT License](LICENSE) - see the [LICENSE](LICENSE) file for details. 📄
@@ -220,4 +210,4 @@ If you have any questions, suggestions, or need assistance, please open an issue
 
 ---
 
-Created by [Timothy J. Baek](https://github.com/tjbck) - Let's make Open WebUI even more amazing together! 💪
+Created by [Timothy Jaeryang Baek](https://github.com/tjbck) - Let's make Open WebUI even more amazing together! 💪

TROUBLESHOOTING.md

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

backend/open_webui/apps/audio/main.py

@@ -1,583 +0,0 @@
-import hashlib
-import json
-import logging
-import os
-import uuid
-from functools import lru_cache
-from pathlib import Path
-
-import requests
-from open_webui.config import (
-    AUDIO_STT_ENGINE,
-    AUDIO_STT_MODEL,
-    AUDIO_STT_OPENAI_API_BASE_URL,
-    AUDIO_STT_OPENAI_API_KEY,
-    AUDIO_TTS_API_KEY,
-    AUDIO_TTS_ENGINE,
-    AUDIO_TTS_MODEL,
-    AUDIO_TTS_OPENAI_API_BASE_URL,
-    AUDIO_TTS_OPENAI_API_KEY,
-    AUDIO_TTS_SPLIT_ON,
-    AUDIO_TTS_VOICE,
-    AUDIO_TTS_AZURE_SPEECH_REGION,
-    AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT,
-    CACHE_DIR,
-    CORS_ALLOW_ORIGIN,
-    WHISPER_MODEL,
-    WHISPER_MODEL_AUTO_UPDATE,
-    WHISPER_MODEL_DIR,
-    AppConfig,
-)
-
-from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS, DEVICE_TYPE
-from fastapi import Depends, FastAPI, File, HTTPException, Request, UploadFile, status
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import FileResponse
-from pydantic import BaseModel
-from open_webui.utils.utils import get_admin_user, get_current_user, get_verified_user
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["AUDIO"])
-
-app = FastAPI()
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=CORS_ALLOW_ORIGIN,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-app.state.config = AppConfig()
-
-app.state.config.STT_OPENAI_API_BASE_URL = AUDIO_STT_OPENAI_API_BASE_URL
-app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
-app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
-app.state.config.STT_MODEL = AUDIO_STT_MODEL
-
-app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
-app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
-app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
-app.state.config.TTS_MODEL = AUDIO_TTS_MODEL
-app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
-app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
-app.state.config.TTS_SPLIT_ON = AUDIO_TTS_SPLIT_ON
-
-app.state.config.TTS_AZURE_SPEECH_REGION = AUDIO_TTS_AZURE_SPEECH_REGION
-app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT
-
-# setting device type for whisper model
-whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
-log.info(f"whisper_device_type: {whisper_device_type}")
-
-SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
-SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
-
-
-class TTSConfigForm(BaseModel):
-    OPENAI_API_BASE_URL: str
-    OPENAI_API_KEY: str
-    API_KEY: str
-    ENGINE: str
-    MODEL: str
-    VOICE: str
-    SPLIT_ON: str
-    AZURE_SPEECH_REGION: str
-    AZURE_SPEECH_OUTPUT_FORMAT: str
-
-
-class STTConfigForm(BaseModel):
-    OPENAI_API_BASE_URL: str
-    OPENAI_API_KEY: str
-    ENGINE: str
-    MODEL: str
-
-
-class AudioConfigUpdateForm(BaseModel):
-    tts: TTSConfigForm
-    stt: STTConfigForm
-
-
-from pydub import AudioSegment
-from pydub.utils import mediainfo
-
-
-def is_mp4_audio(file_path):
-    """Check if the given file is an MP4 audio file."""
-    if not os.path.isfile(file_path):
-        print(f"File not found: {file_path}")
-        return False
-
-    info = mediainfo(file_path)
-    if (
-        info.get("codec_name") == "aac"
-        and info.get("codec_type") == "audio"
-        and info.get("codec_tag_string") == "mp4a"
-    ):
-        return True
-    return False
-
-
-def convert_mp4_to_wav(file_path, output_path):
-    """Convert MP4 audio file to WAV format."""
-    audio = AudioSegment.from_file(file_path, format="mp4")
-    audio.export(output_path, format="wav")
-    print(f"Converted {file_path} to {output_path}")
-
-
-@app.get("/config")
-async def get_audio_config(user=Depends(get_admin_user)):
-    return {
-        "tts": {
-            "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
-            "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
-            "API_KEY": app.state.config.TTS_API_KEY,
-            "ENGINE": app.state.config.TTS_ENGINE,
-            "MODEL": app.state.config.TTS_MODEL,
-            "VOICE": app.state.config.TTS_VOICE,
-            "SPLIT_ON": app.state.config.TTS_SPLIT_ON,
-            "AZURE_SPEECH_REGION": app.state.config.TTS_AZURE_SPEECH_REGION,
-            "AZURE_SPEECH_OUTPUT_FORMAT": app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT,
-        },
-        "stt": {
-            "OPENAI_API_BASE_URL": app.state.config.STT_OPENAI_API_BASE_URL,
-            "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
-            "ENGINE": app.state.config.STT_ENGINE,
-            "MODEL": app.state.config.STT_MODEL,
-        },
-    }
-
-
-@app.post("/config/update")
-async def update_audio_config(
-    form_data: AudioConfigUpdateForm, user=Depends(get_admin_user)
-):
-    app.state.config.TTS_OPENAI_API_BASE_URL = form_data.tts.OPENAI_API_BASE_URL
-    app.state.config.TTS_OPENAI_API_KEY = form_data.tts.OPENAI_API_KEY
-    app.state.config.TTS_API_KEY = form_data.tts.API_KEY
-    app.state.config.TTS_ENGINE = form_data.tts.ENGINE
-    app.state.config.TTS_MODEL = form_data.tts.MODEL
-    app.state.config.TTS_VOICE = form_data.tts.VOICE
-    app.state.config.TTS_SPLIT_ON = form_data.tts.SPLIT_ON
-    app.state.config.TTS_AZURE_SPEECH_REGION = form_data.tts.AZURE_SPEECH_REGION
-    app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT = (
-        form_data.tts.AZURE_SPEECH_OUTPUT_FORMAT
-    )
-
-    app.state.config.STT_OPENAI_API_BASE_URL = form_data.stt.OPENAI_API_BASE_URL
-    app.state.config.STT_OPENAI_API_KEY = form_data.stt.OPENAI_API_KEY
-    app.state.config.STT_ENGINE = form_data.stt.ENGINE
-    app.state.config.STT_MODEL = form_data.stt.MODEL
-
-    return {
-        "tts": {
-            "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
-            "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
-            "API_KEY": app.state.config.TTS_API_KEY,
-            "ENGINE": app.state.config.TTS_ENGINE,
-            "MODEL": app.state.config.TTS_MODEL,
-            "VOICE": app.state.config.TTS_VOICE,
-            "SPLIT_ON": app.state.config.TTS_SPLIT_ON,
-            "AZURE_SPEECH_REGION": app.state.config.TTS_AZURE_SPEECH_REGION,
-            "AZURE_SPEECH_OUTPUT_FORMAT": app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT,
-        },
-        "stt": {
-            "OPENAI_API_BASE_URL": app.state.config.STT_OPENAI_API_BASE_URL,
-            "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
-            "ENGINE": app.state.config.STT_ENGINE,
-            "MODEL": app.state.config.STT_MODEL,
-        },
-    }
-
-
-@app.post("/speech")
-async def speech(request: Request, user=Depends(get_verified_user)):
-    body = await request.body()
-    name = hashlib.sha256(body).hexdigest()
-
-    file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
-    file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
-
-    # Check if the file already exists in the cache
-    if file_path.is_file():
-        return FileResponse(file_path)
-
-    if app.state.config.TTS_ENGINE == "openai":
-        headers = {}
-        headers["Authorization"] = f"Bearer {app.state.config.TTS_OPENAI_API_KEY}"
-        headers["Content-Type"] = "application/json"
-
-        try:
-            body = body.decode("utf-8")
-            body = json.loads(body)
-            body["model"] = app.state.config.TTS_MODEL
-            body = json.dumps(body).encode("utf-8")
-        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,
-            )
-
-            r.raise_for_status()
-
-            # 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()
-                    if "error" in res:
-                        error_detail = f"External: {res['error']['message']}"
-                except Exception:
-                    error_detail = f"External: {e}"
-
-            raise HTTPException(
-                status_code=r.status_code if r != None else 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:
-            log.exception(e)
-            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,
-                detail="Invalid voice id",
-            )
-
-        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,
-            "voice_settings": {"stability": 0.5, "similarity_boost": 0.5},
-        }
-
-        try:
-            r = requests.post(url, json=data, headers=headers)
-
-            r.raise_for_status()
-
-            # 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()
-                    if "error" in res:
-                        error_detail = f"External: {res['error']['message']}"
-                except Exception:
-                    error_detail = f"External: {e}"
-
-            raise HTTPException(
-                status_code=r.status_code if r != None else 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:
-            log.exception(e)
-            raise HTTPException(status_code=400, detail="Invalid JSON payload")
-
-        region = app.state.config.TTS_AZURE_SPEECH_REGION
-        language = app.state.config.TTS_VOICE
-        locale = "-".join(app.state.config.TTS_VOICE.split("-")[:1])
-        output_format = app.state.config.TTS_AZURE_SPEECH_OUTPUT_FORMAT
-        url = f"https://{region}.tts.speech.microsoft.com/cognitiveservices/v1"
-
-        headers = {
-            "Ocp-Apim-Subscription-Key": app.state.config.TTS_API_KEY,
-            "Content-Type": "application/ssml+xml",
-            "X-Microsoft-OutputFormat": output_format,
-        }
-
-        data = f"""<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="{locale}">
-                <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}"
-            )
-
-
-@app.post("/transcriptions")
-def transcribe(
-    file: UploadFile = File(...),
-    user=Depends(get_current_user),
-):
-    log.info(f"file.content_type: {file.content_type}")
-
-    if file.content_type not in ["audio/mpeg", "audio/wav", "audio/ogg", "audio/x-m4a"]:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
-        )
-
-    try:
-        ext = file.filename.split(".")[-1]
-
-        id = uuid.uuid4()
-        filename = f"{id}.{ext}"
-
-        file_dir = f"{CACHE_DIR}/audio/transcriptions"
-        os.makedirs(file_dir, exist_ok=True)
-        file_path = f"{file_dir}/{filename}"
-
-        print(filename)
-
-        contents = file.file.read()
-        with open(file_path, "wb") as f:
-            f.write(contents)
-            f.close()
-
-        if app.state.config.STT_ENGINE == "":
-            from faster_whisper import WhisperModel
-
-            whisper_kwargs = {
-                "model_size_or_path": WHISPER_MODEL,
-                "device": whisper_device_type,
-                "compute_type": "int8",
-                "download_root": WHISPER_MODEL_DIR,
-                "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
-            }
-
-            log.debug(f"whisper_kwargs: {whisper_kwargs}")
-
-            try:
-                model = WhisperModel(**whisper_kwargs)
-            except Exception:
-                log.warning(
-                    "WhisperModel initialization failed, attempting download with local_files_only=False"
-                )
-                whisper_kwargs["local_files_only"] = False
-                model = WhisperModel(**whisper_kwargs)
-
-            segments, info = model.transcribe(file_path, beam_size=5)
-            log.info(
-                "Detected language '%s' with probability %f"
-                % (info.language, info.language_probability)
-            )
-
-            transcript = "".join([segment.text for segment in list(segments)])
-
-            data = {"text": transcript.strip()}
-
-            # save the transcript to a json file
-            transcript_file = f"{file_dir}/{id}.json"
-            with open(transcript_file, "w") as f:
-                json.dump(data, f)
-
-            print(data)
-
-            return data
-
-        elif app.state.config.STT_ENGINE == "openai":
-            if is_mp4_audio(file_path):
-                print("is_mp4_audio")
-                os.rename(file_path, file_path.replace(".wav", ".mp4"))
-                # Convert MP4 audio file to WAV format
-                convert_mp4_to_wav(file_path.replace(".wav", ".mp4"), file_path)
-
-            headers = {"Authorization": f"Bearer {app.state.config.STT_OPENAI_API_KEY}"}
-
-            files = {"file": (filename, open(file_path, "rb"))}
-            data = {"model": app.state.config.STT_MODEL}
-
-            print(files, data)
-
-            r = None
-            try:
-                r = requests.post(
-                    url=f"{app.state.config.STT_OPENAI_API_BASE_URL}/audio/transcriptions",
-                    headers=headers,
-                    files=files,
-                    data=data,
-                )
-
-                r.raise_for_status()
-
-                data = r.json()
-
-                # save the transcript to a json file
-                transcript_file = f"{file_dir}/{id}.json"
-                with open(transcript_file, "w") as f:
-                    json.dump(data, f)
-
-                print(data)
-                return data
-            except Exception as e:
-                log.exception(e)
-                error_detail = "Open WebUI: Server Connection Error"
-                if r is not None:
-                    try:
-                        res = r.json()
-                        if "error" in res:
-                            error_detail = f"External: {res['error']['message']}"
-                    except Exception:
-                        error_detail = f"External: {e}"
-
-                raise HTTPException(
-                    status_code=r.status_code if r != None else 500,
-                    detail=error_detail,
-                )
-
-    except Exception as e:
-        log.exception(e)
-
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
-
-
-def get_available_models() -> list[dict]:
-    if app.state.config.TTS_ENGINE == "openai":
-        return [{"id": "tts-1"}, {"id": "tts-1-hd"}]
-    elif app.state.config.TTS_ENGINE == "elevenlabs":
-        headers = {
-            "xi-api-key": app.state.config.TTS_API_KEY,
-            "Content-Type": "application/json",
-        }
-
-        try:
-            response = requests.get(
-                "https://api.elevenlabs.io/v1/models", headers=headers, timeout=5
-            )
-            response.raise_for_status()
-            models = response.json()
-            return [
-                {"name": model["name"], "id": model["model_id"]} for model in models
-            ]
-        except requests.RequestException as e:
-            log.error(f"Error fetching voices: {str(e)}")
-    return []
-
-
-@app.get("/models")
-async def get_models(user=Depends(get_verified_user)):
-    return {"models": get_available_models()}
-
-
-def get_available_voices() -> dict:
-    """Returns {voice_id: voice_name} dict"""
-    ret = {}
-    if app.state.config.TTS_ENGINE == "openai":
-        ret = {
-            "alloy": "alloy",
-            "echo": "echo",
-            "fable": "fable",
-            "onyx": "onyx",
-            "nova": "nova",
-            "shimmer": "shimmer",
-        }
-    elif app.state.config.TTS_ENGINE == "elevenlabs":
-        try:
-            ret = get_elevenlabs_voices()
-        except Exception:
-            # Avoided @lru_cache with exception
-            pass
-    elif app.state.config.TTS_ENGINE == "azure":
-        try:
-            region = app.state.config.TTS_AZURE_SPEECH_REGION
-            url = f"https://{region}.tts.speech.microsoft.com/cognitiveservices/voices/list"
-            headers = {"Ocp-Apim-Subscription-Key": app.state.config.TTS_API_KEY}
-
-            response = requests.get(url, headers=headers)
-            response.raise_for_status()
-            voices = response.json()
-            for voice in voices:
-                ret[voice["ShortName"]] = (
-                    f"{voice['DisplayName']} ({voice['ShortName']})"
-                )
-        except requests.RequestException as e:
-            log.error(f"Error fetching voices: {str(e)}")
-
-    return ret
-
-
-@lru_cache
-def get_elevenlabs_voices() -> dict:
-    """
-    Note, set the following in your .env file to use Elevenlabs:
-    AUDIO_TTS_ENGINE=elevenlabs
-    AUDIO_TTS_API_KEY=sk_...  # Your Elevenlabs API key
-    AUDIO_TTS_VOICE=EXAVITQu4vr4xnSDxMaL  # From https://api.elevenlabs.io/v1/voices
-    AUDIO_TTS_MODEL=eleven_multilingual_v2
-    """
-    headers = {
-        "xi-api-key": app.state.config.TTS_API_KEY,
-        "Content-Type": "application/json",
-    }
-    try:
-        # TODO: Add retries
-        response = requests.get("https://api.elevenlabs.io/v1/voices", headers=headers)
-        response.raise_for_status()
-        voices_data = response.json()
-
-        voices = {}
-        for voice in voices_data.get("voices", []):
-            voices[voice["voice_id"]] = voice["name"]
-    except requests.RequestException as e:
-        # Avoid @lru_cache with exception
-        log.error(f"Error fetching voices: {str(e)}")
-        raise RuntimeError(f"Error fetching voices: {str(e)}")
-
-    return voices
-
-
-@app.get("/voices")
-async def get_voices(user=Depends(get_verified_user)):
-    return {"voices": [{"id": k, "name": v} for k, v in get_available_voices().items()]}

backend/open_webui/apps/openai/main.py

@@ -1,549 +0,0 @@
-import asyncio
-import hashlib
-import json
-import logging
-from pathlib import Path
-from typing import Literal, Optional, overload
-
-import aiohttp
-import requests
-from open_webui.apps.webui.models.models import Models
-from open_webui.config import (
-    AIOHTTP_CLIENT_TIMEOUT,
-    CACHE_DIR,
-    CORS_ALLOW_ORIGIN,
-    ENABLE_MODEL_FILTER,
-    ENABLE_OPENAI_API,
-    MODEL_FILTER_LIST,
-    OPENAI_API_BASE_URLS,
-    OPENAI_API_KEYS,
-    AppConfig,
-)
-from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
-from fastapi import Depends, FastAPI, HTTPException, Request
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import FileResponse, StreamingResponse
-from pydantic import BaseModel
-from starlette.background import BackgroundTask
-
-
-from open_webui.utils.payload import (
-    apply_model_params_to_body_openai,
-    apply_model_system_prompt_to_body,
-)
-
-from open_webui.utils.utils import get_admin_user, get_verified_user
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["OPENAI"])
-
-app = FastAPI()
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=CORS_ALLOW_ORIGIN,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
-app.state.config = AppConfig()
-
-app.state.config.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
-app.state.config.MODEL_FILTER_LIST = MODEL_FILTER_LIST
-
-app.state.config.ENABLE_OPENAI_API = ENABLE_OPENAI_API
-app.state.config.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS
-app.state.config.OPENAI_API_KEYS = OPENAI_API_KEYS
-
-app.state.MODELS = {}
-
-
-@app.middleware("http")
-async def check_url(request: Request, call_next):
-    if len(app.state.MODELS) == 0:
-        await get_all_models()
-
-    response = await call_next(request)
-    return response
-
-
-@app.get("/config")
-async def get_config(user=Depends(get_admin_user)):
-    return {"ENABLE_OPENAI_API": app.state.config.ENABLE_OPENAI_API}
-
-
-class OpenAIConfigForm(BaseModel):
-    enable_openai_api: Optional[bool] = None
-
-
-@app.post("/config/update")
-async def update_config(form_data: OpenAIConfigForm, user=Depends(get_admin_user)):
-    app.state.config.ENABLE_OPENAI_API = form_data.enable_openai_api
-    return {"ENABLE_OPENAI_API": app.state.config.ENABLE_OPENAI_API}
-
-
-class UrlsUpdateForm(BaseModel):
-    urls: list[str]
-
-
-class KeysUpdateForm(BaseModel):
-    keys: list[str]
-
-
-@app.get("/urls")
-async def get_openai_urls(user=Depends(get_admin_user)):
-    return {"OPENAI_API_BASE_URLS": app.state.config.OPENAI_API_BASE_URLS}
-
-
-@app.post("/urls/update")
-async def update_openai_urls(form_data: UrlsUpdateForm, user=Depends(get_admin_user)):
-    await get_all_models()
-    app.state.config.OPENAI_API_BASE_URLS = form_data.urls
-    return {"OPENAI_API_BASE_URLS": app.state.config.OPENAI_API_BASE_URLS}
-
-
-@app.get("/keys")
-async def get_openai_keys(user=Depends(get_admin_user)):
-    return {"OPENAI_API_KEYS": app.state.config.OPENAI_API_KEYS}
-
-
-@app.post("/keys/update")
-async def update_openai_key(form_data: KeysUpdateForm, user=Depends(get_admin_user)):
-    app.state.config.OPENAI_API_KEYS = form_data.keys
-    return {"OPENAI_API_KEYS": app.state.config.OPENAI_API_KEYS}
-
-
-@app.post("/audio/speech")
-async def speech(request: Request, user=Depends(get_verified_user)):
-    idx = None
-    try:
-        idx = app.state.config.OPENAI_API_BASE_URLS.index("https://api.openai.com/v1")
-        body = await request.body()
-        name = hashlib.sha256(body).hexdigest()
-
-        SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
-        SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
-        file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
-        file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
-
-        # Check if the file already exists in the cache
-        if file_path.is_file():
-            return FileResponse(file_path)
-
-        headers = {}
-        headers["Authorization"] = f"Bearer {app.state.config.OPENAI_API_KEYS[idx]}"
-        headers["Content-Type"] = "application/json"
-        if "openrouter.ai" in app.state.config.OPENAI_API_BASE_URLS[idx]:
-            headers["HTTP-Referer"] = "https://openwebui.com/"
-            headers["X-Title"] = "Open WebUI"
-        r = None
-        try:
-            r = requests.post(
-                url=f"{app.state.config.OPENAI_API_BASE_URLS[idx]}/audio/speech",
-                data=body,
-                headers=headers,
-                stream=True,
-            )
-
-            r.raise_for_status()
-
-            # 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()
-                    if "error" in res:
-                        error_detail = f"External: {res['error']}"
-                except Exception:
-                    error_detail = f"External: {e}"
-
-            raise HTTPException(
-                status_code=r.status_code if r else 500, detail=error_detail
-            )
-
-    except ValueError:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
-
-
-async def fetch_url(url, key):
-    timeout = aiohttp.ClientTimeout(total=5)
-    try:
-        headers = {"Authorization": f"Bearer {key}"}
-        async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
-            async with session.get(url, headers=headers) as response:
-                return await response.json()
-    except Exception as e:
-        # Handle connection error here
-        log.error(f"Connection error: {e}")
-        return None
-
-
-async def cleanup_response(
-    response: Optional[aiohttp.ClientResponse],
-    session: Optional[aiohttp.ClientSession],
-):
-    if response:
-        response.close()
-    if session:
-        await session.close()
-
-
-def merge_models_lists(model_lists):
-    log.debug(f"merge_models_lists {model_lists}")
-    merged_list = []
-
-    for idx, models in enumerate(model_lists):
-        if models is not None and "error" not in models:
-            merged_list.extend(
-                [
-                    {
-                        **model,
-                        "name": model.get("name", model["id"]),
-                        "owned_by": "openai",
-                        "openai": model,
-                        "urlIdx": idx,
-                    }
-                    for model in models
-                    if "api.openai.com"
-                    not in app.state.config.OPENAI_API_BASE_URLS[idx]
-                    or not any(
-                        name in model["id"]
-                        for name in [
-                            "babbage",
-                            "dall-e",
-                            "davinci",
-                            "embedding",
-                            "tts",
-                            "whisper",
-                        ]
-                    )
-                ]
-            )
-
-    return merged_list
-
-
-def is_openai_api_disabled():
-    api_keys = app.state.config.OPENAI_API_KEYS
-    no_keys = len(api_keys) == 1 and api_keys[0] == ""
-    return no_keys or not app.state.config.ENABLE_OPENAI_API
-
-
-async def get_all_models_raw() -> list:
-    if is_openai_api_disabled():
-        return []
-
-    # Check if API KEYS length is same than API URLS length
-    num_urls = len(app.state.config.OPENAI_API_BASE_URLS)
-    num_keys = len(app.state.config.OPENAI_API_KEYS)
-
-    if num_keys != num_urls:
-        # if there are more keys than urls, remove the extra keys
-        if num_keys > num_urls:
-            new_keys = app.state.config.OPENAI_API_KEYS[:num_urls]
-            app.state.config.OPENAI_API_KEYS = new_keys
-        # if there are more urls than keys, add empty keys
-        else:
-            app.state.config.OPENAI_API_KEYS += [""] * (num_urls - num_keys)
-
-    tasks = [
-        fetch_url(f"{url}/models", app.state.config.OPENAI_API_KEYS[idx])
-        for idx, url in enumerate(app.state.config.OPENAI_API_BASE_URLS)
-    ]
-
-    responses = await asyncio.gather(*tasks)
-    log.debug(f"get_all_models:responses() {responses}")
-
-    return responses
-
-
-@overload
-async def get_all_models(raw: Literal[True]) -> list: ...
-
-
-@overload
-async def get_all_models(raw: Literal[False] = False) -> dict[str, list]: ...
-
-
-async def get_all_models(raw=False) -> dict[str, list] | list:
-    log.info("get_all_models()")
-    if is_openai_api_disabled():
-        return [] if raw else {"data": []}
-
-    responses = await get_all_models_raw()
-    if raw:
-        return responses
-
-    def extract_data(response):
-        if response and "data" in response:
-            return response["data"]
-        if isinstance(response, list):
-            return response
-        return None
-
-    models = {"data": merge_models_lists(map(extract_data, responses))}
-
-    log.debug(f"models: {models}")
-    app.state.MODELS = {model["id"]: model for model in models["data"]}
-
-    return models
-
-
-@app.get("/models")
-@app.get("/models/{url_idx}")
-async def get_models(url_idx: Optional[int] = None, user=Depends(get_verified_user)):
-    if url_idx is None:
-        models = await get_all_models()
-        if app.state.config.ENABLE_MODEL_FILTER:
-            if user.role == "user":
-                models["data"] = list(
-                    filter(
-                        lambda model: model["id"] in app.state.config.MODEL_FILTER_LIST,
-                        models["data"],
-                    )
-                )
-                return models
-        return models
-    else:
-        url = app.state.config.OPENAI_API_BASE_URLS[url_idx]
-        key = app.state.config.OPENAI_API_KEYS[url_idx]
-
-        headers = {}
-        headers["Authorization"] = f"Bearer {key}"
-        headers["Content-Type"] = "application/json"
-
-        r = None
-
-        try:
-            r = requests.request(method="GET", url=f"{url}/models", headers=headers)
-            r.raise_for_status()
-
-            response_data = r.json()
-
-            if "api.openai.com" in url:
-                # Filter the response data
-                response_data["data"] = [
-                    model
-                    for model in response_data["data"]
-                    if not any(
-                        name in model["id"]
-                        for name in [
-                            "babbage",
-                            "dall-e",
-                            "davinci",
-                            "embedding",
-                            "tts",
-                            "whisper",
-                        ]
-                    )
-                ]
-
-            return response_data
-        except Exception as e:
-            log.exception(e)
-            error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
-                    if "error" in res:
-                        error_detail = f"External: {res['error']}"
-                except Exception:
-                    error_detail = f"External: {e}"
-
-            raise HTTPException(
-                status_code=r.status_code if r else 500,
-                detail=error_detail,
-            )
-
-
-@app.post("/chat/completions")
-@app.post("/chat/completions/{url_idx}")
-async def generate_chat_completion(
-    form_data: dict,
-    url_idx: Optional[int] = None,
-    user=Depends(get_verified_user),
-):
-    idx = 0
-    payload = {**form_data}
-
-    if "metadata" in payload:
-        del payload["metadata"]
-
-    model_id = form_data.get("model")
-    model_info = Models.get_model_by_id(model_id)
-
-    if model_info:
-        if model_info.base_model_id:
-            payload["model"] = model_info.base_model_id
-
-        params = model_info.params.model_dump()
-        payload = apply_model_params_to_body_openai(params, payload)
-        payload = apply_model_system_prompt_to_body(params, payload, user)
-
-    model = app.state.MODELS[payload.get("model")]
-    idx = model["urlIdx"]
-
-    if "pipeline" in model and model.get("pipeline"):
-        payload["user"] = {
-            "name": user.name,
-            "id": user.id,
-            "email": user.email,
-            "role": user.role,
-        }
-
-    url = app.state.config.OPENAI_API_BASE_URLS[idx]
-    key = app.state.config.OPENAI_API_KEYS[idx]
-
-    # Change max_completion_tokens to max_tokens (Backward compatible)
-    if "api.openai.com" not in url and not payload["model"].lower().startswith("o1-"):
-        if "max_completion_tokens" in payload:
-            # Remove "max_completion_tokens" from the payload
-            payload["max_tokens"] = payload["max_completion_tokens"]
-            del payload["max_completion_tokens"]
-    else:
-        if payload["model"].lower().startswith("o1-") and "max_tokens" in payload:
-            payload["max_completion_tokens"] = payload["max_tokens"]
-            del payload["max_tokens"]
-        if "max_tokens" in payload and "max_completion_tokens" in payload:
-            del payload["max_tokens"]
-
-    # Convert the modified body back to JSON
-    payload = json.dumps(payload)
-
-    log.debug(payload)
-
-    headers = {}
-    headers["Authorization"] = f"Bearer {key}"
-    headers["Content-Type"] = "application/json"
-    if "openrouter.ai" in app.state.config.OPENAI_API_BASE_URLS[idx]:
-        headers["HTTP-Referer"] = "https://openwebui.com/"
-        headers["X-Title"] = "Open WebUI"
-
-    r = None
-    session = None
-    streaming = False
-    response = None
-
-    try:
-        session = aiohttp.ClientSession(
-            trust_env=True, timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
-        )
-        r = await session.request(
-            method="POST",
-            url=f"{url}/chat/completions",
-            data=payload,
-            headers=headers,
-        )
-
-        # Check if response is SSE
-        if "text/event-stream" in r.headers.get("Content-Type", ""):
-            streaming = True
-            return StreamingResponse(
-                r.content,
-                status_code=r.status,
-                headers=dict(r.headers),
-                background=BackgroundTask(
-                    cleanup_response, response=r, session=session
-                ),
-            )
-        else:
-            try:
-                response = await r.json()
-            except Exception as e:
-                log.error(e)
-                response = await r.text()
-
-            r.raise_for_status()
-            return response
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if isinstance(response, dict):
-            if "error" in response:
-                error_detail = f"{response['error']['message'] if 'message' in response['error'] else response['error']}"
-        elif isinstance(response, str):
-            error_detail = response
-
-        raise HTTPException(status_code=r.status if r else 500, detail=error_detail)
-    finally:
-        if not streaming and session:
-            if r:
-                r.close()
-            await session.close()
-
-
-@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
-async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
-    idx = 0
-
-    body = await request.body()
-
-    url = app.state.config.OPENAI_API_BASE_URLS[idx]
-    key = app.state.config.OPENAI_API_KEYS[idx]
-
-    target_url = f"{url}/{path}"
-
-    headers = {}
-    headers["Authorization"] = f"Bearer {key}"
-    headers["Content-Type"] = "application/json"
-
-    r = None
-    session = None
-    streaming = False
-
-    try:
-        session = aiohttp.ClientSession(trust_env=True)
-        r = await session.request(
-            method=request.method,
-            url=target_url,
-            data=body,
-            headers=headers,
-        )
-
-        r.raise_for_status()
-
-        # Check if response is SSE
-        if "text/event-stream" in r.headers.get("Content-Type", ""):
-            streaming = True
-            return StreamingResponse(
-                r.content,
-                status_code=r.status,
-                headers=dict(r.headers),
-                background=BackgroundTask(
-                    cleanup_response, response=r, session=session
-                ),
-            )
-        else:
-            response_data = await r.json()
-            return response_data
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = await r.json()
-                print(res)
-                if "error" in res:
-                    error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
-            except Exception:
-                error_detail = f"External: {e}"
-        raise HTTPException(status_code=r.status if r else 500, detail=error_detail)
-    finally:
-        if not streaming and session:
-            if r:
-                r.close()
-            await session.close()

