version: '3.8'

services:
  classifier:
    build: .
    ports:
      - "7860:7860"
    environment:
      - USE_CUDA=false
      - HF_HOME=/app/.cache/huggingface
      - TORCH_HOME=/app/.cache/torch
      - TOKENIZERS_PARALLELISM=true
    volumes:
      - ./logs:/app/logs
      - ./model_cache:/app/.cache
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '4'
          memory: 16G
        reservations:
          memory: 8G