version: '3.8'

services:
  # Ollama service for local LLM inference
  ollama:
    image: ollama/ollama:latest
    container_name: summarizer-ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  # FastAPI backend service
  api:
    build: .
    container_name: summarizer-api
    ports:
      - "8000:8000"
    environment:
      - OLLAMA_HOST=http://ollama:11434
      - OLLAMA_MODEL=llama3.1:8b
      - OLLAMA_TIMEOUT=60
      - SERVER_HOST=0.0.0.0
      - SERVER_PORT=8000
      - LOG_LEVEL=INFO
    depends_on:
      ollama:
        condition: service_healthy
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s

  # Optional: Nginx reverse proxy for production
  nginx:
    image: nginx:alpine
    container_name: summarizer-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf:ro
    depends_on:
      - api
    restart: unless-stopped
    profiles:
      - production

volumes:
  ollama_data:
    driver: local

networks:
  default:
    name: summarizer-network