A self-hostable web interface for managing and interacting with LLM runners and AI features. It is designed to operate entirely offline and supports various model providers alongside built-in retrieval augmented generation.
Project overview
A self-hostable web interface for managing and interacting with LLM runners and AI features. It is designed to operate entirely offline and supports various model providers alongside built-in retrieval augmented generation.
Project type
RAG · Model Runtime
Use cases
Chat Assistants · Knowledge Q&A
Deployment
Docker / Docker Compose
License
License pending
Best for
General users and developers who require an offline-capable, self-hosted web interface to manage local LLM runners.
Enterprise teams needing a self-hosted AI platform with granular administrative roles and enterprise authentication integrations.
Key capabilities
Connect any OpenAI-compatible API alongside local Ollama models, allowing users to mix and match providers freely.
Extend Open WebUI with Filters, Actions, Pipes, Tools, and Skills, and connect external services through MCP, MCPO, and OpenAPI tool servers.
Retrieval Augmented Generation backed by 9 vector databases and multiple content-extraction engines, supporting hybrid search with reranking.
Search the web through dozens of providers and inject results directly into the conversation.
Pull websites into chat using a URL command or let the model fetch them automatically when needed.
Create and edit images with multiple engines including OpenAI DALL·E, Gemini, ComfyUI (local), and AUTOMATIC1111 (local).
Integrated voice and video calls with multiple Speech-to-Text and Text-to-Speech engines.
Administrators define detailed roles, groups, and permissions, giving each user exactly the access they need securely by default.
Limitations and risks
Requires Python 3.11 to avoid compatibility issues when installing via pip.
The :dev branch contains the latest unstable features and may contain bugs or incomplete features.
Getting started
Installation difficulty is rated as easy, providing a single Docker command installation with bundled Ollama or a straightforward pip install command.
Begin by installing via pip or Docker, then access the web interface at localhost.
Evidence and sources
README: Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-c…
README: 🤝 Broad Model & API Integration: Connect any OpenAI-compatible API alongside local Ollama models. Point the API URL at LMStudio, GroqCloud, Mistral, OpenRouter, vLLM, and more to…
Release: v0.10.2
README: Open WebUI can be installed using pip, the Python package installer. Before proceeding, ensure you're using Python 3.11 to avoid compatibility issues.
README: Effortless Setup: Install seamlessly via pip, uv, Docker, or Kubernetes (kubectl, kustomize, or helm), with :ollama and :cuda tagged images available for container deployments.