compose.yaml

services:
  noticecheck:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "${NOTICECHECK_PORT:-7860}:7860"
    environment:
      MODEL_RUNTIME: transformers
      REQUIRE_CUDA: "1"
      TRANSFORMERS_MODEL_REPO: "${TRANSFORMERS_MODEL_REPO:-openbmb/MiniCPM5-1B}"
      MODEL_ENABLE_THINKING: "${MODEL_ENABLE_THINKING:-0}"
      HF_HOME: /root/.cache/huggingface
      HF_TOKEN: "${HF_TOKEN:-}"
      GRADIO_ANALYTICS_ENABLED: "False"
    volumes:
      - huggingface-cache:/root/.cache/huggingface
      - noticecheck-traces:/app/traces/pending
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test:
        - CMD
        - python
        - -c
        - "import urllib.request; urllib.request.urlopen('http://127.0.0.1:7860/health', timeout=5)"
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 10m
    restart: unless-stopped

volumes:
  huggingface-cache:
  noticecheck-traces: