deploy/docker-compose.yml

version: "3.8"

services:
  api:
    build:
      context: ..
      dockerfile: deploy/Dockerfile.api
    volumes:
      - checkpoints:/app/checkpoints
    environment:
      - ARCISVLM_CONFIG=configs/scale_1.3b.yaml
      - ARCISVLM_CHECKPOINT=${ARCISVLM_CHECKPOINT:-checkpoints/v3_stage1_final.pt}
      - ARCISVLM_DEVICE=cuda
      - HF_TOKEN=${HF_TOKEN:-}
    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

  dashboard:
    build:
      context: ..
      dockerfile: deploy/Dockerfile.dashboard
    environment:
      - NEXT_PUBLIC_API_URL=
      - NEXT_PUBLIC_WS_URL=
    depends_on:
      - api
    restart: unless-stopped

  nginx:
    image: nginx:alpine
    ports:
      - "80:80"
    volumes:
      - ./nginx.conf:/etc/nginx/conf.d/default.conf:ro
    depends_on:
      - api
      - dashboard
    restart: unless-stopped

volumes:
  checkpoints: