Open WebUI
Open WebUI is a self-hosted, extensible AI platform that provides a user-friendly interface for interacting with local models via Ollama and any OpenAI-compatible API. It solves the problem of managing multiple AI providers and models in one place, offering features like RAG, web search, image generation, and multi-model conversations. It is for developers and teams who want a private, customizable AI interface.
🎬 I’m changing how I use AI (Open WebUI + LiteLLM) · NetworkChuck
✨ Key features
- Effortless setup via pip, Docker, or Kubernetes
- Broad model integration with Ollama and OpenAI-compatible APIs
- Granular RBAC and user groups for secure access
- Plugin support for filters, actions, pipes, tools, and skills
- Persistent memory across conversations
- Local RAG with hybrid search and web search integration
🎯 Use cases
- Deploy a private AI chat interface for a team
- Build custom AI agents with tailored instructions and tools
- Integrate multiple AI providers behind a single UI
- Create collaborative channels for team and AI interaction
- Automate scheduled prompts and workflows
📦 Installation
🧰 Requirements: Python 3.11 for pip install, or Docker; optional Ollama or OpenAI API key for external models.
Installation via Python pip 🐍
Open WebUI can be installed using pip, the Python package installer. Before proceeding, ensure you're using Python 3.11 to avoid compatibility issues.
Install Open WebUI: Open your terminal and run the following command to install Open WebUI:
pip install open-webuiRunning Open WebUI: After installation, you can start Open WebUI by executing:
open-webui serve
This will start the Open WebUI server, which you can access at http://localhost:8080
Quick Start with Docker 🐳
[!NOTE]
Please note that for certain Docker environments, additional configurations might be needed. If you encounter any connection issues, our detailed guide on Open WebUI Documentation is ready to assist you.
[!WARNING] When using Docker to install Open WebUI, make sure to include the
-v open-webui:/app/backend/datain your Docker command. This step is crucial as it ensures your database is properly mounted and prevents any loss of data.
[!TIP]
If you wish to utilize Open WebUI with Ollama included or CUDA acceleration, we recom
🚀 Usage
After installation, start the server with open-webui serve (pip) or run the Docker container. Access the web UI at http://localhost:8080 (pip) or http://localhost:3000 (Docker).
❓ FAQ
What are the system requirements for installing Open WebUI?
For pip installation, you need Python 3.11. For Docker, you need Docker installed. Optional GPU support requires Nvidia CUDA container toolkit.
Can I use Open WebUI with OpenAI API only?
Yes, you can run Open WebUI with OpenAI API by setting the OPENAI_API_KEY environment variable in the Docker command.
How do I connect Open WebUI to Ollama running on a different server?
Set the OLLAMA_BASE_URL environment variable to the server's URL when running the Docker container.
What should I do if I encounter a server connection error?
Use the --network=host flag in your Docker command to resolve connection issues, and note that the port changes to 8080.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.