version: '3.8'

services:
  api:
    build:
      context: ..
      dockerfile: docker/Dockerfile.serve
    volumes:
      - ./models:/app/models:ro
    environment:
      - MODEL_PATH=/app/models/openmind-125m
      - CUDA_VISIBLE_DEVICES=0
    ports:
      - "8000:8000"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  frontend:
    build:
      context: ..
      dockerfile: docker/Dockerfile.frontend
    ports:
      - "80:80"
    depends_on:
      - api
    restart: unless-stopped