version: '3.8'

services:
  youlama:
    build: .
    ports:
      - "7860:7860"
    volumes:
      - .:/app
      - ./models:/app/models
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - OLLAMA_HOST=host.docker.internal
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    extra_hosts:
      - "host.docker.internal:host-gateway"

volumes:
  ollama_data: