docker-compose.yml

version: "3.9"

services:
  rag-api:
    build: .
    command: ["python", "main.py", "serve", "--host", "0.0.0.0", "--port", "8000"]
    ports:
      - "8000:8000"
    volumes:
      - ./data:/app/data          # persist ChromaDB + knowledge graph
    env_file:
      - .env
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    depends_on:
      - ollama

  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama_models:/root/.ollama
    restart: unless-stopped
    # To pull a model on first run:
    # docker exec <container> ollama pull llama3.2

  # Optional: Prometheus metrics scraping
  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
    profiles:
      - monitoring   # only start with: docker-compose --profile monitoring up

volumes:
  ollama_models: