version: '3'
services:
  ollama-intel-arc:
    image: intelanalytics/ipex-llm-inference-cpp-xpu:latest
    container_name: ollama-intel-arc
    restart: unless-stopped
    devices:
      - /dev/dri:/dev/dri
    volumes:
      - ollama-volume:/root/.ollama
    ports:
      - 11434:11434
    environment:
      - no_proxy=localhost,127.0.0.1
      - OLLAMA_HOST=0.0.0.0
      - DEVICE=Arc
      - OLLAMA_INTEL_GPU=true
      - OLLAMA_NUM_GPU=999
      - ZES_ENABLE_SYSMAN=1
    command: sh -c 'mkdir -p /llm/ollama && cd /llm/ollama && init-ollama && exec ./ollama serve'

  open-webui:
    image: ghcr.io/open-webui/open-webui:latest
    container_name: open-webui
    volumes:
      - open-webui-volume:/app/backend/data
    depends_on:
      - ollama-intel-arc
    ports:
      - 3000:8080
    environment:
      - WEBUI_AUTH=False
      - ENABLE_OPENAI_API=False
      - ENABLE_OLLAMA_API=True
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped
volumes:
  ollama-volume: {}
  open-webui-volume: {}