- **👥 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.
- **🔍 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 the 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.
- **🌐 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.
- **🔧 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.
- **🏆 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.
- **🔢 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.
- **📚 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.
- **🔊 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.
- **🍞 Update Available Toast Dismissal**: Enhanced user experience by ensuring that once the update available notification is dismissed, it won't reappear for 24 hours.
- **📋 Ollama /embed Form Data**: Adjusted the integration inaccuracies in the /embed form data to ensure it perfectly matches with Ollama's specifications.
- **🔧 O1 Max Completion Tokens Issue**: Resolved compatibility issues with OpenAI's o1 models max_completion_tokens param to ensure smooth operation.
- **🔄 Pip Install Database Issue**: Fixed a critical issue where database changes during pip installations were reverting and not saving chat logs, now ensuring data persistence and reliability in chat operations.
- **🏷️ Chat Rename Tab Update**: Fixed the functionality to change the web browser's tab title simultaneously when a chat is renamed, keeping tab titles consistent.
- **🔧 KaTeX Rendering Improvement**: Resolved specific corner cases in KaTeX rendering to enhance the display of complex mathematical notation.
- **📞 'Call' URL Parameter Fix**: Corrected functionality for 'call' URL search parameter ensuring reliable activation of voice calls through URL triggers.
- **🔄 Configuration Reset Fix**: Fixed the RESET_CONFIG_ON_START to ensure settings revert to default correctly upon each startup, improving reliability in configuration management.
- **🌍 Filter Outlet Hook Fix**: Addressed issues in the filter outlet hook, ensuring all filter functions operate as intended.
- **🔄 Periodic Cleanup Error Resolved**: Fixed a critical RuntimeError related to the 'periodic_usage_pool_cleanup' coroutine, ensuring smooth and efficient performance post-pip install, correcting a persisting issue from version 0.3.26.
- **📊 Enhanced LaTeX Rendering**: Improved rendering for LaTeX content, enhancing clarity and visual presentation in documents and mathematical models.
- **🔄 Event Loop Error Resolution**: Addressed a critical error where a missing running event loop caused 'periodic_usage_pool_cleanup' to fail with pip installs. This fix ensures smoother and more reliable updates and installations, enhancing overall system stability.
- **🖼️ Image Generation Functionality**: Resolved an issue where image generation was not functioning, restoring full capability for visual content creation.
- **⚖️ Rate Response Corrections**: Addressed a problem where rate responses were not working, ensuring reliable feedback mechanisms are operational.
- **🚀 Rendering Optimization**: Significantly improved message rendering performance, enhancing user experience and webui responsiveness.
- **💖 Favorite Response Feature in Chat Overview**: Users can now mark responses as favorite directly from the chat overview, enhancing ease of retrieval and organization of preferred responses.
- **💬 Create Message Pairs with Shortcut**: Implemented creation of new message pairs using Cmd/Ctrl+Shift+Enter, making conversation editing faster and more intuitive.
- **🌍 Expanded User Prompt Variables**: Added weekday, timezone, and language information variables to user prompts to match system prompt variables.
- **🎵 Enhanced Audio Support**: Now includes support for 'audio/x-m4a' files, broadening compatibility with audio content within the platform.
- **🔏 Model URL Search Parameter**: Added an ability to select a model directly via URL parameters, streamlining navigation and model access.
- **📄 Enhanced PDF Citations**: PDF citations now open at the associated page, streamlining reference checks and document handling.
- **🔧Use of Redis in Sockets**: Enhanced socket implementation to fully support Redis, enabling effective stateless instances suitable for scalable load balancing.
- **🌍 Stream Individual Model Responses**: Allows specific models to have individualized streaming settings, enhancing performance and customization.
- **🕒 Display Model Hash and Last Modified Timestamp for Ollama Models**: Provides critical model details directly in the Models workspace for enhanced tracking.
- **❗ Update Info Notification for Admins**: Ensures administrators receive immediate updates upon login, keeping them informed of the latest changes and system statuses.
### Fixed
- **🗑️ Temporary File Handling On Windows**: Fixed an issue causing errors when accessing a temporary file being used by another process, Tools & Functions should now work as intended.
- **🔓 Authentication Toggle Issue**: Resolved the malfunction where setting 'WEBUI_AUTH=False' did not appropriately disable authentication, ensuring that user experience and system security settings function as configured.
- **🔧 Save As Copy Issue for Many Model Chats**: Resolved an error preventing users from save messages as copies in many model chats.
- **🔒 Sidebar Closure on Mobile**: Resolved an issue where the mobile sidebar remained open after menu engagement, improving user interface responsivity and comfort.
- **🛡️ Tooltip XSS Vulnerability**: Resolved a cross-site scripting (XSS) issue within tooltips, ensuring enhanced security and data integrity during user interactions.
### Changed
- **↩️ Deprecated Interface Stream Response Settings**: Moved to advanced parameters to streamline interface settings and enhance user clarity.
- **⚙️ Renamed 'speedRate' to 'playbackRate'**: Standardizes terminology, improving usability and understanding in media settings.
- **🌐 Task Model Unloading Issue**: Modified task handling to use the Ollama /api/chat endpoint instead of OpenAI compatible endpoint, ensuring models stay loaded and ready with custom parameters, thus minimizing delays in task execution.
- **📝 Title Generation Fix for OpenAI Compatible APIs**: Resolved an issue preventing the generation of titles, enhancing consistency and reliability when using multiple API providers.
- **🗃️ RAG Duplicate Collection Issue**: Fixed a bug causing repeated processing of the same uploaded file. Now utilizes indexed files to prevent unnecessary duplications, optimizing resource usage.
