Open WebUI

Open WebUI is a self-hosted AI interface that runs entirely offline and supports various LLM runners including Ollama and OpenAI-compatible APIs. It provides a feature-rich web interface for interacting with language models with built-in RAG capabilities.

Key Features

• Multi-provider support: Works with Ollama, OpenAI, LMStudio, GroqCloud, Mistral, and other OpenAI-compatible APIs
• Local RAG integration: Built-in document processing with 9 vector database options (ChromaDB, PGVector, Qdrant, etc.)
• Web search capabilities: 15+ search providers including SearXNG, Google PSE, Brave Search, and DuckDuckGo
• Image generation & editing: Supports DALL-E, Gemini, ComfyUI, and AUTOMATIC1111
• Voice/video calls: Multiple Speech-to-Text and Text-to-Speech providers
• Enterprise features: RBAC, LDAP/AD integration, SCIM 2.0, SSO support
• Multi-model conversations: Chat with multiple models simultaneously
• Python function calling: Built-in code editor for custom functions
• Cloud storage: S3, Google Cloud Storage, Azure Blob Storage backends

Installation

# Basic installation
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data --name open-webui --restart always \
  ghcr.io/open-webui/open-webui:main

# With Ollama integration
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway \
  -v open-webui:/app/backend/data --name open-webui --restart always \
  ghcr.io/open-webui/open-webui:ollama

Access the interface at http://localhost:3000.

Basic Usage

1. Add a model provider: Navigate to Settings → Connections and configure your API endpoint (Ollama, OpenAI, etc.)
2. Start chatting: Select a model from the dropdown and begin your conversation
3. Upload documents: Use the # command or document library for RAG functionality
4. Web search: Use # followed by search terms to inject web results into your chat

Notable Details

• Language: Python
• Community: 128k+ GitHub stars with active Discord community
• License: Open source (license details in repository)
• Enterprise: Commercial support and LTS versions available
• Deployment: Supports Docker, Kubernetes (kubectl, helm), and cloud-native scaling