docker-compose.yml

services:
  ui-ai-service:

    shm_size: "8gb"
    gpus: all

    build:
      context: .
      dockerfile: Dockerfile
      
    image: ui-ai-service:latest

    container_name: ui-ai-service

    ports:
      - "8000:8000"

    env_file:
      - .env

    environment:
      BASE_MODEL_ID: Qwen/Qwen2.5-VL-3B-Instruct
      HF_HOME: /cache/huggingface
      HF_HUB_CACHE: /cache/huggingface/hub
      TOKENIZERS_PARALLELISM: "false"

    volumes:
      - hf_cache:/cache/huggingface

    restart: unless-stopped

    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/ready"]
      interval: 30s
      timeout: 10s
      start_period: 300s
      retries: 3

    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

volumes:
  hf_cache: