docker-compose.yml

# Docker Compose for local development with GPU support

services:
  # Full application (frontend + backend)
  app:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "7860:7860"
    environment:
      - CUDA_VISIBLE_DEVICES=0
    volumes:
      - ./models:/app/models
      - ./cache:/app/cache
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [ gpu ]
    restart: unless-stopped

  # Development mode: separate frontend and backend
  backend-dev:
    build:
      context: .
      dockerfile: Dockerfile
      target: python-base
    command: python -m uvicorn backend.api.main:app --host 0.0.0.0 --port 8000 --reload
    ports:
      - "8000:8000"
    volumes:
      - ./backend:/app/backend
      - ./models:/app/models
    environment:
      - CUDA_VISIBLE_DEVICES=0
    profiles:
      - dev
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [ gpu ]

  frontend-dev:
    image: node:20-alpine
    working_dir: /app
    command: sh -c "npm install && npm run dev -- --host"
    ports:
      - "5173:5173"
    volumes:
      - ./frontend:/app
      - /app/node_modules
    environment:
      - VITE_API_URL=http://localhost:8000/api
    profiles:
      - dev

  # CPU-only version (no GPU)
  app-cpu:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "7860:7860"
    volumes:
      - ./models:/app/models
    profiles:
      - cpu
    restart: unless-stopped

networks:
  default:
    name: quantizer-network