version: "3.9"

services:
  got-ocr:
    build: .
    image: got-ocr:latest
    container_name: got-ocr-backend
    ports:
      - "8000:8000"
    environment:
      - PYTHONUNBUFFERED=1
    restart: unless-stopped

    # ── GPU support (comment out for CPU-only) ───────────────────────────
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

    # ── Health check ─────────────────────────────────────────────────────
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s   # give model time to load

    # ── Optional: persist HuggingFace model cache across rebuilds ────────
    volumes:
      - hf_cache:/root/.cache/huggingface

volumes:
  hf_cache: