Note in README for deploying to VPS without Docker Compose

README.md

@@ -224,7 +224,7 @@ Before running the above commands to pull the repo and install everything:
 2. Run the **start-services.py** script with the environment argument **public** to indicate you are going to run the package in a public environment. The script will make sure that all ports, except for 80 and 443, are closed down, e.g.
 
 ```bash
-   python start_services.py --profile gpu-nvidia --environment public
+   python3 start_services.py --profile gpu-nvidia --environment public
    ```
 
 3. Set up A records for your DNS provider to point your subdomains you'll set up in the .env file for Caddy
@@ -232,6 +232,15 @@ to the IP address of your cloud instance.
 
    For example, A record to point n8n to [cloud instance IP] for n8n.yourdomain.com
 
+
+**NOTE**: If you are using a cloud machine without the "docker compose" command available by default, such as a Ubuntu GPU instance on DigitalOcean, run these commands before running start_services.py:
+
+- DOCKER_COMPOSE_VERSION=$(curl -s https://api.github.com/repos/docker/compose/releases/latest | grep 'tag_name' | cut -d\" -f4)
+- sudo curl -L "https://github.com/docker/compose/releases/download/${DOCKER_COMPOSE_VERSION}/docker-compose-linux-x86_64" -o /usr/local/bin/docker-compose
+- sudo chmod +x /usr/local/bin/docker-compose
+- sudo mkdir -p /usr/local/lib/docker/cli-plugins
+- sudo ln -s /usr/local/bin/docker-compose /usr/local/lib/docker/cli-plugins/docker-compose
+
 ## ⚡️ Quick start and usage
 
 The main component of the self-hosted AI starter kit is a docker compose file