Skip to main content

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.


⏱️ Quick Start​

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.

🐳 DockerOne-command deploy, the officially recommended path
πŸ“¦ Python (pip / uv)Lightweight install for low-resource or manual setups
☸️ Kubernetes (Helm)Production-ready orchestration with scaling
πŸ–₯️ Desktop appNative app (experimental), no Docker required
πŸ”Œ Connect a providerOllama, OpenAI, Anthropic, llama.cpp, vLLM, and more
βš™οΈ Understanding settingsLearn how Admin Settings and User Settings work together

Start installing β†’


Sharing Open WebUI​

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 & TunnelsTailscale, Cloudflare Tunnels, and local IP access
Reverse ProxiesSecure your instance with Nginx, Caddy, or HAProxy
Team OnboardingAdmin approval flows and Enterprise SSO integrations
Shared ContextChannels, shared chats, and common knowledge bases

Learn how to share Open WebUI β†’


πŸ› οΈ Advanced Topics​

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.

βš–οΈ ScalingMulti-worker, multi-node, Redis-backed sessions
πŸ“Š Logging & observabilityOpenTelemetry traces, metrics, and structured logs
πŸ§ͺ Development setupRun from source for local development and testing

Explore advanced topics β†’


πŸ”„ Updating​

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.

πŸ”„ Manual updateDocker pull + recreate, or pip upgrade
πŸ€– Automated updatesWatchtower, WUD, or Diun
πŸ“Œ Version pinningLock to a specific release for stability
πŸ’Ύ Backup & restoreOne-command volume backup and recovery

Update guide β†’