Open WebUI

Enables offline AI interactions with LLMs, integrating document and web content. Run AI on your own terms. Connect any model, extend with code, and protect what matters without compromise. Open WebUI is a self-hosted AI interface for offline LLM interactions with document and web integration. Docker is recommended for consistent deployment, but pip installation is also supported. It operates fully offline with local LLMs like Ollama, ensuring data privacy. A decent CPU is needed for basic use, with a GPU recommended for image generation or complex models. It integrates with OpenAI-compatible APIs alongside local models like Ollama. Use a reverse proxy like Nginx or Let’s Encrypt, as detailed in the documentation.