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

@@ -1,10 +0,0 @@
-from open_webui.apps.rag.vector.dbs.chroma import ChromaClient
-from open_webui.apps.rag.vector.dbs.milvus import MilvusClient
-
-
-from open_webui.config import VECTOR_DB
-
-if VECTOR_DB == "milvus":
-    VECTOR_DB_CLIENT = MilvusClient()
-else:
-    VECTOR_DB_CLIENT = ChromaClient()

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

@@ -1,386 +0,0 @@
-import json
-import time
-import uuid
-from typing import Optional
-
-from open_webui.apps.webui.internal.db import Base, get_db
-from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Boolean, Column, String, Text
-
-####################
-# Chat DB Schema
-####################
-
-
-class Chat(Base):
-    __tablename__ = "chat"
-
-    id = Column(String, primary_key=True)
-    user_id = Column(String)
-    title = Column(Text)
-    chat = Column(Text)  # Save Chat JSON as Text
-
-    created_at = Column(BigInteger)
-    updated_at = Column(BigInteger)
-
-    share_id = Column(Text, unique=True, nullable=True)
-    archived = Column(Boolean, default=False)
-
-
-class ChatModel(BaseModel):
-    model_config = ConfigDict(from_attributes=True)
-
-    id: str
-    user_id: str
-    title: str
-    chat: str
-
-    created_at: int  # timestamp in epoch
-    updated_at: int  # timestamp in epoch
-
-    share_id: Optional[str] = None
-    archived: bool = False
-
-
-####################
-# Forms
-####################
-
-
-class ChatForm(BaseModel):
-    chat: dict
-
-
-class ChatTitleForm(BaseModel):
-    title: str
-
-
-class ChatResponse(BaseModel):
-    id: str
-    user_id: str
-    title: str
-    chat: dict
-    updated_at: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
-    share_id: Optional[str] = None  # id of the chat to be shared
-    archived: bool
-
-
-class ChatTitleIdResponse(BaseModel):
-    id: str
-    title: str
-    updated_at: int
-    created_at: int
-
-
-class ChatTable:
-    def insert_new_chat(self, user_id: str, form_data: ChatForm) -> Optional[ChatModel]:
-        with get_db() as db:
-            id = str(uuid.uuid4())
-            chat = ChatModel(
-                **{
-                    "id": id,
-                    "user_id": user_id,
-                    "title": (
-                        form_data.chat["title"]
-                        if "title" in form_data.chat
-                        else "New Chat"
-                    ),
-                    "chat": json.dumps(form_data.chat),
-                    "created_at": int(time.time()),
-                    "updated_at": int(time.time()),
-                }
-            )
-
-            result = Chat(**chat.model_dump())
-            db.add(result)
-            db.commit()
-            db.refresh(result)
-            return ChatModel.model_validate(result) if result else None
-
-    def update_chat_by_id(self, id: str, chat: dict) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                chat_obj = db.get(Chat, id)
-                chat_obj.chat = json.dumps(chat)
-                chat_obj.title = chat["title"] if "title" in chat else "New Chat"
-                chat_obj.updated_at = int(time.time())
-                db.commit()
-                db.refresh(chat_obj)
-
-                return ChatModel.model_validate(chat_obj)
-        except Exception:
-            return None
-
-    def insert_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
-        with get_db() as db:
-            # Get the existing chat to share
-            chat = db.get(Chat, chat_id)
-            # Check if the chat is already shared
-            if chat.share_id:
-                return self.get_chat_by_id_and_user_id(chat.share_id, "shared")
-            # Create a new chat with the same data, but with a new ID
-            shared_chat = ChatModel(
-                **{
-                    "id": str(uuid.uuid4()),
-                    "user_id": f"shared-{chat_id}",
-                    "title": chat.title,
-                    "chat": chat.chat,
-                    "created_at": chat.created_at,
-                    "updated_at": int(time.time()),
-                }
-            )
-            shared_result = Chat(**shared_chat.model_dump())
-            db.add(shared_result)
-            db.commit()
-            db.refresh(shared_result)
-
-            # Update the original chat with the share_id
-            result = (
-                db.query(Chat)
-                .filter_by(id=chat_id)
-                .update({"share_id": shared_chat.id})
-            )
-            db.commit()
-            return shared_chat if (shared_result and result) else None
-
-    def update_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                print("update_shared_chat_by_id")
-                chat = db.get(Chat, chat_id)
-                print(chat)
-                chat.title = chat.title
-                chat.chat = chat.chat
-                db.commit()
-                db.refresh(chat)
-
-                return self.get_chat_by_id(chat.share_id)
-        except Exception:
-            return None
-
-    def delete_shared_chat_by_chat_id(self, chat_id: str) -> bool:
-        try:
-            with get_db() as db:
-                db.query(Chat).filter_by(user_id=f"shared-{chat_id}").delete()
-                db.commit()
-
-                return True
-        except Exception:
-            return False
-
-    def update_chat_share_id_by_id(
-        self, id: str, share_id: Optional[str]
-    ) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                chat = db.get(Chat, id)
-                chat.share_id = share_id
-                db.commit()
-                db.refresh(chat)
-                return ChatModel.model_validate(chat)
-        except Exception:
-            return None
-
-    def toggle_chat_archive_by_id(self, id: str) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                chat = db.get(Chat, id)
-                chat.archived = not chat.archived
-                db.commit()
-                db.refresh(chat)
-                return ChatModel.model_validate(chat)
-        except Exception:
-            return None
-
-    def archive_all_chats_by_user_id(self, user_id: str) -> bool:
-        try:
-            with get_db() as db:
-                db.query(Chat).filter_by(user_id=user_id).update({"archived": True})
-                db.commit()
-                return True
-        except Exception:
-            return False
-
-    def get_archived_chat_list_by_user_id(
-        self, user_id: str, skip: int = 0, limit: int = 50
-    ) -> list[ChatModel]:
-        with get_db() as db:
-            all_chats = (
-                db.query(Chat)
-                .filter_by(user_id=user_id, archived=True)
-                .order_by(Chat.updated_at.desc())
-                # .limit(limit).offset(skip)
-                .all()
-            )
-            return [ChatModel.model_validate(chat) for chat in all_chats]
-
-    def get_chat_list_by_user_id(
-        self,
-        user_id: str,
-        include_archived: bool = False,
-        skip: int = 0,
-        limit: int = 50,
-    ) -> list[ChatModel]:
-        with get_db() as db:
-            query = db.query(Chat).filter_by(user_id=user_id)
-            if not include_archived:
-                query = query.filter_by(archived=False)
-            all_chats = (
-                query.order_by(Chat.updated_at.desc())
-                # .limit(limit).offset(skip)
-                .all()
-            )
-            return [ChatModel.model_validate(chat) for chat in all_chats]
-
-    def get_chat_title_id_list_by_user_id(
-        self,
-        user_id: str,
-        include_archived: bool = False,
-        skip: Optional[int] = None,
-        limit: Optional[int] = None,
-    ) -> list[ChatTitleIdResponse]:
-        with get_db() as db:
-            query = db.query(Chat).filter_by(user_id=user_id)
-            if not include_archived:
-                query = query.filter_by(archived=False)
-
-            query = query.order_by(Chat.updated_at.desc()).with_entities(
-                Chat.id, Chat.title, Chat.updated_at, Chat.created_at
-            )
-
-            if limit:
-                query = query.limit(limit)
-            if skip:
-                query = query.offset(skip)
-
-            all_chats = query.all()
-
-            # result has to be destrctured from sqlalchemy `row` and mapped to a dict since the `ChatModel`is not the returned dataclass.
-            return [
-                ChatTitleIdResponse.model_validate(
-                    {
-                        "id": chat[0],
-                        "title": chat[1],
-                        "updated_at": chat[2],
-                        "created_at": chat[3],
-                    }
-                )
-                for chat in all_chats
-            ]
-
-    def get_chat_list_by_chat_ids(
-        self, chat_ids: list[str], skip: int = 0, limit: int = 50
-    ) -> list[ChatModel]:
-        with get_db() as db:
-            all_chats = (
-                db.query(Chat)
-                .filter(Chat.id.in_(chat_ids))
-                .filter_by(archived=False)
-                .order_by(Chat.updated_at.desc())
-                .all()
-            )
-            return [ChatModel.model_validate(chat) for chat in all_chats]
-
-    def get_chat_by_id(self, id: str) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                chat = db.get(Chat, id)
-                return ChatModel.model_validate(chat)
-        except Exception:
-            return None
-
-    def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                chat = db.query(Chat).filter_by(share_id=id).first()
-
-                if chat:
-                    return self.get_chat_by_id(id)
-                else:
-                    return None
-        except Exception:
-            return None
-
-    def get_chat_by_id_and_user_id(self, id: str, user_id: str) -> Optional[ChatModel]:
-        try:
-            with get_db() as db:
-                chat = db.query(Chat).filter_by(id=id, user_id=user_id).first()
-                return ChatModel.model_validate(chat)
-        except Exception:
-            return None
-
-    def get_chats(self, skip: int = 0, limit: int = 50) -> list[ChatModel]:
-        with get_db() as db:
-            all_chats = (
-                db.query(Chat)
-                # .limit(limit).offset(skip)
-                .order_by(Chat.updated_at.desc())
-            )
-            return [ChatModel.model_validate(chat) for chat in all_chats]
-
-    def get_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
-        with get_db() as db:
-            all_chats = (
-                db.query(Chat)
-                .filter_by(user_id=user_id)
-                .order_by(Chat.updated_at.desc())
-            )
-            return [ChatModel.model_validate(chat) for chat in all_chats]
-
-    def get_archived_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
-        with get_db() as db:
-            all_chats = (
-                db.query(Chat)
-                .filter_by(user_id=user_id, archived=True)
-                .order_by(Chat.updated_at.desc())
-            )
-            return [ChatModel.model_validate(chat) for chat in all_chats]
-
-    def delete_chat_by_id(self, id: str) -> bool:
-        try:
-            with get_db() as db:
-                db.query(Chat).filter_by(id=id).delete()
-                db.commit()
-
-                return True and self.delete_shared_chat_by_chat_id(id)
-        except Exception:
-            return False
-
-    def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
-        try:
-            with get_db() as db:
-                db.query(Chat).filter_by(id=id, user_id=user_id).delete()
-                db.commit()
-
-                return True and self.delete_shared_chat_by_chat_id(id)
-        except Exception:
-            return False
-
-    def delete_chats_by_user_id(self, user_id: str) -> bool:
-        try:
-            with get_db() as db:
-                self.delete_shared_chats_by_user_id(user_id)
-
-                db.query(Chat).filter_by(user_id=user_id).delete()
-                db.commit()
-
-                return True
-        except Exception:
-            return False
-
-    def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
-        try:
-            with get_db() as db:
-                chats_by_user = db.query(Chat).filter_by(user_id=user_id).all()
-                shared_chat_ids = [f"shared-{chat.id}" for chat in chats_by_user]
-
-                db.query(Chat).filter(Chat.user_id.in_(shared_chat_ids)).delete()
-                db.commit()
-
-                return True
-        except Exception:
-            return False
-
-
-Chats = ChatTable()

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

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

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

@@ -1,121 +0,0 @@
-import logging
-import time
-from typing import Optional
-
-from open_webui.apps.webui.internal.db import Base, JSONField, get_db
-from open_webui.env import SRC_LOG_LEVELS
-from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
-####################
-# Files DB Schema
-####################
-
-
-class File(Base):
-    __tablename__ = "file"
-
-    id = Column(String, primary_key=True)
-    user_id = Column(String)
-    filename = Column(Text)
-    meta = Column(JSONField)
-    created_at = Column(BigInteger)
-
-
-class FileModel(BaseModel):
-    id: str
-    user_id: str
-    filename: str
-    meta: dict
-    created_at: int  # timestamp in epoch
-
-    model_config = ConfigDict(from_attributes=True)
-
-
-####################
-# Forms
-####################
-
-
-class FileModelResponse(BaseModel):
-    id: str
-    user_id: str
-    filename: str
-    meta: dict
-    created_at: int  # timestamp in epoch
-
-
-class FileForm(BaseModel):
-    id: str
-    filename: str
-    meta: dict = {}
-
-
-class FilesTable:
-    def insert_new_file(self, user_id: str, form_data: FileForm) -> Optional[FileModel]:
-        with get_db() as db:
-            file = FileModel(
-                **{
-                    **form_data.model_dump(),
-                    "user_id": user_id,
-                    "created_at": int(time.time()),
-                }
-            )
-
-            try:
-                result = File(**file.model_dump())
-                db.add(result)
-                db.commit()
-                db.refresh(result)
-                if result:
-                    return FileModel.model_validate(result)
-                else:
-                    return None
-            except Exception as e:
-                print(f"Error creating tool: {e}")
-                return None
-
-    def get_file_by_id(self, id: str) -> Optional[FileModel]:
-        with get_db() as db:
-            try:
-                file = db.get(File, id)
-                return FileModel.model_validate(file)
-            except Exception:
-                return None
-
-    def get_files(self) -> list[FileModel]:
-        with get_db() as db:
-            return [FileModel.model_validate(file) for file in db.query(File).all()]
-
-    def get_files_by_user_id(self, user_id: str) -> list[FileModel]:
-        with get_db() as db:
-            return [
-                FileModel.model_validate(file)
-                for file in db.query(File).filter_by(user_id=user_id).all()
-            ]
-
-    def delete_file_by_id(self, id: str) -> bool:
-        with get_db() as db:
-            try:
-                db.query(File).filter_by(id=id).delete()
-                db.commit()
-
-                return True
-            except Exception:
-                return False
-
-    def delete_all_files(self) -> bool:
-        with get_db() as db:
-            try:
-                db.query(File).delete()
-                db.commit()
-
-                return True
-            except Exception:
-                return False
-
-
-Files = FilesTable()

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

@@ -1,262 +0,0 @@
-import logging
-import time
-import uuid
-from typing import Optional
-
-from open_webui.apps.webui.internal.db import Base, get_db
-from open_webui.env import SRC_LOG_LEVELS
-from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
-####################
-# Tag DB Schema
-####################
-
-
-class Tag(Base):
-    __tablename__ = "tag"
-
-    id = Column(String, primary_key=True)
-    name = Column(String)
-    user_id = Column(String)
-    data = Column(Text, nullable=True)
-
-
-class ChatIdTag(Base):
-    __tablename__ = "chatidtag"
-
-    id = Column(String, primary_key=True)
-    tag_name = Column(String)
-    chat_id = Column(String)
-    user_id = Column(String)
-    timestamp = Column(BigInteger)
-
-
-class TagModel(BaseModel):
-    id: str
-    name: str
-    user_id: str
-    data: Optional[str] = None
-
-    model_config = ConfigDict(from_attributes=True)
-
-
-class ChatIdTagModel(BaseModel):
-    id: str
-    tag_name: str
-    chat_id: str
-    user_id: str
-    timestamp: int
-
-    model_config = ConfigDict(from_attributes=True)
-
-
-####################
-# Forms
-####################
-
-
-class ChatIdTagForm(BaseModel):
-    tag_name: str
-    chat_id: str
-
-
-class TagChatIdsResponse(BaseModel):
-    chat_ids: list[str]
-
-
-class ChatTagsResponse(BaseModel):
-    tags: list[str]
-
-
-class TagTable:
-    def insert_new_tag(self, name: str, user_id: str) -> Optional[TagModel]:
-        with get_db() as db:
-            id = str(uuid.uuid4())
-            tag = TagModel(**{"id": id, "user_id": user_id, "name": name})
-            try:
-                result = Tag(**tag.model_dump())
-                db.add(result)
-                db.commit()
-                db.refresh(result)
-                if result:
-                    return TagModel.model_validate(result)
-                else:
-                    return None
-            except Exception:
-                return None
-
-    def get_tag_by_name_and_user_id(
-        self, name: str, user_id: str
-    ) -> Optional[TagModel]:
-        try:
-            with get_db() as db:
-                tag = db.query(Tag).filter_by(name=name, user_id=user_id).first()
-                return TagModel.model_validate(tag)
-        except Exception:
-            return None
-
-    def add_tag_to_chat(
-        self, user_id: str, form_data: ChatIdTagForm
-    ) -> Optional[ChatIdTagModel]:
-        tag = self.get_tag_by_name_and_user_id(form_data.tag_name, user_id)
-        if tag is None:
-            tag = self.insert_new_tag(form_data.tag_name, user_id)
-
-        id = str(uuid.uuid4())
-        chatIdTag = ChatIdTagModel(
-            **{
-                "id": id,
-                "user_id": user_id,
-                "chat_id": form_data.chat_id,
-                "tag_name": tag.name,
-                "timestamp": int(time.time()),
-            }
-        )
-        try:
-            with get_db() as db:
-                result = ChatIdTag(**chatIdTag.model_dump())
-                db.add(result)
-                db.commit()
-                db.refresh(result)
-                if result:
-                    return ChatIdTagModel.model_validate(result)
-                else:
-                    return None
-        except Exception:
-            return None
-
-    def get_tags_by_user_id(self, user_id: str) -> list[TagModel]:
-        with get_db() as db:
-            tag_names = [
-                chat_id_tag.tag_name
-                for chat_id_tag in (
-                    db.query(ChatIdTag)
-                    .filter_by(user_id=user_id)
-                    .order_by(ChatIdTag.timestamp.desc())
-                    .all()
-                )
-            ]
-
-            return [
-                TagModel.model_validate(tag)
-                for tag in (
-                    db.query(Tag)
-                    .filter_by(user_id=user_id)
-                    .filter(Tag.name.in_(tag_names))
-                    .all()
-                )
-            ]
-
-    def get_tags_by_chat_id_and_user_id(
-        self, chat_id: str, user_id: str
-    ) -> list[TagModel]:
-        with get_db() as db:
-            tag_names = [
-                chat_id_tag.tag_name
-                for chat_id_tag in (
-                    db.query(ChatIdTag)
-                    .filter_by(user_id=user_id, chat_id=chat_id)
-                    .order_by(ChatIdTag.timestamp.desc())
-                    .all()
-                )
-            ]
-
-            return [
-                TagModel.model_validate(tag)
-                for tag in (
-                    db.query(Tag)
-                    .filter_by(user_id=user_id)
-                    .filter(Tag.name.in_(tag_names))
-                    .all()
-                )
-            ]
-
-    def get_chat_ids_by_tag_name_and_user_id(
-        self, tag_name: str, user_id: str
-    ) -> list[ChatIdTagModel]:
-        with get_db() as db:
-            return [
-                ChatIdTagModel.model_validate(chat_id_tag)
-                for chat_id_tag in (
-                    db.query(ChatIdTag)
-                    .filter_by(user_id=user_id, tag_name=tag_name)
-                    .order_by(ChatIdTag.timestamp.desc())
-                    .all()
-                )
-            ]
-
-    def count_chat_ids_by_tag_name_and_user_id(
-        self, tag_name: str, user_id: str
-    ) -> int:
-        with get_db() as db:
-            return (
-                db.query(ChatIdTag)
-                .filter_by(tag_name=tag_name, user_id=user_id)
-                .count()
-            )
-
-    def delete_tag_by_tag_name_and_user_id(self, tag_name: str, user_id: str) -> bool:
-        try:
-            with get_db() as db:
-                res = (
-                    db.query(ChatIdTag)
-                    .filter_by(tag_name=tag_name, user_id=user_id)
-                    .delete()
-                )
-                log.debug(f"res: {res}")
-                db.commit()
-
-                tag_count = self.count_chat_ids_by_tag_name_and_user_id(
-                    tag_name, user_id
-                )
-                if tag_count == 0:
-                    # Remove tag item from Tag col as well
-                    db.query(Tag).filter_by(name=tag_name, user_id=user_id).delete()
-                    db.commit()
-                return True
-        except Exception as e:
-            log.error(f"delete_tag: {e}")
-            return False
-
-    def delete_tag_by_tag_name_and_chat_id_and_user_id(
-        self, tag_name: str, chat_id: str, user_id: str
-    ) -> bool:
-        try:
-            with get_db() as db:
-                res = (
-                    db.query(ChatIdTag)
-                    .filter_by(tag_name=tag_name, chat_id=chat_id, user_id=user_id)
-                    .delete()
-                )
-                log.debug(f"res: {res}")
-                db.commit()
-
-                tag_count = self.count_chat_ids_by_tag_name_and_user_id(
-                    tag_name, user_id
-                )
-                if tag_count == 0:
-                    # Remove tag item from Tag col as well
-                    db.query(Tag).filter_by(name=tag_name, user_id=user_id).delete()
-                    db.commit()
-
-                return True
-        except Exception as e:
-            log.error(f"delete_tag: {e}")
-            return False
-
-    def delete_tags_by_chat_id_and_user_id(self, chat_id: str, user_id: str) -> bool:
-        tags = self.get_tags_by_chat_id_and_user_id(chat_id, user_id)
-
-        for tag in tags:
-            self.delete_tag_by_tag_name_and_chat_id_and_user_id(
-                tag.tag_name, chat_id, user_id
-            )
-
-        return True
-
-
-Tags = TagTable()

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

@@ -1,432 +0,0 @@
-import re
-import uuid
-
-from open_webui.apps.webui.models.auths import (
-    AddUserForm,
-    ApiKey,
-    Auths,
-    SigninForm,
-    SigninResponse,
-    SignupForm,
-    UpdatePasswordForm,
-    UpdateProfileForm,
-    UserResponse,
-)
-from open_webui.apps.webui.models.users import Users
-from open_webui.config import WEBUI_AUTH
-from open_webui.constants import ERROR_MESSAGES, WEBHOOK_MESSAGES
-from open_webui.env import (
-    WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
-    WEBUI_AUTH_TRUSTED_NAME_HEADER,
-)
-from fastapi import APIRouter, Depends, HTTPException, Request, status
-from fastapi.responses import Response
-from pydantic import BaseModel
-from open_webui.utils.misc import parse_duration, validate_email_format
-from open_webui.utils.utils import (
-    create_api_key,
-    create_token,
-    get_admin_user,
-    get_current_user,
-    get_password_hash,
-)
-from open_webui.utils.webhook import post_webhook
-
-router = APIRouter()
-
-############################
-# GetSessionUser
-############################
-
-
-@router.get("/", response_model=UserResponse)
-async def get_session_user(
-    request: Request, response: Response, user=Depends(get_current_user)
-):
-    token = create_token(
-        data={"id": user.id},
-        expires_delta=parse_duration(request.app.state.config.JWT_EXPIRES_IN),
-    )
-
-    # Set the cookie token
-    response.set_cookie(
-        key="token",
-        value=token,
-        httponly=True,  # Ensures the cookie is not accessible via JavaScript
-    )
-
-    return {
-        "id": user.id,
-        "email": user.email,
-        "name": user.name,
-        "role": user.role,
-        "profile_image_url": user.profile_image_url,
-    }
-
-
-############################
-# Update Profile
-############################
-
-
-@router.post("/update/profile", response_model=UserResponse)
-async def update_profile(
-    form_data: UpdateProfileForm, session_user=Depends(get_current_user)
-):
-    if session_user:
-        user = Users.update_user_by_id(
-            session_user.id,
-            {"profile_image_url": form_data.profile_image_url, "name": form_data.name},
-        )
-        if user:
-            return user
-        else:
-            raise HTTPException(400, detail=ERROR_MESSAGES.DEFAULT())
-    else:
-        raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
-
-
-############################
-# Update Password
-############################
-
-
-@router.post("/update/password", response_model=bool)
-async def update_password(
-    form_data: UpdatePasswordForm, session_user=Depends(get_current_user)
-):
-    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
-        raise HTTPException(400, detail=ERROR_MESSAGES.ACTION_PROHIBITED)
-    if session_user:
-        user = Auths.authenticate_user(session_user.email, form_data.password)
-
-        if user:
-            hashed = get_password_hash(form_data.new_password)
-            return Auths.update_user_password_by_id(user.id, hashed)
-        else:
-            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_PASSWORD)
-    else:
-        raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
-
-
-############################
-# SignIn
-############################
-
-
-@router.post("/signin", response_model=SigninResponse)
-async def signin(request: Request, response: Response, form_data: SigninForm):
-    if WEBUI_AUTH_TRUSTED_EMAIL_HEADER:
-        if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers:
-            raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_TRUSTED_HEADER)
-
-        trusted_email = request.headers[WEBUI_AUTH_TRUSTED_EMAIL_HEADER].lower()
-        trusted_name = trusted_email
-        if WEBUI_AUTH_TRUSTED_NAME_HEADER:
-            trusted_name = request.headers.get(
-                WEBUI_AUTH_TRUSTED_NAME_HEADER, trusted_email
-            )
-        if not Users.get_user_by_email(trusted_email.lower()):
-            await signup(
-                request,
-                response,
-                SignupForm(
-                    email=trusted_email, password=str(uuid.uuid4()), name=trusted_name
-                ),
-            )
-        user = Auths.authenticate_user_by_trusted_header(trusted_email)
-    elif WEBUI_AUTH == False:
-        admin_email = "admin@localhost"
-        admin_password = "admin"
-
-        if Users.get_user_by_email(admin_email.lower()):
-            user = Auths.authenticate_user(admin_email.lower(), admin_password)
-        else:
-            if Users.get_num_users() != 0:
-                raise HTTPException(400, detail=ERROR_MESSAGES.EXISTING_USERS)
-
-            await signup(
-                request,
-                response,
-                SignupForm(email=admin_email, password=admin_password, name="User"),
-            )
-
-            user = Auths.authenticate_user(admin_email.lower(), admin_password)
-    else:
-        user = Auths.authenticate_user(form_data.email.lower(), form_data.password)
-
-    if user:
-        token = create_token(
-            data={"id": user.id},
-            expires_delta=parse_duration(request.app.state.config.JWT_EXPIRES_IN),
-        )
-
-        # Set the cookie token
-        response.set_cookie(
-            key="token",
-            value=token,
-            httponly=True,  # Ensures the cookie is not accessible via JavaScript
-        )
-
-        return {
-            "token": token,
-            "token_type": "Bearer",
-            "id": user.id,
-            "email": user.email,
-            "name": user.name,
-            "role": user.role,
-            "profile_image_url": user.profile_image_url,
-        }
-    else:
-        raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
-
-
-############################
-# SignUp
-############################
-
-
-@router.post("/signup", response_model=SigninResponse)
-async def signup(request: Request, response: Response, form_data: SignupForm):
-    if WEBUI_AUTH:
-        if (
-            not request.app.state.config.ENABLE_SIGNUP
-            or not request.app.state.config.ENABLE_LOGIN_FORM
-        ):
-            raise HTTPException(
-                status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
-            )
-    else:
-        if Users.get_num_users() != 0:
-            raise HTTPException(
-                status.HTTP_403_FORBIDDEN, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
-            )
-
-    if not validate_email_format(form_data.email.lower()):
-        raise HTTPException(
-            status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
-        )
-
-    if Users.get_user_by_email(form_data.email.lower()):
-        raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
-
-    try:
-        role = (
-            "admin"
-            if Users.get_num_users() == 0
-            else request.app.state.config.DEFAULT_USER_ROLE
-        )
-        hashed = get_password_hash(form_data.password)
-        user = Auths.insert_new_auth(
-            form_data.email.lower(),
-            hashed,
-            form_data.name,
-            form_data.profile_image_url,
-            role,
-        )
-
-        if user:
-            token = create_token(
-                data={"id": user.id},
-                expires_delta=parse_duration(request.app.state.config.JWT_EXPIRES_IN),
-            )
-
-            # Set the cookie token
-            response.set_cookie(
-                key="token",
-                value=token,
-                httponly=True,  # Ensures the cookie is not accessible via JavaScript
-            )
-
-            if request.app.state.config.WEBHOOK_URL:
-                post_webhook(
-                    request.app.state.config.WEBHOOK_URL,
-                    WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
-                    {
-                        "action": "signup",
-                        "message": WEBHOOK_MESSAGES.USER_SIGNUP(user.name),
-                        "user": user.model_dump_json(exclude_none=True),
-                    },
-                )
-
-            return {
-                "token": token,
-                "token_type": "Bearer",
-                "id": user.id,
-                "email": user.email,
-                "name": user.name,
-                "role": user.role,
-                "profile_image_url": user.profile_image_url,
-            }
-        else:
-            raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_USER_ERROR)
-    except Exception as err:
-        raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
-
-
-############################
-# AddUser
-############################
-
-
-@router.post("/add", response_model=SigninResponse)
-async def add_user(form_data: AddUserForm, user=Depends(get_admin_user)):
-    if not validate_email_format(form_data.email.lower()):
-        raise HTTPException(
-            status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.INVALID_EMAIL_FORMAT
-        )
-
-    if Users.get_user_by_email(form_data.email.lower()):
-        raise HTTPException(400, detail=ERROR_MESSAGES.EMAIL_TAKEN)
-
-    try:
-        print(form_data)
-        hashed = get_password_hash(form_data.password)
-        user = Auths.insert_new_auth(
-            form_data.email.lower(),
-            hashed,
-            form_data.name,
-            form_data.profile_image_url,
-            form_data.role,
-        )
-
-        if user:
-            token = create_token(data={"id": user.id})
-            return {
-                "token": token,
-                "token_type": "Bearer",
-                "id": user.id,
-                "email": user.email,
-                "name": user.name,
-                "role": user.role,
-                "profile_image_url": user.profile_image_url,
-            }
-        else:
-            raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_USER_ERROR)
-    except Exception as err:
-        raise HTTPException(500, detail=ERROR_MESSAGES.DEFAULT(err))
-
-
-############################
-# GetAdminDetails
-############################
-
-
-@router.get("/admin/details")
-async def get_admin_details(request: Request, user=Depends(get_current_user)):
-    if request.app.state.config.SHOW_ADMIN_DETAILS:
-        admin_email = request.app.state.config.ADMIN_EMAIL
-        admin_name = None
-
-        print(admin_email, admin_name)
-
-        if admin_email:
-            admin = Users.get_user_by_email(admin_email)
-            if admin:
-                admin_name = admin.name
-        else:
-            admin = Users.get_first_user()
-            if admin:
-                admin_email = admin.email
-                admin_name = admin.name
-
-        return {
-            "name": admin_name,
-            "email": admin_email,
-        }
-    else:
-        raise HTTPException(400, detail=ERROR_MESSAGES.ACTION_PROHIBITED)
-
-
-############################
-# ToggleSignUp
-############################
-
-
-@router.get("/admin/config")
-async def get_admin_config(request: Request, user=Depends(get_admin_user)):
-    return {
-        "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
-        "ENABLE_SIGNUP": request.app.state.config.ENABLE_SIGNUP,
-        "DEFAULT_USER_ROLE": request.app.state.config.DEFAULT_USER_ROLE,
-        "JWT_EXPIRES_IN": request.app.state.config.JWT_EXPIRES_IN,
-        "ENABLE_COMMUNITY_SHARING": request.app.state.config.ENABLE_COMMUNITY_SHARING,
-        "ENABLE_MESSAGE_RATING": request.app.state.config.ENABLE_MESSAGE_RATING,
-    }
-
-
-class AdminConfig(BaseModel):
-    SHOW_ADMIN_DETAILS: bool
-    ENABLE_SIGNUP: bool
-    DEFAULT_USER_ROLE: str
-    JWT_EXPIRES_IN: str
-    ENABLE_COMMUNITY_SHARING: bool
-    ENABLE_MESSAGE_RATING: bool
-
-
-@router.post("/admin/config")
-async def update_admin_config(
-    request: Request, form_data: AdminConfig, user=Depends(get_admin_user)
-):
-    request.app.state.config.SHOW_ADMIN_DETAILS = form_data.SHOW_ADMIN_DETAILS
-    request.app.state.config.ENABLE_SIGNUP = form_data.ENABLE_SIGNUP
-
-    if form_data.DEFAULT_USER_ROLE in ["pending", "user", "admin"]:
-        request.app.state.config.DEFAULT_USER_ROLE = form_data.DEFAULT_USER_ROLE
-
-    pattern = r"^(-1|0|(-?\d+(\.\d+)?)(ms|s|m|h|d|w))$"
-
-    # Check if the input string matches the pattern
-    if re.match(pattern, form_data.JWT_EXPIRES_IN):
-        request.app.state.config.JWT_EXPIRES_IN = form_data.JWT_EXPIRES_IN
-
-    request.app.state.config.ENABLE_COMMUNITY_SHARING = (
-        form_data.ENABLE_COMMUNITY_SHARING
-    )
-    request.app.state.config.ENABLE_MESSAGE_RATING = form_data.ENABLE_MESSAGE_RATING
-
-    return {
-        "SHOW_ADMIN_DETAILS": request.app.state.config.SHOW_ADMIN_DETAILS,
-        "ENABLE_SIGNUP": request.app.state.config.ENABLE_SIGNUP,
-        "DEFAULT_USER_ROLE": request.app.state.config.DEFAULT_USER_ROLE,
-        "JWT_EXPIRES_IN": request.app.state.config.JWT_EXPIRES_IN,
-        "ENABLE_COMMUNITY_SHARING": request.app.state.config.ENABLE_COMMUNITY_SHARING,
-        "ENABLE_MESSAGE_RATING": request.app.state.config.ENABLE_MESSAGE_RATING,
-    }
-
-
-############################
-# API Key
-############################
-
-
-# create api key
-@router.post("/api_key", response_model=ApiKey)
-async def create_api_key_(user=Depends(get_current_user)):
-    api_key = create_api_key()
-    success = Users.update_user_api_key_by_id(user.id, api_key)
-    if success:
-        return {
-            "api_key": api_key,
-        }
-    else:
-        raise HTTPException(500, detail=ERROR_MESSAGES.CREATE_API_KEY_ERROR)
-
-
-# delete api key
-@router.delete("/api_key", response_model=bool)
-async def delete_api_key(user=Depends(get_current_user)):
-    success = Users.update_user_api_key_by_id(user.id, None)
-    return success
-
-
-# get api key
-@router.get("/api_key", response_model=ApiKey)
-async def get_api_key(user=Depends(get_current_user)):
-    api_key = Users.get_user_api_key_by_id(user.id)
-    if api_key:
-        return {
-            "api_key": api_key,
-        }
-    else:
-        raise HTTPException(404, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)

