services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    volumes:
      - ./ollama_data:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_ORIGINS=*
      - OLLAMA_NUM_PARALLEL=4
      - OLLAMA_MAX_LOADED_MODELS=2
      - OLLAMA_KEEP_ALIVE=10m
      - OLLAMA_FLASH_ATTENTION=1
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "ollama", "list"]
      interval: 30s
      timeout: 10s
      retries: 5

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    restart: unless-stopped
    ports:
      - "11435:8080"
    volumes:
      - ./open-webui_data:/app/backend/data
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
    depends_on:
      - ollama