services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "11434:11434"
    environment:
      - OLLAMA_HOST=0.0.0.0
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - OLLAMA_CONTEXT_LENGTH=8192
    volumes:
      - ollama_data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - capabilities: [gpu]
    runtime: nvidia

  ollama-exporter:
    image: ghcr.io/mikeh-22/ollama-exporter:latest
    container_name: ollama-exporter
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - OLLAMA_URL=http://ollama:11434
    ports:
      - "9101:9101"
    volumes:
      - /sys:/sys:ro
      - /var/run/docker.sock:/var/run/docker.sock
    depends_on:
      - ollama

  openwebui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: openwebui
    restart: unless-stopped
    ports:
      - "3000:8080"
    environment:
      - OLLAMA_API_BASE=http://ollama:11434
    volumes:
      - openwebui_data:/app/backend/data
    depends_on:
      - ollama

volumes:
  ollama_data:
  openwebui_data: