version: '3.8'

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    ports:
      - "127.0.0.1:11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 3

  api:
    build:
      context: .
      dockerfile: Dockerfile.api
    container_name: openelm-api
    ports:
      - "8001:8000"
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
      - OLLAMA_MODEL=apple/OpenELM-3B-Instruct
    depends_on:
      ollama:
        condition: service_healthy
    restart: unless-stopped

volumes:
  ollama_data: