docker-compose.yml

services:

  quantumai:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: quantumai
    restart: unless-stopped
    ports:
      - "8000:8000"

    environment:
      # ── Required API keys ──────────────────────────────────────────────
      # Set these in a .env file in the project root (never commit that file)
      GROQ_API_KEY: ${GROQ_API_KEY}
      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}

      # ── Optional tuning ────────────────────────────────────────────────
      # Uvicorn log level: debug | info | warning | error
      LOG_LEVEL: ${LOG_LEVEL:-info}

    volumes:
      # Persist Chroma vector DB between restarts so it doesn't re-index on every boot
      - chroma_data:/app/chroma_db

    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s   # give the model/embeddings time to load

    # Cap resource usage — adjust to your machine
    deploy:
      resources:
        limits:
          memory: 2g
        reservations:
          memory: 512m

volumes:
  chroma_data:
    driver: local