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

@@ -1,218 +0,0 @@
-import logging
-import os
-import shutil
-import uuid
-from pathlib import Path
-from typing import Optional
-
-from open_webui.apps.webui.models.files import FileForm, FileModel, Files
-from open_webui.config import UPLOAD_DIR
-from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
-from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
-from fastapi.responses import FileResponse
-from open_webui.utils.utils import get_admin_user, get_verified_user
-
-log = logging.getLogger(__name__)
-log.setLevel(SRC_LOG_LEVELS["MODELS"])
-
-
-router = APIRouter()
-
-############################
-# Upload File
-############################
-
-
-@router.post("/")
-def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
-    log.info(f"file.content_type: {file.content_type}")
-    try:
-        unsanitized_filename = file.filename
-        filename = os.path.basename(unsanitized_filename)
-
-        # replace filename with uuid
-        id = str(uuid.uuid4())
-        name = filename
-        filename = f"{id}_{filename}"
-        file_path = f"{UPLOAD_DIR}/{filename}"
-
-        contents = file.file.read()
-        with open(file_path, "wb") as f:
-            f.write(contents)
-            f.close()
-
-        file = Files.insert_new_file(
-            user.id,
-            FileForm(
-                **{
-                    "id": id,
-                    "filename": filename,
-                    "meta": {
-                        "name": name,
-                        "content_type": file.content_type,
-                        "size": len(contents),
-                        "path": file_path,
-                    },
-                }
-            ),
-        )
-
-        if file:
-            return file
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.DEFAULT("Error uploading file"),
-            )
-
-    except Exception as e:
-        log.exception(e)
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT(e),
-        )
-
-
-############################
-# List Files
-############################
-
-
-@router.get("/", response_model=list[FileModel])
-async def list_files(user=Depends(get_verified_user)):
-    if user.role == "admin":
-        files = Files.get_files()
-    else:
-        files = Files.get_files_by_user_id(user.id)
-    return files
-
-
-############################
-# Delete All Files
-############################
-
-
-@router.delete("/all")
-async def delete_all_files(user=Depends(get_admin_user)):
-    result = Files.delete_all_files()
-
-    if result:
-        folder = f"{UPLOAD_DIR}"
-        try:
-            # Check if the directory exists
-            if os.path.exists(folder):
-                # Iterate over all the files and directories in the specified directory
-                for filename in os.listdir(folder):
-                    file_path = os.path.join(folder, filename)
-                    try:
-                        if os.path.isfile(file_path) or os.path.islink(file_path):
-                            os.unlink(file_path)  # Remove the file or link
-                        elif os.path.isdir(file_path):
-                            shutil.rmtree(file_path)  # Remove the directory
-                    except Exception as e:
-                        print(f"Failed to delete {file_path}. Reason: {e}")
-            else:
-                print(f"The directory {folder} does not exist")
-        except Exception as e:
-            print(f"Failed to process the directory {folder}. Reason: {e}")
-
-        return {"message": "All files deleted successfully"}
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT("Error deleting files"),
-        )
-
-
-############################
-# Get File By Id
-############################
-
-
-@router.get("/{id}", response_model=Optional[FileModel])
-async def get_file_by_id(id: str, user=Depends(get_verified_user)):
-    file = Files.get_file_by_id(id)
-
-    if file and (file.user_id == user.id or user.role == "admin"):
-        return file
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-############################
-# Get File Content By Id
-############################
-
-
-@router.get("/{id}/content", response_model=Optional[FileModel])
-async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
-    file = Files.get_file_by_id(id)
-
-    if file and (file.user_id == user.id or user.role == "admin"):
-        file_path = Path(file.meta["path"])
-
-        # Check if the file already exists in the cache
-        if file_path.is_file():
-            print(f"file_path: {file_path}")
-            return FileResponse(file_path)
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-@router.get("/{id}/content/{file_name}", response_model=Optional[FileModel])
-async def get_file_content_by_id(id: str, user=Depends(get_verified_user)):
-    file = Files.get_file_by_id(id)
-
-    if file and (file.user_id == user.id or user.role == "admin"):
-        file_path = Path(file.meta["path"])
-
-        # Check if the file already exists in the cache
-        if file_path.is_file():
-            print(f"file_path: {file_path}")
-            return FileResponse(file_path)
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-############################
-# Delete File By Id
-############################
-
-
-@router.delete("/{id}")
-async def delete_file_by_id(id: str, user=Depends(get_verified_user)):
-    file = Files.get_file_by_id(id)
-    if file and (file.user_id == user.id or user.role == "admin"):
-        result = Files.delete_file_by_id(id)
-        if result:
-            return {"message": "File deleted successfully"}
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.DEFAULT("Error deleting file"),
-            )
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_404_NOT_FOUND,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )

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

@@ -1,104 +0,0 @@
-from typing import Optional
-
-from open_webui.apps.webui.models.models import (
-    ModelForm,
-    ModelModel,
-    ModelResponse,
-    Models,
-)
-from open_webui.constants import ERROR_MESSAGES
-from fastapi import APIRouter, Depends, HTTPException, Request, status
-from open_webui.utils.utils import get_admin_user, get_verified_user
-
-router = APIRouter()
-
-###########################
-# getModels
-###########################
-
-
-@router.get("/", response_model=list[ModelResponse])
-async def get_models(id: Optional[str] = None, user=Depends(get_verified_user)):
-    if id:
-        model = Models.get_model_by_id(id)
-        if model:
-            return [model]
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.NOT_FOUND,
-            )
-    else:
-        return Models.get_all_models()
-
-
-############################
-# AddNewModel
-############################
-
-
-@router.post("/add", response_model=Optional[ModelModel])
-async def add_new_model(
-    request: Request,
-    form_data: ModelForm,
-    user=Depends(get_admin_user),
-):
-    if form_data.id in request.app.state.MODELS:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.MODEL_ID_TAKEN,
-        )
-    else:
-        model = Models.insert_new_model(form_data, user.id)
-
-        if model:
-            return model
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.DEFAULT(),
-            )
-
-
-############################
-# UpdateModelById
-############################
-
-
-@router.post("/update", response_model=Optional[ModelModel])
-async def update_model_by_id(
-    request: Request,
-    id: str,
-    form_data: ModelForm,
-    user=Depends(get_admin_user),
-):
-    model = Models.get_model_by_id(id)
-    if model:
-        model = Models.update_model_by_id(id, form_data)
-        return model
-    else:
-        if form_data.id in request.app.state.MODELS:
-            model = Models.insert_new_model(form_data, user.id)
-            if model:
-                return model
-            else:
-                raise HTTPException(
-                    status_code=status.HTTP_401_UNAUTHORIZED,
-                    detail=ERROR_MESSAGES.DEFAULT(),
-                )
-        else:
-            raise HTTPException(
-                status_code=status.HTTP_401_UNAUTHORIZED,
-                detail=ERROR_MESSAGES.DEFAULT(),
-            )
-
-
-############################
-# DeleteModelById
-############################
-
-
-@router.delete("/delete", response_model=bool)
-async def delete_model_by_id(id: str, user=Depends(get_admin_user)):
-    result = Models.delete_model_by_id(id)
-    return result

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

@@ -1,90 +0,0 @@
-from typing import Optional
-
-from open_webui.apps.webui.models.prompts import PromptForm, PromptModel, Prompts
-from open_webui.constants import ERROR_MESSAGES
-from fastapi import APIRouter, Depends, HTTPException, status
-from open_webui.utils.utils import get_admin_user, get_verified_user
-
-router = APIRouter()
-
-############################
-# GetPrompts
-############################
-
-
-@router.get("/", response_model=list[PromptModel])
-async def get_prompts(user=Depends(get_verified_user)):
-    return Prompts.get_prompts()
-
-
-############################
-# CreateNewPrompt
-############################
-
-
-@router.post("/create", response_model=Optional[PromptModel])
-async def create_new_prompt(form_data: PromptForm, user=Depends(get_admin_user)):
-    prompt = Prompts.get_prompt_by_command(form_data.command)
-    if prompt is None:
-        prompt = Prompts.insert_new_prompt(user.id, form_data)
-
-        if prompt:
-            return prompt
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT(),
-        )
-    raise HTTPException(
-        status_code=status.HTTP_400_BAD_REQUEST,
-        detail=ERROR_MESSAGES.COMMAND_TAKEN,
-    )
-
-
-############################
-# GetPromptByCommand
-############################
-
-
-@router.get("/command/{command}", response_model=Optional[PromptModel])
-async def get_prompt_by_command(command: str, user=Depends(get_verified_user)):
-    prompt = Prompts.get_prompt_by_command(f"/{command}")
-
-    if prompt:
-        return prompt
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.NOT_FOUND,
-        )
-
-
-############################
-# UpdatePromptByCommand
-############################
-
-
-@router.post("/command/{command}/update", response_model=Optional[PromptModel])
-async def update_prompt_by_command(
-    command: str,
-    form_data: PromptForm,
-    user=Depends(get_admin_user),
-):
-    prompt = Prompts.update_prompt_by_command(f"/{command}", form_data)
-    if prompt:
-        return prompt
-    else:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-
-
-############################
-# DeletePromptByCommand
-############################
-
-
-@router.delete("/command/{command}/delete", response_model=bool)
-async def delete_prompt_by_command(command: str, user=Depends(get_admin_user)):
-    result = Prompts.delete_prompt_by_command(f"/{command}")
-    return result

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

@@ -1,140 +0,0 @@
-import site
-from pathlib import Path
-
-import black
-import markdown
-from open_webui.config import DATA_DIR, ENABLE_ADMIN_EXPORT
-from open_webui.env import FONTS_DIR
-from open_webui.constants import ERROR_MESSAGES
-from fastapi import APIRouter, Depends, HTTPException, Response, status
-from fpdf import FPDF
-from pydantic import BaseModel
-from starlette.responses import FileResponse
-from open_webui.utils.misc import get_gravatar_url
-from open_webui.utils.utils import get_admin_user
-
-router = APIRouter()
-
-
-@router.get("/gravatar")
-async def get_gravatar(
-    email: str,
-):
-    return get_gravatar_url(email)
-
-
-class CodeFormatRequest(BaseModel):
-    code: str
-
-
-@router.post("/code/format")
-async def format_code(request: CodeFormatRequest):
-    try:
-        formatted_code = black.format_str(request.code, mode=black.Mode())
-        return {"code": formatted_code}
-    except black.NothingChanged:
-        return {"code": request.code}
-    except Exception as e:
-        raise HTTPException(status_code=400, detail=str(e))
-
-
-class MarkdownForm(BaseModel):
-    md: str
-
-
-@router.post("/markdown")
-async def get_html_from_markdown(
-    form_data: MarkdownForm,
-):
-    return {"html": markdown.markdown(form_data.md)}
-
-
-class ChatForm(BaseModel):
-    title: str
-    messages: list[dict]
-
-
-@router.post("/pdf")
-async def download_chat_as_pdf(
-    form_data: ChatForm,
-):
-    global FONTS_DIR
-
-    pdf = FPDF()
-    pdf.add_page()
-
-    # When running using `pip install` the static directory is in the site packages.
-    if not FONTS_DIR.exists():
-        FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
-    # When running using `pip install -e .` the static directory is in the site packages.
-    # This path only works if `open-webui serve` is run from the root of this project.
-    if not FONTS_DIR.exists():
-        FONTS_DIR = Path("./backend/static/fonts")
-
-    pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
-    pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
-    pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
-    pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
-    pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
-    pdf.add_font("NotoSansSC", "", f"{FONTS_DIR}/NotoSansSC-Regular.ttf")
-
-    pdf.set_font("NotoSans", size=12)
-    pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP", "NotoSansSC"])
-
-    pdf.set_auto_page_break(auto=True, margin=15)
-
-    # Adjust the effective page width for multi_cell
-    effective_page_width = (
-        pdf.w - 2 * pdf.l_margin - 10
-    )  # Subtracted an additional 10 for extra padding
-
-    # Add chat messages
-    for message in form_data.messages:
-        role = message["role"]
-        content = message["content"]
-        pdf.set_font("NotoSans", "B", size=14)  # Bold for the role
-        pdf.multi_cell(effective_page_width, 10, f"{role.upper()}", 0, "L")
-        pdf.ln(1)  # Extra space between messages
-
-        pdf.set_font("NotoSans", size=10)  # Regular for content
-        pdf.multi_cell(effective_page_width, 6, content, 0, "L")
-        pdf.ln(1.5)  # Extra space between messages
-
-    # Save the pdf with name .pdf
-    pdf_bytes = pdf.output()
-
-    return Response(
-        content=bytes(pdf_bytes),
-        media_type="application/pdf",
-        headers={"Content-Disposition": "attachment;filename=chat.pdf"},
-    )
-
-
-@router.get("/db/download")
-async def download_db(user=Depends(get_admin_user)):
-    if not ENABLE_ADMIN_EXPORT:
-        raise HTTPException(
-            status_code=status.HTTP_401_UNAUTHORIZED,
-            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
-        )
-    from open_webui.apps.webui.internal.db import engine
-
-    if engine.name != "sqlite":
-        raise HTTPException(
-            status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DB_NOT_SQLITE,
-        )
-    return FileResponse(
-        engine.url.database,
-        media_type="application/octet-stream",
-        filename="webui.db",
-    )
-
-
-@router.get("/litellm/config")
-async def download_litellm_config_yaml(user=Depends(get_admin_user)):
-    return FileResponse(
-        f"{DATA_DIR}/litellm/config.yaml",
-        media_type="application/octet-stream",
-        filename="config.yaml",
-    )

backend/open_webui/config.py

@@ -10,7 +10,7 @@ from urllib.parse import urlparse
 import chromadb
 import requests
 import yaml
-from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.internal.db import Base, get_db
 from open_webui.env import (
     OPEN_WEBUI_DIR,
     DATA_DIR,
@@ -20,6 +20,8 @@ from open_webui.env import (
     WEBUI_FAVICON_URL,
     WEBUI_NAME,
     log,
+    DATABASE_URL,
+    OFFLINE_MODE,
 )
 from pydantic import BaseModel
 from sqlalchemy import JSON, Column, DateTime, Integer, func
@@ -264,6 +266,13 @@ class AppConfig:
 # WEBUI_AUTH (Required for security)
 ####################################
 
+ENABLE_API_KEY = PersistentConfig(
+    "ENABLE_API_KEY",
+    "auth.api_key.enable",
+    os.environ.get("ENABLE_API_KEY", "True").lower() == "true",
+)
+
+
 JWT_EXPIRES_IN = PersistentConfig(
     "JWT_EXPIRES_IN", "auth.jwt_expiry", os.environ.get("JWT_EXPIRES_IN", "-1")
 )
@@ -298,6 +307,18 @@ GOOGLE_CLIENT_SECRET = PersistentConfig(
     os.environ.get("GOOGLE_CLIENT_SECRET", ""),
 )
 
+GOOGLE_DRIVE_CLIENT_ID = PersistentConfig(
+    "GOOGLE_DRIVE_CLIENT_ID",
+    "google_drive.client_id",
+    os.environ.get("GOOGLE_DRIVE_CLIENT_ID", ""),
+)
+
+GOOGLE_DRIVE_API_KEY = PersistentConfig(
+    "GOOGLE_DRIVE_API_KEY",
+    "google_drive.api_key",
+    os.environ.get("GOOGLE_DRIVE_API_KEY", ""),
+)
+
 GOOGLE_OAUTH_SCOPE = PersistentConfig(
     "GOOGLE_OAUTH_SCOPE",
     "oauth.google.scope",
@@ -383,7 +404,7 @@ OAUTH_USERNAME_CLAIM = PersistentConfig(
 )
 
 OAUTH_PICTURE_CLAIM = PersistentConfig(
-    "OAUTH_USERNAME_CLAIM",
+    "OAUTH_PICTURE_CLAIM",
     "oauth.oidc.avatar_claim",
     os.environ.get("OAUTH_PICTURE_CLAIM", "picture"),
 )
@@ -394,6 +415,54 @@ OAUTH_EMAIL_CLAIM = PersistentConfig(
     os.environ.get("OAUTH_EMAIL_CLAIM", "email"),
 )
 
+OAUTH_GROUPS_CLAIM = PersistentConfig(
+    "OAUTH_GROUPS_CLAIM",
+    "oauth.oidc.group_claim",
+    os.environ.get("OAUTH_GROUP_CLAIM", "groups"),
+)
+
+ENABLE_OAUTH_ROLE_MANAGEMENT = PersistentConfig(
+    "ENABLE_OAUTH_ROLE_MANAGEMENT",
+    "oauth.enable_role_mapping",
+    os.environ.get("ENABLE_OAUTH_ROLE_MANAGEMENT", "False").lower() == "true",
+)
+
+ENABLE_OAUTH_GROUP_MANAGEMENT = PersistentConfig(
+    "ENABLE_OAUTH_GROUP_MANAGEMENT",
+    "oauth.enable_group_mapping",
+    os.environ.get("ENABLE_OAUTH_GROUP_MANAGEMENT", "False").lower() == "true",
+)
+
+OAUTH_ROLES_CLAIM = PersistentConfig(
+    "OAUTH_ROLES_CLAIM",
+    "oauth.roles_claim",
+    os.environ.get("OAUTH_ROLES_CLAIM", "roles"),
+)
+
+OAUTH_ALLOWED_ROLES = PersistentConfig(
+    "OAUTH_ALLOWED_ROLES",
+    "oauth.allowed_roles",
+    [
+        role.strip()
+        for role in os.environ.get("OAUTH_ALLOWED_ROLES", "user,admin").split(",")
+    ],
+)
+
+OAUTH_ADMIN_ROLES = PersistentConfig(
+    "OAUTH_ADMIN_ROLES",
+    "oauth.admin_roles",
+    [role.strip() for role in os.environ.get("OAUTH_ADMIN_ROLES", "admin").split(",")],
+)
+
+OAUTH_ALLOWED_DOMAINS = PersistentConfig(
+    "OAUTH_ALLOWED_DOMAINS",
+    "oauth.allowed_domains",
+    [
+        domain.strip()
+        for domain in os.environ.get("OAUTH_ALLOWED_DOMAINS", "*").split(",")
+    ],
+)
+
 
 def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
@@ -506,6 +575,18 @@ if CUSTOM_NAME:
         pass
 
 
+####################################
+# STORAGE PROVIDER
+####################################
+
+STORAGE_PROVIDER = os.environ.get("STORAGE_PROVIDER", "")  # defaults to local, s3
+
+S3_ACCESS_KEY_ID = os.environ.get("S3_ACCESS_KEY_ID", None)
+S3_SECRET_ACCESS_KEY = os.environ.get("S3_SECRET_ACCESS_KEY", None)
+S3_REGION_NAME = os.environ.get("S3_REGION_NAME", None)
+S3_BUCKET_NAME = os.environ.get("S3_BUCKET_NAME", None)
+S3_ENDPOINT_URL = os.environ.get("S3_ENDPOINT_URL", None)
+
 ####################################
 # File Upload DIR
 ####################################
@@ -521,35 +602,10 @@ Path(UPLOAD_DIR).mkdir(parents=True, exist_ok=True)
 CACHE_DIR = f"{DATA_DIR}/cache"
 Path(CACHE_DIR).mkdir(parents=True, exist_ok=True)
 
-
-####################################
-# Docs DIR
-####################################
-
-DOCS_DIR = os.getenv("DOCS_DIR", f"{DATA_DIR}/docs")
-Path(DOCS_DIR).mkdir(parents=True, exist_ok=True)
-
-
-####################################
-# Tools DIR
-####################################
-
-TOOLS_DIR = os.getenv("TOOLS_DIR", f"{DATA_DIR}/tools")
-Path(TOOLS_DIR).mkdir(parents=True, exist_ok=True)
-
-
-####################################
-# Functions DIR
-####################################
-
-FUNCTIONS_DIR = os.getenv("FUNCTIONS_DIR", f"{DATA_DIR}/functions")
-Path(FUNCTIONS_DIR).mkdir(parents=True, exist_ok=True)
-
 ####################################
 # OLLAMA_BASE_URL
 ####################################
 
-
 ENABLE_OLLAMA_API = PersistentConfig(
     "ENABLE_OLLAMA_API",
     "ollama.enable",
@@ -561,15 +617,11 @@ OLLAMA_API_BASE_URL = os.environ.get(
 )
 
 OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
-AIOHTTP_CLIENT_TIMEOUT = os.environ.get("AIOHTTP_CLIENT_TIMEOUT", "")
-
-if AIOHTTP_CLIENT_TIMEOUT == "":
-    AIOHTTP_CLIENT_TIMEOUT = None
-else:
-    try:
-        AIOHTTP_CLIENT_TIMEOUT = int(AIOHTTP_CLIENT_TIMEOUT)
-    except Exception:
-        AIOHTTP_CLIENT_TIMEOUT = 300
+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", "")
@@ -602,6 +654,12 @@ OLLAMA_BASE_URLS = PersistentConfig(
     "OLLAMA_BASE_URLS", "ollama.base_urls", OLLAMA_BASE_URLS
 )
 
+OLLAMA_API_CONFIGS = PersistentConfig(
+    "OLLAMA_API_CONFIGS",
+    "ollama.api_configs",
+    {},
+)
+
 ####################################
 # OPENAI_API
 ####################################
@@ -642,21 +700,32 @@ OPENAI_API_BASE_URLS = PersistentConfig(
     "OPENAI_API_BASE_URLS", "openai.api_base_urls", OPENAI_API_BASE_URLS
 )
 
-OPENAI_API_KEY = ""
+OPENAI_API_CONFIGS = PersistentConfig(
+    "OPENAI_API_CONFIGS",
+    "openai.api_configs",
+    {},
+)
 
+# Get the actual OpenAI API key based on the base URL
+OPENAI_API_KEY = ""
 try:
     OPENAI_API_KEY = OPENAI_API_KEYS.value[
         OPENAI_API_BASE_URLS.value.index("https://api.openai.com/v1")
     ]
 except Exception:
     pass
-
 OPENAI_API_BASE_URL = "https://api.openai.com/v1"
 
 ####################################
 # WEBUI
 ####################################
 
+
+WEBUI_URL = PersistentConfig(
+    "WEBUI_URL", "webui.url", os.environ.get("WEBUI_URL", "http://localhost:3000")
+)
+
+
 ENABLE_SIGNUP = PersistentConfig(
     "ENABLE_SIGNUP",
     "ui.enable_signup",
@@ -673,6 +742,7 @@ ENABLE_LOGIN_FORM = PersistentConfig(
     os.environ.get("ENABLE_LOGIN_FORM", "True").lower() == "true",
 )
 
+
 DEFAULT_LOCALE = PersistentConfig(
     "DEFAULT_LOCALE",
     "ui.default_locale",
@@ -717,18 +787,47 @@ DEFAULT_PROMPT_SUGGESTIONS = PersistentConfig(
     ],
 )
 
+MODEL_ORDER_LIST = PersistentConfig(
+    "MODEL_ORDER_LIST",
+    "ui.model_order_list",
+    [],
+)
+
 DEFAULT_USER_ROLE = PersistentConfig(
     "DEFAULT_USER_ROLE",
     "ui.default_user_role",
     os.getenv("DEFAULT_USER_ROLE", "pending"),
 )
 
-USER_PERMISSIONS_CHAT_DELETION = (
-    os.environ.get("USER_PERMISSIONS_CHAT_DELETION", "True").lower() == "true"
+USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS", "False").lower()
+    == "true"
 )
 
-USER_PERMISSIONS_CHAT_EDITING = (
-    os.environ.get("USER_PERMISSIONS_CHAT_EDITING", "True").lower() == "true"
+USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS", "False").lower()
+    == "true"
+)
+
+USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS = (
+    os.environ.get("USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS", "False").lower() == "true"
+)
+
+USER_PERMISSIONS_CHAT_FILE_UPLOAD = (
+    os.environ.get("USER_PERMISSIONS_CHAT_FILE_UPLOAD", "True").lower() == "true"
+)
+
+USER_PERMISSIONS_CHAT_DELETE = (
+    os.environ.get("USER_PERMISSIONS_CHAT_DELETE", "True").lower() == "true"
+)
+
+USER_PERMISSIONS_CHAT_EDIT = (
+    os.environ.get("USER_PERMISSIONS_CHAT_EDIT", "True").lower() == "true"
 )
 
 USER_PERMISSIONS_CHAT_TEMPORARY = (
@@ -737,27 +836,50 @@ USER_PERMISSIONS_CHAT_TEMPORARY = (
 
 USER_PERMISSIONS = PersistentConfig(
     "USER_PERMISSIONS",
-    "ui.user_permissions",
+    "user.permissions",
     {
+        "workspace": {
+            "models": USER_PERMISSIONS_WORKSPACE_MODELS_ACCESS,
+            "knowledge": USER_PERMISSIONS_WORKSPACE_KNOWLEDGE_ACCESS,
+            "prompts": USER_PERMISSIONS_WORKSPACE_PROMPTS_ACCESS,
+            "tools": USER_PERMISSIONS_WORKSPACE_TOOLS_ACCESS,
+        },
         "chat": {
-            "deletion": USER_PERMISSIONS_CHAT_DELETION,
-            "editing": USER_PERMISSIONS_CHAT_EDITING,
+            "file_upload": USER_PERMISSIONS_CHAT_FILE_UPLOAD,
+            "delete": USER_PERMISSIONS_CHAT_DELETE,
+            "edit": USER_PERMISSIONS_CHAT_EDIT,
             "temporary": USER_PERMISSIONS_CHAT_TEMPORARY,
-        }
+        },
     },
 )
 
-ENABLE_MODEL_FILTER = PersistentConfig(
-    "ENABLE_MODEL_FILTER",
-    "model_filter.enable",
-    os.environ.get("ENABLE_MODEL_FILTER", "False").lower() == "true",
+ENABLE_CHANNELS = PersistentConfig(
+    "ENABLE_CHANNELS",
+    "channels.enable",
+    os.environ.get("ENABLE_CHANNELS", "False").lower() == "true",
 )
-MODEL_FILTER_LIST = os.environ.get("MODEL_FILTER_LIST", "")
-MODEL_FILTER_LIST = PersistentConfig(
-    "MODEL_FILTER_LIST",
-    "model_filter.list",
-    [model.strip() for model in MODEL_FILTER_LIST.split(";")],
+
+
+ENABLE_EVALUATION_ARENA_MODELS = PersistentConfig(
+    "ENABLE_EVALUATION_ARENA_MODELS",
+    "evaluation.arena.enable",
+    os.environ.get("ENABLE_EVALUATION_ARENA_MODELS", "True").lower() == "true",
 )
+EVALUATION_ARENA_MODELS = PersistentConfig(
+    "EVALUATION_ARENA_MODELS",
+    "evaluation.arena.models",
+    [],
+)
+
+DEFAULT_ARENA_MODEL = {
+    "id": "arena-model",
+    "name": "Arena Model",
+    "meta": {
+        "profile_image_url": "/favicon.png",
+        "description": "Submit your questions to anonymous AI chatbots and vote on the best response.",
+        "model_ids": None,
+    },
+}
 
 WEBHOOK_URL = PersistentConfig(
     "WEBHOOK_URL", "webhook_url", os.environ.get("WEBHOOK_URL", "")
@@ -872,19 +994,155 @@ TITLE_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
     os.environ.get("TITLE_GENERATION_PROMPT_TEMPLATE", ""),
 )
 
-ENABLE_SEARCH_QUERY = PersistentConfig(
-    "ENABLE_SEARCH_QUERY",
-    "task.search.enable",
-    os.environ.get("ENABLE_SEARCH_QUERY", "True").lower() == "true",
+DEFAULT_TITLE_GENERATION_PROMPT_TEMPLATE = """Create a concise, 3-5 word title with an emoji as a title for the chat history, in the given language. Suitable Emojis for the summary can be used to enhance understanding but avoid quotation marks or special formatting. RESPOND ONLY WITH THE TITLE TEXT.
+
+Examples of titles:
+📉 Stock Market Trends
+🍪 Perfect Chocolate Chip Recipe
+Evolution of Music Streaming
+Remote Work Productivity Tips
+Artificial Intelligence in Healthcare
+🎮 Video Game Development Insights
+
+<chat_history>
+{{MESSAGES:END:2}}
+</chat_history>"""
+
+
+TAGS_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "TAGS_GENERATION_PROMPT_TEMPLATE",
+    "task.tags.prompt_template",
+    os.environ.get("TAGS_GENERATION_PROMPT_TEMPLATE", ""),
+)
+
+DEFAULT_TAGS_GENERATION_PROMPT_TEMPLATE = """### Task:
+Generate 1-3 broad tags categorizing the main themes of the chat history, along with 1-3 more specific subtopic tags.
+
+### Guidelines:
+- Start with high-level domains (e.g. Science, Technology, Philosophy, Arts, Politics, Business, Health, Sports, Entertainment, Education)
+- Consider including relevant subfields/subdomains if they are strongly represented throughout the conversation
+- If content is too short (less than 3 messages) or too diverse, use only ["General"]
+- Use the chat's primary language; default to English if multilingual
+- Prioritize accuracy over specificity
+
+### Output:
+JSON format: { "tags": ["tag1", "tag2", "tag3"] }
+
+### Chat History:
+<chat_history>
+{{MESSAGES:END:6}}
+</chat_history>"""
+
+ENABLE_TAGS_GENERATION = PersistentConfig(
+    "ENABLE_TAGS_GENERATION",
+    "task.tags.enable",
+    os.environ.get("ENABLE_TAGS_GENERATION", "True").lower() == "true",
 )
 
 
-SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
-    "SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE",
-    "task.search.prompt_template",
-    os.environ.get("SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE", ""),
+ENABLE_SEARCH_QUERY_GENERATION = PersistentConfig(
+    "ENABLE_SEARCH_QUERY_GENERATION",
+    "task.query.search.enable",
+    os.environ.get("ENABLE_SEARCH_QUERY_GENERATION", "True").lower() == "true",
 )
 
+ENABLE_RETRIEVAL_QUERY_GENERATION = PersistentConfig(
+    "ENABLE_RETRIEVAL_QUERY_GENERATION",
+    "task.query.retrieval.enable",
+    os.environ.get("ENABLE_RETRIEVAL_QUERY_GENERATION", "True").lower() == "true",
+)
+
+
+QUERY_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "QUERY_GENERATION_PROMPT_TEMPLATE",
+    "task.query.prompt_template",
+    os.environ.get("QUERY_GENERATION_PROMPT_TEMPLATE", ""),
+)
+
+DEFAULT_QUERY_GENERATION_PROMPT_TEMPLATE = """### Task:
+Analyze the chat history to determine the necessity of generating search queries, 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. 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:
+Strictly return in JSON format: 
+{
+  "queries": ["query1", "query2"]
+}
+
+### Chat History:
+<chat_history>
+{{MESSAGES:END:6}}
+</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",
@@ -893,6 +1151,19 @@ TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
 )
 
 
+DEFAULT_TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = """Available Tools: {{TOOLS}}\nReturn an empty string if no tools match the query. If a function tool matches, construct and return a JSON object in the format {\"name\": \"functionName\", \"parameters\": {\"requiredFunctionParamKey\": \"requiredFunctionParamValue\"}} using the appropriate tool and its parameters. Only return the object and limit the response to the JSON object without additional text."""
+
+
+DEFAULT_EMOJI_GENERATION_PROMPT_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., 😊, 😢, 😡, 😱).
+
+Message: ```{{prompt}}```"""
+
+DEFAULT_MOA_GENERATION_PROMPT_TEMPLATE = """You have been provided with a set of responses from various models to the latest user query: "{{prompt}}"
+
+Your task is to synthesize these responses into a single, high-quality response. It is crucial to critically evaluate the information provided in these responses, recognizing that some of it may be biased or incorrect. Your response should not simply replicate the given answers but should offer a refined, accurate, and comprehensive reply to the instruction. Ensure your response is well-structured, coherent, and adheres to the highest standards of accuracy and reliability.
+
+Responses from models: {{responses}}"""
+
 ####################################
 # Vector Database
 ####################################
@@ -905,6 +1176,8 @@ CHROMA_TENANT = os.environ.get("CHROMA_TENANT", chromadb.DEFAULT_TENANT)
 CHROMA_DATABASE = os.environ.get("CHROMA_DATABASE", chromadb.DEFAULT_DATABASE)
 CHROMA_HTTP_HOST = os.environ.get("CHROMA_HTTP_HOST", "")
 CHROMA_HTTP_PORT = int(os.environ.get("CHROMA_HTTP_PORT", "8000"))
+CHROMA_CLIENT_AUTH_PROVIDER = os.environ.get("CHROMA_CLIENT_AUTH_PROVIDER", "")
+CHROMA_CLIENT_AUTH_CREDENTIALS = os.environ.get("CHROMA_CLIENT_AUTH_CREDENTIALS", "")
 # Comma-separated list of header=value pairs
 CHROMA_HTTP_HEADERS = os.environ.get("CHROMA_HTTP_HEADERS", "")
 if CHROMA_HTTP_HEADERS:
@@ -920,10 +1193,37 @@ CHROMA_HTTP_SSL = os.environ.get("CHROMA_HTTP_SSL", "false").lower() == "true"
 
 MILVUS_URI = os.environ.get("MILVUS_URI", f"{DATA_DIR}/vector_db/milvus.db")
 
+# Qdrant
+QDRANT_URI = os.environ.get("QDRANT_URI", None)
+QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY", None)
+
+# OpenSearch
+OPENSEARCH_URI = os.environ.get("OPENSEARCH_URI", "https://localhost:9200")
+OPENSEARCH_SSL = os.environ.get("OPENSEARCH_SSL", True)
+OPENSEARCH_CERT_VERIFY = os.environ.get("OPENSEARCH_CERT_VERIFY", False)
+OPENSEARCH_USERNAME = os.environ.get("OPENSEARCH_USERNAME", None)
+OPENSEARCH_PASSWORD = os.environ.get("OPENSEARCH_PASSWORD", None)
+
+# Pgvector
+PGVECTOR_DB_URL = os.environ.get("PGVECTOR_DB_URL", DATABASE_URL)
+if VECTOR_DB == "pgvector" and not PGVECTOR_DB_URL.startswith("postgres"):
+    raise ValueError(
+        "Pgvector requires setting PGVECTOR_DB_URL or using Postgres with vector extension as the primary database."
+    )
+
 ####################################
-# RAG
+# Information Retrieval (RAG)
 ####################################
 
+
+# If configured, Google Drive will be available as an upload option.
+ENABLE_GOOGLE_DRIVE_INTEGRATION = PersistentConfig(
+    "ENABLE_GOOGLE_DRIVE_INTEGRATION",
+    "google_drive.enable",
+    os.getenv("ENABLE_GOOGLE_DRIVE_INTEGRATION", "False").lower() == "true",
+)
+
+
 # RAG Content Extraction
 CONTENT_EXTRACTION_ENGINE = PersistentConfig(
     "CONTENT_EXTRACTION_ENGINE",
@@ -998,17 +1298,21 @@ RAG_EMBEDDING_MODEL = PersistentConfig(
 log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL.value}")
 
 RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
-    os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
+    not OFFLINE_MODE
+    and os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "True").lower() == "true"
 )
 
 RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE = (
-    os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
+    os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "True").lower() == "true"
 )
 
-RAG_EMBEDDING_OPENAI_BATCH_SIZE = PersistentConfig(
-    "RAG_EMBEDDING_OPENAI_BATCH_SIZE",
-    "rag.embedding_openai_batch_size",
-    int(os.environ.get("RAG_EMBEDDING_OPENAI_BATCH_SIZE", "1")),
+RAG_EMBEDDING_BATCH_SIZE = PersistentConfig(
+    "RAG_EMBEDDING_BATCH_SIZE",
+    "rag.embedding_batch_size",
+    int(
+        os.environ.get("RAG_EMBEDDING_BATCH_SIZE")
+        or os.environ.get("RAG_EMBEDDING_OPENAI_BATCH_SIZE", "1")
+    ),
 )
 
 RAG_RERANKING_MODEL = PersistentConfig(
@@ -1020,13 +1324,30 @@ if RAG_RERANKING_MODEL.value != "":
     log.info(f"Reranking model set: {RAG_RERANKING_MODEL.value}")
 
 RAG_RERANKING_MODEL_AUTO_UPDATE = (
-    os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "").lower() == "true"
+    not OFFLINE_MODE
+    and os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "True").lower() == "true"
 )
 
 RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
-    os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
+    os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "True").lower() == "true"
 )
 
+
+RAG_TEXT_SPLITTER = PersistentConfig(
+    "RAG_TEXT_SPLITTER",
+    "rag.text_splitter",
+    os.environ.get("RAG_TEXT_SPLITTER", ""),
+)
+
+
+TIKTOKEN_CACHE_DIR = os.environ.get("TIKTOKEN_CACHE_DIR", f"{CACHE_DIR}/tiktoken")
+TIKTOKEN_ENCODING_NAME = PersistentConfig(
+    "TIKTOKEN_ENCODING_NAME",
+    "rag.tiktoken_encoding_name",
+    os.environ.get("TIKTOKEN_ENCODING_NAME", "cl100k_base"),
+)
+
+
 CHUNK_SIZE = PersistentConfig(
     "CHUNK_SIZE", "rag.chunk_size", int(os.environ.get("CHUNK_SIZE", "1000"))
 )
@@ -1036,23 +1357,34 @@ CHUNK_OVERLAP = PersistentConfig(
     int(os.environ.get("CHUNK_OVERLAP", "100")),
 )
 
-DEFAULT_RAG_TEMPLATE = """You are given a user query, some textual context and rules, all inside xml tags. You have to answer the query based on the context while respecting the rules.
+DEFAULT_RAG_TEMPLATE = """### Task:
+Respond to the user query using the provided context, incorporating inline citations in the format [source_id] **only when the <source_id> tag is explicitly provided** in the context.
+
+### Guidelines:
+- If you don't know the answer, clearly state that.
+- If uncertain, ask the user for clarification.
+- Respond in the same language as the user's query.
+- If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
+- If the answer isn't present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
+- **Only include inline citations using [source_id] when a <source_id> tag is explicitly provided in the context.**  
+- Do not cite if the <source_id> tag is not provided in the context.  
+- Do not use XML tags in your response.
+- Ensure citations are concise and directly related to the information provided.
+
+### Example of Citation:
+If the user asks about a specific topic and the information is found in "whitepaper.pdf" with a provided <source_id>, the response should include the citation like so:  
+* "According to the study, the proposed method increases efficiency by 20% [whitepaper.pdf]."
+If no <source_id> is present, the response should omit the citation.
+
+### Output:
+Provide a clear and direct response to the user's query, including inline citations in the format [source_id] only when the <source_id> tag is present in the context.
 
 <context>
-[context]
+{{CONTEXT}}
 </context>
 
-<rules>
-- If you don't know, just say so.
-- If you are not sure, ask for clarification.
-- Answer in the same language as the user query.
-- If the context appears unreadable or of poor quality, tell the user then answer as best as you can.
-- If the answer is not in the context but you think you know the answer, explain that to the user then answer with your own knowledge.
-- Answer directly and without using xml tags.
-</rules>
-
 <user_query>
-[query]
+{{QUERY}}
 </user_query>
 """
 
@@ -1073,6 +1405,19 @@ RAG_OPENAI_API_KEY = PersistentConfig(
     os.getenv("RAG_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+RAG_OLLAMA_BASE_URL = PersistentConfig(
+    "RAG_OLLAMA_BASE_URL",
+    "rag.ollama.url",
+    os.getenv("RAG_OLLAMA_BASE_URL", OLLAMA_BASE_URL),
+)
+
+RAG_OLLAMA_API_KEY = PersistentConfig(
+    "RAG_OLLAMA_API_KEY",
+    "rag.ollama.key",
+    os.getenv("RAG_OLLAMA_API_KEY", ""),
+)
+
+
 ENABLE_RAG_LOCAL_WEB_FETCH = (
     os.getenv("ENABLE_RAG_LOCAL_WEB_FETCH", "False").lower() == "true"
 )
@@ -1083,6 +1428,12 @@ 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",
@@ -1108,6 +1459,7 @@ RAG_WEB_SEARCH_DOMAIN_FILTER_LIST = PersistentConfig(
     ],
 )
 
+
 SEARXNG_QUERY_URL = PersistentConfig(
     "SEARXNG_QUERY_URL",
     "rag.web.search.searxng_query_url",
@@ -1132,6 +1484,18 @@ BRAVE_SEARCH_API_KEY = PersistentConfig(
     os.getenv("BRAVE_SEARCH_API_KEY", ""),
 )
 
+KAGI_SEARCH_API_KEY = PersistentConfig(
+    "KAGI_SEARCH_API_KEY",
+    "rag.web.search.kagi_search_api_key",
+    os.getenv("KAGI_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",
@@ -1162,6 +1526,12 @@ TAVILY_API_KEY = PersistentConfig(
     os.getenv("TAVILY_API_KEY", ""),
 )
 
+JINA_API_KEY = PersistentConfig(
+    "JINA_API_KEY",
+    "rag.web.search.jina_api_key",
+    os.getenv("JINA_API_KEY", ""),
+)
+
 SEARCHAPI_API_KEY = PersistentConfig(
     "SEARCHAPI_API_KEY",
     "rag.web.search.searchapi_api_key",
@@ -1174,6 +1544,21 @@ SEARCHAPI_ENGINE = PersistentConfig(
     os.getenv("SEARCHAPI_ENGINE", ""),
 )
 
+BING_SEARCH_V7_ENDPOINT = PersistentConfig(
+    "BING_SEARCH_V7_ENDPOINT",
+    "rag.web.search.bing_search_v7_endpoint",
+    os.environ.get(
+        "BING_SEARCH_V7_ENDPOINT", "https://api.bing.microsoft.com/v7.0/search"
+    ),
+)
+
+BING_SEARCH_V7_SUBSCRIPTION_KEY = PersistentConfig(
+    "BING_SEARCH_V7_SUBSCRIPTION_KEY",
+    "rag.web.search.bing_search_v7_subscription_key",
+    os.environ.get("BING_SEARCH_V7_SUBSCRIPTION_KEY", ""),
+)
+
+
 RAG_WEB_SEARCH_RESULT_COUNT = PersistentConfig(
     "RAG_WEB_SEARCH_RESULT_COUNT",
     "rag.web.search.result_count",
@@ -1187,17 +1572,6 @@ RAG_WEB_SEARCH_CONCURRENT_REQUESTS = PersistentConfig(
 )
 
 
-####################################
-# Transcribe
-####################################
-
-WHISPER_MODEL = os.getenv("WHISPER_MODEL", "base")
-WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
-WHISPER_MODEL_AUTO_UPDATE = (
-    os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
-)
-
-
 ####################################
 # Images
 ####################################
@@ -1236,7 +1610,7 @@ AUTOMATIC1111_CFG_SCALE = PersistentConfig(
 
 
 AUTOMATIC1111_SAMPLER = PersistentConfig(
-    "AUTOMATIC1111_SAMPLERE",
+    "AUTOMATIC1111_SAMPLER",
     "image_generation.automatic1111.sampler",
     (
         os.environ.get("AUTOMATIC1111_SAMPLER")
@@ -1261,6 +1635,12 @@ COMFYUI_BASE_URL = PersistentConfig(
     os.getenv("COMFYUI_BASE_URL", ""),
 )
 
+COMFYUI_API_KEY = PersistentConfig(
+    "COMFYUI_API_KEY",
+    "image_generation.comfyui.api_key",
+    os.getenv("COMFYUI_API_KEY", ""),
+)
+
 COMFYUI_DEFAULT_WORKFLOW = """
 {
   "3": {
@@ -1413,6 +1793,20 @@ IMAGE_GENERATION_MODEL = PersistentConfig(
 # Audio
 ####################################
 
+# Transcription
+WHISPER_MODEL = PersistentConfig(
+    "WHISPER_MODEL",
+    "audio.stt.whisper_model",
+    os.getenv("WHISPER_MODEL", "base"),
+)
+
+WHISPER_MODEL_DIR = os.getenv("WHISPER_MODEL_DIR", f"{CACHE_DIR}/whisper/models")
+WHISPER_MODEL_AUTO_UPDATE = (
+    not OFFLINE_MODE
+    and os.environ.get("WHISPER_MODEL_AUTO_UPDATE", "").lower() == "true"
+)
+
+
 AUDIO_STT_OPENAI_API_BASE_URL = PersistentConfig(
     "AUDIO_STT_OPENAI_API_BASE_URL",
     "audio.stt.openai.api_base_url",
@@ -1434,7 +1828,7 @@ AUDIO_STT_ENGINE = PersistentConfig(
 AUDIO_STT_MODEL = PersistentConfig(
     "AUDIO_STT_MODEL",
     "audio.stt.model",
-    os.getenv("AUDIO_STT_MODEL", "whisper-1"),
+    os.getenv("AUDIO_STT_MODEL", ""),
 )
 
 AUDIO_TTS_OPENAI_API_BASE_URL = PersistentConfig(
@@ -1492,3 +1886,74 @@ AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT = PersistentConfig(
         "AUDIO_TTS_AZURE_SPEECH_OUTPUT_FORMAT", "audio-24khz-160kbitrate-mono-mp3"
     ),
 )
+
+
+####################################
+# LDAP
+####################################
+
+ENABLE_LDAP = PersistentConfig(
+    "ENABLE_LDAP",
+    "ldap.enable",
+    os.environ.get("ENABLE_LDAP", "false").lower() == "true",
+)
+
+LDAP_SERVER_LABEL = PersistentConfig(
+    "LDAP_SERVER_LABEL",
+    "ldap.server.label",
+    os.environ.get("LDAP_SERVER_LABEL", "LDAP Server"),
+)
+
+LDAP_SERVER_HOST = PersistentConfig(
+    "LDAP_SERVER_HOST",
+    "ldap.server.host",
+    os.environ.get("LDAP_SERVER_HOST", "localhost"),
+)
+
+LDAP_SERVER_PORT = PersistentConfig(
+    "LDAP_SERVER_PORT",
+    "ldap.server.port",
+    int(os.environ.get("LDAP_SERVER_PORT", "389")),
+)
+
+LDAP_ATTRIBUTE_FOR_USERNAME = PersistentConfig(
+    "LDAP_ATTRIBUTE_FOR_USERNAME",
+    "ldap.server.attribute_for_username",
+    os.environ.get("LDAP_ATTRIBUTE_FOR_USERNAME", "uid"),
+)
+
+LDAP_APP_DN = PersistentConfig(
+    "LDAP_APP_DN", "ldap.server.app_dn", os.environ.get("LDAP_APP_DN", "")
+)
+
+LDAP_APP_PASSWORD = PersistentConfig(
+    "LDAP_APP_PASSWORD",
+    "ldap.server.app_password",
+    os.environ.get("LDAP_APP_PASSWORD", ""),
+)
+
+LDAP_SEARCH_BASE = PersistentConfig(
+    "LDAP_SEARCH_BASE", "ldap.server.users_dn", os.environ.get("LDAP_SEARCH_BASE", "")
+)
+
+LDAP_SEARCH_FILTERS = PersistentConfig(
+    "LDAP_SEARCH_FILTER",
+    "ldap.server.search_filter",
+    os.environ.get("LDAP_SEARCH_FILTER", ""),
+)
+
+LDAP_USE_TLS = PersistentConfig(
+    "LDAP_USE_TLS",
+    "ldap.server.use_tls",
+    os.environ.get("LDAP_USE_TLS", "True").lower() == "true",
+)
+
+LDAP_CA_CERT_FILE = PersistentConfig(
+    "LDAP_CA_CERT_FILE",
+    "ldap.server.ca_cert_file",
+    os.environ.get("LDAP_CA_CERT_FILE", ""),
+)
+
+LDAP_CIPHERS = PersistentConfig(
+    "LDAP_CIPHERS", "ldap.server.ciphers", os.environ.get("LDAP_CIPHERS", "ALL")
+)

backend/open_webui/constants.py

@@ -20,7 +20,9 @@ class ERROR_MESSAGES(str, Enum):
     def __str__(self) -> str:
         return super().__str__()
 
-    DEFAULT = lambda err="": f"Something went wrong :/\n{err if err else ''}"
+    DEFAULT = (
+        lambda err="": f'{"Something went wrong :/" if err == "" else "[ERROR: " + str(err) + "]"}'
+    )
     ENV_VAR_NOT_FOUND = "Required environment variable not found. Terminating now."
     CREATE_USER_ERROR = "Oops! Something went wrong while creating your account. Please try again later. If the issue persists, contact support for assistance."
     DELETE_USER_ERROR = "Oops! Something went wrong. We encountered an issue while trying to delete the user. Please give it another shot."
@@ -34,8 +36,8 @@ class ERROR_MESSAGES(str, Enum):
 
     ID_TAKEN = "Uh-oh! This id is already registered. Please choose another id string."
     MODEL_ID_TAKEN = "Uh-oh! This model id is already registered. Please choose another model id string."
-
     NAME_TAG_TAKEN = "Uh-oh! This name tag is already registered. Please choose another name tag string."
+
     INVALID_TOKEN = (
         "Your session has expired or the token is invalid. Please sign in again."
     )
@@ -60,6 +62,7 @@ class ERROR_MESSAGES(str, Enum):
     NOT_FOUND = "We could not find what you're looking for :/"
     USER_NOT_FOUND = "We could not find what you're looking for :/"
     API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature."
+    API_KEY_NOT_ALLOWED = "Use of API key is not enabled in the environment."
 
     MALICIOUS = "Unusual activities detected, please try again in a few minutes."
 
@@ -73,6 +76,7 @@ class ERROR_MESSAGES(str, Enum):
     OPENAI_NOT_FOUND = lambda name="": "OpenAI API was not found"
     OLLAMA_NOT_FOUND = "WebUI could not connect to Ollama"
     CREATE_API_KEY_ERROR = "Oops! Something went wrong while creating your API key. Please try again later. If the issue persists, contact support for assistance."
+    API_KEY_CREATION_NOT_ALLOWED = "API key creation is not allowed in the environment."
 
     EMPTY_CONTENT = "The content provided is empty. Please ensure that there is text or data present before proceeding."
 
