services:
  ollama-intel-arc:
    #image: intelanalytics/ipex-llm-inference-cpp-xpu:latest
    #build:
    #  context: ./ipex-ollama
    #  dockerfile: Dockerfile
    #  args:
    #    IPEXLLM_RELEASE_REPO: ipex-llm/ipex-llm
    #    IPEXLLM_RELEASE_VERSON: v2.3.0
    #    IPEXLLM_PORTABLE_ZIP_FILENAME: ollama-ipex-llm-2.2.0-ubuntu.tgz
    image: intelanalytics/ipex-llm-inference-cpp-xpu:latest
    #image: docker.io/library/ollama-intel-gpu-ollama-intel-gpu
    container_name: ollama-intel-arc
    restart: unless-stopped
    devices:
      #- /dev/dri:/dev/dri
      - /dev/dri/renderD128:/dev/dri/renderD128
    volumes:
      - /tmp/.X11-unix:/tmp/.X11-unix
      - ollama-volume:/root/.ollama
    ports:
      - 11435:11434
    environment:
      - OLLAMA_NUM_PARALLEL=1
      - OLLAMA_DEFAULT_KEEPALIVE="6h"
      - OLLAMA_KEEP_ALIVE=24h
      - OLLAMA_MAX_LOADED_MODELS=2
      - OLLAMA_MAX_QUEUE=512
      - OLLAMA_MAX_VRAM=0
      #- 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_DEVICE_INFO=1
      - DISPLAY=${DISPLAY-:0}

      # # Available low_bit format including sym_int4, sym_int8, fp16 etc.
      - USE_XETLA=OFF
      - ZES_ENABLE_SYSMAN=1

      # Add some intel specific adjustments
      #  https://github.com/intel/ipex-llm/blob/main/docs/mddocs/Quickstart/fastchat_quickstart.md

      - SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
      - ENABLE_SDP_FUSION=1

      # [optional] under most circumstances, the following environment variable may improve performance,
      # but sometimes this may also cause performance degradation
      - SYCL_CACHE_PERSISTENT=1

      # For Intel Core™ Ultra Processors (Series 2) with processor number 2xxK or 2xxH (code name Arrow Lake):
      #- IPEX_LLM_NPU_ARL=1

      # For Intel Core™ Ultra Processors (Series 1) with processor number 1xxH (code name Meteor Lake):
      #- IPEX_LLM_NPU_MTL=1

      # Parallel workers
      #- OMP_NUM_THREADS=48

    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:
      - 4040:8080
    environment:
      - OLLAMA_BASE_URL=http://ollama-intel-arc:11434

      - WEBUI_AUTH=False
      #- ENABLE_OPENAI_API=False
      #- ENABLE_OLLAMA_API=True
      - ENABLE_IMAGE_GENERATION=True
      - IMAGE_GENERATION_ENGINE=automatic1111
      - IMAGE_GENERATION_MODEL=dreamshaper_8
      - IMAGE_SIZE=400x400
      - IMAGE_STEPS=8
      - AUTOMATIC1111_BASE_URL=http://sdnext-ipex:7860/
      - AUTOMATIC1111_CFG_SCALE=2
      - AUTOMATIC1111_SAMPLER=DPM++ SDE
      - AUTOMATIC1111_SCHEDULER=Karras
      - ENABLE_RAG_WEB_SEARCH=True

      - SCARF_NO_ANALYTICS=true
      - DO_NOT_TRACK=true
      - ANONYMIZED_TELEMETRY=false
    extra_hosts:
      - host.docker.internal:host-gateway
    restart: unless-stopped

volumes:
  ollama-volume: {}
  open-webui-volume: {}