Open WebUI
ActiveDescription
Open WebUI is a feature-rich, user-friendly self-hosted AI platform supporting Ollama and OpenAI-compatible APIs, with RAG, agents, and MCP capabilities.
Key Features
- Ollama/OpenAI API integration — Supports local Ollama models and OpenAI-compatible APIs (LMStudio, Groq, Mistral, etc.)
- Local RAG engine — 9 vector databases (ChromaDB, PGVector, Qdrant, etc.) with multiple document extraction engines
- Voice/video calls — Integrated STT (Whisper, Deepgram) and TTS (ElevenLabs, OpenAI) for hands-free communication
- Model builder — Create Ollama models via Web UI with custom characters/agents and community model imports
- Python function tools — Built-in code editor for extending LLM Function Calling with pure Python functions
- Enterprise access control — RBAC, LDAP/SSO authentication, and SCIM 2.0 automated user provisioning
Use Cases
💡 Deploy a private AI chat platform connected to local Ollama models for fully offline conversations
💡 Build RAG-based Q&A systems over internal documents with PDF/Word upload and retrieval
💡 Set up a parallel multi-model comparison environment to call multiple LLMs simultaneously
💡 Create voice-interactive AI assistants with real-time speech-to-text and text-to-speech
💡 Deploy an LDAP-authenticated AI platform on enterprise intranet for unified user management
Tags
Categories
Quick Start
# Quick start with Docker (includes Ollama support)
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway \
-e OLLAMA_BASE_URL=http://host.docker.internal:11434 \
--name open-webui ghcr.io/open-webui/open-webui:main
# Visit http://localhost:3000 to create admin account
# Configure Ollama or OpenAI API connection in settings