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 a built-in inference engine for RAG, making it a comprehensive AI deployment solution for individuals and enterprises.

Open WebUI is more than just a chat interface — it includes plugins, RBAC, memory, channels, automation, calendar, voice/video calls, image generation, and enterprise authentication (LDAP, SSO, SCIM). The project is MIT-licensed and hosted at openwebui.com with source on GitHub. It supports PostgreSQL or SQLite storage, 9 vector databases, and horizontal scalability.

Open WebUI can be installed via pip, Docker, or Kubernetes. Docker is the recommended approach.

Docker (Recommended)

# With Ollama on the same machine
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

Bundled with Ollama

docker run -d -p 3000:8080 --gpus=all \
  -v ollama:/root/.ollama \
  -v open-webui:/app/backend/data \
  --name open-webui --restart always \
  ghcr.io/open-webui/open-webui:ollama

Pip Install

pip install open-webui
open-webui serve

The web UI is then accessible at http://localhost:8080 (Docker) or http://localhost:3000.

Open WebUI offers an extensive feature set that goes far beyond basic chat interfaces:

Feature	Description
Multi-Model Chat	Engage several models at once in parallel conversations
RAG Pipeline	Local RAG with 9 vector DBs, hybrid search, and reranking
Plugin System	Filters, Actions, Pipes, Tools, Skills, MCP integration
RBAC & Auth	Granular roles, groups, permissions, LDAP/SSO/SCIM
Voice/Video	Hands-free calls with multiple STT/TTS providers
Image Generation	DALL-E, Gemini, ComfyUI, AUTOMATIC1111 integration
Channels & Notes	Real-time team spaces, rich editor, AI rewriting
Automations	Scheduled prompts with calendar and run history
Observability	Usage analytics, model evaluation, OpenTelemetry

Open WebUI connects to any OpenAI-compatible API alongside local Ollama models. You can mix and match providers freely — point the API URL at LM Studio, GroqCloud, Mistral, OpenRouter, vLLM, or any custom endpoint. The platform supports model wrapping with custom instructions, tools, and knowledge to build specialized agents, with per-user/group access control.

• Ollama integration — Native support for local models via the Ollama API
• OpenAI-compatible — Connect any provider with an OpenAI-compatible endpoint
• Custom model presets — Wrap models with system prompts, tools, and knowledge bases
• Model evaluation — Built-in arena with A/B testing and ELO-based leaderboards
• Community models — Import model presets from the Open WebUI Community

Open WebUI includes a comprehensive RAG pipeline with support for 9 vector databases (ChromaDB, PGVector, Qdrant, Milvus, Elasticsearch, OpenSearch, Pinecone, S3Vector, Oracle 23ai), multiple content extraction engines (Tika, Docling, Document Intelligence, Mistral OCR, PaddleOCR-vl), and hybrid search (BM25 + vector) with reranking.

Documents can be loaded into chat or pulled from your library using the # command. Web search is supported through 20+ providers including SearXNG, Google PSE, Brave, Kagi, Tavily, Perplexity, Firecrawl, and DuckDuckGo. The oikb companion tool syncs knowledge bases from 45+ sources including GitHub, Confluence, Notion, and SharePoint.

Open WebUI supports flexible database and storage configurations. Choose between SQLite (with optional encryption) or PostgreSQL. Files can be stored locally or on S3-compatible storage, Google Cloud Storage, or Azure Blob Storage. For enterprise deployments, Redis-backed session management enables horizontal scaling across multiple workers behind a load balancer.

Option	Choices
Database	SQLite (encrypted optional), PostgreSQL
Vector Store	ChromaDB, PGVector, Qdrant, Milvus, Elasticsearch, Pinecone, and more
File Storage	Local, S3, GCS, Azure Blob
Auth	Local, LDAP, SSO (OAuth), SCIM 2.0
Deployment	Docker, Kubernetes, pip, native desktop app