version: '3.8'

services:
  # Main vLLM service with GPU support
  vllm:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "8000:8000"
    environment:
      - MODEL_PATH=/models
      - MODEL_NAME=meta-llama/Llama-3.1-8B-Instruct
      - MODEL_FORMAT=hf
      - REDIS_URL=redis://redis:6379
      - GPU_MEMORY_UTILIZATION=0.9
      - LOG_LEVEL=INFO
    volumes:
      - ./models:/models:ro
      - ./logs:/app/logs
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    depends_on:
      - redis
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s

  # Optional Redis for caching
  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    volumes:
      - redis_data:/data
    restart: unless-stopped

  # Prometheus metrics collection
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=200h'
      - '--web.enable-lifecycle'
    restart: unless-stopped

  # Traefik for HTTPS and reverse proxy
  traefik:
    image: traefik:v3.0
    command:
      - '--api.dashboard=true'
      - '--providers.docker=true'
      - '--providers.docker.exposedbydefault=false'
      - '--entrypoints.web.address=:80'
      - '--entrypoints.websecure.address=:443'
      - '--certificatesresolvers.myresolver.acme.tlschallenge=true'
      - '--certificatesresolvers.myresolver.acme.email=your-email@example.com'
      - '--certificatesresolvers.myresolver.acme.storage=/letsencrypt/acme.json'
    ports:
      - "80:80"
      - "443:443"
      - "8080:8080"  # Traefik dashboard
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - traefik_data:/letsencrypt
    restart: unless-stopped

  # Optional: Grafana for visualization
  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin123
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning
    depends_on:
      - prometheus
    restart: unless-stopped

volumes:
  redis_data:
  prometheus_data:
  traefik_data:
  grafana_data:

networks:
  default:
    driver: bridge