@@ -90,6 +94,15 @@ class ERROR_MESSAGES(str, Enum):
         "The Ollama API is disabled. Please enable it to use this feature."
     )
 
+    FILE_TOO_LARGE = (
+        lambda size="": f"Oops! The file you're trying to upload is too large. Please upload a file that is less than {size}."
+    )
+
+    DUPLICATE_CONTENT = (
+        "Duplicate content detected. Please provide unique content to proceed."
+    )
+    FILE_NOT_PROCESSED = "Extracted content is not available for this file. Please ensure that the file is processed before proceeding."
+
 
 class TASKS(str, Enum):
     def __str__(self) -> str:
@@ -97,7 +110,9 @@ class TASKS(str, Enum):
 
     DEFAULT = lambda task="": f"{task if task else 'generation'}"
     TITLE_GENERATION = "title_generation"
+    TAGS_GENERATION = "tags_generation"
     EMOJI_GENERATION = "emoji_generation"
     QUERY_GENERATION = "query_generation"
+    AUTOCOMPLETE_GENERATION = "autocomplete_generation"
     FUNCTION_CALLING = "function_calling"
     MOA_RESPONSE_GENERATION = "moa_response_generation"

backend/open_webui/env.py

@@ -103,8 +103,6 @@ WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
 if WEBUI_NAME != "Open WebUI":
     WEBUI_NAME += " (Open WebUI)"
 
-WEBUI_URL = os.environ.get("WEBUI_URL", "http://localhost:3000")
-
 WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"
 
 
@@ -195,6 +193,15 @@ CHANGELOG = changelog_json
 
 SAFE_MODE = os.environ.get("SAFE_MODE", "false").lower() == "true"
 
+####################################
+# ENABLE_FORWARD_USER_INFO_HEADERS
+####################################
+
+ENABLE_FORWARD_USER_INFO_HEADERS = (
+    os.environ.get("ENABLE_FORWARD_USER_INFO_HEADERS", "False").lower() == "true"
+)
+
+
 ####################################
 # WEBUI_BUILD_HASH
 ####################################
@@ -230,6 +237,8 @@ if FROM_INIT_PY:
     DATA_DIR = Path(os.getenv("DATA_DIR", OPEN_WEBUI_DIR / "data"))
 
 
+STATIC_DIR = Path(os.getenv("STATIC_DIR", OPEN_WEBUI_DIR / "static"))
+
 FONTS_DIR = Path(os.getenv("FONTS_DIR", OPEN_WEBUI_DIR / "static" / "fonts"))
 
 FRONTEND_BUILD_DIR = Path(os.getenv("FRONTEND_BUILD_DIR", BASE_DIR / "build")).resolve()
@@ -258,11 +267,56 @@ DATABASE_URL = os.environ.get("DATABASE_URL", f"sqlite:///{DATA_DIR}/webui.db")
 if "postgres://" in DATABASE_URL:
     DATABASE_URL = DATABASE_URL.replace("postgres://", "postgresql://")
 
+DATABASE_POOL_SIZE = os.environ.get("DATABASE_POOL_SIZE", 0)
+
+if DATABASE_POOL_SIZE == "":
+    DATABASE_POOL_SIZE = 0
+else:
+    try:
+        DATABASE_POOL_SIZE = int(DATABASE_POOL_SIZE)
+    except Exception:
+        DATABASE_POOL_SIZE = 0
+
+DATABASE_POOL_MAX_OVERFLOW = os.environ.get("DATABASE_POOL_MAX_OVERFLOW", 0)
+
+if DATABASE_POOL_MAX_OVERFLOW == "":
+    DATABASE_POOL_MAX_OVERFLOW = 0
+else:
+    try:
+        DATABASE_POOL_MAX_OVERFLOW = int(DATABASE_POOL_MAX_OVERFLOW)
+    except Exception:
+        DATABASE_POOL_MAX_OVERFLOW = 0
+
+DATABASE_POOL_TIMEOUT = os.environ.get("DATABASE_POOL_TIMEOUT", 30)
+
+if DATABASE_POOL_TIMEOUT == "":
+    DATABASE_POOL_TIMEOUT = 30
+else:
+    try:
+        DATABASE_POOL_TIMEOUT = int(DATABASE_POOL_TIMEOUT)
+    except Exception:
+        DATABASE_POOL_TIMEOUT = 30
+
+DATABASE_POOL_RECYCLE = os.environ.get("DATABASE_POOL_RECYCLE", 3600)
+
+if DATABASE_POOL_RECYCLE == "":
+    DATABASE_POOL_RECYCLE = 3600
+else:
+    try:
+        DATABASE_POOL_RECYCLE = int(DATABASE_POOL_RECYCLE)
+    except Exception:
+        DATABASE_POOL_RECYCLE = 3600
 
 RESET_CONFIG_ON_START = (
     os.environ.get("RESET_CONFIG_ON_START", "False").lower() == "true"
 )
 
+####################################
+# REDIS
+####################################
+
+REDIS_URL = os.environ.get("REDIS_URL", "redis://localhost:6379/0")
+
 ####################################
 # WEBUI_AUTH (Required for security)
 ####################################
@@ -273,6 +327,9 @@ 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
@@ -304,4 +361,34 @@ ENABLE_WEBSOCKET_SUPPORT = (
 
 WEBSOCKET_MANAGER = os.environ.get("WEBSOCKET_MANAGER", "")
 
-WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", "redis://localhost:6379/0")
+WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", REDIS_URL)
+
+AIOHTTP_CLIENT_TIMEOUT = os.environ.get("AIOHTTP_CLIENT_TIMEOUT", "")
+
+if AIOHTTP_CLIENT_TIMEOUT == "":
+    AIOHTTP_CLIENT_TIMEOUT = None
+else:
+    try:
+        AIOHTTP_CLIENT_TIMEOUT = int(AIOHTTP_CLIENT_TIMEOUT)
+    except Exception:
+        AIOHTTP_CLIENT_TIMEOUT = 300
+
+AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = os.environ.get(
+    "AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", ""
+)
+
+if AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST == "":
+    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = None
+else:
+    try:
+        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = int(
+            AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST
+        )
+    except Exception:
+        AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = 5
+
+####################################
+# OFFLINE_MODE
+####################################
+
+OFFLINE_MODE = os.environ.get("OFFLINE_MODE", "false").lower() == "true"

backend/open_webui/functions.py

@@ -1,56 +1,42 @@
+import logging
+import sys
 import inspect
 import json
-import logging
-from typing import AsyncGenerator, Generator, Iterator
 
-from open_webui.apps.socket.main import get_event_call, get_event_emitter
-from open_webui.apps.webui.models.functions import Functions
-from open_webui.apps.webui.models.models import Models
-from open_webui.apps.webui.routers import (
-    auths,
-    chats,
-    configs,
-    documents,
-    files,
-    functions,
-    memories,
-    models,
-    prompts,
-    tools,
-    users,
-    utils,
-)
-from open_webui.apps.webui.utils import load_function_module_by_id
-from open_webui.config import (
-    ADMIN_EMAIL,
-    CORS_ALLOW_ORIGIN,
-    DEFAULT_MODELS,
-    DEFAULT_PROMPT_SUGGESTIONS,
-    DEFAULT_USER_ROLE,
-    ENABLE_COMMUNITY_SHARING,
-    ENABLE_LOGIN_FORM,
-    ENABLE_MESSAGE_RATING,
-    ENABLE_SIGNUP,
-    JWT_EXPIRES_IN,
-    OAUTH_EMAIL_CLAIM,
-    OAUTH_PICTURE_CLAIM,
-    OAUTH_USERNAME_CLAIM,
-    SHOW_ADMIN_DETAILS,
-    USER_PERMISSIONS,
-    WEBHOOK_URL,
-    WEBUI_AUTH,
-    WEBUI_BANNERS,
-    AppConfig,
-)
-from open_webui.env import (
-    WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
-    WEBUI_AUTH_TRUSTED_NAME_HEADER,
-)
-from fastapi import FastAPI
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
+from typing import AsyncGenerator, Generator, Iterator
+from fastapi import (
+    Depends,
+    FastAPI,
+    File,
+    Form,
+    HTTPException,
+    Request,
+    UploadFile,
+    status,
+)
+from starlette.responses import Response, StreamingResponse
+
+
+from open_webui.socket.main import (
+    get_event_call,
+    get_event_emitter,
+)
+
+
+from open_webui.models.functions import Functions
+from open_webui.models.models import Models
+
+from open_webui.utils.plugin import load_function_module_by_id
+from open_webui.utils.tools import get_tools
+from open_webui.utils.access_control import has_access
+
+from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+
 from open_webui.utils.misc import (
+    add_or_update_system_message,
+    get_last_user_message,
+    prepend_to_first_user_message_content,
     openai_chat_chunk_message_template,
     openai_chat_completion_message_template,
 )
@@ -60,86 +46,18 @@ from open_webui.utils.payload import (
 )
 
 
-from open_webui.utils.tools import get_tools
-
-app = FastAPI()
-
+logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
 log = logging.getLogger(__name__)
-
-app.state.config = AppConfig()
-
-app.state.config.ENABLE_SIGNUP = ENABLE_SIGNUP
-app.state.config.ENABLE_LOGIN_FORM = ENABLE_LOGIN_FORM
-app.state.config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
-app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
-app.state.AUTH_TRUSTED_NAME_HEADER = WEBUI_AUTH_TRUSTED_NAME_HEADER
+log.setLevel(SRC_LOG_LEVELS["MAIN"])
 
 
-app.state.config.SHOW_ADMIN_DETAILS = SHOW_ADMIN_DETAILS
-app.state.config.ADMIN_EMAIL = ADMIN_EMAIL
-
-
-app.state.config.DEFAULT_MODELS = DEFAULT_MODELS
-app.state.config.DEFAULT_PROMPT_SUGGESTIONS = DEFAULT_PROMPT_SUGGESTIONS
-app.state.config.DEFAULT_USER_ROLE = DEFAULT_USER_ROLE
-app.state.config.USER_PERMISSIONS = USER_PERMISSIONS
-app.state.config.WEBHOOK_URL = WEBHOOK_URL
-app.state.config.BANNERS = WEBUI_BANNERS
-
-app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
-app.state.config.ENABLE_MESSAGE_RATING = ENABLE_MESSAGE_RATING
-
-app.state.config.OAUTH_USERNAME_CLAIM = OAUTH_USERNAME_CLAIM
-app.state.config.OAUTH_PICTURE_CLAIM = OAUTH_PICTURE_CLAIM
-app.state.config.OAUTH_EMAIL_CLAIM = OAUTH_EMAIL_CLAIM
-
-app.state.MODELS = {}
-app.state.TOOLS = {}
-app.state.FUNCTIONS = {}
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=CORS_ALLOW_ORIGIN,
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-
-app.include_router(configs.router, prefix="/configs", tags=["configs"])
-app.include_router(auths.router, prefix="/auths", tags=["auths"])
-app.include_router(users.router, prefix="/users", tags=["users"])
-app.include_router(chats.router, prefix="/chats", tags=["chats"])
-
-app.include_router(documents.router, prefix="/documents", tags=["documents"])
-app.include_router(models.router, prefix="/models", tags=["models"])
-app.include_router(prompts.router, prefix="/prompts", tags=["prompts"])
-
-app.include_router(memories.router, prefix="/memories", tags=["memories"])
-app.include_router(files.router, prefix="/files", tags=["files"])
-app.include_router(tools.router, prefix="/tools", tags=["tools"])
-app.include_router(functions.router, prefix="/functions", tags=["functions"])
-
-app.include_router(utils.router, prefix="/utils", tags=["utils"])
-
-
-@app.get("/")
-async def get_status():
-    return {
-        "status": True,
-        "auth": WEBUI_AUTH,
-        "default_models": app.state.config.DEFAULT_MODELS,
-        "default_prompt_suggestions": app.state.config.DEFAULT_PROMPT_SUGGESTIONS,
-    }
-
-
-def get_function_module(pipe_id: str):
+def get_function_module_by_id(request: Request, pipe_id: str):
     # Check if function is already loaded
-    if pipe_id not in app.state.FUNCTIONS:
+    if pipe_id not in request.app.state.FUNCTIONS:
         function_module, _, _ = load_function_module_by_id(pipe_id)
-        app.state.FUNCTIONS[pipe_id] = function_module
+        request.app.state.FUNCTIONS[pipe_id] = function_module
     else:
-        function_module = app.state.FUNCTIONS[pipe_id]
+        function_module = request.app.state.FUNCTIONS[pipe_id]
 
     if hasattr(function_module, "valves") and hasattr(function_module, "Valves"):
         valves = Functions.get_function_valves_by_id(pipe_id)
@@ -147,12 +65,12 @@ def get_function_module(pipe_id: str):
     return function_module
 
 
-async def get_pipe_models():
+async def get_function_models(request):
     pipes = Functions.get_functions_by_type("pipe", active_only=True)
     pipe_models = []
 
     for pipe in pipes:
-        function_module = get_function_module(pipe.id)
+        function_module = get_function_module_by_id(request, pipe.id)
 
         # Check if function is a manifold
         if hasattr(function_module, "pipes"):
@@ -169,7 +87,9 @@ async def get_pipe_models():
                 log.exception(e)
                 sub_pipes = []
 
-            print(sub_pipes)
+            log.debug(
+                f"get_function_models: function '{pipe.id}' is a manifold of {sub_pipes}"
+            )
 
             for p in sub_pipes:
                 sub_pipe_id = f'{pipe.id}.{p["id"]}'
@@ -179,6 +99,7 @@ async def get_pipe_models():
                     sub_pipe_name = f"{function_module.name}{sub_pipe_name}"
 
                 pipe_flag = {"type": pipe.type}
+
                 pipe_models.append(
                     {
                         "id": sub_pipe_id,
@@ -192,6 +113,10 @@ async def get_pipe_models():
         else:
             pipe_flag = {"type": "pipe"}
 
+            log.debug(
+                f"get_function_models: function '{pipe.id}' is a single pipe {{ 'id': {pipe.id}, 'name': {pipe.name} }}"
+            )
+
             pipe_models.append(
                 {
                     "id": pipe.id,
@@ -206,73 +131,69 @@ async def get_pipe_models():
     return pipe_models
 
 
-async def execute_pipe(pipe, params):
-    if inspect.iscoroutinefunction(pipe):
-        return await pipe(**params)
-    else:
-        return pipe(**params)
+async def generate_function_chat_completion(
+    request, form_data, user, models: dict = {}
+):
+    async def execute_pipe(pipe, params):
+        if inspect.iscoroutinefunction(pipe):
+            return await pipe(**params)
+        else:
+            return pipe(**params)
 
+    async def get_message_content(res: str | Generator | AsyncGenerator) -> str:
+        if isinstance(res, str):
+            return res
+        if isinstance(res, Generator):
+            return "".join(map(str, res))
+        if isinstance(res, AsyncGenerator):
+            return "".join([str(stream) async for stream in res])
 
-async def get_message_content(res: str | Generator | AsyncGenerator) -> str:
-    if isinstance(res, str):
-        return res
-    if isinstance(res, Generator):
-        return "".join(map(str, res))
-    if isinstance(res, AsyncGenerator):
-        return "".join([str(stream) async for stream in res])
+    def process_line(form_data: dict, line):
+        if isinstance(line, BaseModel):
+            line = line.model_dump_json()
+            line = f"data: {line}"
+        if isinstance(line, dict):
+            line = f"data: {json.dumps(line)}"
 
-
-def process_line(form_data: dict, line):
-    if isinstance(line, BaseModel):
-        line = line.model_dump_json()
-        line = f"data: {line}"
-    if isinstance(line, dict):
-        line = f"data: {json.dumps(line)}"
-
-    try:
-        line = line.decode("utf-8")
-    except Exception:
-        pass
-
-    if line.startswith("data:"):
-        return f"{line}\n\n"
-    else:
-        line = openai_chat_chunk_message_template(form_data["model"], line)
-        return f"data: {json.dumps(line)}\n\n"
-
-
-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
-
-
-def get_function_params(function_module, form_data, user, extra_params=None):
-    if extra_params is None:
-        extra_params = {}
-
-    pipe_id = get_pipe_id(form_data)
-
-    # Get the signature of the function
-    sig = inspect.signature(function_module.pipe)
-    params = {"body": form_data} | {
-        k: v for k, v in extra_params.items() if k in sig.parameters
-    }
-
-    if "__user__" in params and hasattr(function_module, "UserValves"):
-        user_valves = Functions.get_user_valves_by_id_and_user_id(pipe_id, user.id)
         try:
-            params["__user__"]["valves"] = function_module.UserValves(**user_valves)
-        except Exception as e:
-            log.exception(e)
-            params["__user__"]["valves"] = function_module.UserValves()
+            line = line.decode("utf-8")
+        except Exception:
+            pass
 
-    return params
+        if line.startswith("data:"):
+            return f"{line}\n\n"
+        else:
+            line = openai_chat_chunk_message_template(form_data["model"], line)
+            return f"data: {json.dumps(line)}\n\n"
 
+    def get_pipe_id(form_data: dict) -> str:
+        pipe_id = form_data["model"]
+        if "." in pipe_id:
+            pipe_id, _ = pipe_id.split(".", 1)
+        return pipe_id
+
+    def get_function_params(function_module, form_data, user, extra_params=None):
+        if extra_params is None:
+            extra_params = {}
+
+        pipe_id = get_pipe_id(form_data)
+
+        # Get the signature of the function
+        sig = inspect.signature(function_module.pipe)
+        params = {"body": form_data} | {
+            k: v for k, v in extra_params.items() if k in sig.parameters
+        }
+
+        if "__user__" in params and hasattr(function_module, "UserValves"):
+            user_valves = Functions.get_user_valves_by_id_and_user_id(pipe_id, user.id)
+            try:
+                params["__user__"]["valves"] = function_module.UserValves(**user_valves)
+            except Exception as e:
+                log.exception(e)
+                params["__user__"]["valves"] = function_module.UserValves()
+
+        return params
 
-async def generate_function_chat_completion(form_data, user):
     model_id = form_data.get("model")
     model_info = Models.get_model_by_id(model_id)
 
@@ -287,17 +208,20 @@ async def generate_function_chat_completion(form_data, user):
     __event_emitter__ = None
     __event_call__ = None
     __task__ = None
+    __task_body__ = None
 
     if metadata:
         if all(k in metadata for k in ("session_id", "chat_id", "message_id")):
             __event_emitter__ = get_event_emitter(metadata)
             __event_call__ = get_event_call(metadata)
         __task__ = metadata.get("task", None)
+        __task_body__ = metadata.get("task_body", None)
 
     extra_params = {
         "__event_emitter__": __event_emitter__,
         "__event_call__": __event_call__,
         "__task__": __task__,
+        "__task_body__": __task_body__,
         "__files__": files,
         "__user__": {
             "id": user.id,
@@ -305,14 +229,16 @@ async def generate_function_chat_completion(form_data, user):
             "name": user.name,
             "role": user.role,
         },
+        "__metadata__": metadata,
+        "__request__": request,
     }
     extra_params["__tools__"] = get_tools(
-        app,
+        request,
         tool_ids,
         user,
         {
             **extra_params,
-            "__model__": app.state.MODELS[form_data["model"]],
+            "__model__": models.get(form_data["model"], None),
             "__messages__": form_data["messages"],
             "__files__": files,
         },
@@ -327,12 +253,12 @@ async def generate_function_chat_completion(form_data, user):
         form_data = apply_model_system_prompt_to_body(params, form_data, user)
 
     pipe_id = get_pipe_id(form_data)
-    function_module = get_function_module(pipe_id)
+    function_module = get_function_module_by_id(request, pipe_id)
 
     pipe = function_module.pipe
     params = get_function_params(function_module, form_data, user, extra_params)
 
-    if form_data["stream"]:
+    if form_data.get("stream", False):
 
         async def stream_content():
             try:
@@ -348,7 +274,7 @@ async def generate_function_chat_completion(form_data, user):
                     return
 
             except Exception as e:
-                print(f"Error: {e}")
+                log.error(f"Error: {e}")
                 yield f"data: {json.dumps({'error': {'detail':str(e)}})}\n\n"
                 return
 
@@ -378,7 +304,7 @@ async def generate_function_chat_completion(form_data, user):
             res = await execute_pipe(pipe, params)
 
         except Exception as e:
-            print(f"Error: {e}")
+            log.error(f"Error: {e}")
             return {"error": {"detail": str(e)}}
 
         if isinstance(res, StreamingResponse) or isinstance(res, dict):

backend/open_webui/internal/db.py

@@ -3,12 +3,21 @@ import logging
 from contextlib import contextmanager
 from typing import Any, Optional
 
-from open_webui.apps.webui.internal.wrappers import register_connection
-from open_webui.env import OPEN_WEBUI_DIR, DATABASE_URL, SRC_LOG_LEVELS
+from open_webui.internal.wrappers import register_connection
+from open_webui.env import (
+    OPEN_WEBUI_DIR,
+    DATABASE_URL,
+    SRC_LOG_LEVELS,
+    DATABASE_POOL_MAX_OVERFLOW,
+    DATABASE_POOL_RECYCLE,
+    DATABASE_POOL_SIZE,
+    DATABASE_POOL_TIMEOUT,
+)
 from peewee_migrate import Router
 from sqlalchemy import Dialect, create_engine, types
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import scoped_session, sessionmaker
+from sqlalchemy.pool import QueuePool, NullPool
 from sqlalchemy.sql.type_api import _T
 from typing_extensions import Self
 
@@ -45,7 +54,7 @@ def handle_peewee_migration(DATABASE_URL):
     try:
         # Replace the postgresql:// with postgres:// to handle the peewee migration
         db = register_connection(DATABASE_URL.replace("postgresql://", "postgres://"))
-        migrate_dir = OPEN_WEBUI_DIR / "apps" / "webui" / "internal" / "migrations"
+        migrate_dir = OPEN_WEBUI_DIR / "internal" / "migrations"
         router = Router(db, logger=log, migrate_dir=migrate_dir)
         router.run()
         db.close()
@@ -71,7 +80,20 @@ if "sqlite" in SQLALCHEMY_DATABASE_URL:
         SQLALCHEMY_DATABASE_URL, connect_args={"check_same_thread": False}
     )
 else:
-    engine = create_engine(SQLALCHEMY_DATABASE_URL, pool_pre_ping=True)
+    if DATABASE_POOL_SIZE > 0:
+        engine = create_engine(
+            SQLALCHEMY_DATABASE_URL,
+            pool_size=DATABASE_POOL_SIZE,
+            max_overflow=DATABASE_POOL_MAX_OVERFLOW,
+            pool_timeout=DATABASE_POOL_TIMEOUT,
+            pool_recycle=DATABASE_POOL_RECYCLE,
+            pool_pre_ping=True,
+            poolclass=QueuePool,
+        )
+    else:
+        engine = create_engine(
+            SQLALCHEMY_DATABASE_URL, pool_pre_ping=True, poolclass=NullPool
+        )
 
 
 SessionLocal = sessionmaker(

backend/open_webui/migrations/env.py

@@ -1,7 +1,7 @@
 from logging.config import fileConfig
 
 from alembic import context
-from open_webui.apps.webui.models.auths import Auth
+from open_webui.models.auths import Auth
 from open_webui.env import DATABASE_URL
 from sqlalchemy import engine_from_config, pool
 

backend/open_webui/migrations/script.py.mako

@@ -9,7 +9,7 @@ from typing import Sequence, Union
 
 from alembic import op
 import sqlalchemy as sa
-import open_webui.apps.webui.internal.db
+import open_webui.internal.db
 ${imports if imports else ""}
 
 # revision identifiers, used by Alembic.

backend/open_webui/migrations/scripts/revision.py

@@ -1,19 +0,0 @@
-from alembic import command
-from alembic.config import Config
-
-from open_webui.env import OPEN_WEBUI_DIR
-
-alembic_cfg = Config(OPEN_WEBUI_DIR / "alembic.ini")
-
-# Set the script location dynamically
-migrations_path = OPEN_WEBUI_DIR / "migrations"
-alembic_cfg.set_main_option("script_location", str(migrations_path))
-
-
-def revision(message: str) -> None:
-    command.revision(alembic_cfg, message=message, autogenerate=False)
-
-
-if __name__ == "__main__":
-    input_message = input("Enter the revision message: ")
-    revision(input_message)

backend/open_webui/migrations/util.py

@@ -7,3 +7,9 @@ def get_existing_tables():
     inspector = Inspector.from_engine(con)
     tables = set(inspector.get_table_names())
     return tables
+
+
+def get_revision_id():
+    import uuid
+
+    return str(uuid.uuid4()).replace("-", "")[:12]

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

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

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

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

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

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

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

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

backend/open_webui/migrations/versions/57c599a3cb57_add_channel_table.py

@@ -0,0 +1,48 @@
+"""Add channel table
+
+Revision ID: 57c599a3cb57
+Revises: 922e7a387820
+Create Date: 2024-12-22 03:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+revision = "57c599a3cb57"
+down_revision = "922e7a387820"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.create_table(
+        "channel",
+        sa.Column("id", sa.Text(), nullable=False, primary_key=True, unique=True),
+        sa.Column("user_id", sa.Text()),
+        sa.Column("name", sa.Text()),
+        sa.Column("description", sa.Text(), nullable=True),
+        sa.Column("data", sa.JSON(), nullable=True),
+        sa.Column("meta", sa.JSON(), nullable=True),
+        sa.Column("access_control", sa.JSON(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=True),
+        sa.Column("updated_at", sa.BigInteger(), nullable=True),
+    )
+
+    op.create_table(
+        "message",
+        sa.Column("id", sa.Text(), nullable=False, primary_key=True, unique=True),
+        sa.Column("user_id", sa.Text()),
+        sa.Column("channel_id", sa.Text(), nullable=True),
+        sa.Column("content", sa.Text()),
+        sa.Column("data", sa.JSON(), nullable=True),
+        sa.Column("meta", sa.JSON(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=True),
+        sa.Column("updated_at", sa.BigInteger(), nullable=True),
+    )
+
+
+def downgrade():
+    op.drop_table("channel")
+
+    op.drop_table("message")

backend/open_webui/migrations/versions/6a39f3d8e55c_add_knowledge_table.py

@@ -0,0 +1,80 @@
+"""Add knowledge table
+
+Revision ID: 6a39f3d8e55c
+Revises: c0fbf31ca0db
+Create Date: 2024-10-01 14:02:35.241684
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table, column, select
+import json
+
+
+revision = "6a39f3d8e55c"
+down_revision = "c0fbf31ca0db"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # Creating the 'knowledge' table
+    print("Creating knowledge table")
+    knowledge_table = op.create_table(
+        "knowledge",
+        sa.Column("id", sa.Text(), primary_key=True),
+        sa.Column("user_id", sa.Text(), nullable=False),
+        sa.Column("name", sa.Text(), nullable=False),
+        sa.Column("description", sa.Text(), nullable=True),
+        sa.Column("data", sa.JSON(), nullable=True),
+        sa.Column("meta", sa.JSON(), nullable=True),
+        sa.Column("created_at", sa.BigInteger(), nullable=False),
+        sa.Column("updated_at", sa.BigInteger(), nullable=True),
+    )
+
+    print("Migrating data from document table to knowledge table")
+    # Representation of the existing 'document' table
+    document_table = table(
+        "document",
+        column("collection_name", sa.String()),
+        column("user_id", sa.String()),
+        column("name", sa.String()),
+        column("title", sa.Text()),
+        column("content", sa.Text()),
+        column("timestamp", sa.BigInteger()),
+    )
+
+    # Select all from existing document table
+    documents = op.get_bind().execute(
+        select(
+            document_table.c.collection_name,
+            document_table.c.user_id,
+            document_table.c.name,
+            document_table.c.title,
+            document_table.c.content,
+            document_table.c.timestamp,
+        )
+    )
+
+    # Insert data into knowledge table from document table
+    for doc in documents:
+        op.get_bind().execute(
+            knowledge_table.insert().values(
+                id=doc.collection_name,
+                user_id=doc.user_id,
+                description=doc.name,
+                meta={
+                    "legacy": True,
+                    "document": True,
+                    "tags": json.loads(doc.content or "{}").get("tags", []),
+                },
+                name=doc.title,
+                created_at=doc.timestamp,
+                updated_at=doc.timestamp,  # using created_at for both created_at and updated_at in project
+            )
+        )
+
+
+def downgrade():
+    op.drop_table("knowledge")

backend/open_webui/migrations/versions/7826ab40b532_update_file_table.py

@@ -0,0 +1,26 @@
+"""Update file table
+
+Revision ID: 7826ab40b532
+Revises: 57c599a3cb57
+Create Date: 2024-12-23 03:00:00.000000
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+revision = "7826ab40b532"
+down_revision = "57c599a3cb57"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.add_column(
+        "file",
+        sa.Column("access_control", sa.JSON(), nullable=True),
+    )
+
+
+def downgrade():
+    op.drop_column("file", "access_control")

backend/open_webui/migrations/versions/7e5b5dc7342b_init.py

@@ -11,8 +11,8 @@ from typing import Sequence, Union
 import sqlalchemy as sa
 from alembic import op
 
-import open_webui.apps.webui.internal.db
-from open_webui.apps.webui.internal.db import JSONField
+import open_webui.internal.db
+from open_webui.internal.db import JSONField
 from open_webui.migrations.util import get_existing_tables
 
 # revision identifiers, used by Alembic.

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

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

backend/open_webui/migrations/versions/af906e964978_add_feedback_table.py

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

backend/open_webui/migrations/versions/c0fbf31ca0db_update_file_table.py

@@ -0,0 +1,32 @@
+"""Update file table
+
+Revision ID: c0fbf31ca0db
+Revises: ca81bd47c050
+Create Date: 2024-09-20 15:26:35.241684
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = "c0fbf31ca0db"
+down_revision: Union[str, None] = "ca81bd47c050"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column("file", sa.Column("hash", sa.Text(), nullable=True))
+    op.add_column("file", sa.Column("data", sa.JSON(), nullable=True))
+    op.add_column("file", sa.Column("updated_at", sa.BigInteger(), nullable=True))
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("file", "updated_at")
+    op.drop_column("file", "data")
+    op.drop_column("file", "hash")

backend/open_webui/migrations/versions/c29facfe716b_update_file_table_path.py

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

backend/open_webui/migrations/versions/c69f45358db4_add_folder_table.py

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

backend/open_webui/models/auths.py

@@ -2,12 +2,12 @@ import logging
 import uuid
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, get_db
-from open_webui.apps.webui.models.users import UserModel, Users
+from open_webui.internal.db import Base, get_db
+from open_webui.models.users import UserModel, Users
 from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel
 from sqlalchemy import Boolean, Column, String, Text
-from open_webui.utils.utils import verify_password
+from open_webui.utils.auth import verify_password
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -64,6 +64,11 @@ class SigninForm(BaseModel):
     password: str
 
 
+class LdapForm(BaseModel):
+    user: str
+    password: str
+
+
 class ProfileImageUrlForm(BaseModel):
     profile_image_url: str
 

backend/open_webui/models/channels.py

@@ -0,0 +1,132 @@
+import json
+import time
+import uuid
+from typing import Optional
+
+from open_webui.internal.db import Base, get_db
+from open_webui.utils.access_control import has_access
+
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
+from sqlalchemy import or_, func, select, and_, text
+from sqlalchemy.sql import exists
+
+####################
+# Channel DB Schema
+####################
+
+
+class Channel(Base):
+    __tablename__ = "channel"
+
+    id = Column(Text, primary_key=True)
+    user_id = Column(Text)
+
+    name = Column(Text)
+    description = Column(Text, nullable=True)
+
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+    access_control = Column(JSON, nullable=True)
+
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class ChannelModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+
+    id: str
+    user_id: str
+    description: Optional[str] = None
+
+    name: str
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+    access_control: Optional[dict] = None
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class ChannelForm(BaseModel):
+    name: str
+    description: Optional[str] = None
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+    access_control: Optional[dict] = None
+
+
+class ChannelTable:
+    def insert_new_channel(
+        self, form_data: ChannelForm, user_id: str
+    ) -> Optional[ChannelModel]:
+        with get_db() as db:
+            channel = ChannelModel(
+                **{
+                    **form_data.model_dump(),
+                    "name": form_data.name.lower(),
+                    "id": str(uuid.uuid4()),
+                    "user_id": user_id,
+                    "created_at": int(time.time_ns()),
+                    "updated_at": int(time.time_ns()),
+                }
+            )
+
+            new_channel = Channel(**channel.model_dump())
+
+            db.add(new_channel)
+            db.commit()
+            return channel
+
+    def get_channels(self) -> list[ChannelModel]:
+        with get_db() as db:
+            channels = db.query(Channel).all()
+            return [ChannelModel.model_validate(channel) for channel in channels]
+
+    def get_channels_by_user_id(
+        self, user_id: str, permission: str = "read"
+    ) -> list[ChannelModel]:
+        channels = self.get_channels()
+        return [
+            channel
+            for channel in channels
+            if channel.user_id == user_id
+            or has_access(user_id, permission, channel.access_control)
+        ]
+
+    def get_channel_by_id(self, id: str) -> Optional[ChannelModel]:
+        with get_db() as db:
+            channel = db.query(Channel).filter(Channel.id == id).first()
+            return ChannelModel.model_validate(channel) if channel else None
+
+    def update_channel_by_id(
+        self, id: str, form_data: ChannelForm
+    ) -> Optional[ChannelModel]:
+        with get_db() as db:
+            channel = db.query(Channel).filter(Channel.id == id).first()
+            if not channel:
+                return None
+
+            channel.name = form_data.name
+            channel.data = form_data.data
+            channel.meta = form_data.meta
+            channel.access_control = form_data.access_control
+            channel.updated_at = int(time.time_ns())
+
+            db.commit()
+            return ChannelModel.model_validate(channel) if channel else None
+
+    def delete_channel_by_id(self, id: str):
+        with get_db() as db:
+            db.query(Channel).filter(Channel.id == id).delete()
+            db.commit()
+            return True
+
+
+Channels = ChannelTable()

backend/open_webui/models/chats.py

@@ -0,0 +1,897 @@
+import json
+import time
+import uuid
+from typing import Optional
+
+from open_webui.internal.db import Base, get_db
+from open_webui.models.tags import TagModel, Tag, Tags
+
+
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
+from sqlalchemy import or_, func, select, and_, text
+from sqlalchemy.sql import exists
+
+####################
+# Chat DB Schema
+####################
+
+
+class Chat(Base):
+    __tablename__ = "chat"
+
+    id = Column(String, primary_key=True)
+    user_id = Column(String)
+    title = Column(Text)
+    chat = Column(JSON)
+
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+    share_id = Column(Text, unique=True, nullable=True)
+    archived = Column(Boolean, default=False)
+    pinned = Column(Boolean, default=False, nullable=True)
+
+    meta = Column(JSON, server_default="{}")
+    folder_id = Column(Text, nullable=True)
+
+
+class ChatModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+
+    id: str
+    user_id: str
+    title: str
+    chat: dict
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+    share_id: Optional[str] = None
+    archived: bool = False
+    pinned: Optional[bool] = False
+
+    meta: dict = {}
+    folder_id: Optional[str] = None
+
+
+####################
+# Forms
+####################
+
+
+class ChatForm(BaseModel):
+    chat: dict
+
+
+class ChatImportForm(ChatForm):
+    meta: Optional[dict] = {}
+    pinned: Optional[bool] = False
+    folder_id: Optional[str] = None
+
+
+class ChatTitleMessagesForm(BaseModel):
+    title: str
+    messages: list[dict]
+
+
+class ChatTitleForm(BaseModel):
+    title: str
+
+
+class ChatResponse(BaseModel):
+    id: str
+    user_id: str
+    title: str
+    chat: dict
+    updated_at: int  # timestamp in epoch
+    created_at: int  # timestamp in epoch
+    share_id: Optional[str] = None  # id of the chat to be shared
+    archived: bool
+    pinned: Optional[bool] = False
+    meta: dict = {}
+    folder_id: Optional[str] = None
+
+
+class ChatTitleIdResponse(BaseModel):
+    id: str
+    title: str
+    updated_at: int
+    created_at: int
+
+
+class ChatTable:
+    def insert_new_chat(self, user_id: str, form_data: ChatForm) -> Optional[ChatModel]:
+        with get_db() as db:
+            id = str(uuid.uuid4())
+            chat = ChatModel(
+                **{
+                    "id": id,
+                    "user_id": user_id,
+                    "title": (
+                        form_data.chat["title"]
+                        if "title" in form_data.chat
+                        else "New Chat"
+                    ),
+                    "chat": form_data.chat,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            result = Chat(**chat.model_dump())
+            db.add(result)
+            db.commit()
+            db.refresh(result)
+            return ChatModel.model_validate(result) if result else None
+
+    def import_chat(
+        self, user_id: str, form_data: ChatImportForm
+    ) -> Optional[ChatModel]:
+        with get_db() as db:
+            id = str(uuid.uuid4())
+            chat = ChatModel(
+                **{
+                    "id": id,
+                    "user_id": user_id,
+                    "title": (
+                        form_data.chat["title"]
+                        if "title" in form_data.chat
+                        else "New Chat"
+                    ),
+                    "chat": form_data.chat,
+                    "meta": form_data.meta,
+                    "pinned": form_data.pinned,
+                    "folder_id": form_data.folder_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            result = Chat(**chat.model_dump())
+            db.add(result)
+            db.commit()
+            db.refresh(result)
+            return ChatModel.model_validate(result) if result else None
+
+    def update_chat_by_id(self, id: str, chat: dict) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat_item = db.get(Chat, id)
+                chat_item.chat = chat
+                chat_item.title = chat["title"] if "title" in chat else "New Chat"
+                chat_item.updated_at = int(time.time())
+                db.commit()
+                db.refresh(chat_item)
+
+                return ChatModel.model_validate(chat_item)
+        except Exception:
+            return None
+
+    def update_chat_title_by_id(self, id: str, title: str) -> Optional[ChatModel]:
+        chat = self.get_chat_by_id(id)
+        if chat is None:
+            return None
+
+        chat = chat.chat
+        chat["title"] = title
+
+        return self.update_chat_by_id(id, chat)
+
+    def update_chat_tags_by_id(
+        self, id: str, tags: list[str], user
+    ) -> Optional[ChatModel]:
+        chat = self.get_chat_by_id(id)
+        if chat is None:
+            return None
+
+        self.delete_all_tags_by_id_and_user_id(id, user.id)
+
+        for tag in chat.meta.get("tags", []):
+            if self.count_chats_by_tag_name_and_user_id(tag, user.id) == 0:
+                Tags.delete_tag_by_name_and_user_id(tag, user.id)
+
+        for tag_name in tags:
+            if tag_name.lower() == "none":
+                continue
+
+            self.add_chat_tag_by_id_and_user_id_and_tag_name(id, user.id, tag_name)
+        return self.get_chat_by_id(id)
+
+    def get_chat_title_by_id(self, id: str) -> Optional[str]:
+        chat = self.get_chat_by_id(id)
+        if chat is None:
+            return None
+
+        return chat.chat.get("title", "New Chat")
+
+    def get_messages_by_chat_id(self, id: str) -> Optional[dict]:
+        chat = self.get_chat_by_id(id)
+        if chat is None:
+            return None
+
+        return chat.chat.get("history", {}).get("messages", {}) or {}
+
+    def upsert_message_to_chat_by_id_and_message_id(
+        self, id: str, message_id: str, message: dict
+    ) -> Optional[ChatModel]:
+        chat = self.get_chat_by_id(id)
+        if chat is None:
+            return None
+
+        chat = chat.chat
+        history = chat.get("history", {})
+
+        if message_id in history.get("messages", {}):
+            history["messages"][message_id] = {
+                **history["messages"][message_id],
+                **message,
+            }
+        else:
+            history["messages"][message_id] = message
+
+        history["currentId"] = message_id
+
+        chat["history"] = history
+        return self.update_chat_by_id(id, chat)
+
+    def add_message_status_to_chat_by_id_and_message_id(
+        self, id: str, message_id: str, status: dict
+    ) -> Optional[ChatModel]:
+        chat = self.get_chat_by_id(id)
+        if chat is None:
+            return None
+
+        chat = chat.chat
+        history = chat.get("history", {})
+
+        if message_id in history.get("messages", {}):
+            status_history = history["messages"][message_id].get("statusHistory", [])
+            status_history.append(status)
+            history["messages"][message_id]["statusHistory"] = status_history
+
+        chat["history"] = history
+        return self.update_chat_by_id(id, chat)
+
+    def insert_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+        with get_db() as db:
+            # Get the existing chat to share
+            chat = db.get(Chat, chat_id)
+            # Check if the chat is already shared
+            if chat.share_id:
+                return self.get_chat_by_id_and_user_id(chat.share_id, "shared")
+            # Create a new chat with the same data, but with a new ID
+            shared_chat = ChatModel(
+                **{
+                    "id": str(uuid.uuid4()),
+                    "user_id": f"shared-{chat_id}",
+                    "title": chat.title,
+                    "chat": chat.chat,
+                    "created_at": chat.created_at,
+                    "updated_at": int(time.time()),
+                }
+            )
+            shared_result = Chat(**shared_chat.model_dump())
+            db.add(shared_result)
+            db.commit()
+            db.refresh(shared_result)
+
+            # Update the original chat with the share_id
+            result = (
+                db.query(Chat)
+                .filter_by(id=chat_id)
+                .update({"share_id": shared_chat.id})
+            )
+            db.commit()
+            return shared_chat if (shared_result and result) else None
+
+    def update_shared_chat_by_chat_id(self, chat_id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, chat_id)
+                shared_chat = (
+                    db.query(Chat).filter_by(user_id=f"shared-{chat_id}").first()
+                )
+
+                if shared_chat is None:
+                    return self.insert_shared_chat_by_chat_id(chat_id)
+
+                shared_chat.title = chat.title
+                shared_chat.chat = chat.chat
+
+                shared_chat.updated_at = int(time.time())
+                db.commit()
+                db.refresh(shared_chat)
+
+                return ChatModel.model_validate(shared_chat)
+        except Exception:
+            return None
+
+    def delete_shared_chat_by_chat_id(self, chat_id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(user_id=f"shared-{chat_id}").delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
+    def update_chat_share_id_by_id(
+        self, id: str, share_id: Optional[str]
+    ) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.share_id = share_id
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def toggle_chat_pinned_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.pinned = not chat.pinned
+                chat.updated_at = int(time.time())
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def toggle_chat_archive_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.archived = not chat.archived
+                chat.updated_at = int(time.time())
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def archive_all_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(user_id=user_id).update({"archived": True})
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def get_archived_chat_list_by_user_id(
+        self, user_id: str, skip: int = 0, limit: int = 50
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                .filter_by(user_id=user_id, archived=True)
+                .order_by(Chat.updated_at.desc())
+                # .limit(limit).offset(skip)
+                .all()
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chat_list_by_user_id(
+        self,
+        user_id: str,
+        include_archived: bool = False,
+        skip: int = 0,
+        limit: int = 50,
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(user_id=user_id).filter_by(folder_id=None)
+            if not include_archived:
+                query = query.filter_by(archived=False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            all_chats = query.all()
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chat_title_id_list_by_user_id(
+        self,
+        user_id: str,
+        include_archived: bool = False,
+        skip: Optional[int] = None,
+        limit: Optional[int] = None,
+    ) -> list[ChatTitleIdResponse]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(user_id=user_id).filter_by(folder_id=None)
+            query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
+
+            if not include_archived:
+                query = query.filter_by(archived=False)
+
+            query = query.order_by(Chat.updated_at.desc()).with_entities(
+                Chat.id, Chat.title, Chat.updated_at, Chat.created_at
+            )
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            all_chats = query.all()
+
+            # result has to be destrctured from sqlalchemy `row` and mapped to a dict since the `ChatModel`is not the returned dataclass.
+            return [
+                ChatTitleIdResponse.model_validate(
+                    {
+                        "id": chat[0],
+                        "title": chat[1],
+                        "updated_at": chat[2],
+                        "created_at": chat[3],
+                    }
+                )
+                for chat in all_chats
+            ]
+
+    def get_chat_list_by_chat_ids(
+        self, chat_ids: list[str], skip: int = 0, limit: int = 50
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                .filter(Chat.id.in_(chat_ids))
+                .filter_by(archived=False)
+                .order_by(Chat.updated_at.desc())
+                .all()
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chat_by_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.query(Chat).filter_by(share_id=id).first()
+
+                if chat:
+                    return self.get_chat_by_id(id)
+                else:
+                    return None
+        except Exception:
+            return None
+
+    def get_chat_by_id_and_user_id(self, id: str, user_id: str) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.query(Chat).filter_by(id=id, user_id=user_id).first()
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def get_chats(self, skip: int = 0, limit: int = 50) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                # .limit(limit).offset(skip)
+                .order_by(Chat.updated_at.desc())
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                .filter_by(user_id=user_id)
+                .order_by(Chat.updated_at.desc())
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_pinned_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                .filter_by(user_id=user_id, pinned=True, archived=False)
+                .order_by(Chat.updated_at.desc())
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_archived_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
+        with get_db() as db:
+            all_chats = (
+                db.query(Chat)
+                .filter_by(user_id=user_id, archived=True)
+                .order_by(Chat.updated_at.desc())
+            )
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chats_by_user_id_and_search_text(
+        self,
+        user_id: str,
+        search_text: str,
+        include_archived: bool = False,
+        skip: int = 0,
+        limit: int = 60,
+    ) -> list[ChatModel]:
+        """
+        Filters chats based on a search query using Python, allowing pagination using skip and limit.
+        """
+        search_text = search_text.lower().strip()
+
+        if not search_text:
+            return self.get_chat_list_by_user_id(user_id, include_archived, skip, limit)
+
+        search_text_words = search_text.split(" ")
+
+        # search_text might contain 'tag:tag_name' format so we need to extract the tag_name, split the search_text and remove the tags
+        tag_ids = [
+            word.replace("tag:", "").replace(" ", "_").lower()
+            for word in search_text_words
+            if word.startswith("tag:")
+        ]
+
+        search_text_words = [
+            word for word in search_text_words if not word.startswith("tag:")
+        ]
+
+        search_text = " ".join(search_text_words)
+
+        with get_db() as db:
+            query = db.query(Chat).filter(Chat.user_id == user_id)
+
+            if not include_archived:
+                query = query.filter(Chat.archived == False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            # Check if the database dialect is either 'sqlite' or 'postgresql'
+            dialect_name = db.bind.dialect.name
+            if dialect_name == "sqlite":
+                # SQLite case: using JSON1 extension for JSON searching
+                query = query.filter(
+                    (
+                        Chat.title.ilike(
+                            f"%{search_text}%"
+                        )  # Case-insensitive search in title
+                        | text(
+                            """
+                            EXISTS (
+                                SELECT 1 
+                                FROM json_each(Chat.chat, '$.messages') AS message 
+                                WHERE LOWER(message.value->>'content') LIKE '%' || :search_text || '%'
+                            )
+                            """
+                        )
+                    ).params(search_text=search_text)
+                )
+
+                # Check if there are any tags to filter, it should have all the tags
+                if "none" in tag_ids:
+                    query = query.filter(
+                        text(
+                            """
+                            NOT EXISTS (
+                                SELECT 1
+                                FROM json_each(Chat.meta, '$.tags') AS tag
+                            )
+                            """
+                        )
+                    )
+                elif tag_ids:
+                    query = query.filter(
+                        and_(
+                            *[
+                                text(
+                                    f"""
+                                    EXISTS (
+                                        SELECT 1
+                                        FROM json_each(Chat.meta, '$.tags') AS tag
+                                        WHERE tag.value = :tag_id_{tag_idx}
+                                    )
+                                    """
+                                ).params(**{f"tag_id_{tag_idx}": tag_id})
+                                for tag_idx, tag_id in enumerate(tag_ids)
+                            ]
+                        )
+                    )
+
+            elif dialect_name == "postgresql":
+                # PostgreSQL relies on proper JSON query for search
+                query = query.filter(
+                    (
+                        Chat.title.ilike(
+                            f"%{search_text}%"
+                        )  # Case-insensitive search in title
+                        | text(
+                            """
+                            EXISTS (
+                                SELECT 1
+                                FROM json_array_elements(Chat.chat->'messages') AS message
+                                WHERE LOWER(message->>'content') LIKE '%' || :search_text || '%'
+                            )
+                            """
+                        )
+                    ).params(search_text=search_text)
+                )
+
+                # Check if there are any tags to filter, it should have all the tags
+                if "none" in tag_ids:
+                    query = query.filter(
+                        text(
+                            """
+                            NOT EXISTS (
+                                SELECT 1
+                                FROM json_array_elements_text(Chat.meta->'tags') AS tag
+                            )
+                            """
+                        )
+                    )
+                elif tag_ids:
+                    query = query.filter(
+                        and_(
+                            *[
+                                text(
+                                    f"""
+                                    EXISTS (
+                                        SELECT 1
+                                        FROM json_array_elements_text(Chat.meta->'tags') AS tag
+                                        WHERE tag = :tag_id_{tag_idx}
+                                    )
+                                    """
+                                ).params(**{f"tag_id_{tag_idx}": tag_id})
+                                for tag_idx, tag_id in enumerate(tag_ids)
+                            ]
+                        )
+                    )
+            else:
+                raise NotImplementedError(
+                    f"Unsupported dialect: {db.bind.dialect.name}"
+                )
+
+            # Perform pagination at the SQL level
+            all_chats = query.offset(skip).limit(limit).all()
+
+            print(len(all_chats))
+
+            # Validate and return chats
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chats_by_folder_id_and_user_id(
+        self, folder_id: str, user_id: str
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(folder_id=folder_id, user_id=user_id)
+            query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
+            query = query.filter_by(archived=False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            all_chats = query.all()
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def get_chats_by_folder_ids_and_user_id(
+        self, folder_ids: list[str], user_id: str
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter(
+                Chat.folder_id.in_(folder_ids), Chat.user_id == user_id
+            )
+            query = query.filter(or_(Chat.pinned == False, Chat.pinned == None))
+            query = query.filter_by(archived=False)
+
+            query = query.order_by(Chat.updated_at.desc())
+
+            all_chats = query.all()
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def update_chat_folder_id_by_id_and_user_id(
+        self, id: str, user_id: str, folder_id: str
+    ) -> Optional[ChatModel]:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.folder_id = folder_id
+                chat.updated_at = int(time.time())
+                chat.pinned = False
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def get_chat_tags_by_id_and_user_id(self, id: str, user_id: str) -> list[TagModel]:
+        with get_db() as db:
+            chat = db.get(Chat, id)
+            tags = chat.meta.get("tags", [])
+            return [Tags.get_tag_by_name_and_user_id(tag, user_id) for tag in tags]
+
+    def get_chat_list_by_user_id_and_tag_name(
+        self, user_id: str, tag_name: str, skip: int = 0, limit: int = 50
+    ) -> list[ChatModel]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(user_id=user_id)
+            tag_id = tag_name.replace(" ", "_").lower()
+
+            print(db.bind.dialect.name)
+            if db.bind.dialect.name == "sqlite":
+                # SQLite JSON1 querying for tags within the meta JSON field
+                query = query.filter(
+                    text(
+                        f"EXISTS (SELECT 1 FROM json_each(Chat.meta, '$.tags') WHERE json_each.value = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+            elif db.bind.dialect.name == "postgresql":
+                # PostgreSQL JSON query for tags within the meta JSON field (for `json` type)
+                query = query.filter(
+                    text(
+                        "EXISTS (SELECT 1 FROM json_array_elements_text(Chat.meta->'tags') elem WHERE elem = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+            else:
+                raise NotImplementedError(
+                    f"Unsupported dialect: {db.bind.dialect.name}"
+                )
+
+            all_chats = query.all()
+            print("all_chats", all_chats)
+            return [ChatModel.model_validate(chat) for chat in all_chats]
+
+    def add_chat_tag_by_id_and_user_id_and_tag_name(
+        self, id: str, user_id: str, tag_name: str
+    ) -> Optional[ChatModel]:
+        tag = Tags.get_tag_by_name_and_user_id(tag_name, user_id)
+        if tag is None:
+            tag = Tags.insert_new_tag(tag_name, user_id)
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+
+                tag_id = tag.id
+                if tag_id not in chat.meta.get("tags", []):
+                    chat.meta = {
+                        **chat.meta,
+                        "tags": list(set(chat.meta.get("tags", []) + [tag_id])),
+                    }
+
+                db.commit()
+                db.refresh(chat)
+                return ChatModel.model_validate(chat)
+        except Exception:
+            return None
+
+    def count_chats_by_tag_name_and_user_id(self, tag_name: str, user_id: str) -> int:
+        with get_db() as db:  # Assuming `get_db()` returns a session object
+            query = db.query(Chat).filter_by(user_id=user_id, archived=False)
+
+            # Normalize the tag_name for consistency
+            tag_id = tag_name.replace(" ", "_").lower()
+
+            if db.bind.dialect.name == "sqlite":
+                # SQLite JSON1 support for querying the tags inside the `meta` JSON field
+                query = query.filter(
+                    text(
+                        f"EXISTS (SELECT 1 FROM json_each(Chat.meta, '$.tags') WHERE json_each.value = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+
+            elif db.bind.dialect.name == "postgresql":
+                # PostgreSQL JSONB support for querying the tags inside the `meta` JSON field
+                query = query.filter(
+                    text(
+                        "EXISTS (SELECT 1 FROM json_array_elements_text(Chat.meta->'tags') elem WHERE elem = :tag_id)"
+                    )
+                ).params(tag_id=tag_id)
+
+            else:
+                raise NotImplementedError(
+                    f"Unsupported dialect: {db.bind.dialect.name}"
+                )
+
+            # Get the count of matching records
+            count = query.count()
+
+            # Debugging output for inspection
+            print(f"Count of chats for tag '{tag_name}':", count)
+
+            return count
+
+    def delete_tag_by_id_and_user_id_and_tag_name(
+        self, id: str, user_id: str, tag_name: str
+    ) -> bool:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                tags = chat.meta.get("tags", [])
+                tag_id = tag_name.replace(" ", "_").lower()
+
+                tags = [tag for tag in tags if tag != tag_id]
+                chat.meta = {
+                    **chat.meta,
+                    "tags": list(set(tags)),
+                }
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def delete_all_tags_by_id_and_user_id(self, id: str, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                chat = db.get(Chat, id)
+                chat.meta = {
+                    **chat.meta,
+                    "tags": [],
+                }
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
+    def delete_chat_by_id(self, id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(id=id).delete()
+                db.commit()
+
+                return True and self.delete_shared_chat_by_chat_id(id)
+        except Exception:
+            return False
+
+    def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(id=id, user_id=user_id).delete()
+                db.commit()
+
+                return True and self.delete_shared_chat_by_chat_id(id)
+        except Exception:
+            return False
+
+    def delete_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                self.delete_shared_chats_by_user_id(user_id)
+
+                db.query(Chat).filter_by(user_id=user_id).delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
+    def delete_chats_by_user_id_and_folder_id(
+        self, user_id: str, folder_id: str
+    ) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Chat).filter_by(user_id=user_id, folder_id=folder_id).delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
+    def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                chats_by_user = db.query(Chat).filter_by(user_id=user_id).all()
+                shared_chat_ids = [f"shared-{chat.id}" for chat in chats_by_user]
+
+                db.query(Chat).filter(Chat.user_id.in_(shared_chat_ids)).delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
+
+Chats = ChatTable()

backend/open_webui/models/feedbacks.py

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

backend/open_webui/models/files.py

@@ -0,0 +1,235 @@
+import logging
+import time
+from typing import Optional
+
+from open_webui.internal.db import Base, JSONField, get_db
+from open_webui.env import SRC_LOG_LEVELS
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, String, Text, JSON
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+####################
+# Files DB Schema
+####################
+
+
+class File(Base):
+    __tablename__ = "file"
+    id = Column(String, primary_key=True)
+    user_id = Column(String)
+    hash = Column(Text, nullable=True)
+
+    filename = Column(Text)
+    path = Column(Text, nullable=True)
+
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+
+    access_control = Column(JSON, nullable=True)
+
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class FileModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+
+    id: str
+    user_id: str
+    hash: Optional[str] = None
+
+    filename: str
+    path: Optional[str] = None
+
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+    access_control: Optional[dict] = None
+
+    created_at: Optional[int]  # timestamp in epoch
+    updated_at: Optional[int]  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class FileMeta(BaseModel):
+    name: Optional[str] = None
+    content_type: Optional[str] = None
+    size: Optional[int] = None
+
+    model_config = ConfigDict(extra="allow")
+
+
+class FileModelResponse(BaseModel):
+    id: str
+    user_id: str
+    hash: Optional[str] = None
+
+    filename: str
+    data: Optional[dict] = None
+    meta: FileMeta
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+    model_config = ConfigDict(extra="allow")
+
+
+class FileMetadataResponse(BaseModel):
+    id: str
+    meta: dict
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+class FileForm(BaseModel):
+    id: str
+    hash: Optional[str] = None
+    filename: str
+    path: str
+    data: dict = {}
+    meta: dict = {}
+    access_control: Optional[dict] = None
+
+
+class FilesTable:
+    def insert_new_file(self, user_id: str, form_data: FileForm) -> Optional[FileModel]:
+        with get_db() as db:
+            file = FileModel(
+                **{
+                    **form_data.model_dump(),
+                    "user_id": user_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            try:
+                result = File(**file.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return FileModel.model_validate(result)
+                else:
+                    return None
+            except Exception as e:
+                print(f"Error creating tool: {e}")
+                return None
+
+    def get_file_by_id(self, id: str) -> Optional[FileModel]:
+        with get_db() as db:
+            try:
+                file = db.get(File, id)
+                return FileModel.model_validate(file)
+            except Exception:
+                return None
+
+    def get_file_metadata_by_id(self, id: str) -> Optional[FileMetadataResponse]:
+        with get_db() as db:
+            try:
+                file = db.get(File, id)
+                return FileMetadataResponse(
+                    id=file.id,
+                    meta=file.meta,
+                    created_at=file.created_at,
+                    updated_at=file.updated_at,
+                )
+            except Exception:
+                return None
+
+    def get_files(self) -> list[FileModel]:
+        with get_db() as db:
+            return [FileModel.model_validate(file) for file in db.query(File).all()]
+
+    def get_files_by_ids(self, ids: list[str]) -> list[FileModel]:
+        with get_db() as db:
+            return [
+                FileModel.model_validate(file)
+                for file in db.query(File)
+                .filter(File.id.in_(ids))
+                .order_by(File.updated_at.desc())
+                .all()
+            ]
+
+    def get_file_metadatas_by_ids(self, ids: list[str]) -> list[FileMetadataResponse]:
+        with get_db() as db:
+            return [
+                FileMetadataResponse(
+                    id=file.id,
+                    meta=file.meta,
+                    created_at=file.created_at,
+                    updated_at=file.updated_at,
+                )
+                for file in db.query(File)
+                .filter(File.id.in_(ids))
+                .order_by(File.updated_at.desc())
+                .all()
+            ]
+
+    def get_files_by_user_id(self, user_id: str) -> list[FileModel]:
+        with get_db() as db:
+            return [
+                FileModel.model_validate(file)
+                for file in db.query(File).filter_by(user_id=user_id).all()
+            ]
+
+    def update_file_hash_by_id(self, id: str, hash: str) -> Optional[FileModel]:
+        with get_db() as db:
+            try:
+                file = db.query(File).filter_by(id=id).first()
+                file.hash = hash
+                db.commit()
+
+                return FileModel.model_validate(file)
+            except Exception:
+                return None
+
+    def update_file_data_by_id(self, id: str, data: dict) -> Optional[FileModel]:
+        with get_db() as db:
+            try:
+                file = db.query(File).filter_by(id=id).first()
+                file.data = {**(file.data if file.data else {}), **data}
+                db.commit()
+                return FileModel.model_validate(file)
+            except Exception as e:
+
+                return None
+
+    def update_file_metadata_by_id(self, id: str, meta: dict) -> Optional[FileModel]:
+        with get_db() as db:
+            try:
+                file = db.query(File).filter_by(id=id).first()
+                file.meta = {**(file.meta if file.meta else {}), **meta}
+                db.commit()
+                return FileModel.model_validate(file)
+            except Exception:
+                return None
+
+    def delete_file_by_id(self, id: str) -> bool:
+        with get_db() as db:
+            try:
+                db.query(File).filter_by(id=id).delete()
+                db.commit()
+
+                return True
+            except Exception:
+                return False
+
+    def delete_all_files(self) -> bool:
+        with get_db() as db:
+            try:
+                db.query(File).delete()
+                db.commit()
+
+                return True
+            except Exception:
+                return False
+
+
+Files = FilesTable()

backend/open_webui/models/folders.py

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

backend/open_webui/models/functions.py

@@ -2,8 +2,8 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, JSONField, get_db
-from open_webui.apps.webui.models.users import Users
+from open_webui.internal.db import Base, JSONField, get_db
+from open_webui.models.users import Users
 from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Boolean, Column, String, Text

backend/open_webui/models/groups.py

@@ -0,0 +1,193 @@
+import json
+import logging
+import time
+from typing import Optional
+import uuid
+
+from open_webui.internal.db import Base, get_db
+from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.models.files import FileMetadataResponse
+
+
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, String, Text, JSON, func
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+####################
+# UserGroup DB Schema
+####################
+
+
+class Group(Base):
+    __tablename__ = "group"
+
+    id = Column(Text, unique=True, primary_key=True)
+    user_id = Column(Text)
+
+    name = Column(Text)
+    description = Column(Text)
+
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+
+    permissions = Column(JSON, nullable=True)
+    user_ids = Column(JSON, nullable=True)
+
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class GroupModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+    id: str
+    user_id: str
+
+    name: str
+    description: str
+
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+    permissions: Optional[dict] = None
+    user_ids: list[str] = []
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class GroupResponse(BaseModel):
+    id: str
+    user_id: str
+    name: str
+    description: str
+    permissions: Optional[dict] = None
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+    user_ids: list[str] = []
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+class GroupForm(BaseModel):
+    name: str
+    description: str
+
+
+class GroupUpdateForm(GroupForm):
+    permissions: Optional[dict] = None
+    user_ids: Optional[list[str]] = None
+    admin_ids: Optional[list[str]] = None
+
+
+class GroupTable:
+    def insert_new_group(
+        self, user_id: str, form_data: GroupForm
+    ) -> Optional[GroupModel]:
+        with get_db() as db:
+            group = GroupModel(
+                **{
+                    **form_data.model_dump(),
+                    "id": str(uuid.uuid4()),
+                    "user_id": user_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            try:
+                result = Group(**group.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return GroupModel.model_validate(result)
+                else:
+                    return None
+
+            except Exception:
+                return None
+
+    def get_groups(self) -> list[GroupModel]:
+        with get_db() as db:
+            return [
+                GroupModel.model_validate(group)
+                for group in db.query(Group).order_by(Group.updated_at.desc()).all()
+            ]
+
+    def get_groups_by_member_id(self, user_id: str) -> list[GroupModel]:
+        with get_db() as db:
+            return [
+                GroupModel.model_validate(group)
+                for group in db.query(Group)
+                .filter(
+                    func.json_array_length(Group.user_ids) > 0
+                )  # Ensure array exists
+                .filter(
+                    Group.user_ids.cast(String).like(f'%"{user_id}"%')
+                )  # String-based check
+                .order_by(Group.updated_at.desc())
+                .all()
+            ]
+
+    def get_group_by_id(self, id: str) -> Optional[GroupModel]:
+        try:
+            with get_db() as db:
+                group = db.query(Group).filter_by(id=id).first()
+                return GroupModel.model_validate(group) if group else None
+        except Exception:
+            return None
+
+    def get_group_user_ids_by_id(self, id: str) -> Optional[str]:
+        group = self.get_group_by_id(id)
+        if group:
+            return group.user_ids
+        else:
+            return None
+
+    def update_group_by_id(
+        self, id: str, form_data: GroupUpdateForm, overwrite: bool = False
+    ) -> Optional[GroupModel]:
+        try:
+            with get_db() as db:
+                db.query(Group).filter_by(id=id).update(
+                    {
+                        **form_data.model_dump(exclude_none=True),
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+                return self.get_group_by_id(id=id)
+        except Exception as e:
+            log.exception(e)
+            return None
+
+    def delete_group_by_id(self, id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Group).filter_by(id=id).delete()
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def delete_all_groups(self) -> bool:
+        with get_db() as db:
+            try:
+                db.query(Group).delete()
+                db.commit()
+
+                return True
+            except Exception:
+                return False
+
+
+Groups = GroupTable()

