#talk2aiagents4pharma
services:
  # CPU variant – start with: docker compose --profile cpu up
  ollama:
    image: ollama/ollama:latest
    container_name: ollama-server
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/version"]
      interval: 30s
      timeout: 10s
      retries: 3
    entrypoint: ["/bin/sh", "-c"]
    command: >
      "ollama serve &
      sleep 10 &&
      ollama pull nomic-embed-text &&
      tail -f /dev/null"
    networks:
      - app-network
    profiles: ["cpu"]

  # NVIDIA GPU variant – start with: docker compose --profile nvidia up
  ollama-nvidia:
    image: ollama/ollama:latest
    container_name: ollama-server-nvidia
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/version"]
      interval: 30s
      timeout: 10s
      retries: 3
    entrypoint: ["/bin/sh", "-c"]
    command: >
      "ollama serve &
      sleep 10 &&
      ollama pull nomic-embed-text &&
      tail -f /dev/null"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - app-network
    profiles: ["nvidia"]

  # AMD GPU variant – start with: docker compose --profile amd up
  ollama-amd:
    image: ollama/ollama:rocm
    container_name: ollama-server-amd
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/version"]
      interval: 30s
      timeout: 10s
      retries: 3
    entrypoint: ["/bin/sh", "-c"]
    command: >
      "ollama serve &
      sleep 10 &&
      ollama pull nomic-embed-text &&
      tail -f /dev/null"
    devices:
      - /dev/kfd
      - /dev/dri
    networks:
      - app-network
    profiles: ["amd"]

  talk2aiagents4pharma:
    image: virtualpatientengine/talk2aiagents4pharma:latest
    container_name: talk2aiagents4pharma
    ports:
      - "8501:8501"
    env_file:
      - .env
    restart: unless-stopped
    networks:
      - app-network

volumes:
  ollama_data:
    name: ollama_data
    # Uncomment the line below if you want to use an existing volume:
    # external: true

networks:
  app-network:
    name: app-network