Logo Open WebUI

Artificial Intelligence

Open WebUI

Web interface for your LLMs — Ollama, OpenAI, Mistral — hosted on your own server.

About Open WebUI

Open WebUI is a source-available chat interface, compatible with Ollama and the OpenAI APIs, that lets you interact with language models from your browser. Deployed on your VPS, it replaces ChatGPT without sending your data to third parties: your conversations, documents and history stay on your infrastructure.

It is the ideal tool for teams that want to experiment with local LLMs (Llama 3, Mistral, Gemma) or remote ones while keeping full control of their exchanges. Open WebUI supports RAG (Retrieval-Augmented Generation), multi-model conversations and session sharing between users.

What gets installed

Ready when the VPS starts

Compatible OS
Ubuntu 24.04
Application
Open WebUI
Tech stack
DockerPythonOllama (optional)
Minimum RAM
2 GB
Minimum CPU
2 vCPU
Default port
3000
Access
root over SSH

Key features

  • Compatible with Ollama (local models) and the OpenAI/Anthropic API
  • Built-in RAG: query your PDF documents, texts and knowledge bases
  • Multi-user management with roles and permissions
  • Persistent conversation history, exportable
  • Multimodal support: text, images, code
  • Responsive interface, light/dark theme

When to use this solution?

Internal team

Deploy a shared AI assistant for your team, connected to your internal documents, without exposing your data to OpenAI.

Development & testing

Test different LLM models side by side before integrating one of them into your application.

Intelligent knowledge base

Upload your PDFs, procedures and technical docs — ask questions in natural language.

Guide

Deploy Open WebUI on your VPS

  1. What the installation does for you

    When the VPS is created, ServOrbit installs Docker if it is missing, then starts the official ghcr.io/open-webui/open-webui:main container, with its data in the open-webui volume. The interface listens on 127.0.0.1:3000, the server's loopback interface: nothing is published on its IP address. Ollama is not included: Open WebUI alone needs 2 GB of RAM, and if you add Ollama on the same VPS, plan for at least 8 GB more for it.

  2. Find the address and access details

    The “Open WebUI is installed” email and your VPS page in the client area, under “Installed applications”, tell you how to open the app: its address when a domain is in place, otherwise the SSH tunnel command and the port. You will also find the link to this guide and the “Support” button there.

  3. Open Open WebUI without a domain

    From your computer, run ssh -L 3000:127.0.0.1:3000 root@<vps-ip>, keep the session open, then open http://localhost:3000. The port may have been reassigned during installation: use the one shown in your client area, 3000 being only the catalogue default.

  4. Log in for the first time

    Do it right away: the first account created on the sign-up screen becomes the administrator, and the following ones stay pending your approval. Then connect your models in the admin panel, under Connections: an API key from OpenAI or a compatible service, or the address of an Ollama instance reachable from the container.

  5. Publish over HTTPS on a domain

    When Open WebUI is installed from your client area with a chosen address — your own domain or a free ServOrbit subdomain — the platform sets up the nginx vhost and the Let's Encrypt certificate. An installation made when the VPS was created, or without an address, is published from the VPS page: the “Attach a domain” button in the app's block (a domain from your account, the free subdomain, or a name you point to the server).

  6. Appendix: redo everything by hand

    To reinstall without the platform: install Docker, then run docker run -d --name open-webui --restart unless-stopped -p 127.0.0.1:3000:8080 -v open-webui:/app/backend/data --add-host=host.docker.internal:host-gateway ghcr.io/open-webui/open-webui:main. Put a reverse proxy in front (nginx, for example) with a Let's Encrypt certificate (certbot --nginx -d <domain>).

Frequently asked questions

Questions about Open WebUI

← Back to Artificial IntelligenceAll applications
Open WebUI is a self-hosted web interface for interacting with LLMs (Large Language Models) such as Llama, Mistral or GPT-4. It works like ChatGPT but runs on your own server.

Embed the deploy button

Maintaining a project that uses Open WebUI? This button lets your readers deploy it on a VPS in one click, without reading Docker documentation.

Deploy Open WebUI on ServOrbit
Markdown
[![Deploy Open WebUI on ServOrbit](https://servorbit.com/brand/deploy/button.svg)](https://servorbit.com/vps-cloud?template=open-webui&utm_source=deploy-badge&utm_medium=referral&utm_campaign=open-webui)
HTML
<a href="https://servorbit.com/vps-cloud?template=open-webui&utm_source=deploy-badge&utm_medium=referral&utm_campaign=open-webui"><img src="https://servorbit.com/brand/deploy/button.svg" alt="Deploy Open WebUI on ServOrbit" height="40"></a>

The button points to a VPS order with the template preselected. The image is served from servorbit.com — nothing to host on your side.

Need help?

Browse our help center and FAQ, or reach our team — callback, WhatsApp or email.

Message us on WhatsAppopens in a new tab