version: '3.8'

services:
  quran-api:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: quran-transcription-api
    ports:
      - "8888:8888"
    environment:
      - PYTHONUNBUFFERED=1
      - CUDA_VISIBLE_DEVICES=0
      - WHISPER_MODEL=OdyAsh/faster-whisper-base-ar-quran
      - COMPUTE_TYPE=float16
      - CORS_ORIGINS=http://localhost:3000,http://localhost:5173
      - LOG_LEVEL=INFO
    volumes:
      # Cache Hugging Face models locally
      - huggingface_cache:/root/.cache/huggingface
      # Log output
      - ./logs:/app/logs
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8888/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    # Uncomment for GPU support (requires nvidia-docker)
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

  # Optional: Redis for caching (future use)
  # redis:
  #   image: redis:7-alpine
  #   container_name: quran-redis
  #   ports:
  #     - "6379:6379"
  #   restart: unless-stopped

volumes:
  huggingface_cache:
    driver: local

networks:
  default:
    name: quran-network