Getting Started with Open WebUI
From zero to your first AI conversation in under five minutes.
Open WebUI runs anywhere (Docker, Kubernetes, pip, bare metal) and connects to any model provider out of the box. Pick an install method, connect a provider, and start chatting.
β±οΈ Quick Startβ
Install Open WebUI, connect a model, and start chatting.
Everything you need for a working setup. Choose Docker for the fastest path, Python for lightweight installs, or Kubernetes for production orchestration. Each guide includes connecting your first model provider.
| π³ Docker | One-command deploy, the officially recommended path |
| π¦ Python (pip / uv) | Lightweight install for low-resource or manual setups |
| βΈοΈ Kubernetes (Helm) | Production-ready orchestration with scaling |
| π₯οΈ Desktop app | Native app (experimental), no Docker required |
| π Connect a provider | Ollama, OpenAI, Anthropic, llama.cpp, vLLM, and more |
| βοΈ Understanding settings | Learn how Admin Settings and User Settings work together |
Sharing Open WebUIβ
Bring AI to your entire organization with a single deployment.
Open WebUI isn't just a local interface for AI. It is designed to be a centralized AI operating system for teams. Deploy it once to leverage frictionless onboarding, collaborative intelligence, resource pooling, and centralized security.
| LAN & Tunnels | Tailscale, Cloudflare Tunnels, and local IP access |
| Reverse Proxies | Secure your instance with Nginx, Caddy, or HAProxy |
| Team Onboarding | Admin approval flows and Enterprise SSO integrations |
| Shared Context | Channels, shared chats, and common knowledge bases |
Learn how to share Open WebUI β
π οΈ Advanced Topicsβ
Scale, observe, and customize your deployment.
Go beyond the basics. Configure environment variables, connect external databases, add cloud storage, enable OpenTelemetry, or scale horizontally with Redis and multiple workers.
| βοΈ Scaling | Multi-worker, multi-node, Redis-backed sessions |
| π Logging & observability | OpenTelemetry traces, metrics, and structured logs |
| π§ͺ Development setup | Run from source for local development and testing |
π Updatingβ
Stay current with the latest features and security patches.
Update manually with a single Docker or pip command, or automate with Watchtower, WUD, or Diun. Includes backup/restore procedures and version pinning for production.
| π Manual update | Docker pull + recreate, or pip upgrade |
| π€ Automated updates | Watchtower, WUD, or Diun |
| π Version pinning | Lock to a specific release for stability |
| πΎ Backup & restore | One-command volume backup and recovery |