services:
  ollama:
    image: ollama/ollama:latest
    network_mode: "host"
    volumes:
      - ollama:/root/.ollama # this solution synchronizes with the docker volume and loads the model rocket fast
    ports:
      - "11434:11434"
    command: []
  llamastack:
    depends_on:
    - ollama
    image: llamastack/distribution-ollama
    network_mode: "host"
    volumes:
      - ~/.llama:/root/.llama
      # Link to ollama run.yaml file
      - ./run.yaml:/root/my-run.yaml
    ports:
      - "5000:5000"
    # Hack: wait for ollama server to start before starting docker
    entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
    deploy:
      restart_policy:
        condition: on-failure
        delay: 3s
        max_attempts: 5
        window: 60s
volumes:
  ollama: