Welcome to Open WebUI
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-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.Quick Start
Get up and running with Open WebUI in minutes
Installation
Complete installation guide for Docker, pip, and Kubernetes
Configuration
Configure environment variables and settings
Development
Set up a local development environment
Why Open WebUI?
Open WebUI provides a comprehensive platform for deploying and managing AI models with enterprise-grade features and user-friendly interfaces.Core Capabilities
Effortless Setup Install seamlessly using Docker or Kubernetes (kubectl, kustomize or helm) for a hassle-free experience with support for both:ollama and :cuda tagged images.
Multiple AI Provider Support
Effortlessly integrate OpenAI-compatible APIs for versatile conversations alongside Ollama models. Customize the OpenAI API URL to link with LMStudio, GroqCloud, Mistral, OpenRouter, and more.
Responsive Design
Enjoy a seamless experience across Desktop PC, Laptop, and Mobile devices with Progressive Web App (PWA) support for mobile.
Key Features
RAG Integration
Built-in Retrieval Augmented Generation with support for 9 vector databases and multiple content extraction engines (Tika, Docling, Document Intelligence, Mistral OCR)
Voice & Video
Hands-free voice and video call features using multiple Speech-to-Text providers (Local Whisper, OpenAI, Deepgram, Azure) and Text-to-Speech engines
Model Builder
Create Ollama models via the Web UI with custom characters/agents and import models through Open WebUI Community integration
Python Functions
Native Python function calling with built-in code editor. Bring Your Own Function (BYOF) by adding pure Python functions
Advanced Features
Web Search & Browsing Perform web searches using 15+ providers including SearXNG, Google PSE, Brave Search, Kagi, Tavily, and more. Integrate websites directly into chat using the# command.
Image Generation
Create and edit images using multiple engines including OpenAI’s DALL-E, Gemini, ComfyUI (local), and AUTOMATIC1111 (local).
Enterprise Authentication
Full support for LDAP/Active Directory integration, SCIM 2.0 automated provisioning, and SSO via trusted headers alongside OAuth providers.
Production Observability
Built-in OpenTelemetry support for traces, metrics, and logs, enabling comprehensive monitoring with your existing observability stack.
Horizontal Scalability
Redis-backed session management and WebSocket support for multi-worker and multi-node deployments behind load balancers.
Database & Storage Options
Open WebUI provides flexible database and storage configurations:- SQLite (with optional encryption) - Default, perfect for single-instance deployments
- PostgreSQL - For production deployments requiring advanced features
- Cloud Storage - S3, Google Cloud Storage, Azure Blob Storage for scalable deployments
- Vector Databases - ChromaDB, PGVector, Qdrant, Milvus, Elasticsearch, OpenSearch, Pinecone, S3Vector, Oracle 23ai
Security & Access Control
Granular Permissions Administrators can create detailed user roles and permissions, ensuring a secure user environment with customized user experiences. Role-Based Access Control (RBAC) Ensure secure access with restricted permissions. Only authorized individuals can access your Ollama, and exclusive model creation/pulling rights are reserved for administrators.Next Steps
Install Open WebUI
Choose your installation method and get started
Quick Start Guide
From installation to first chat in minutes
Looking for an Enterprise Plan? Open WebUI offers enhanced capabilities including custom theming and branding, Service Level Agreement (SLA) support, and Long-Term Support (LTS) versions.
Community & Support
Join our vibrant community for support and discussions:- Discord: Connect with other users and get help
- GitHub: Report issues and contribute to the project
- Documentation: Comprehensive guides and API references
Ready to get started? Head over to the Installation Guide or jump straight to the Quick Start.