- **🖼️ Image Generation Enhancement**: Refactored OpenAI image generation endpoint to be asynchronous, preventing the WebUI from becoming unresponsive during processing, thus enhancing user experience.
- **🔓 Downgrade Authlib**: Reverted Authlib to version 1.3.1 to address and resolve issues concerning OAuth functionality.
- **🔍 Improved Message Interaction**: Enhanced the message node interface to allow for easier focus redirection with a simple click, streamlining user interaction.
- **⭐ Chat Overview**: Introducing a node-based interactive messages diagram for improved visualization of conversation flows.
- **🔗 Multiple Vector DB Support**: Now supports multiple vector databases, including the newly added Milvus support. Community contributions for additional database support are highly encouraged!
- **📡 Experimental Non-Stream Chat Completion**: Experimental feature allowing the use of OpenAI o1 models, which do not support streaming, ensuring more versatile model deployment.
- **🔍 Experimental Colbert-AI Reranker Integration**: Added support for "jinaai/jina-colbert-v2" as a reranker, enhancing search relevance and accuracy. Note: it may not function at all on low-spec computers.
- **🕸️ ENABLE_WEBSOCKET_SUPPORT**: Added environment variable for instances to ignore websocket upgrades, stabilizing connections on platforms with websocket issues.
- **🔊 Azure Speech Service Integration**: Added support for Azure Speech services for Text-to-Speech (TTS).
- **🎚️ Customizable Playback Speed**: Playback speed control is now available in Call mode settings, allowing users to adjust audio playback speed to their preferences.
- **🧠 Enhanced Error Messaging**: System now displays helpful error messages directly to users during chat completion issues.
- **📂 Save Model as Transparent PNG**: Model profile images are now saved as PNGs, supporting transparency and improving visual integration.
- **📱 iPhone Compatibility Adjustments**: Added padding to accommodate the iPhone navigation bar, improving UI display on these devices.
- **🔧 Enhanced AUTOMATIC1111 Settings**: Users can now configure 'CFG Scale', 'Sampler', and 'Scheduler' parameters directly in the admin settings, enhancing workflow flexibility without source code modifications.
- **🌍 i18n Updates**: Enhanced translations for Chinese, Ukrainian, Russian, and French, fostering a better localized experience.
### Fixed
- **🛠️ Chat Message Deletion**: Resolved issues with chat message deletion, ensuring a smoother user interaction and system stability.
- **🔢 Ordered List Numbering**: Fixed the incorrect ordering in lists.
### Changed
- **🎨 Transparent Icon Handling**: Allowed model icons to be displayed on transparent backgrounds, improving UI aesthetics.
- **📝 Improved RAG Template**: Enhanced Retrieval-Augmented Generation template, optimizing context handling and error checking for more precise operation.
- **🐳 Docker Launch Issue**: Resolved the problem preventing Open-WebUI from launching correctly when using Docker.
### Changed
- **🔍 Enhanced Search Prompts**: Improved the search query generation prompts for better accuracy and user interaction, enhancing the overall search experience.
- **🛠️ Installation of Tools & Functions Requirements**: Fixed a bug where necessary requirements for tools and functions were not properly installing.
- **🔗 Inline Image Link Rendering**: Enabled rendering of images directly from links in chat.
- **📞 Post-Call User Interface Cleanup**: Adjusted UI behavior to automatically close chat controls after a voice call ends, reducing screen clutter.
- **🎙️ Microphone Deactivation Post-Call**: Addressed an issue where the microphone remained active after calls.
- **✍️ Markdown Spacing Correction**: Corrected spacing in Markdown rendering, ensuring text appears neatly and as expected.
- **🔄 Message Re-rendering**: Fixed an issue causing all response messages to re-render with each new message, now improving chat performance.
### Changed
- **🌐 Refined Web Search Integration**: Deprecated the Search Query Generation Prompt threshold; introduced a toggle button for "Enable Web Search Query Generation" allowing users to opt-in to using web search more judiciously.
- **📝 Default Prompt Templates Update**: Emptied environment variable templates for search and title generation now default to the Open WebUI default prompt templates, simplifying configuration efforts.
- **🌐 Translation Update**: Improved Chinese translations.
### Fixed
- **📂 DATA_DIR Overriding**: Fixed an issue to avoid overriding DATA_DIR, preventing errors when directories are set identically, ensuring smoother operation and data management.
- **🛠️ Frontmatter Extraction**: Fixed the extraction process for frontmatter in tools and functions.
### Changed
- **🎨 UI Styling**: Refined the user interface styling for enhanced visual coherence and user experience.
- **🛠️ Direct Database Execution for Tools & Functions**: Enhanced the execution of Python files for tools and functions, now directly loading from the database for a more streamlined backend process.
### Fixed
- **🔄 Automatic Rewrite of Import Statements in Tools & Functions**: Tool and function scripts that import 'utils', 'apps', 'main', 'config' will now automatically rename these with 'open_webui.', ensuring compatibility and consistency across different modules.
- **🎨 Styling Adjustments**: Minor fixes in the visual styling to improve user experience and interface consistency.
- **🔄 Import/Export Configuration**: Users can now import and export webui configurations from admin settings > Database, simplifying setup replication across systems.
- **🌍 Web Search via URL Parameter**: Added support for activating web search directly through URL by setting 'web-search=true'.
- **🌐 SearchApi Integration**: Added support for SearchApi as an alternative web search provider, enhancing search capabilities within the platform.
- **🔍 Literal Type Support in Tools**: Tools now support the Literal type.
- **🌍 Updated Translations**: Improved translations for Chinese, Ukrainian, and Catalan.
### Fixed
- **🔧 Pip Install Issue**: Resolved the issue where pip install failed due to missing 'alembic.ini', ensuring smoother installation processes.
- **🌃 Automatic Theme Update**: Fixed an issue where the color theme did not update dynamically with system changes.
- **🛠️ User Agent in ComfyUI**: Added default headers in ComfyUI to fix access issues, improving reliability in network communications.
- **🔄 Missing Chat Completion Response Headers**: Ensured proper return of proxied response headers during chat completion, improving API reliability.
- **🔗 Websocket Connection Prioritization**: Modified socket.io configuration to prefer websockets and more reliably fallback to polling, enhancing connection stability.
- **🎭 Accessibility Enhancements**: Added missing ARIA labels for buttons, improving accessibility for visually impaired users.
- **⚖️ Advanced Parameter**: Fixed an issue ensuring that advanced parameters are correctly applied in all scenarios, ensuring consistent behavior of user-defined settings.
### Changed
- **🔁 Namespace Reorganization**: Reorganized all Python files under the 'open_webui' namespace to streamline the project structure and improve maintainability. Tools and functions importing from 'utils' should now use 'open_webui.utils'.
- **🚧 Dependency Updates**: Updated several backend dependencies like 'aiohttp', 'authlib', 'duckduckgo-search', 'flask-cors', and 'langchain' to their latest versions, enhancing performance and security.
- **🚀 Config DB Migration**: Migrated configuration handling from config.json to the database, enabling high-availability setups and load balancing across multiple Open WebUI instances.
- **🔗 Call Mode Activation via URL**: Added a 'call=true' URL search parameter enabling direct shortcuts to activate call mode, enhancing user interaction on mobile devices.
- **✨ TTS Content Control**: Added functionality to control how message content is segmented for Text-to-Speech (TTS) generation requests, allowing for more flexible speech output options.
- **😄 Show Knowledge Search Status**: Enhanced model usage transparency by displaying status when working with knowledge-augmented models, helping users understand the system's state during queries.
- **👆 Click-to-Copy for Codespan**: Enhanced interactive experience in the WebUI by allowing users to click to copy content from code spans directly.
- **🚫 API User Blocking via Model Filter**: Introduced the ability to block API users based on customized model filters, enhancing security and control over API access.
- **🎬 Call Overlay Styling**: Adjusted call overlay styling on large screens to not cover the entire interface, but only the chat control area, for a more unobtrusive interaction experience.
### Fixed
- **🔧 LaTeX Rendering Issue**: Addressed an issue that affected the correct rendering of LaTeX.
- **📁 File Leak Prevention**: Resolved the issue of uploaded files mistakenly being accessible across user chats.
- **🔧 Pipe Functions with '**files**' Param**: Fixed issues with '**files**' parameter not functioning correctly in pipe functions.
- **📝 Markdown Processing for RAG**: Fixed issues with processing Markdown in files.
- **🚫 Duplicate System Prompts**: Fixed bugs causing system prompts to duplicate.
### Changed
- **🔋 Wakelock Permission**: Optimized the activation of wakelock to only engage during call mode, conserving device resources and improving battery performance during idle periods.
- **🔍 Content-Type for Ollama Chats**: Added 'application/x-ndjson' content-type to '/api/chat' endpoint responses to match raw Ollama responses.
- **✋ Disable Signups Conditionally**: Implemented conditional logic to disable sign-ups when 'ENABLE_LOGIN_FORM' is set to false.
- **🔗 Temporary Chat Activation**: Integrated a new URL parameter 'temporary-chat=true' to enable temporary chat sessions directly through the URL.
- **🌄 ComfyUI Seed Node Support**: Introduced seed node support in ComfyUI for image generation, allowing users to specify node IDs for randomized seed assignment.
### Fixed
- **🛠️ Tools and Functions**: Resolved a critical issue where Tools and Functions were not properly functioning, restoring full capability and reliability to these essential features.
- **🔘 Chat Action Button in Many Model Chat**: Fixed the malfunctioning of chat action buttons in many model chat environments, ensuring a smoother and more responsive user interaction.
- **🛠️ Custom ComfyUI Workflow**: Deprecating several older environment variables, this enhancement introduces a new, customizable workflow for a more tailored user experience.
- **🔀 Merge Responses in Many Model Chat**: Enhances the dialogue by merging responses from multiple models into a single, coherent reply, improving the interaction quality in many model chats.
- **✅ Multiple Instances of Same Model in Chats**: Enhanced many model chat to support adding multiple instances of the same model.
- **🔧 Quick Actions in Model Workspace**: Enhanced Shift key quick actions for hiding/unhiding and deleting models, facilitating a smoother workflow.
- **🗨️ Markdown Rendering in User Messages**: User messages are now rendered in Markdown, enhancing readability and interaction.
- **💬 Temporary Chat Feature**: Introduced a temporary chat feature, deprecating the old chat history setting to enhance user interaction flexibility.
- **🖋️ User Message Editing**: Enhanced the user chat editing feature to allow saving changes without sending, providing more flexibility in message management.
- **🛡️ Security Enhancements**: Various security improvements implemented across the platform to ensure safer user experiences.
- **🌍 Updated Translations**: Enhanced translations for Chinese, Ukrainian, and Bahasa Malaysia, improving localization and user comprehension.
### Fixed
- **📑 Mermaid Rendering Issue**: Addressed issues with Mermaid chart rendering to ensure clean and clear visual data representation.
- **🎭 PWA Icon Maskability**: Fixed the Progressive Web App icon to be maskable, ensuring proper display on various device home screens.
