EdgeCraftRAG: Fix multiple issues (#1143)

Signed-off-by: Mingyuan Qi <mingyuan.qi@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

EdgeCraftRAG/docker_compose/intel/gpu/arc/compose.yaml

@@ -14,12 +14,15 @@ services:
     volumes:
       - ${MODEL_PATH:-${PWD}}:/home/user/models
       - ${DOC_PATH:-${PWD}}:/home/user/docs
+      - ${GRADIO_PATH:-${PWD}}:/home/user/gradio_cache
+      - ${HF_CACHE:-${HOME}/.cache}:/home/user/.cache
     ports:
       - ${PIPELINE_SERVICE_PORT:-16010}:${PIPELINE_SERVICE_PORT:-16010}
     devices:
       - /dev/dri:/dev/dri
     group_add:
-      - video
+      - ${VIDEOGROUPID:-44}
+      - ${RENDERGROUPID:-109}
   ecrag:
     image: ${REGISTRY:-opea}/edgecraftrag:${TAG:-latest}
     container_name: edgecraftrag
@@ -48,31 +51,42 @@ services:
       PIPELINE_SERVICE_HOST_IP: ${PIPELINE_SERVICE_HOST_IP:-${HOST_IP}}
       UI_SERVICE_PORT: ${UI_SERVICE_PORT:-8082}
       UI_SERVICE_HOST_IP: ${UI_SERVICE_HOST_IP:-0.0.0.0}
+    volumes:
+      - ${GRADIO_PATH:-${PWD}}:/home/user/gradio_cache
     ports:
-        - ${UI_SERVICE_PORT:-8082}:${UI_SERVICE_PORT:-8082}
+      - ${UI_SERVICE_PORT:-8082}:${UI_SERVICE_PORT:-8082}
     restart: always
     depends_on:
       - server
       - ecrag
-  # vllm-service:
-  #   image: vllm:openvino
+  # vllm-openvino-server:
   #   container_name: vllm-openvino-server
+  #   image: opea/vllm-arc:latest
   #   ports:
-  #     - "8008:80"
+  #     - ${VLLM_SERVICE_PORT:-8008}:80
   #   environment:
-  #     no_proxy: ${no_proxy}
-  #     http_proxy: ${http_proxy}
-  #     https_proxy: ${https_proxy}
-  #     vLLM_ENDPOINT: ${vLLM_ENDPOINT}
-  #     LLM_MODEL: ${LLM_MODEL}
+  #     HTTPS_PROXY: ${https_proxy}
+  #     HTTP_PROXY: ${https_proxy}
+  #     VLLM_OPENVINO_DEVICE: GPU
+  #     HF_ENDPOINT: ${HF_ENDPOINT}
+  #     HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+  #   volumes:
+  #     - /dev/dri/by-path:/dev/dri/by-path
+  #     - $HOME/.cache/huggingface:/root/.cache/huggingface
+  #   devices:
+  #     - /dev/dri
+  #   group_add:
+  #     - ${VIDEOGROUPID:-44}
+  #     - ${RENDERGROUPID:-109}
   #   entrypoint: /bin/bash -c "\
   #     cd / && \
   #     export VLLM_CPU_KVCACHE_SPACE=50 && \
+  #     export VLLM_OPENVINO_ENABLE_QUANTIZED_WEIGHTS=ON && \
   #     python3 -m vllm.entrypoints.openai.api_server \
   #       --model '${LLM_MODEL}' \
+  #       --max_model_len=1024 \
   #       --host 0.0.0.0 \
   #       --port 80"
-
 networks:
   default:
     driver: bridge