services: cf-docuvision: build: . network_mode: host env_file: .env environment: CF_DOCUVISION_PORT: "8003" volumes: # Cache HuggingFace model weights across rebuilds - ${HOME}/.cache/huggingface:/root/.cache/huggingface # Optional: mount a local model path to skip HF download # - /Library/Assets/LLM/dolphin-v2:/models/dolphin-v2:ro restart: unless-stopped deploy: resources: reservations: devices: - driver: nvidia count: 1 capabilities: [gpu] healthcheck: test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8003/health')"] interval: 30s timeout: 10s retries: 3 start_period: 120s