- **🔀 Cloned Model Chat Freezing Issue**: Fixed a bug where cloning many model chats would cause freezing, enhancing stability and responsiveness.
- **🔍 Generic Error Handling and Refinements**: Various minor fixes and refinements to address previously untracked issues, ensuring smoother operations.
### Changed
- **🖼️ Image Generation Refactor**: Overhauled image generation processes for improved efficiency and quality.
- **🔨 Refactor Tool and Function Calling**: Refactored tool and function calling mechanisms for improved clarity and maintainability.
- **🌐 Backend Library Updates**: Updated critical backend libraries including SQLAlchemy, uvicorn[standard], faster-whisper, bcrypt, and boto3 for enhanced performance and security.
### Removed
- **🚫 Deprecated ComfyUI Environment Variables**: Removed several outdated environment variables related to ComfyUI settings, simplifying configuration management.
- **🎨 Enhanced Markdown Rendering**: Significant improvements in rendering markdown, ensuring smooth and reliable display of LaTeX and Mermaid charts, enhancing user experience with more robust visual content.
- **🔄 Auto-Install Tools & Functions Python Dependencies**: For 'Tools' and 'Functions', Open WebUI now automatically install extra python requirements specified in the frontmatter, streamlining setup processes and customization.
- **🌀 OAuth Email Claim Customization**: Introduced an 'OAUTH_EMAIL_CLAIM' variable to allow customization of the default "email" claim within OAuth configurations, providing greater flexibility in authentication processes.
- **📶 Websocket Reconnection**: Enhanced reliability with the capability to automatically reconnect when a websocket is closed, ensuring consistent and stable communication.
- **🤳 Haptic Feedback on Support Devices**: Android devices now support haptic feedback for an immersive tactile experience during certain interactions.
### Fixed
- **🛠️ ComfyUI Performance Improvement**: Addressed an issue causing FastAPI to stall when ComfyUI image generation was active; now runs in a separate thread to prevent UI unresponsiveness.
- **🔀 Session Handling**: Fixed an issue mandating session_id on client-side to ensure smoother session management and transitions.
- **🖋️ Minor Bug Fixes and Format Corrections**: Various minor fixes including typo corrections, backend formatting improvements, and test amendments enhancing overall system stability and performance.
### Changed
- **🚀 Migration to SvelteKit 2**: Upgraded the underlying framework to SvelteKit version 2, offering enhanced speed, better code structure, and improved deployment capabilities.
- **🧹 General Cleanup and Refactoring**: Performed broad cleanup and refactoring across the platform, improving code efficiency and maintaining high standards of code health.
- **🚧 Integration Testing Improvements**: Modified how Cypress integration tests detect chat messages and updated sharing tests for better reliability and accuracy.
- **📁 Standardized '.safetensors' File Extension**: Renamed the '.sft' file extension to '.safetensors' for ComfyUI workflows, standardizing file formats across the platform.
### Removed
- **🗑️ Deprecated Frontend Functions**: Removed frontend functions that were migrated to backend to declutter the codebase and reduce redundancy.
- **🔄 Sidebar Infinite Scroll**: Added an infinite scroll feature in the sidebar for more efficient chat navigation, reducing load times and enhancing user experience.
- **🚀 Enhanced Markdown Rendering**: Support for rendering all code blocks and making images clickable for preview; codespan styling is also enhanced to improve readability and user interaction.
- **🔒 Admin Shared Chat Visibility**: Admins no longer have default visibility over shared chats when ENABLE_ADMIN_CHAT_ACCESS is set to false, tightening security and privacy settings for users.
- **🌍 Language Updates**: Added Malay (Bahasa Malaysia) translation and updated Catalan and Traditional Chinese translations to improve accessibility for more users.
### Fixed
- **📊 Markdown Rendering Issues**: Resolved issues with markdown rendering to ensure consistent and correct display across components.
- **🛠️ Styling Issues**: Multiple fixes applied to styling throughout the application, improving the overall visual experience and interface consistency.
- **🗃️ Modal Handling**: Fixed an issue where modals were not closing correctly in various model chat scenarios, enhancing usability and interface reliability.
- **📄 Missing OpenAI Usage Information**: Resolved issues where usage statistics for OpenAI services were not being correctly displayed, ensuring users have access to crucial data for managing and monitoring their API consumption.
- **🔧 Non-Streaming Support for Functions Plugin**: Fixed a functionality issue with the Functions plugin where non-streaming operations were not functioning as intended, restoring full capabilities for async and sync integration within the platform.
- **🔄 Environment Variable Type Correction (COMFYUI_FLUX_FP8_CLIP)**: Corrected the data type of the 'COMFYUI_FLUX_FP8_CLIP' environment variable from string to boolean, ensuring environment settings apply correctly and enhance configuration management.
### Changed
- **🔧 Backend Dependency Updates**: Updated several backend dependencies such as boto3, pypdf, python-pptx, validators, and black, ensuring up-to-date security and performance optimizations.
- **⌨️ Arrow Keys Model Selection**: Users can now use arrow keys for quicker model selection, enhancing accessibility.
- **🔍 Fuzzy Search in Model Selector**: Enhanced model selector with fuzzy search to locate models swiftly, including descriptions.
- **🕹️ ComfyUI Flux Image Generation**: Added support for the new Flux image gen model; introduces environment controls like weight precision and CLIP model options in Settings.
- **🖥 Enhanced Latex Rendering**: Adjustments made to latex rendering processes, now accurately detecting and presenting latex inputs from text.
- **🌐 Internationalization**: Enhanced with new Romanian and updated Vietnamese and Ukrainian translations, helping broaden accessibility for international users.
- **🚧 Refactoring Various Components**: Numerous refactoring changes across styling, file handling, and function simplifications for clarity and performance.
- **🎛️ User Valves Management**: Moved user valves from settings to direct chat controls for more user-friendly access during interactions.
- **📁 Files Chat Controls**: We've reverted to the old file handling behavior where uploaded files are always included. You can now manage files directly within the chat controls section, giving you the ability to remove files as needed.
- **🔧 "Action" Function Support**: Introducing a new "Action" function to write custom buttons to the message toolbar. This feature enables more interactive messaging, with documentation coming soon.
- **📜 Citations Handling**: For newly uploaded files in documents workspace, citations will now display the actual filename. Additionally, you can click on these filenames to open the file in a new tab for easier access.
- **🛠️ Event Emitter and Call Updates**: Enhanced 'event_emitter' to allow message replacement and 'event_call' to support text input for Tools and Functions. Detailed documentation will be provided shortly.
- **🎨 Styling Refactor**: Various styling updates for a cleaner and more cohesive user interface.
- **🌐 Enhanced Translations**: Improved translations for Catalan, Ukrainian, and Brazilian Portuguese.
### Fixed
- **🔧 Chat Controls Priority**: Resolved an issue where Chat Controls values were being overridden by model information parameters. The priority is now Chat Controls, followed by Global Settings, then Model Settings.
- **🪲 Debug Logs**: Fixed an issue where debug logs were not being logged properly.
- **🔑 Automatic1111 Auth Key**: The auth key for Automatic1111 is no longer required.
- **📝 Title Generation**: Ensured that the title generation runs only once, even when multiple models are in a chat.
- **✅ Boolean Values in Params**: Added support for boolean values in parameters.
- **🖼️ Files Overlay Styling**: Fixed the styling issue with the files overlay.
- **💬 Chat Controls**: Easily adjust parameters for each chat session, offering more precise control over your interactions.
- **📌 Pinned Chats**: Support for pinned chats, allowing you to keep important conversations easily accessible.
- **📄 Apache Tika Integration**: Added support for using Apache Tika as a document loader, enhancing document processing capabilities.
- **🛠️ Custom Environment for OpenID Claims**: Allows setting custom claims for OpenID, providing more flexibility in user authentication.
- **🔧 Enhanced Tools & Functions API**: Introduced 'event_emitter' and 'event_call', now you can also add citations for better documentation and tracking. Detailed documentation will be provided on our documentation website.
- **↔️ Sideways Scrolling in Settings**: Settings tabs container now supports horizontal scrolling for easier navigation.
- **🌑 Darker OLED Theme**: Includes a new, darker OLED theme and improved styling for the light theme, enhancing visual appeal.
- **🌐 Language Updates**: Updated translations for Indonesian, German, French, and Catalan languages, expanding accessibility.
### Fixed
- **⏰ OpenAI Streaming Timeout**: Resolved issues with OpenAI streaming response using the 'AIOHTTP_CLIENT_TIMEOUT' setting, ensuring reliable performance.
- **💡 User Valves**: Fixed malfunctioning user valves, ensuring proper functionality.
- **🔄 Collapsible Components**: Addressed issues with collapsible components not working, restoring expected behavior.
### Changed
- **🗃️ Database Backend**: Switched from Peewee to SQLAlchemy for improved concurrency support, enhancing database performance.
- **🌐 Enhanced Internationalization (i18n)**: Newly introduced Indonesian translation, and updated translations for Turkish, Chinese, and Catalan languages to improve user accessibility.
### Fixed
- **🕵️♂️ Browser Language Detection**: Corrected the issue where the application was not properly detecting and adapting to the browser's language settings.
- **🔐 OIDC Admin Role Assignment**: Fixed a bug where the admin role was not being assigned to the first user who signed up via OpenID Connect (OIDC).
- **💬 Chat/Completions Endpoint**: Resolved an issue where the chat/completions endpoint was non-functional when the stream option was set to False.
- **🚫 'WEBUI_AUTH' Configuration**: Addressed the problem where setting 'WEBUI_AUTH' to False was not being applied correctly.
### Changed
- **📦 Dependency Update**: Upgraded 'authlib' from version 1.3.0 to 1.3.1 to ensure better security and performance enhancements.
- **✨ "Functions" Feature**: You can now utilize "Functions" like filters (middleware) and pipe (model) functions directly within the WebUI. While largely compatible with Pipelines, these native functions can be executed easily within Open WebUI. Example use cases for filter functions include usage monitoring, real-time translation, moderation, and automemory. For pipe functions, the scope ranges from Cohere and Anthropic integration directly within Open WebUI, enabling "Valves" for per-user OpenAI API key usage, and much more. If you encounter issues, SAFE_MODE has been introduced.
- **📁 Files API**: Compatible with OpenAI, this feature allows for custom Retrieval-Augmented Generation (RAG) in conjunction with the Filter Function. More examples will be shared on our community platform and official documentation website.
- **🛠️ Tool Enhancements**: Tools now support citations and "Valves". Documentation will be available shortly.
- **🔗 Iframe Support via Files API**: Enables rendering HTML directly into your chat interface using functions and tools. Use cases include playing games like DOOM and Snake, displaying a weather applet, and implementing Anthropic "artifacts"-like features. Stay tuned for updates on our community platform and documentation.
- **📞 Enhanced Voice Call**: Text-to-speech (TTS) callback now operates in real-time for each sentence, reducing latency by not waiting for full completion.
- **👆 Tap to Interrupt**: During a call, you can now stop the assistant from speaking by simply tapping, instead of using voice. This resolves the issue of the speaker's voice being mistakenly registered as input.