backend/open_webui/models/knowledge.py

@@ -0,0 +1,221 @@
+import json
+import logging
+import time
+from typing import Optional
+import uuid
+
+from open_webui.internal.db import Base, get_db
+from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.models.files import FileMetadataResponse
+from open_webui.models.users import Users, UserResponse
+
+
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, String, Text, JSON
+
+from open_webui.utils.access_control import has_access
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+####################
+# Knowledge DB Schema
+####################
+
+
+class Knowledge(Base):
+    __tablename__ = "knowledge"
+
+    id = Column(Text, unique=True, primary_key=True)
+    user_id = Column(Text)
+
+    name = Column(Text)
+    description = Column(Text)
+
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
+    created_at = Column(BigInteger)
+    updated_at = Column(BigInteger)
+
+
+class KnowledgeModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+
+    id: str
+    user_id: str
+
+    name: str
+    description: str
+
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+    access_control: Optional[dict] = None
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class KnowledgeUserModel(KnowledgeModel):
+    user: Optional[UserResponse] = None
+
+
+class KnowledgeResponse(KnowledgeModel):
+    files: Optional[list[FileMetadataResponse | dict]] = None
+
+
+class KnowledgeUserResponse(KnowledgeUserModel):
+    files: Optional[list[FileMetadataResponse | dict]] = None
+
+
+class KnowledgeForm(BaseModel):
+    name: str
+    description: str
+    data: Optional[dict] = None
+    access_control: Optional[dict] = None
+
+
+class KnowledgeTable:
+    def insert_new_knowledge(
+        self, user_id: str, form_data: KnowledgeForm
+    ) -> Optional[KnowledgeModel]:
+        with get_db() as db:
+            knowledge = KnowledgeModel(
+                **{
+                    **form_data.model_dump(),
+                    "id": str(uuid.uuid4()),
+                    "user_id": user_id,
+                    "created_at": int(time.time()),
+                    "updated_at": int(time.time()),
+                }
+            )
+
+            try:
+                result = Knowledge(**knowledge.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return KnowledgeModel.model_validate(result)
+                else:
+                    return None
+            except Exception:
+                return None
+
+    def get_knowledge_bases(self) -> list[KnowledgeUserModel]:
+        with get_db() as db:
+            knowledge_bases = []
+            for knowledge in (
+                db.query(Knowledge).order_by(Knowledge.updated_at.desc()).all()
+            ):
+                user = Users.get_user_by_id(knowledge.user_id)
+                knowledge_bases.append(
+                    KnowledgeUserModel.model_validate(
+                        {
+                            **KnowledgeModel.model_validate(knowledge).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+            return knowledge_bases
+
+    def get_knowledge_bases_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[KnowledgeUserModel]:
+        knowledge_bases = self.get_knowledge_bases()
+        return [
+            knowledge_base
+            for knowledge_base in knowledge_bases
+            if knowledge_base.user_id == user_id
+            or has_access(user_id, permission, knowledge_base.access_control)
+        ]
+
+    def get_knowledge_by_id(self, id: str) -> Optional[KnowledgeModel]:
+        try:
+            with get_db() as db:
+                knowledge = db.query(Knowledge).filter_by(id=id).first()
+                return KnowledgeModel.model_validate(knowledge) if knowledge else None
+        except Exception:
+            return None
+
+    def update_knowledge_by_id(
+        self, id: str, form_data: KnowledgeForm, overwrite: bool = False
+    ) -> Optional[KnowledgeModel]:
+        try:
+            with get_db() as db:
+                knowledge = self.get_knowledge_by_id(id=id)
+                db.query(Knowledge).filter_by(id=id).update(
+                    {
+                        **form_data.model_dump(),
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+                return self.get_knowledge_by_id(id=id)
+        except Exception as e:
+            log.exception(e)
+            return None
+
+    def update_knowledge_data_by_id(
+        self, id: str, data: dict
+    ) -> Optional[KnowledgeModel]:
+        try:
+            with get_db() as db:
+                knowledge = self.get_knowledge_by_id(id=id)
+                db.query(Knowledge).filter_by(id=id).update(
+                    {
+                        "data": data,
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+                return self.get_knowledge_by_id(id=id)
+        except Exception as e:
+            log.exception(e)
+            return None
+
+    def delete_knowledge_by_id(self, id: str) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Knowledge).filter_by(id=id).delete()
+                db.commit()
+                return True
+        except Exception:
+            return False
+
+    def delete_all_knowledge(self) -> bool:
+        with get_db() as db:
+            try:
+                db.query(Knowledge).delete()
+                db.commit()
+
+                return True
+            except Exception:
+                return False
+
+
+Knowledges = KnowledgeTable()

backend/open_webui/models/memories.py

@@ -2,7 +2,7 @@ import time
 import uuid
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.internal.db import Base, get_db
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text
 

backend/open_webui/models/messages.py

@@ -0,0 +1,141 @@
+import json
+import time
+import uuid
+from typing import Optional
+
+from open_webui.internal.db import Base, get_db
+from open_webui.models.tags import TagModel, Tag, Tags
+
+
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Boolean, Column, String, Text, JSON
+from sqlalchemy import or_, func, select, and_, text
+from sqlalchemy.sql import exists
+
+####################
+# Message DB Schema
+####################
+
+
+class Message(Base):
+    __tablename__ = "message"
+    id = Column(Text, primary_key=True)
+
+    user_id = Column(Text)
+    channel_id = Column(Text, nullable=True)
+
+    content = Column(Text)
+    data = Column(JSON, nullable=True)
+    meta = Column(JSON, nullable=True)
+
+    created_at = Column(BigInteger)  # time_ns
+    updated_at = Column(BigInteger)  # time_ns
+
+
+class MessageModel(BaseModel):
+    model_config = ConfigDict(from_attributes=True)
+
+    id: str
+    user_id: str
+    channel_id: Optional[str] = None
+
+    content: str
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+    created_at: int  # timestamp in epoch
+    updated_at: int  # timestamp in epoch
+
+
+####################
+# Forms
+####################
+
+
+class MessageForm(BaseModel):
+    content: str
+    data: Optional[dict] = None
+    meta: Optional[dict] = None
+
+
+class MessageTable:
+    def insert_new_message(
+        self, form_data: MessageForm, channel_id: str, user_id: str
+    ) -> Optional[MessageModel]:
+        with get_db() as db:
+            id = str(uuid.uuid4())
+
+            ts = int(time.time_ns())
+            message = MessageModel(
+                **{
+                    "id": id,
+                    "user_id": user_id,
+                    "channel_id": channel_id,
+                    "content": form_data.content,
+                    "data": form_data.data,
+                    "meta": form_data.meta,
+                    "created_at": ts,
+                    "updated_at": ts,
+                }
+            )
+
+            result = Message(**message.model_dump())
+            db.add(result)
+            db.commit()
+            db.refresh(result)
+            return MessageModel.model_validate(result) if result else None
+
+    def get_message_by_id(self, id: str) -> Optional[MessageModel]:
+        with get_db() as db:
+            message = db.get(Message, id)
+            return MessageModel.model_validate(message) if message else None
+
+    def get_messages_by_channel_id(
+        self, channel_id: str, skip: int = 0, limit: int = 50
+    ) -> list[MessageModel]:
+        with get_db() as db:
+            all_messages = (
+                db.query(Message)
+                .filter_by(channel_id=channel_id)
+                .order_by(Message.created_at.desc())
+                .offset(skip)
+                .limit(limit)
+                .all()
+            )
+            return [MessageModel.model_validate(message) for message in all_messages]
+
+    def get_messages_by_user_id(
+        self, user_id: str, skip: int = 0, limit: int = 50
+    ) -> list[MessageModel]:
+        with get_db() as db:
+            all_messages = (
+                db.query(Message)
+                .filter_by(user_id=user_id)
+                .order_by(Message.created_at.desc())
+                .offset(skip)
+                .limit(limit)
+                .all()
+            )
+            return [MessageModel.model_validate(message) for message in all_messages]
+
+    def update_message_by_id(
+        self, id: str, form_data: MessageForm
+    ) -> Optional[MessageModel]:
+        with get_db() as db:
+            message = db.get(Message, id)
+            message.content = form_data.content
+            message.data = form_data.data
+            message.meta = form_data.meta
+            message.updated_at = int(time.time_ns())
+            db.commit()
+            db.refresh(message)
+            return MessageModel.model_validate(message) if message else None
+
+    def delete_message_by_id(self, id: str) -> bool:
+        with get_db() as db:
+            db.query(Message).filter_by(id=id).delete()
+            db.commit()
+            return True
+
+
+Messages = MessageTable()

backend/open_webui/models/models.py

@@ -2,10 +2,21 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, JSONField, get_db
+from open_webui.internal.db import Base, JSONField, get_db
 from open_webui.env import SRC_LOG_LEVELS
+
+from open_webui.models.users import Users, UserResponse
+
+
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, Text
+
+from sqlalchemy import or_, and_, func
+from sqlalchemy.dialects import postgresql, sqlite
+from sqlalchemy import BigInteger, Column, Text, JSON, Boolean
+
+
+from open_webui.utils.access_control import has_access
+
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -67,6 +78,25 @@ class Model(Base):
         Holds a JSON encoded blob of metadata, see `ModelMeta`.
     """
 
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
+    is_active = Column(Boolean, default=True)
+
     updated_at = Column(BigInteger)
     created_at = Column(BigInteger)
 
@@ -80,6 +110,9 @@ class ModelModel(BaseModel):
     params: ModelParams
     meta: ModelMeta
 
+    access_control: Optional[dict] = None
+
+    is_active: bool
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
 
@@ -91,12 +124,12 @@ class ModelModel(BaseModel):
 ####################
 
 
-class ModelResponse(BaseModel):
-    id: str
-    name: str
-    meta: ModelMeta
-    updated_at: int  # timestamp in epoch
-    created_at: int  # timestamp in epoch
+class ModelUserResponse(ModelModel):
+    user: Optional[UserResponse] = None
+
+
+class ModelResponse(ModelModel):
+    pass
 
 
 class ModelForm(BaseModel):
@@ -105,6 +138,8 @@ class ModelForm(BaseModel):
     name: str
     meta: ModelMeta
     params: ModelParams
+    access_control: Optional[dict] = None
+    is_active: bool = True
 
 
 class ModelsTable:
@@ -138,6 +173,39 @@ class ModelsTable:
         with get_db() as db:
             return [ModelModel.model_validate(model) for model in db.query(Model).all()]
 
+    def get_models(self) -> list[ModelUserResponse]:
+        with get_db() as db:
+            models = []
+            for model in db.query(Model).filter(Model.base_model_id != None).all():
+                user = Users.get_user_by_id(model.user_id)
+                models.append(
+                    ModelUserResponse.model_validate(
+                        {
+                            **ModelModel.model_validate(model).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+            return models
+
+    def get_base_models(self) -> list[ModelModel]:
+        with get_db() as db:
+            return [
+                ModelModel.model_validate(model)
+                for model in db.query(Model).filter(Model.base_model_id == None).all()
+            ]
+
+    def get_models_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[ModelUserResponse]:
+        models = self.get_models()
+        return [
+            model
+            for model in models
+            if model.user_id == user_id
+            or has_access(user_id, permission, model.access_control)
+        ]
+
     def get_model_by_id(self, id: str) -> Optional[ModelModel]:
         try:
             with get_db() as db:
@@ -146,6 +214,23 @@ class ModelsTable:
         except Exception:
             return None
 
+    def toggle_model_by_id(self, id: str) -> Optional[ModelModel]:
+        with get_db() as db:
+            try:
+                is_active = db.query(Model).filter_by(id=id).first().is_active
+
+                db.query(Model).filter_by(id=id).update(
+                    {
+                        "is_active": not is_active,
+                        "updated_at": int(time.time()),
+                    }
+                )
+                db.commit()
+
+                return self.get_model_by_id(id)
+            except Exception:
+                return None
+
     def update_model_by_id(self, id: str, model: ModelForm) -> Optional[ModelModel]:
         try:
             with get_db() as db:
@@ -153,7 +238,7 @@ class ModelsTable:
                 result = (
                     db.query(Model)
                     .filter_by(id=id)
-                    .update(model.model_dump(exclude={"id"}, exclude_none=True))
+                    .update(model.model_dump(exclude={"id"}))
                 )
                 db.commit()
 
@@ -175,5 +260,15 @@ class ModelsTable:
         except Exception:
             return False
 
+    def delete_all_models(self) -> bool:
+        try:
+            with get_db() as db:
+                db.query(Model).delete()
+                db.commit()
+
+                return True
+        except Exception:
+            return False
+
 
 Models = ModelsTable()

backend/open_webui/models/prompts.py

@@ -1,9 +1,13 @@
 import time
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, get_db
+from open_webui.internal.db import Base, get_db
+from open_webui.models.users import Users, UserResponse
+
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
+from sqlalchemy import BigInteger, Column, String, Text, JSON
+
+from open_webui.utils.access_control import has_access
 
 ####################
 # Prompts DB Schema
@@ -19,6 +23,23 @@ class Prompt(Base):
     content = Column(Text)
     timestamp = Column(BigInteger)
 
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
 
 class PromptModel(BaseModel):
     command: str
@@ -27,6 +48,7 @@ class PromptModel(BaseModel):
     content: str
     timestamp: int  # timestamp in epoch
 
+    access_control: Optional[dict] = None
     model_config = ConfigDict(from_attributes=True)
 
 
@@ -35,10 +57,15 @@ class PromptModel(BaseModel):
 ####################
 
 
+class PromptUserResponse(PromptModel):
+    user: Optional[UserResponse] = None
+
+
 class PromptForm(BaseModel):
     command: str
     title: str
     content: str
+    access_control: Optional[dict] = None
 
 
 class PromptsTable:
@@ -48,16 +75,14 @@ class PromptsTable:
         prompt = PromptModel(
             **{
                 "user_id": user_id,
-                "command": form_data.command,
-                "title": form_data.title,
-                "content": form_data.content,
+                **form_data.model_dump(),
                 "timestamp": int(time.time()),
             }
         )
 
         try:
             with get_db() as db:
-                result = Prompt(**prompt.dict())
+                result = Prompt(**prompt.model_dump())
                 db.add(result)
                 db.commit()
                 db.refresh(result)
@@ -76,11 +101,34 @@ class PromptsTable:
         except Exception:
             return None
 
-    def get_prompts(self) -> list[PromptModel]:
+    def get_prompts(self) -> list[PromptUserResponse]:
         with get_db() as db:
-            return [
-                PromptModel.model_validate(prompt) for prompt in db.query(Prompt).all()
-            ]
+            prompts = []
+
+            for prompt in db.query(Prompt).order_by(Prompt.timestamp.desc()).all():
+                user = Users.get_user_by_id(prompt.user_id)
+                prompts.append(
+                    PromptUserResponse.model_validate(
+                        {
+                            **PromptModel.model_validate(prompt).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+
+            return prompts
+
+    def get_prompts_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[PromptUserResponse]:
+        prompts = self.get_prompts()
+
+        return [
+            prompt
+            for prompt in prompts
+            if prompt.user_id == user_id
+            or has_access(user_id, permission, prompt.access_control)
+        ]
 
     def update_prompt_by_command(
         self, command: str, form_data: PromptForm
@@ -90,6 +138,7 @@ class PromptsTable:
                 prompt = db.query(Prompt).filter_by(command=command).first()
                 prompt.title = form_data.title
                 prompt.content = form_data.content
+                prompt.access_control = form_data.access_control
                 prompt.timestamp = int(time.time())
                 db.commit()
                 return PromptModel.model_validate(prompt)

backend/open_webui/models/tags.py

@@ -0,0 +1,109 @@
+import logging
+import time
+import uuid
+from typing import Optional
+
+from open_webui.internal.db import Base, get_db
+
+
+from open_webui.env import SRC_LOG_LEVELS
+from pydantic import BaseModel, ConfigDict
+from sqlalchemy import BigInteger, Column, String, JSON, PrimaryKeyConstraint
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["MODELS"])
+
+
+####################
+# Tag DB Schema
+####################
+class Tag(Base):
+    __tablename__ = "tag"
+    id = Column(String)
+    name = Column(String)
+    user_id = Column(String)
+    meta = Column(JSON, nullable=True)
+
+    # Unique constraint ensuring (id, user_id) is unique, not just the `id` column
+    __table_args__ = (PrimaryKeyConstraint("id", "user_id", name="pk_id_user_id"),)
+
+
+class TagModel(BaseModel):
+    id: str
+    name: str
+    user_id: str
+    meta: Optional[dict] = None
+    model_config = ConfigDict(from_attributes=True)
+
+
+####################
+# Forms
+####################
+
+
+class TagChatIdForm(BaseModel):
+    name: str
+    chat_id: str
+
+
+class TagTable:
+    def insert_new_tag(self, name: str, user_id: str) -> Optional[TagModel]:
+        with get_db() as db:
+            id = name.replace(" ", "_").lower()
+            tag = TagModel(**{"id": id, "user_id": user_id, "name": name})
+            try:
+                result = Tag(**tag.model_dump())
+                db.add(result)
+                db.commit()
+                db.refresh(result)
+                if result:
+                    return TagModel.model_validate(result)
+                else:
+                    return None
+            except Exception as e:
+                print(e)
+                return None
+
+    def get_tag_by_name_and_user_id(
+        self, name: str, user_id: str
+    ) -> Optional[TagModel]:
+        try:
+            id = name.replace(" ", "_").lower()
+            with get_db() as db:
+                tag = db.query(Tag).filter_by(id=id, user_id=user_id).first()
+                return TagModel.model_validate(tag)
+        except Exception:
+            return None
+
+    def get_tags_by_user_id(self, user_id: str) -> list[TagModel]:
+        with get_db() as db:
+            return [
+                TagModel.model_validate(tag)
+                for tag in (db.query(Tag).filter_by(user_id=user_id).all())
+            ]
+
+    def get_tags_by_ids_and_user_id(
+        self, ids: list[str], user_id: str
+    ) -> list[TagModel]:
+        with get_db() as db:
+            return [
+                TagModel.model_validate(tag)
+                for tag in (
+                    db.query(Tag).filter(Tag.id.in_(ids), Tag.user_id == user_id).all()
+                )
+            ]
+
+    def delete_tag_by_name_and_user_id(self, name: str, user_id: str) -> bool:
+        try:
+            with get_db() as db:
+                id = name.replace(" ", "_").lower()
+                res = db.query(Tag).filter_by(id=id, user_id=user_id).delete()
+                log.debug(f"res: {res}")
+                db.commit()
+                return True
+        except Exception as e:
+            log.error(f"delete_tag: {e}")
+            return False
+
+
+Tags = TagTable()

backend/open_webui/models/tools.py

@@ -2,11 +2,14 @@ import logging
 import time
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, JSONField, get_db
-from open_webui.apps.webui.models.users import Users
+from open_webui.internal.db import Base, JSONField, get_db
+from open_webui.models.users import Users, UserResponse
 from open_webui.env import SRC_LOG_LEVELS
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import BigInteger, Column, String, Text
+from sqlalchemy import BigInteger, Column, String, Text, JSON
+
+from open_webui.utils.access_control import has_access
+
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -26,6 +29,24 @@ class Tool(Base):
     specs = Column(JSONField)
     meta = Column(JSONField)
     valves = Column(JSONField)
+
+    access_control = Column(JSON, nullable=True)  # Controls data access levels.
+    # Defines access control rules for this entry.
+    # - `None`: Public access, available to all users with the "user" role.
+    # - `{}`: Private access, restricted exclusively to the owner.
+    # - Custom permissions: Specific access control for reading and writing;
+    #   Can specify group or user-level restrictions:
+    #   {
+    #      "read": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      },
+    #      "write": {
+    #          "group_ids": ["group_id1", "group_id2"],
+    #          "user_ids":  ["user_id1", "user_id2"]
+    #      }
+    #   }
+
     updated_at = Column(BigInteger)
     created_at = Column(BigInteger)
 
@@ -42,6 +63,8 @@ class ToolModel(BaseModel):
     content: str
     specs: list[dict]
     meta: ToolMeta
+    access_control: Optional[dict] = None
+
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
 
@@ -53,20 +76,30 @@ class ToolModel(BaseModel):
 ####################
 
 
+class ToolUserModel(ToolModel):
+    user: Optional[UserResponse] = None
+
+
 class ToolResponse(BaseModel):
     id: str
     user_id: str
     name: str
     meta: ToolMeta
+    access_control: Optional[dict] = None
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
 
 
+class ToolUserResponse(ToolResponse):
+    user: Optional[UserResponse] = None
+
+
 class ToolForm(BaseModel):
     id: str
     name: str
     content: str
     meta: ToolMeta
+    access_control: Optional[dict] = None
 
 
 class ToolValves(BaseModel):
@@ -109,9 +142,32 @@ class ToolsTable:
         except Exception:
             return None
 
-    def get_tools(self) -> list[ToolModel]:
+    def get_tools(self) -> list[ToolUserModel]:
         with get_db() as db:
-            return [ToolModel.model_validate(tool) for tool in db.query(Tool).all()]
+            tools = []
+            for tool in db.query(Tool).order_by(Tool.updated_at.desc()).all():
+                user = Users.get_user_by_id(tool.user_id)
+                tools.append(
+                    ToolUserModel.model_validate(
+                        {
+                            **ToolModel.model_validate(tool).model_dump(),
+                            "user": user.model_dump() if user else None,
+                        }
+                    )
+                )
+            return tools
+
+    def get_tools_by_user_id(
+        self, user_id: str, permission: str = "write"
+    ) -> list[ToolUserModel]:
+        tools = self.get_tools()
+
+        return [
+            tool
+            for tool in tools
+            if tool.user_id == user_id
+            or has_access(user_id, permission, tool.access_control)
+        ]
 
     def get_tool_valves_by_id(self, id: str) -> Optional[dict]:
         try:

backend/open_webui/models/users.py

@@ -1,8 +1,8 @@
 import time
 from typing import Optional
 
-from open_webui.apps.webui.internal.db import Base, JSONField, get_db
-from open_webui.apps.webui.models.chats import Chats
+from open_webui.internal.db import Base, JSONField, get_db
+from open_webui.models.chats import Chats
 from pydantic import BaseModel, ConfigDict
 from sqlalchemy import BigInteger, Column, String, Text
 
@@ -62,6 +62,21 @@ class UserModel(BaseModel):
 ####################
 
 
+class UserResponse(BaseModel):
+    id: str
+    name: str
+    email: str
+    role: str
+    profile_image_url: str
+
+
+class UserNameResponse(BaseModel):
+    id: str
+    name: str
+    role: str
+    profile_image_url: str
+
+
 class UserRoleUpdateForm(BaseModel):
     id: str
     role: str
@@ -139,13 +154,25 @@ class UsersTable:
         except Exception:
             return None
 
-    def get_users(self, skip: int = 0, limit: int = 50) -> list[UserModel]:
+    def get_users(
+        self, skip: Optional[int] = None, limit: Optional[int] = None
+    ) -> list[UserModel]:
         with get_db() as db:
-            users = (
-                db.query(User)
-                # .offset(skip).limit(limit)
-                .all()
-            )
+
+            query = db.query(User).order_by(User.created_at.desc())
+
+            if skip:
+                query = query.offset(skip)
+            if limit:
+                query = query.limit(limit)
+
+            users = query.all()
+
+            return [UserModel.model_validate(user) for user in users]
+
+    def get_users_by_user_ids(self, user_ids: list[str]) -> list[UserModel]:
+        with get_db() as db:
+            users = db.query(User).filter(User.id.in_(user_ids)).all()
             return [UserModel.model_validate(user) for user in users]
 
     def get_num_users(self) -> Optional[int]:
@@ -160,6 +187,22 @@ class UsersTable:
         except Exception:
             return None
 
+    def get_user_webhook_url_by_id(self, id: str) -> Optional[str]:
+        try:
+            with get_db() as db:
+                user = db.query(User).filter_by(id=id).first()
+
+                if user.settings is None:
+                    return None
+                else:
+                    return (
+                        user.settings.get("ui", {})
+                        .get("notifications", {})
+                        .get("webhook_url", None)
+                    )
+        except Exception:
+            return None
+
     def update_user_role_by_id(self, id: str, role: str) -> Optional[UserModel]:
         try:
             with get_db() as db:

backend/open_webui/retrieval/loaders/main.py

@@ -0,0 +1,192 @@
+import requests
+import logging
+import ftfy
+import sys
+
+from langchain_community.document_loaders import (
+    BSHTMLLoader,
+    CSVLoader,
+    Docx2txtLoader,
+    OutlookMessageLoader,
+    PyPDFLoader,
+    TextLoader,
+    UnstructuredEPubLoader,
+    UnstructuredExcelLoader,
+    UnstructuredMarkdownLoader,
+    UnstructuredPowerPointLoader,
+    UnstructuredRSTLoader,
+    UnstructuredXMLLoader,
+    YoutubeLoader,
+)
+from langchain_core.documents import Document
+from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
+
+logging.basicConfig(stream=sys.stdout, level=GLOBAL_LOG_LEVEL)
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+known_source_ext = [
+    "go",
+    "py",
+    "java",
+    "sh",
+    "bat",
+    "ps1",
+    "cmd",
+    "js",
+    "ts",
+    "css",
+    "cpp",
+    "hpp",
+    "h",
+    "c",
+    "cs",
+    "sql",
+    "log",
+    "ini",
+    "pl",
+    "pm",
+    "r",
+    "dart",
+    "dockerfile",
+    "env",
+    "php",
+    "hs",
+    "hsc",
+    "lua",
+    "nginxconf",
+    "conf",
+    "m",
+    "mm",
+    "plsql",
+    "perl",
+    "rb",
+    "rs",
+    "db2",
+    "scala",
+    "bash",
+    "swift",
+    "vue",
+    "svelte",
+    "msg",
+    "ex",
+    "exs",
+    "erl",
+    "tsx",
+    "jsx",
+    "hs",
+    "lhs",
+]
+
+
+class TikaLoader:
+    def __init__(self, url, file_path, mime_type=None):
+        self.url = url
+        self.file_path = file_path
+        self.mime_type = mime_type
+
+    def load(self) -> list[Document]:
+        with open(self.file_path, "rb") as f:
+            data = f.read()
+
+        if self.mime_type is not None:
+            headers = {"Content-Type": self.mime_type}
+        else:
+            headers = {}
+
+        endpoint = self.url
+        if not endpoint.endswith("/"):
+            endpoint += "/"
+        endpoint += "tika/text"
+
+        r = requests.put(endpoint, data=data, headers=headers)
+
+        if r.ok:
+            raw_metadata = r.json()
+            text = raw_metadata.get("X-TIKA:content", "<No text content found>")
+
+            if "Content-Type" in raw_metadata:
+                headers["Content-Type"] = raw_metadata["Content-Type"]
+
+            log.debug("Tika extracted text: %s", text)
+
+            return [Document(page_content=text, metadata=headers)]
+        else:
+            raise Exception(f"Error calling Tika: {r.reason}")
+
+
+class Loader:
+    def __init__(self, engine: str = "", **kwargs):
+        self.engine = engine
+        self.kwargs = kwargs
+
+    def load(
+        self, filename: str, file_content_type: str, file_path: str
+    ) -> list[Document]:
+        loader = self._get_loader(filename, file_content_type, file_path)
+        docs = loader.load()
+
+        return [
+            Document(
+                page_content=ftfy.fix_text(doc.page_content), metadata=doc.metadata
+            )
+            for doc in docs
+        ]
+
+    def _get_loader(self, filename: str, file_content_type: str, file_path: str):
+        file_ext = filename.split(".")[-1].lower()
+
+        if self.engine == "tika" and self.kwargs.get("TIKA_SERVER_URL"):
+            if file_ext in known_source_ext or (
+                file_content_type and file_content_type.find("text/") >= 0
+            ):
+                loader = TextLoader(file_path, autodetect_encoding=True)
+            else:
+                loader = TikaLoader(
+                    url=self.kwargs.get("TIKA_SERVER_URL"),
+                    file_path=file_path,
+                    mime_type=file_content_type,
+                )
+        else:
+            if file_ext == "pdf":
+                loader = PyPDFLoader(
+                    file_path, extract_images=self.kwargs.get("PDF_EXTRACT_IMAGES")
+                )
+            elif file_ext == "csv":
+                loader = CSVLoader(file_path)
+            elif file_ext == "rst":
+                loader = UnstructuredRSTLoader(file_path, mode="elements")
+            elif file_ext == "xml":
+                loader = UnstructuredXMLLoader(file_path)
+            elif file_ext in ["htm", "html"]:
+                loader = BSHTMLLoader(file_path, open_encoding="unicode_escape")
+            elif file_ext == "md":
+                loader = TextLoader(file_path, autodetect_encoding=True)
+            elif file_content_type == "application/epub+zip":
+                loader = UnstructuredEPubLoader(file_path)
+            elif (
+                file_content_type
+                == "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+                or file_ext == "docx"
+            ):
+                loader = Docx2txtLoader(file_path)
+            elif file_content_type in [
+                "application/vnd.ms-excel",
+                "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+            ] or file_ext in ["xls", "xlsx"]:
+                loader = UnstructuredExcelLoader(file_path)
+            elif file_content_type in [
+                "application/vnd.ms-powerpoint",
+                "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+            ] or file_ext in ["ppt", "pptx"]:
+                loader = UnstructuredPowerPointLoader(file_path)
+            elif file_ext == "msg":
+                loader = OutlookMessageLoader(file_path)
+            elif file_ext in known_source_ext or (
+                file_content_type and file_content_type.find("text/") >= 0
+            ):
+                loader = TextLoader(file_path, autodetect_encoding=True)
+            else:
+                loader = TextLoader(file_path, autodetect_encoding=True)
+
+        return loader

backend/open_webui/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/retrieval/models/colbert.py

