version: '3.8'

services:
  ollama-intel-gpu:
    container_name: ollama-intel-gpu
    image: intelanalytics/ipex-llm-inference-cpp-xpu:latest
    restart: unless-stopped
    ports:
      - "11434:11434"
    devices:
      - /dev/dri:/dev/dri
    volumes:
      - ./ollama:/root/.ollama
    environment:
      - no_proxy=localhost,127.0.0.1
      - DEVICE=Arc
      - OLLAMA_HOST=0.0.0.0:11434
    entrypoint: /bin/bash /root/.ollama/start.sh
    #command: /bin/bash source ipex-llm-init --gpu --device $DEVICE && chmod +X /llm/scripts/start-ollama.sh && bash /llm/scripts/start-ollama.sh

  #ollama:
    #image: ollama/ollama
    #container_name: ollama
    #ports:
    #  - "11434:11434"
    #volumes:
    #  - ./ollama:/root/.ollama
    #restart: unless-stopped
    #deploy:
    #  resources:
    #    reservations:
    #      devices:
    #        - capabilities: ["gpu"]
    # For older versions of Docker, you might need to use the environment method
    # environment:
    #   - NVIDIA_VISIBLE_DEVICES=all

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    ports:
      - "8282:8080"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    volumes:
      - ./open-webui:/app/backend/data
    restart: unless-stopped