- **😊 Emoji Call**: Toggle this feature on from the Settings > Interface, allowing LLMs to express emotions using emojis during voice calls for a more dynamic interaction.
- **🖱️ Quick Archive/Delete**: Use the Shift key + mouseover on the chat list to swiftly archive or delete items.
- **📝 Markdown Support in Model Descriptions**: You can now format model descriptions with markdown, enabling bold text, links, etc.
- **🧠 Editable Memories**: Adds the capability to modify memories.
- **📋 Admin Panel Sorting**: Introduces the ability to sort users/chats within the admin panel.
- **🌑 Dark Mode for Quick Selectors**: Dark mode now available for chat quick selectors (prompts, models, documents).
- **🔧 Advanced Parameters**: Adds 'num_keep' and 'num_batch' to advanced parameters for customization.
- **📅 Dynamic System Prompts**: New variables '{{CURRENT_DATETIME}}', '{{CURRENT_TIME}}', '{{USER_LOCATION}}' added for system prompts. Ensure '{{USER_LOCATION}}' is toggled on from Settings > Interface.
- **🌐 Tavily Web Search**: Includes Tavily as a web search provider option.
- **🖊️ Federated Auth Usernames**: Ability to set user names for federated authentication.
- **🔗 Auto Clean URLs**: When adding connection URLs, trailing slashes are now automatically removed.
- **🌐 Enhanced Translations**: Improved Chinese and Swedish translations.
### Fixed
- **⏳ AIOHTTP_CLIENT_TIMEOUT**: Introduced a new environment variable 'AIOHTTP_CLIENT_TIMEOUT' for requests to Ollama lasting longer than 5 minutes. Default is 300 seconds; set to blank ('') for no timeout.
- **❌ Message Delete Freeze**: Resolved an issue where message deletion would sometimes cause the web UI to freeze.
- **🔒 Mixed Content with HTTPS Issue**: Resolved a problem where mixed content (HTTP and HTTPS) was causing security warnings and blocking resources on HTTPS sites.
- **🔍 Web Search Issue**: Addressed the problem where web search functionality was not working correctly. The 'ENABLE_RAG_LOCAL_WEB_FETCH' option has been reintroduced to restore proper web searching capabilities.
- **💾 RAG Template Not Being Saved**: Fixed an issue where the RAG template was not being saved correctly, ensuring your custom templates are now preserved as expected.
- **🛠️ Native Python Function Calling**: Introducing native Python function calling within Open WebUI. We’ve also included a built-in code editor to seamlessly develop and integrate function code within the 'Tools' workspace. With this, you can significantly enhance your LLM’s capabilities by creating custom RAG pipelines, web search tools, and even agent-like features such as sending Discord messages.
- **🌐 DuckDuckGo Integration**: Added DuckDuckGo as a web search provider, giving you more search options.
- **🌏 Enhanced Translations**: Improved translations for Vietnamese and Chinese languages, making the interface more accessible.
### Fixed
- **🔗 Web Search URL Error Handling**: Fixed the issue where a single URL error would disrupt the data loading process in Web Search mode. Now, such errors will be handled gracefully to ensure uninterrupted data loading.
- **🖥️ Frontend Responsiveness**: Resolved the problem where the frontend would stop responding if the backend encounters an error while downloading a model. Improved error handling to maintain frontend stability.
- **🔧 Dependency Issues in pip**: Fixed issues related to pip installations, ensuring all dependencies are correctly managed to prevent installation errors.
- **🔍 Web Search Query Status**: The web search query will now persist in the results section to aid in easier debugging and tracking of search queries.
- **🌐 New Web Search Provider**: We have added Serply as a new option for web search providers, giving you more choices for your search needs.
- **🌏 Improved Translations**: We've enhanced translations for Chinese and Portuguese.
### Fixed
- **🎤 Audio File Upload Issue**: The bug that prevented audio files from being uploaded in chat input has been fixed, ensuring smooth communication.
- **💬 Message Input Handling**: Improved the handling of message inputs by instantly clearing images and text after sending, along with immediate visual indications when a response message is loading, enhancing user feedback.
- **⚙️ Parameter Registration and Validation**: Fixed the issue where parameters were not registering in certain cases and addressed the problem where users were unable to save due to invalid input errors.
- **📚 Knowledge Support for Models**: Attach documents directly to models from the models workspace, enhancing the information available to each model.
- **🎙️ Hands-Free Voice Call Feature**: Initiate voice calls without needing to use your hands, making interactions more seamless.
- **📹 Video Call Feature**: Enable video calls with supported vision models like Llava and GPT-4o, adding a visual dimension to your communications.
- **🎛️ Enhanced UI for Voice Recording**: Improved user interface for the voice recording feature, making it more intuitive and user-friendly.
- **🌐 External STT Support**: Now support for external Speech-To-Text services, providing more flexibility in choosing your STT provider.
- **⚙️ Unified Settings**: Consolidated settings including document settings under a new admin settings section for easier management.
- **📝 RAG Implementation**: Updated the RAG (Retrieval-Augmented Generation) implementation to use a system prompt for context, instead of overriding the user's prompt.
- **🔄 Settings Relocation**: Moved Models, Connections, Audio, and Images settings to the admin settings for better organization.
- **✍️ Improved Title Generation**: Enhanced the default prompt for title generation, yielding better results.
- **🔧 Backend Task Management**: Tasks like title generation and search query generation are now managed on the backend side and controlled only by the admin.
- **🔍 Editable Search Query Prompt**: You can now edit the search query generation prompt, offering more control over how queries are generated.
