- **📚 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.
- **📥 Upload Pipeline**: Directly upload pipelines from the admin settings > pipelines section, streamlining the pipeline management process.
- **🌍 Improved Language Support**: Enhanced support for Chinese and Ukrainian languages, better catering to a global user base.
### Fixed
- **🛠️ Playground Issue**: Fixed the playground not functioning properly, ensuring a smoother user experience.
- **🔥 Temperature Parameter Issue**: Corrected the issue where the temperature value '0' was not being passed correctly.
- **📝 Prompt Input Clearing**: Resolved prompt input textarea not being cleared right away, ensuring a clean slate for new inputs.
- **🎨 Various UI Styling Issues**: Fixed numerous user interface styling problems for a more cohesive look.
- **👥 Active Users Display**: Fixed active users showing active sessions instead of actual users, now reflecting accurate user activity.
### Changed
- **🔄 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.
