services:
  llm-chat:
    build:
      context: .
      dockerfile: Dockerfile
    platform: linux/amd64
    privileged: true
    container_name: llm-chat
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    volumes:
      - ./app:/app
      - ./models:/models
      - ./cache/cache:/root/.cache
      - ./cache/site-packages:/usr/local/lib/python3.10/site-packages
      - ./offline_packages:/offline_packages
    # entrypoint: sleep 1000000 #./app/entrypoint.sh
    ports:
      - "8080:8080"
    networks:
      - apps
networks:
  apps:
    name: apps
    driver: bridge
    ipam:
      driver: default
      config:
        - subnet: "172.100.0.0/24"
          gateway: "172.100.0.1"