- **📏 Prompt Length Threshold**: Set the prompt length threshold for search query generation from the admin settings, giving more customization options.
- **📣 Settings Consolidation**: Merged the Banners admin setting with the Interface admin setting for a more streamlined settings area.
- **👥 Active Users Indicator**: Now you can see how many people are currently active and what they are running. This helps you gauge when performance might slow down due to a high number of users.
- **🗂️ Create Ollama Modelfile**: The option to create a modelfile for Ollama has been reintroduced in the Settings > Models section, making it easier to manage your models.
- **⚙️ Default Model Setting**: Added an option to set the default model from Settings > Interface. This feature is now easily accessible, especially convenient for mobile users as it was previously hidden.
- **🌐 Enhanced Translations**: We've improved the Chinese translations and added support for Turkmen and Norwegian languages to make the interface more accessible globally.
### Fixed
- **📱 Mobile View Improvements**: The UI now uses dvh (dynamic viewport height) instead of vh (viewport height), providing a better and more responsive experience for mobile users.
- **👤 Improved Account Pending Page**: The account pending page now displays admin details by default to avoid confusion. You can disable this feature in the admin settings if needed.
- **🌐 HTTP Proxy Support**: We have enabled the use of the 'http_proxy' environment variable in OpenAI and Ollama API calls, making it easier to configure network settings.
- **❓ Quick Access to Documentation**: You can now easily access Open WebUI documents via a question mark button located at the bottom right corner of the screen (available on larger screens like PCs).
- **🌍 Enhanced Translation**: Improvements have been made to translations.
### Fixed
- **🔍 SearxNG Web Search**: Fixed the issue where the SearxNG web search functionality was not working properly.
- **📁 Export Chat as JSON**: You can now export individual chats as JSON files from the navbar menu by navigating to 'Download > Export Chat'. This makes sharing specific conversations easier.
- **✏️ Edit Titles with Double Click**: Double-click on titles to rename them quickly and efficiently.
- **🧩 Batch Multiple Embeddings**: Introduced 'RAG_EMBEDDING_OPENAI_BATCH_SIZE' to process multiple embeddings in a batch, enhancing performance for large datasets.
- **🌍 Improved Translations**: Enhanced the translation quality across various languages for a better user experience.
### Fixed
- **🛠️ Modelfile Migration Script**: Fixed an issue where the modelfile migration script would fail if an invalid modelfile was encountered.
- **💬 Zhuyin Input Method on Mac**: Resolved an issue where using the Zhuyin input method in the Web UI on a Mac caused text to send immediately upon pressing the enter key, leading to incorrect input.
- **🔊 Local TTS Voice Selection**: Fixed the issue where the selected local Text-to-Speech (TTS) voice was not being displayed in settings.
- **🌊 Mermaid Rendering Support**: We've included support for Mermaid rendering. This allows you to create beautiful diagrams and flowcharts directly within Open WebUI.
- **🔄 New Environment Variable 'RESET_CONFIG_ON_START'**: Introducing a new environment variable: 'RESET_CONFIG_ON_START'. Set this variable to reset your configuration settings upon starting the application, making it easier to revert to default settings.
- **🌐 Improved Vietnamese Translation**: Enhanced Vietnamese language support for a better user experience for our Vietnamese-speaking community.
### Fixed
- **🔧 OpenAI URL API Save Issue**: Corrected a problem preventing the saving of OpenAI URL API settings.
- **🚫 Display Issue with Disabled Ollama API**: Fixed the display bug causing models to appear in settings when the Ollama API was disabled.
### Changed
- **💡 Versioning Update**: As a reminder from our previous update, version 0.2.y will focus primarily on bug fixes, while major updates will be designated as 0.x from now on for better version tracking.
- **🔧 Pipelines Support**: Open WebUI now includes a plugin framework for enhanced customization and functionality (https://github.com/open-webui/pipelines). Easily add custom logic and integrate Python libraries, from AI agents to home automation APIs.
- **🔍 Web Search Support**: Introducing built-in web search capabilities via RAG API, allowing users to search using SearXNG, Google Programmatic Search Engine, Brave Search, serpstack, and serper. Activate it effortlessly by adding necessary variables from Document settings > Web Params.
- **🚫 Bundled LiteLLM Support Deprecated**: Migrate your LiteLLM config.yaml to a self-hosted LiteLLM instance. LiteLLM can still be added via OpenAI Connections. Download the LiteLLM config.yaml from admin settings > database > export LiteLLM config.yaml.
- **🔒 Auth Disable Option**: Introducing the ability to disable authentication. Set 'WEBUI_AUTH' to False to disable authentication. Note: Only applicable for fresh installations without existing users.
- **📹 Enhanced YouTube RAG Pipeline**: Now supports non-English videos for an enriched experience.
- **🔊 Specify OpenAI TTS Models**: Customize your TTS experience by specifying OpenAI TTS models.
- **🔧 Additional Environment Variables**: Discover more environment variables in our comprehensive documentation at Open WebUI Documentation (https://docs.openwebui.com).
- **🌐 Language Support**: Arabic, Finnish, and Hindi added; Improved support for German, Vietnamese, and Chinese.
### Fixed
- **🛠️ Model Selector Styling**: Addressed styling issues for improved user experience.
- **🔍 Scroll Gesture Bug**: Adjusted gesture sensitivity to prevent accidental activation when scrolling through code on mobile; now requires scrolling from the leftmost side to open the sidebar.
### Changed
- **🔄 Unlimited Context Length**: Advanced settings now allow unlimited max context length (previously limited to 16000).
- **👑 Super Admin Assignment**: The first signup is automatically assigned a super admin role, unchangeable by other admins.
- **🛡️ Admin User Restrictions**: User action buttons from the admin panel are now disabled for users with admin roles.
- **🔝 Default Model Selector**: Set as default model option now exclusively available on the landing page.
- **🌍 Language Support Expansion**: Added support for Bangla (bn-BD), along with enhancements to Chinese, Spanish, and Ukrainian translations.
- **💻 Improved LaTeX Rendering Performance**: Enjoy faster rendering times for LaTeX equations.
- **🔧 More Environment Variables**: Explore additional environment variables in our documentation (https://docs.openwebui.com), including the 'ENABLE_LITELLM' option to manage memory usage.
### Fixed
- **🔧 Ollama Compatibility**: Resolved errors occurring when Ollama server version isn't an integer, such as SHA builds or RCs.
- **🐛 Various OpenAI API Issues**: Addressed several issues related to the OpenAI API.
- **🛑 Stop Sequence Issue**: Fixed the problem where the stop sequence with a backslash '\' was not functioning.
- **🔤 Font Fallback**: Corrected font fallback issue.
- **🔗 Webhook Integration**: Now you can subscribe to new user sign-up events via webhook. Simply navigate to the admin panel > admin settings > webhook URL.
- **🛡️ Enhanced Model Filtering**: Alongside Ollama, OpenAI proxy model whitelisting, we've added model filtering functionality for LiteLLM proxy.
- **🌍 Expanded Language Support**: Spanish, Catalan, and Vietnamese languages are now available, with improvements made to others.
- 🌍 **Localization**: You can now change the UI language in Settings > General. We support Ukrainian, German, Farsi (Persian), Traditional and Simplified Chinese and French translations. You can help us to translate the UI into your language! More info in our [CONTRIBUTION.md](https://github.com/open-webui/open-webui/blob/main/docs/CONTRIBUTING.md#-translations-and-internationalization).
- 🎨 **System-wide Theme**: Introducing a new system-wide theme for enhanced visual experience.
- 🌑 **Dark Background on Select Fields**: Improved readability by adding a dark background to select fields, addressing issues on certain browsers/devices.
- **Multiple OPENAI_API_BASE_URLS Issue**: Resolved issue where multiple base URLs caused conflicts when one wasn't functioning.
- **RAG Encoding Issue**: Fixed encoding problem in RAG.
- **🔄 Multiple Ollama Servers Support**: Enjoy enhanced scalability and performance with support for multiple Ollama servers in a single WebUI. Load balancing features are now available, providing improved efficiency (#788, #278).
- **🔧 Support for Claude 3 and Gemini**: Responding to user requests, we've expanded our toolset to include Claude 3 and Gemini, offering a wider range of functionalities within our platform (#1064).
- **🔍 OCR Functionality for PDF Loader**: We've augmented our PDF loader with Optical Character Recognition (OCR) capabilities. Now, extract text from scanned documents and images within PDFs, broadening the scope of content processing (#1050).
### Fixed
- **🛠️ RAG Collection**: Implemented a dynamic mechanism to recreate RAG collections, ensuring users have up-to-date and accurate data (#1031).
- **📝 User Agent Headers**: Fixed issue of RAG web requests being sent with empty user_agent headers, reducing rejections from certain websites. Realistic headers are now utilized for these requests (#1024).
- **⏹️ Playground Cancel Functionality**: Introducing a new "Cancel" option for stopping Ollama generation in the Playground, enhancing user control and usability (#1006).
- **🔤 Typographical Error in 'ASSISTANT' Field**: Corrected a typographical error in the 'ASSISTANT' field within the GGUF model upload template for accuracy and consistency (#1061).
### Changed
- **🔄 Refactored Message Deletion Logic**: Streamlined message deletion process for improved efficiency and user experience, simplifying interactions within the platform (#1004).
- **⚠️ Deprecation of `OLLAMA_API_BASE_URL`**: Deprecated `OLLAMA_API_BASE_URL` environment variable; recommend using `OLLAMA_BASE_URL` instead. Refer to our documentation for further details.
- **🎮 Playground Feature (Beta)**: Explore the full potential of the raw API through an intuitive UI with our new playground feature, accessible to admins. Simply click on the bottom name area of the sidebar to access it. The playground feature offers two modes text completion (notebook) and chat completion. As it's in beta, please report any issues you encounter.
- **🛠️ Direct Database Download for Admins**: Admins can now download the database directly from the WebUI via the admin settings.
- **🎨 Additional RAG Settings**: Customize your RAG process with the ability to edit the TOP K value. Navigate to Documents > Settings > General to make changes.
- Resolved input autofocus issue on mobile when the sidebar is open, making it easier to use.
- Corrected numbered list display issue in Safari (#963).
- Restricted user ability to delete chats without proper permissions (#993).
### Changed
- **Simplified Ollama Settings**: Ollama settings now don't require the `/api` suffix. You can now utilize the Ollama base URL directly, e.g., `http://localhost:11434`. Also, an `OLLAMA_BASE_URL` environment variable has been added.
- **Database Renaming**: Starting from this release, `ollama.db` will be automatically renamed to `webui.db`.
- Fixed a bug where defining an OpenAI-compatible API server using 'OPENAI_API_BASE_URL' containing 'openai' string resulted in hiding models not containing 'gpt' string from the model menu. (Issue #930)
- **🏷️ Document Pre-tagging**: Simply click the "+" button at the top, enter tag names in the popup window, or select from a list of existing tags. Then, upload files with the added tags for streamlined organization.
- **🤖 Change embedding model**: Change the embedding model used to generate embeddings for your chats in the Dockerfile. Use any sentence transformer model from huggingface.co.
