Decouple the openwebui and the ollama. in inference-cpp-xpu dockerfile

docker/llm/inference-cpp/Dockerfile

@@ -45,19 +45,6 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO
     # Install opencl-related repos
     apt-get update && \
     apt-get install -y --no-install-recommends intel-opencl-icd intel-level-zero-gpu=1.3.26241.33-647~22.04 level-zero level-zero-dev --allow-downgrades && \
-    # install nodejs and npm and get webui
-    apt purge nodejs -y && \
-    apt purge libnode-dev -y && \
-    apt autoremove -y && \
-    apt clean -y && \
-    wget -qO- https://deb.nodesource.com/setup_18.x | sudo -E bash - && \
-    apt install -y nodejs && \
-    git clone https://github.com/open-webui/open-webui.git /llm/open-webui && \
-    git -C /llm/open-webui checkout e29a999dc910afad91995221cb4bb7c274f87cd6 && \
-    cp -RPp /llm/open-webui/.env.example /llm/open-webui/.env && \
-    # Build frontend
-    npm --prefix /llm/open-webui i && \
-    npm --prefix /llm/open-webui run build && \
     # Install Dependencies
     # remove blinker to avoid error
     find /usr/lib/python3/dist-packages/ -name 'blinker*' -exec rm -rf {} + && \
@@ -67,7 +54,6 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO
 
 COPY ./start-llama-cpp.sh /llm/scripts/start-llama-cpp.sh
 COPY ./start-ollama.sh /llm/scripts/start-ollama.sh
-COPY ./start-open-webui.sh /llm/scripts/start-open-webui.sh
 COPY ./benchmark_llama-cpp.sh /llm/scripts/benchmark_llama-cpp.sh
 
 WORKDIR /llm/

docker/llm/inference-cpp/README.md

@@ -154,12 +154,25 @@ Please refer to this [documentation](https://ipex-llm.readthedocs.io/en/latest/d
 
 ### Running Open WebUI with Intel GPU
 
-Start the ollama and load the model first, then use the open-webui to chat.
-If you have difficulty accessing the huggingface repositories, you may use a mirror, e.g. add export HF_ENDPOINT=https://hf-mirror.com before running bash start.sh.
+1. Start the ollama and load the model first, then use the open-webui to chat.
+
+If you have difficulty accessing the huggingface repositories, you may use a mirror, e.g. add export HF_ENDPOINT=https://hf-mirror.com and run following script to start open-webui docker.
+
 ```bash
-cd /llm/scripts/
-bash start-open-webui.sh
-# INFO:     Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)
+export DOCKER_IMAGE=ghcr.io/open-webui/open-webui:main
+export CONTAINER_NAME=<YOUR-DOCKER-CONTAINER-NAME>
+
+docker rm -f $CONTAINER_NAME
+
+docker run -itd \
+            -v open-webui:/app/backend/data \
+            -e PORT=8080 \
+            --privileged \
+            --network=host \
+            --name $CONTAINER_NAME \
+            --restart always $DOCKER_IMAGE
 ```
 
+2. Visit <http://localhost:8080> to use open-webui, the default ollama serve address in open-webui is `http://localhost:11434`, you can change it in connections on `http://localhost:8080/admin/settings`.
+
 For how to log-in or other guide, Please refer to this [documentation](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/open_webui_with_ollama_quickstart.html) for more details.