open-webui One-stop self-hosted AI platform

open-webui is a powerful and user-friendly self-hosted AI platform that supports fully offline operation, integrates multiple leading LLM runners (including Ollama and OpenAI-compatible APIs), and offers web search, local RAG integration, permission management, and session persistence. Developed with a JavaScript and Python hybrid stack, it features mobile adaptation, Markdown and LaTeX rendering, and multi-platform compatibility; it has earned a 9.6 rating on HelloGitHub, boasts 93.7k★ and 505 contributors, and aims to deliver a one-stop local AI experience for developers.

Source code: https://github.com/open-webui/open-webui
Documentation: https://docs.openwebui.com/

• 🚀 Effortless Setup: Install seamlessly using Docker or Kubernetes (kubectl, kustomize or helm) for a hassle-free experience with support for both :ollama and :cuda tagged images.

• 🤝 Ollama/OpenAI API Integration: Effortlessly integrate OpenAI-compatible APIs for versatile conversations alongside Ollama models. Customize the OpenAI API URL to link with LMStudio, GroqCloud, Mistral, OpenRouter, and more.

• 🛡️ 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.

• 📱 Progressive Web App (PWA) for Mobile: Enjoy a native app-like experience on your mobile device with our PWA, providing offline access on localhost and a seamless user interface.

• ✒️🔢 Full Markdown and LaTeX Support: Elevate your LLM experience with comprehensive Markdown and LaTeX capabilities for enriched interaction.

• 🎤📹 Hands-Free Voice/Video Call: Experience seamless communication with integrated hands-free voice and video call features, allowing for a more dynamic and interactive chat environment.

• 🛠️ Model Builder: Easily create Ollama models via the Web UI. Create and add custom characters/agents, customize chat elements, and import models effortlessly through Open WebUI Community integration.

• 🐍 Native Python Function Calling Tool: Enhance your LLMs with built-in code editor support in the tools workspace. Bring Your Own Function (BYOF) by simply adding your pure Python functions, enabling seamless integration with LLMs.

• 📚 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, 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.

• 🎨 Image Generation Integration: Seamlessly incorporate image generation capabilities using options such as AUTOMATIC1111 API or ComfyUI (local), and OpenAI’s DALL-E (external), enriching your chat experience with dynamic visual content.

• ⚙️ Many Models Conversations: Effortlessly engage with various models simultaneously, harnessing their unique strengths for optimal responses. Enhance your experience by leveraging a diverse set of models in parallel.

• 🔐 Role-Based Access Control (RBAC): Ensure secure access with restricted permissions; only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.

• 🌐🌍 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. Launch your Pipelines instance, set the OpenAI URL to the Pipelines URL, and explore endless possibilities. 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.