How to Set Up Open WebUI for Ollama on Linux

Open WebUI provides a beautiful ChatGPT-like interface for your self-hosted Ollama installation — supporting multiple users, conversation history and model switching.

Prerequisites

• Ollama installed and running (see previous guide)
• Docker installed
• 2GB+ free RAM

Step 1 — Deploy with Docker

# If Ollama is on the same server
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

Step 2 — Access the Interface

http://your-server:3000

Create an admin account on first access. The first account automatically gets admin privileges.

Step 3 — Configure Ollama Connection

# Settings → Connections → Ollama API URL
http://host.docker.internal:11434

# Test connection — should show your installed models

Step 4 — Nginx Reverse Proxy with SSL

server {
    listen 443 ssl;
    server_name chat.yourdomain.com;

    ssl_certificate /etc/letsencrypt/live/chat.yourdomain.com/fullchain.pem;
    ssl_certificate_key /etc/letsencrypt/live/chat.yourdomain.com/privkey.pem;

    location / {
        proxy_pass http://localhost:3000;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "upgrade";
        proxy_read_timeout 300s;
    }
}

Step 5 — Multi-User Setup

# Admin Panel → Users → Add User
# Set role: User (limited) or Admin (full access)
# Users can only see their own conversations

Step 6 — Enable RAG (Document Chat)

Open WebUI supports RAG — upload PDFs, text files or web URLs and chat with their content:

# In chat interface:
# Click + → Upload Document
# Ask questions about the document content

Conclusion

Open WebUI transforms Ollama into a full team AI platform. Our team deploys self-hosted AI environments including Open WebUI with SSO and multi-user management.