What is Open WebUI?
Open WebUI is a feature-rich, self-hosted web interface for interacting with LLMs. It looks and feels like ChatGPT but runs entirely on your own infrastructure — no data leaves your server.
Key Features
- Multi-model — Switch between Ollama models or any OpenAI-compatible API mid-conversation.
- User management — Create accounts, set roles, restrict model access per user/group.
- Conversation history — All chats saved locally, searchable, exportable.
- RAG built-in — Upload documents directly in the chat; the UI handles chunking and retrieval.
- Image generation — Integrates with Stable Diffusion (Automatic1111, ComfyUI).
- Web search — Built-in web search tool for models.
- Pipelines — Build custom processing pipelines between the UI and models.
- Multimodal — Vision models work out of the box (LLaVA, Gemma, etc.).
Quick Start with Docker
docker run -d -p 3000:8080 \
-v open-webui:/app/backend/data \
--name open-webui \
ghcr.io/open-webui/open-webui:main
Then open http://localhost:3000. Connects to Ollama at localhost:11434 by default.
Who Is It For?
Perfect for: small teams who want a private company AI assistant, developers testing local models, privacy-conscious individuals who don't want conversations stored on OpenAI servers.