Open WebUI on a VPS: A Private ChatGPT Interface for Your Team

What Open WebUI Gives You

• A ChatGPT-like interface that runs in any browser
• Multi-user support with separate accounts and conversation histories
• Support for multiple models — switch between them in the UI
• File uploads, RAG, and image support depending on your model
• All data stays on your server

Step 1: Install Docker

curl -fsSL https://get.docker.com | sh
apt install -y docker-compose-plugin

Step 2: Deploy Open WebUI

mkdir ~/openwebui && cd ~/openwebui
nano docker-compose.yml

version: '3.8'
services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    restart: always
    ports:
      - "3000:8080"
    environment:
      - OLLAMA_BASE_URL=http://host.docker.internal:11434
    volumes:
      - open-webui:/app/backend/data
    extra_hosts:
      - "host.docker.internal:host-gateway"

volumes:
  open-webui:

docker compose up -d

Open WebUI is now running on port 3000.

Step 3: Set Up HTTPS with Nginx

apt install -y nginx certbot python3-certbot-nginx
nano /etc/nginx/sites-available/openwebui

server {
    server_name ai.yourdomain.com;

    location / {
        proxy_pass http://localhost:3000;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection 'upgrade';
        proxy_set_header Host $host;
        proxy_cache_bypass $http_upgrade;
    }
}

ln -s /etc/nginx/sites-available/openwebui /etc/nginx/sites-enabled/
certbot --nginx -d ai.yourdomain.com
nginx -t && systemctl reload nginx

Step 4: Create Your Admin Account

Open https://ai.yourdomain.com in your browser. The first account you create becomes the admin. From the admin panel you can create additional user accounts for teammates.

Step 5: Select Your Model

In the top navigation, open the model selector and choose the Ollama model you pulled. If you pulled multiple models, you can switch between them per conversation.

Keeping It Updated

cd ~/openwebui
docker compose pull
docker compose up -d

What it costs

Open WebUI itself is light; the RAM goes to the model behind it. For a team sharing a 7B model, the Pro plan (4 vCPU, 8 GB) is the practical pick. NoctHost bills hourly from a prepaid balance, so a shared private ChatGPT for the team costs what it uses, and you pay with crypto, no card or KYC required.