@@ -0,0 +1,81 @@
+import os
+import torch
+import numpy as np
+from colbert.infra import ColBERTConfig
+from colbert.modeling.checkpoint import Checkpoint
+
+
+class ColBERT:
+    def __init__(self, name, **kwargs) -> None:
+        print("ColBERT: Loading model", name)
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+
+        DOCKER = kwargs.get("env") == "docker"
+        if DOCKER:
+            # This is a workaround for the issue with the docker container
+            # where the torch extension is not loaded properly
+            # and the following error is thrown:
+            # /root/.cache/torch_extensions/py311_cpu/segmented_maxsim_cpp/segmented_maxsim_cpp.so: cannot open shared object file: No such file or directory
+
+            lock_file = (
+                "/root/.cache/torch_extensions/py311_cpu/segmented_maxsim_cpp/lock"
+            )
+            if os.path.exists(lock_file):
+                os.remove(lock_file)
+
+        self.ckpt = Checkpoint(
+            name,
+            colbert_config=ColBERTConfig(model_name=name),
+        ).to(self.device)
+        pass
+
+    def calculate_similarity_scores(self, query_embeddings, document_embeddings):
+
+        query_embeddings = query_embeddings.to(self.device)
+        document_embeddings = document_embeddings.to(self.device)
+
+        # Validate dimensions to ensure compatibility
+        if query_embeddings.dim() != 3:
+            raise ValueError(
+                f"Expected query embeddings to have 3 dimensions, but got {query_embeddings.dim()}."
+            )
+        if document_embeddings.dim() != 3:
+            raise ValueError(
+                f"Expected document embeddings to have 3 dimensions, but got {document_embeddings.dim()}."
+            )
+        if query_embeddings.size(0) not in [1, document_embeddings.size(0)]:
+            raise ValueError(
+                "There should be either one query or queries equal to the number of documents."
+            )
+
+        # Transpose the query embeddings to align for matrix multiplication
+        transposed_query_embeddings = query_embeddings.permute(0, 2, 1)
+        # Compute similarity scores using batch matrix multiplication
+        computed_scores = torch.matmul(document_embeddings, transposed_query_embeddings)
+        # Apply max pooling to extract the highest semantic similarity across each document's sequence
+        maximum_scores = torch.max(computed_scores, dim=1).values
+
+        # Sum up the maximum scores across features to get the overall document relevance scores
+        final_scores = maximum_scores.sum(dim=1)
+
+        normalized_scores = torch.softmax(final_scores, dim=0)
+
+        return normalized_scores.detach().cpu().numpy().astype(np.float32)
+
+    def predict(self, sentences):
+
+        query = sentences[0][0]
+        docs = [i[1] for i in sentences]
+
+        # Embedding the documents
+        embedded_docs = self.ckpt.docFromText(docs, bsize=32)[0]
+        # Embedding the queries
+        embedded_queries = self.ckpt.queryFromText([query], bsize=32)
+        embedded_query = embedded_queries[0]
+
+        # Calculate retrieval scores for the query against all documents
+        scores = self.calculate_similarity_scores(
+            embedded_query.unsqueeze(0), embedded_docs
+        )
+
+        return scores

backend/open_webui/retrieval/utils.py

@@ -3,6 +3,7 @@ import os
 import uuid
 from typing import Optional, Union
 
+import asyncio
 import requests
 
 from huggingface_hub import snapshot_download
@@ -10,17 +11,11 @@ from langchain.retrievers import ContextualCompressionRetriever, EnsembleRetriev
 from langchain_community.retrievers import BM25Retriever
 from langchain_core.documents import Document
 
-
-from open_webui.apps.ollama.main import (
-    GenerateEmbeddingsForm,
-    generate_ollama_embeddings,
-)
-from open_webui.apps.rag.vector.connector import VECTOR_DB_CLIENT
+from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
 from open_webui.utils.misc import get_last_user_message
 
 from open_webui.env import SRC_LOG_LEVELS
 
-
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["RAG"])
 
@@ -65,20 +60,19 @@ class VectorSearchRetriever(BaseRetriever):
 
 def query_doc(
     collection_name: str,
-    query: str,
-    embedding_function,
+    query_embedding: list[float],
     k: int,
 ):
     try:
         result = VECTOR_DB_CLIENT.search(
             collection_name=collection_name,
-            vectors=[embedding_function(query)],
+            vectors=[query_embedding],
             limit=k,
         )
 
-        print("result", result)
+        if result:
+            log.info(f"query_doc:result {result.ids} {result.metadatas}")
 
-        log.info(f"query_doc:result {result}")
         return result
     except Exception as e:
         print(e)
@@ -129,7 +123,10 @@ def query_doc_with_hybrid_search(
             "metadatas": [[d.metadata for d in result]],
         }
 
-        log.info(f"query_doc_with_hybrid_search:result {result}")
+        log.info(
+            "query_doc_with_hybrid_search:result "
+            + f'{result["metadatas"]} {result["distances"]}'
+        )
         return result
     except Exception as e:
         raise e
@@ -180,32 +177,34 @@ def merge_and_sort_query_results(
 
 def query_collection(
     collection_names: list[str],
-    query: str,
+    queries: list[str],
     embedding_function,
     k: int,
 ) -> dict:
     results = []
-    for collection_name in collection_names:
-        if collection_name:
-            try:
-                result = query_doc(
-                    collection_name=collection_name,
-                    query=query,
-                    k=k,
-                    embedding_function=embedding_function,
-                )
-                results.append(result.model_dump())
-            except Exception as e:
-                log.exception(f"Error when querying the collection: {e}")
-        else:
-            pass
+    for query in queries:
+        query_embedding = embedding_function(query)
+        for collection_name in collection_names:
+            if collection_name:
+                try:
+                    result = query_doc(
+                        collection_name=collection_name,
+                        k=k,
+                        query_embedding=query_embedding,
+                    )
+                    if result is not None:
+                        results.append(result.model_dump())
+                except Exception as e:
+                    log.exception(f"Error when querying the collection: {e}")
+            else:
+                pass
 
     return merge_and_sort_query_results(results, k=k)
 
 
 def query_collection_with_hybrid_search(
     collection_names: list[str],
-    query: str,
+    queries: list[str],
     embedding_function,
     k: int,
     reranking_function,
@@ -215,15 +214,16 @@ def query_collection_with_hybrid_search(
     error = False
     for collection_name in collection_names:
         try:
-            result = query_doc_with_hybrid_search(
-                collection_name=collection_name,
-                query=query,
-                embedding_function=embedding_function,
-                k=k,
-                reranking_function=reranking_function,
-                r=r,
-            )
-            results.append(result)
+            for query in queries:
+                result = query_doc_with_hybrid_search(
+                    collection_name=collection_name,
+                    query=query,
+                    embedding_function=embedding_function,
+                    k=k,
+                    reranking_function=reranking_function,
+                    r=r,
+                )
+                results.append(result)
         except Exception as e:
             log.exception(
                 "Error when querying the collection with " f"hybrid_search: {e}"
@@ -238,160 +238,135 @@ def query_collection_with_hybrid_search(
     return merge_and_sort_query_results(results, k=k, reverse=True)
 
 
-def rag_template(template: str, context: str, query: str):
-    count = template.count("[context]")
-    assert "[context]" in template, "RAG template does not contain '[context]'"
-
-    if "<context>" in context and "</context>" in context:
-        log.debug(
-            "WARNING: Potential prompt injection attack: the RAG "
-            "context contains '<context>' and '</context>'. This might be "
-            "nothing, or the user might be trying to hack something."
-        )
-
-    if "[query]" in context:
-        query_placeholder = f"[query-{str(uuid.uuid4())}]"
-        template = template.replace("[query]", query_placeholder)
-        template = template.replace("[context]", context)
-        template = template.replace(query_placeholder, query)
-    else:
-        template = template.replace("[context]", context)
-        template = template.replace("[query]", query)
-    return template
-
-
 def get_embedding_function(
     embedding_engine,
     embedding_model,
     embedding_function,
-    openai_key,
-    openai_url,
-    batch_size,
+    url,
+    key,
+    embedding_batch_size,
 ):
     if embedding_engine == "":
         return lambda query: embedding_function.encode(query).tolist()
     elif embedding_engine in ["ollama", "openai"]:
-        if embedding_engine == "ollama":
-            func = lambda query: generate_ollama_embeddings(
-                GenerateEmbeddingsForm(
-                    **{
-                        "model": embedding_model,
-                        "prompt": query,
-                    }
-                )
-            )
-        elif embedding_engine == "openai":
-            func = lambda query: generate_openai_embeddings(
-                model=embedding_model,
-                text=query,
-                key=openai_key,
-                url=openai_url,
-            )
+        func = lambda query: generate_embeddings(
+            engine=embedding_engine,
+            model=embedding_model,
+            text=query,
+            url=url,
+            key=key,
+        )
 
-        def generate_multiple(query, f):
+        def generate_multiple(query, func):
             if isinstance(query, list):
-                if embedding_engine == "openai":
-                    embeddings = []
-                    for i in range(0, len(query), batch_size):
-                        embeddings.extend(f(query[i : i + batch_size]))
-                    return embeddings
-                else:
-                    return [f(q) for q in query]
+                embeddings = []
+                for i in range(0, len(query), embedding_batch_size):
+                    embeddings.extend(func(query[i : i + embedding_batch_size]))
+                return embeddings
             else:
-                return f(query)
+                return func(query)
 
         return lambda query: generate_multiple(query, func)
 
 
-def get_rag_context(
+def get_sources_from_files(
     files,
-    messages,
+    queries,
     embedding_function,
     k,
     reranking_function,
     r,
     hybrid_search,
 ):
-    log.debug(f"files: {files} {messages} {embedding_function} {reranking_function}")
-    query = get_last_user_message(messages)
+    log.debug(f"files: {files} {queries} {embedding_function} {reranking_function}")
 
     extracted_collections = []
     relevant_contexts = []
 
     for file in files:
-        context = None
-
-        collection_names = (
-            file["collection_names"]
-            if file["type"] == "collection"
-            else [file["collection_name"]] if file["collection_name"] else []
-        )
-
-        collection_names = set(collection_names).difference(extracted_collections)
-        if not collection_names:
-            log.debug(f"skipping {file} as it has already been extracted")
-            continue
-
-        try:
+        if file.get("context") == "full":
+            context = {
+                "documents": [[file.get("file").get("data", {}).get("content")]],
+                "metadatas": [[{"file_id": file.get("id"), "name": file.get("name")}]],
+            }
+        else:
             context = None
-            if file["type"] == "text":
-                context = file["content"]
-            else:
-                if hybrid_search:
-                    try:
-                        context = query_collection_with_hybrid_search(
+
+            collection_names = []
+            if file.get("type") == "collection":
+                if file.get("legacy"):
+                    collection_names = file.get("collection_names", [])
+                else:
+                    collection_names.append(file["id"])
+            elif file.get("collection_name"):
+                collection_names.append(file["collection_name"])
+            elif file.get("id"):
+                if file.get("legacy"):
+                    collection_names.append(f"{file['id']}")
+                else:
+                    collection_names.append(f"file-{file['id']}")
+
+            collection_names = set(collection_names).difference(extracted_collections)
+            if not collection_names:
+                log.debug(f"skipping {file} as it has already been extracted")
+                continue
+
+            try:
+                context = None
+                if file.get("type") == "text":
+                    context = file["content"]
+                else:
+                    if hybrid_search:
+                        try:
+                            context = query_collection_with_hybrid_search(
+                                collection_names=collection_names,
+                                queries=queries,
+                                embedding_function=embedding_function,
+                                k=k,
+                                reranking_function=reranking_function,
+                                r=r,
+                            )
+                        except Exception as e:
+                            log.debug(
+                                "Error when using hybrid search, using"
+                                " non hybrid search as fallback."
+                            )
+
+                    if (not hybrid_search) or (context is None):
+                        context = query_collection(
                             collection_names=collection_names,
-                            query=query,
+                            queries=queries,
                             embedding_function=embedding_function,
                             k=k,
-                            reranking_function=reranking_function,
-                            r=r,
-                        )
-                    except Exception as e:
-                        log.debug(
-                            "Error when using hybrid search, using"
-                            " non hybrid search as fallback."
                         )
+            except Exception as e:
+                log.exception(e)
 
-                if (not hybrid_search) or (context is None):
-                    context = query_collection(
-                        collection_names=collection_names,
-                        query=query,
-                        embedding_function=embedding_function,
-                        k=k,
-                    )
-        except Exception as e:
-            log.exception(e)
+            extracted_collections.extend(collection_names)
 
         if context:
-            relevant_contexts.append({**context, "source": file})
-
-        extracted_collections.extend(collection_names)
-
-    contexts = []
-    citations = []
+            if "data" in file:
+                del file["data"]
+            relevant_contexts.append({**context, "file": file})
 
+    sources = []
     for context in relevant_contexts:
         try:
             if "documents" in context:
-                contexts.append(
-                    "\n\n".join(
-                        [text for text in context["documents"][0] if text is not None]
-                    )
-                )
-
                 if "metadatas" in context:
-                    citations.append(
-                        {
-                            "source": context["source"],
-                            "document": context["documents"][0],
-                            "metadata": context["metadatas"][0],
-                        }
-                    )
+                    source = {
+                        "source": context["file"],
+                        "document": context["documents"][0],
+                        "metadata": context["metadatas"][0],
+                    }
+                    if "distances" in context and context["distances"]:
+                        source["distances"] = context["distances"][0]
+
+                    sources.append(source)
         except Exception as e:
             log.exception(e)
 
-    return contexts, citations
+    return sources
 
 
 def get_model_path(model: str, update_model: bool = False):
@@ -432,22 +407,8 @@ def get_model_path(model: str, update_model: bool = False):
         return model
 
 
-def generate_openai_embeddings(
-    model: str,
-    text: Union[str, list[str]],
-    key: str,
-    url: str = "https://api.openai.com/v1",
-):
-    if isinstance(text, list):
-        embeddings = generate_openai_batch_embeddings(model, text, key, url)
-    else:
-        embeddings = generate_openai_batch_embeddings(model, [text], key, url)
-
-    return embeddings[0] if isinstance(text, str) else embeddings
-
-
 def generate_openai_batch_embeddings(
-    model: str, texts: list[str], key: str, url: str = "https://api.openai.com/v1"
+    model: str, texts: list[str], url: str = "https://api.openai.com/v1", key: str = ""
 ) -> Optional[list[list[float]]]:
     try:
         r = requests.post(
@@ -469,6 +430,53 @@ def generate_openai_batch_embeddings(
         return None
 
 
+def generate_ollama_batch_embeddings(
+    model: str, texts: list[str], url: str, key: str = ""
+) -> Optional[list[list[float]]]:
+    try:
+        r = requests.post(
+            f"{url}/api/embed",
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {key}",
+            },
+            json={"input": texts, "model": model},
+        )
+        r.raise_for_status()
+        data = r.json()
+
+        if "embeddings" in data:
+            return data["embeddings"]
+        else:
+            raise "Something went wrong :/"
+    except Exception as e:
+        print(e)
+        return None
+
+
+def generate_embeddings(engine: str, model: str, text: Union[str, list[str]], **kwargs):
+    url = kwargs.get("url", "")
+    key = kwargs.get("key", "")
+
+    if engine == "ollama":
+        if isinstance(text, list):
+            embeddings = generate_ollama_batch_embeddings(
+                **{"model": model, "texts": text, "url": url, "key": key}
+            )
+        else:
+            embeddings = generate_ollama_batch_embeddings(
+                **{"model": model, "texts": [text], "url": url, "key": key}
+            )
+        return embeddings[0] if isinstance(text, str) else embeddings
+    elif engine == "openai":
+        if isinstance(text, list):
+            embeddings = generate_openai_batch_embeddings(model, text, url, key)
+        else:
+            embeddings = generate_openai_batch_embeddings(model, [text], url, key)
+
+        return embeddings[0] if isinstance(text, str) else embeddings
+
+
 import operator
 from typing import Optional, Sequence
 

backend/open_webui/retrieval/vector/connector.py

@@ -0,0 +1,22 @@
+from open_webui.config import VECTOR_DB
+
+if VECTOR_DB == "milvus":
+    from open_webui.retrieval.vector.dbs.milvus import MilvusClient
+
+    VECTOR_DB_CLIENT = MilvusClient()
+elif VECTOR_DB == "qdrant":
+    from open_webui.retrieval.vector.dbs.qdrant import QdrantClient
+
+    VECTOR_DB_CLIENT = QdrantClient()
+elif VECTOR_DB == "opensearch":
+    from open_webui.retrieval.vector.dbs.opensearch import OpenSearchClient
+
+    VECTOR_DB_CLIENT = OpenSearchClient()
+elif VECTOR_DB == "pgvector":
+    from open_webui.retrieval.vector.dbs.pgvector import PgvectorClient
+
+    VECTOR_DB_CLIENT = PgvectorClient()
+else:
+    from open_webui.retrieval.vector.dbs.chroma import ChromaClient
+
+    VECTOR_DB_CLIENT = ChromaClient()

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

@@ -4,7 +4,7 @@ from chromadb.utils.batch_utils import create_batches
 
 from typing import Optional
 
-from open_webui.apps.rag.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.retrieval.vector.main import VectorItem, SearchResult, GetResult
 from open_webui.config import (
     CHROMA_DATA_PATH,
     CHROMA_HTTP_HOST,
@@ -13,11 +13,24 @@ from open_webui.config import (
     CHROMA_HTTP_SSL,
     CHROMA_TENANT,
     CHROMA_DATABASE,
+    CHROMA_CLIENT_AUTH_PROVIDER,
+    CHROMA_CLIENT_AUTH_CREDENTIALS,
 )
 
 
 class ChromaClient:
     def __init__(self):
+        settings_dict = {
+            "allow_reset": True,
+            "anonymized_telemetry": False,
+        }
+        if CHROMA_CLIENT_AUTH_PROVIDER is not None:
+            settings_dict["chroma_client_auth_provider"] = CHROMA_CLIENT_AUTH_PROVIDER
+        if CHROMA_CLIENT_AUTH_CREDENTIALS is not None:
+            settings_dict["chroma_client_auth_credentials"] = (
+                CHROMA_CLIENT_AUTH_CREDENTIALS
+            )
+
         if CHROMA_HTTP_HOST != "":
             self.client = chromadb.HttpClient(
                 host=CHROMA_HTTP_HOST,
@@ -26,12 +39,12 @@ class ChromaClient:
                 ssl=CHROMA_HTTP_SSL,
                 tenant=CHROMA_TENANT,
                 database=CHROMA_DATABASE,
-                settings=Settings(allow_reset=True, anonymized_telemetry=False),
+                settings=Settings(**settings_dict),
             )
         else:
             self.client = chromadb.PersistentClient(
                 path=CHROMA_DATA_PATH,
-                settings=Settings(allow_reset=True, anonymized_telemetry=False),
+                settings=Settings(**settings_dict),
                 tenant=CHROMA_TENANT,
                 database=CHROMA_DATABASE,
             )
@@ -49,22 +62,49 @@ class ChromaClient:
         self, collection_name: str, vectors: list[list[float | int]], limit: int
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
-        collection = self.client.get_collection(name=collection_name)
-        if collection:
-            result = collection.query(
-                query_embeddings=vectors,
-                n_results=limit,
-            )
+        try:
+            collection = self.client.get_collection(name=collection_name)
+            if collection:
+                result = collection.query(
+                    query_embeddings=vectors,
+                    n_results=limit,
+                )
 
-            return SearchResult(
-                **{
-                    "ids": result["ids"],
-                    "distances": result["distances"],
-                    "documents": result["documents"],
-                    "metadatas": result["metadatas"],
-                }
-            )
-        return None
+                return SearchResult(
+                    **{
+                        "ids": result["ids"],
+                        "distances": result["distances"],
+                        "documents": result["documents"],
+                        "metadatas": result["metadatas"],
+                    }
+                )
+            return None
+        except Exception as e:
+            return None
+
+    def query(
+        self, collection_name: str, filter: dict, limit: Optional[int] = None
+    ) -> Optional[GetResult]:
+        # Query the items from the collection based on the filter.
+        try:
+            collection = self.client.get_collection(name=collection_name)
+            if collection:
+                result = collection.get(
+                    where=filter,
+                    limit=limit,
+                )
+
+                return GetResult(
+                    **{
+                        "ids": [result["ids"]],
+                        "documents": [result["documents"]],
+                        "metadatas": [result["metadatas"]],
+                    }
+                )
+            return None
+        except Exception as e:
+            print(e)
+            return None
 
     def get(self, collection_name: str) -> Optional[GetResult]:
         # Get all the items in the collection.
@@ -82,7 +122,9 @@ class ChromaClient:
 
     def insert(self, collection_name: str, items: list[VectorItem]):
         # Insert the items into the collection, if the collection does not exist, it will be created.
-        collection = self.client.get_or_create_collection(name=collection_name)
+        collection = self.client.get_or_create_collection(
+            name=collection_name, metadata={"hnsw:space": "cosine"}
+        )
 
         ids = [item["id"] for item in items]
         documents = [item["text"] for item in items]
@@ -100,7 +142,9 @@ class ChromaClient:
 
     def upsert(self, collection_name: str, items: list[VectorItem]):
         # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
-        collection = self.client.get_or_create_collection(name=collection_name)
+        collection = self.client.get_or_create_collection(
+            name=collection_name, metadata={"hnsw:space": "cosine"}
+        )
 
         ids = [item["id"] for item in items]
         documents = [item["text"] for item in items]
@@ -111,11 +155,19 @@ class ChromaClient:
             ids=ids, documents=documents, embeddings=embeddings, metadatas=metadatas
         )
 
-    def delete(self, collection_name: str, ids: list[str]):
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[list[str]] = None,
+        filter: Optional[dict] = None,
+    ):
         # Delete the items from the collection based on the ids.
         collection = self.client.get_collection(name=collection_name)
         if collection:
-            collection.delete(ids=ids)
+            if ids:
+                collection.delete(ids=ids)
+            elif filter:
+                collection.delete(where=filter)
 
     def reset(self):
         # Resets the database. This will delete all collections and item entries.

backend/open_webui/retrieval/vector/dbs/milvus.py

@@ -4,7 +4,7 @@ import json
 
 from typing import Optional
 
-from open_webui.apps.rag.vector.main import VectorItem, SearchResult, GetResult
+from open_webui.retrieval.vector.main import VectorItem, SearchResult, GetResult
 from open_webui.config import (
     MILVUS_URI,
 )
@@ -16,8 +16,6 @@ class MilvusClient:
         self.client = Client(uri=MILVUS_URI)
 
     def _result_to_get_result(self, result) -> GetResult:
-        print(result)
-
         ids = []
         documents = []
         metadatas = []
@@ -26,7 +24,6 @@ class MilvusClient:
             _ids = []
             _documents = []
             _metadatas = []
-
             for item in match:
                 _ids.append(item.get("id"))
                 _documents.append(item.get("data", {}).get("text"))
@@ -45,8 +42,6 @@ class MilvusClient:
         )
 
     def _result_to_search_result(self, result) -> SearchResult:
-        print(result)
-
         ids = []
         distances = []
         documents = []
@@ -102,7 +97,10 @@ class MilvusClient:
 
         index_params = self.client.prepare_index_params()
         index_params.add_index(
-            field_name="vector", index_type="HNSW", metric_type="COSINE", params={}
+            field_name="vector",
+            index_type="HNSW",
+            metric_type="COSINE",
+            params={"M": 16, "efConstruction": 100},
         )
 
         self.client.create_collection(
@@ -113,12 +111,14 @@ class MilvusClient:
 
     def has_collection(self, collection_name: str) -> bool:
         # Check if the collection exists based on the collection name.
+        collection_name = collection_name.replace("-", "_")
         return self.client.has_collection(
             collection_name=f"{self.collection_prefix}_{collection_name}"
         )
 
     def delete_collection(self, collection_name: str):
         # Delete the collection based on the collection name.
+        collection_name = collection_name.replace("-", "_")
         return self.client.drop_collection(
             collection_name=f"{self.collection_prefix}_{collection_name}"
         )
@@ -127,6 +127,7 @@ class MilvusClient:
         self, collection_name: str, vectors: list[list[float | int]], limit: int
     ) -> Optional[SearchResult]:
         # Search for the nearest neighbor items based on the vectors and return 'limit' number of results.
+        collection_name = collection_name.replace("-", "_")
         result = self.client.search(
             collection_name=f"{self.collection_prefix}_{collection_name}",
             data=vectors,
@@ -136,8 +137,68 @@ class MilvusClient:
 
         return self._result_to_search_result(result)
 
+    def query(self, collection_name: str, filter: dict, limit: Optional[int] = None):
+        # Construct the filter string for querying
+        collection_name = collection_name.replace("-", "_")
+        if not self.has_collection(collection_name):
+            return None
+
+        filter_string = " && ".join(
+            [
+                f'metadata["{key}"] == {json.dumps(value)}'
+                for key, value in filter.items()
+            ]
+        )
+
+        max_limit = 16383  # The maximum number of records per request
+        all_results = []
+
+        if limit is None:
+            limit = float("inf")  # Use infinity as a placeholder for no limit
+
+        # Initialize offset and remaining to handle pagination
+        offset = 0
+        remaining = limit
+
+        try:
+            # Loop until there are no more items to fetch or the desired limit is reached
+            while remaining > 0:
+                print("remaining", remaining)
+                current_fetch = min(
+                    max_limit, remaining
+                )  # Determine how many items to fetch in this iteration
+
+                results = self.client.query(
+                    collection_name=f"{self.collection_prefix}_{collection_name}",
+                    filter=filter_string,
+                    output_fields=["*"],
+                    limit=current_fetch,
+                    offset=offset,
+                )
+
+                if not results:
+                    break
+
+                all_results.extend(results)
+                results_count = len(results)
+                remaining -= (
+                    results_count  # Decrease remaining by the number of items fetched
+                )
+                offset += results_count
+
+                # Break the loop if the results returned are less than the requested fetch count
+                if results_count < current_fetch:
+                    break
+
+            print(all_results)
+            return self._result_to_get_result([all_results])
+        except Exception as e:
+            print(e)
+            return None
+
     def get(self, collection_name: str) -> Optional[GetResult]:
         # Get all the items in the collection.
+        collection_name = collection_name.replace("-", "_")
         result = self.client.query(
             collection_name=f"{self.collection_prefix}_{collection_name}",
             filter='id != ""',
@@ -146,6 +207,7 @@ class MilvusClient:
 
     def insert(self, collection_name: str, items: list[VectorItem]):
         # Insert the items into the collection, if the collection does not exist, it will be created.
+        collection_name = collection_name.replace("-", "_")
         if not self.client.has_collection(
             collection_name=f"{self.collection_prefix}_{collection_name}"
         ):
@@ -168,6 +230,7 @@ class MilvusClient:
 
     def upsert(self, collection_name: str, items: list[VectorItem]):
         # Update the items in the collection, if the items are not present, insert them. If the collection does not exist, it will be created.
+        collection_name = collection_name.replace("-", "_")
         if not self.client.has_collection(
             collection_name=f"{self.collection_prefix}_{collection_name}"
         ):
@@ -188,17 +251,35 @@ class MilvusClient:
             ],
         )
 
-    def delete(self, collection_name: str, ids: list[str]):
+    def delete(
+        self,
+        collection_name: str,
+        ids: Optional[list[str]] = None,
+        filter: Optional[dict] = None,
+    ):
         # Delete the items from the collection based on the ids.
+        collection_name = collection_name.replace("-", "_")
+        if ids:
+            return self.client.delete(
+                collection_name=f"{self.collection_prefix}_{collection_name}",
+                ids=ids,
+            )
+        elif filter:
+            # Convert the filter dictionary to a string using JSON_CONTAINS.
+            filter_string = " && ".join(
+                [
+                    f'metadata["{key}"] == {json.dumps(value)}'
+                    for key, value in filter.items()
+                ]
+            )
 
-        return self.client.delete(
-            collection_name=f"{self.collection_prefix}_{collection_name}",
-            ids=ids,
-        )
+            return self.client.delete(
+                collection_name=f"{self.collection_prefix}_{collection_name}",
+                filter=filter_string,
+            )
 
     def reset(self):
         # Resets the database. This will delete all collections and item entries.
-
         collection_names = self.client.list_collections()
         for collection_name in collection_names:
             if collection_name.startswith(self.collection_prefix):

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

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

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

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

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

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

backend/open_webui/retrieval/web/bing.py

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

backend/open_webui/retrieval/web/brave.py

@@ -2,7 +2,7 @@ import logging
 from typing import Optional
 
 import requests
-from open_webui.apps.rag.search.main import SearchResult, get_filtered_results
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 from open_webui.env import SRC_LOG_LEVELS
 
 log = logging.getLogger(__name__)

backend/open_webui/retrieval/web/duckduckgo.py

@@ -1,7 +1,7 @@
 import logging
 from typing import Optional
 
-from open_webui.apps.rag.search.main import SearchResult, get_filtered_results
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
 from duckduckgo_search import DDGS
 from open_webui.env import SRC_LOG_LEVELS