version: "3.8"

services:
  floorgen-api:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: floorgen-api
    restart: unless-stopped
    ports:
      - "8000:8000"
    environment:
      - FLOORGEN_HOST=0.0.0.0
      - FLOORGEN_PORT=8000
      - FLOORGEN_DEVICE=cuda
      - FLOORGEN_LOG_LEVEL=INFO
      - FLOORGEN_DATA_DIR=/app/data/processed
      - FLOORGEN_CHECKPOINT=/app/checkpoints/rag_diffusion.pt
    volumes:
      - ./data/processed:/app/data/processed:ro
      - ./checkpoints:/app/checkpoints:ro
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s