docker-compose.gpu.yml

version: "3.9"

services:
  web:
    build:
      context: .
      dockerfile: Dockerfile.gpu
    ports:
      - "8000:8000"
    environment:
      - NOTEKING_LLM_API_KEY=${NOTEKING_LLM_API_KEY}
      - NOTEKING_LLM_BASE_URL=${NOTEKING_LLM_BASE_URL:-}
      - NOTEKING_LLM_MODEL=${NOTEKING_LLM_MODEL:-gpt-4o-mini}
      - NOTEKING_PROXY=${NOTEKING_PROXY:-}
      - BILIBILI_SESSDATA=${BILIBILI_SESSDATA:-}
      - HF_TOKEN=${HF_TOKEN:-}
    volumes:
      - noteking_output:/app/noteking_output
      - noteking_cache:/root/.noteking
      - huggingface_cache:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped

volumes:
  noteking_output:
  noteking_cache:
  huggingface_cache: