Update vLLM-fork version to v0.7.2+Gaudi-1.21.0

Signed-off-by: CICD-at-OPEA <CICD@opea.dev>
Merge branch 'main' into update_vLLM-fork
2025-05-20 22:41:44 +00:00 · 2025-05-20 10:54:35 +08:00 · 2025-05-20 10:05:00 +08:00 · 2025-05-19 09:31:56 +08:00 · 2025-05-16 15:19:36 +08:00 · 2025-05-16 15:19:07 +08:00
77 changed files with 688 additions and 582 deletions
--- a/.github/env/_build_image.sh
+++ b/.github/env/_build_image.sh
@@ -2,4 +2,4 @@
 # SPDX-License-Identifier: Apache-2.0

 export VLLM_VER=v0.8.3
-export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+export VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
--- a/.github/workflows/_run-docker-compose.yml
+++ b/.github/workflows/_run-docker-compose.yml
@@ -204,6 +204,10 @@ jobs:
          if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi

          echo "Cleaning up images ..."
+          df -h
+          sleep 1
+          docker system df
+          sleep 1
          if [[ "${{ inputs.hardware }}" == "xeon"* ]]; then
              docker system prune -a -f
          else
@@ -213,7 +217,13 @@ jobs:
              docker images --filter reference="opea/comps-base" -q | xargs -r docker rmi && sleep 1s
              docker system prune -f
          fi
+          sleep 5
          docker images
+          sleep 1
+          df -h
+          sleep 1
+          docker system df
+          sleep 1

      - name: Publish pipeline artifact
        if: ${{ !cancelled() }}
--- a/.github/workflows/pr-link-path-scan.yml
+++ b/.github/workflows/pr-link-path-scan.yml
@@ -80,6 +80,7 @@ jobs:
      - name: Checking Relative Path Validity
        run: |
          cd ${{github.workspace}}
+          delay=15
          fail="FALSE"
          repo_name=${{ github.event.pull_request.head.repo.full_name }}
          branch="https://github.com/$repo_name/blob/${{ github.event.pull_request.head.ref }}"
@@ -111,14 +112,15 @@ jobs:
                if [[ "$png_line" == *#* ]]; then
                  if [ -n "changed_files" ] && echo "$changed_files" | grep -q "^${refer_path}$"; then
                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIExamples||')$png_path
+                    sleep $delay
                    response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
                    if [ "$response" -ne 200 ]; then
-                      echo "**********Validation failed, try again**********"
+                      echo "**********Validation failed ($response), try again**********"
                      response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url_dev")
                      if [ "$response_retry" -eq 200 ]; then
                        echo "*****Retry successfully*****"
                      else
-                        echo "Invalid path from ${{github.workspace}}/$refer_path: $png_path"
+                        echo "Invalid path ($response_retry) from ${{github.workspace}}/$refer_path: $png_path"
                        fail="TRUE"
                      fi
                    else
--- a/AgentQnA/tests/step1_build_images.sh
+++ b/AgentQnA/tests/step1_build_images.sh
@@ -37,7 +37,7 @@ function build_agent_docker_image_gaudi_vllm() {
    get_genai_comps

    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build agent image with --no-cache..."
--- a/AudioQnA/tests/test_compose_on_gaudi.sh
+++ b/AudioQnA/tests/test_compose_on_gaudi.sh
@@ -27,7 +27,7 @@ function build_docker_images() {

    git clone https://github.com/HabanaAI/vllm-fork.git
    cd vllm-fork/
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    echo "Check out vLLM tag ${VLLM_FORK_VER}"
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

--- a/AvatarChatbot/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/AvatarChatbot/docker_compose/amd/gpu/rocm/set_env.sh
@@ -41,7 +41,7 @@ export FACE="/home/user/comps/animation/src/assets/img/avatar5.png"
 # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
 export AUDIO='None'
 export FACESIZE=96
-export OUTFILE="/outputs/result.mp4"
+export OUTFILE="./outputs/result.mp4"
 export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
 export UPSCALE_FACTOR=1
-export FPS=10
+export FPS=5
--- a/AvatarChatbot/docker_compose/intel/cpu/xeon/set_env.sh
+++ b/AvatarChatbot/docker_compose/intel/cpu/xeon/set_env.sh
@@ -5,3 +5,32 @@
 pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
+
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export host_ip=$(hostname -I | awk '{print $1}')
+export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+export WAV2LIP_ENDPOINT=http://$host_ip:7860
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export WHISPER_SERVER_HOST_IP=${host_ip}
+export WHISPER_SERVER_PORT=7066
+export SPEECHT5_SERVER_HOST_IP=${host_ip}
+export SPEECHT5_SERVER_PORT=7055
+export LLM_SERVER_HOST_IP=${host_ip}
+export LLM_SERVER_PORT=3006
+export ANIMATION_SERVICE_HOST_IP=${host_ip}
+export ANIMATION_SERVICE_PORT=3008
+
+export MEGA_SERVICE_PORT=8888
+
+export DEVICE="cpu"
+export WAV2LIP_PORT=7860
+export INFERENCE_MODE='wav2lip+gfpgan'
+export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
+export FACE="/home/user/comps/animation/src/assets/img/avatar5.png"
+# export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
+export AUDIO='None'
+export FACESIZE=96
+export OUTFILE="/outputs/result.mp4"
+export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
+export UPSCALE_FACTOR=1
+export FPS=10
--- a/AvatarChatbot/docker_compose/intel/hpu/gaudi/set_env.sh
+++ b/AvatarChatbot/docker_compose/intel/hpu/gaudi/set_env.sh
@@ -5,3 +5,35 @@
 pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
+
+export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
+export host_ip=$(hostname -I | awk '{print $1}')
+
+export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
+
+export WAV2LIP_ENDPOINT=http://$host_ip:7860
+
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export WHISPER_SERVER_HOST_IP=${host_ip}
+export WHISPER_SERVER_PORT=7066
+export SPEECHT5_SERVER_HOST_IP=${host_ip}
+export SPEECHT5_SERVER_PORT=7055
+export LLM_SERVER_HOST_IP=${host_ip}
+export LLM_SERVER_PORT=3006
+export ANIMATION_SERVICE_HOST_IP=${host_ip}
+export ANIMATION_SERVICE_PORT=3008
+
+export MEGA_SERVICE_PORT=8888
+
+export DEVICE="hpu"
+export WAV2LIP_PORT=7860
+export INFERENCE_MODE='wav2lip+gfpgan'
+export CHECKPOINT_PATH='/usr/local/lib/python3.10/dist-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
+export FACE="/home/user/comps/animation/src/assets/img/avatar1.jpg"
+# export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
+export AUDIO='None'
+export FACESIZE=96
+export OUTFILE="/outputs/result.mp4"
+export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
+export UPSCALE_FACTOR=1
+export FPS=10
--- a/AvatarChatbot/tests/README.md
+++ b/AvatarChatbot/tests/README.md
@@ -0,0 +1,27 @@
+# AvatarChatbot E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon with TGI:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_on_gaudi.sh
+```
+
+On AMD ROCm with TGI:
+
+```bash
+bash test_compose_on_rocm.sh
+```
--- a/AvatarChatbot/tests/test_compose_on_gaudi.sh
+++ b/AvatarChatbot/tests/test_compose_on_gaudi.sh
@@ -45,37 +45,7 @@ function build_docker_images() {
 function start_services() {
    cd $WORKPATH/docker_compose/intel/hpu/gaudi

-    export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
-    export host_ip=$(hostname -I | awk '{print $1}')
-
-    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
-
-    export WAV2LIP_ENDPOINT=http://$host_ip:7860
-
-    export MEGA_SERVICE_HOST_IP=${host_ip}
-    export WHISPER_SERVER_HOST_IP=${host_ip}
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_HOST_IP=${host_ip}
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_HOST_IP=${host_ip}
-    export LLM_SERVER_PORT=3006
-    export ANIMATION_SERVICE_HOST_IP=${host_ip}
-    export ANIMATION_SERVICE_PORT=3008
-
-    export MEGA_SERVICE_PORT=8888
-
-    export DEVICE="hpu"
-    export WAV2LIP_PORT=7860
-    export INFERENCE_MODE='wav2lip+gfpgan'
-    export CHECKPOINT_PATH='/usr/local/lib/python3.10/dist-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-    export FACE="/home/user/comps/animation/src/assets/img/avatar1.jpg"
-    # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
-    export AUDIO='None'
-    export FACESIZE=96
-    export OUTFILE="/outputs/result.mp4"
-    export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
-    export UPSCALE_FACTOR=1
-    export FPS=10
+    source set_env.sh

    # Start Docker Containers
    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
--- a/AvatarChatbot/tests/test_compose_on_rocm.sh
+++ b/AvatarChatbot/tests/test_compose_on_rocm.sh
@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0

-set -e
+set -xe
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}
 echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
@@ -42,48 +42,8 @@ function build_docker_images() {

 function start_services() {
    cd $WORKPATH/docker_compose/amd/gpu/rocm
-
-    export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
    export OPENAI_API_KEY=$OPENAI_API_KEY
-    export host_ip=${ip_address}
-
-    export TGI_SERVICE_PORT=3006
-    export TGI_LLM_ENDPOINT=http://${host_ip}:${TGI_SERVICE_PORT}
-    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-
-    export ASR_ENDPOINT=http://${host_ip}:7066
-    export TTS_ENDPOINT=http://${host_ip}:7055
-    export WAV2LIP_ENDPOINT=http://${host_ip}:7860
-
-    export MEGA_SERVICE_HOST_IP=${host_ip}
-    export ASR_SERVICE_HOST_IP=${host_ip}
-    export TTS_SERVICE_HOST_IP=${host_ip}
-    export LLM_SERVICE_HOST_IP=${host_ip}
-    export ANIMATION_SERVICE_HOST_IP=${host_ip}
-    export WHISPER_SERVER_HOST_IP=${host_ip}
-    export WHISPER_SERVER_PORT=7066
-
-    export SPEECHT5_SERVER_HOST_IP=${host_ip}
-    export SPEECHT5_SERVER_PORT=7055
-
-    export MEGA_SERVICE_PORT=8888
-    export ASR_SERVICE_PORT=3001
-    export TTS_SERVICE_PORT=3002
-    export LLM_SERVICE_PORT=3006
-    export ANIMATION_SERVICE_PORT=3008
-
-    export DEVICE="cpu"
-    export WAV2LIP_PORT=7860
-    export INFERENCE_MODE='wav2lip+gfpgan'
-    export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-    export FACE="/home/user/comps/animation/src/assets/img/avatar5.png"
-    # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
-    export AUDIO='None'
-    export FACESIZE=96
-    export OUTFILE="./outputs/result.mp4"
-    export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
-    export UPSCALE_FACTOR=1
-    export FPS=5
+    source set_env.sh

    # Start Docker Containers
    docker compose up -d --force-recreate
--- a/AvatarChatbot/tests/test_compose_on_xeon.sh
+++ b/AvatarChatbot/tests/test_compose_on_xeon.sh
@@ -45,37 +45,7 @@ function build_docker_images() {
 function start_services() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon

-    export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
-    export host_ip=$(hostname -I | awk '{print $1}')
-
-    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
-
-    export WAV2LIP_ENDPOINT=http://$host_ip:7860
-
-    export MEGA_SERVICE_HOST_IP=${host_ip}
-    export WHISPER_SERVER_HOST_IP=${host_ip}
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_HOST_IP=${host_ip}
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_HOST_IP=${host_ip}
-    export LLM_SERVER_PORT=3006
-    export ANIMATION_SERVICE_HOST_IP=${host_ip}
-    export ANIMATION_SERVICE_PORT=3008
-
-    export MEGA_SERVICE_PORT=8888
-
-    export DEVICE="cpu"
-    export WAV2LIP_PORT=7860
-    export INFERENCE_MODE='wav2lip+gfpgan'
-    export CHECKPOINT_PATH='/usr/local/lib/python3.11/site-packages/Wav2Lip/checkpoints/wav2lip_gan.pth'
-    export FACE="/home/user/comps/animation/src/assets/img/avatar5.png"
-    # export AUDIO='assets/audio/eg3_ref.wav' # audio file path is optional, will use base64str in the post request as input if is 'None'
-    export AUDIO='None'
-    export FACESIZE=96
-    export OUTFILE="/outputs/result.mp4"
-    export GFPGAN_MODEL_VERSION=1.4 # latest version, can roll back to v1.3 if needed
-    export UPSCALE_FACTOR=1
-    export FPS=10
+    source set_env.sh

    # Start Docker Containers
    docker compose up -d
--- a/ChatQnA/tests/test_compose_faqgen_on_gaudi.sh
+++ b/ChatQnA/tests/test_compose_faqgen_on_gaudi.sh
@@ -24,7 +24,7 @@ function build_docker_images() {
    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
    popd && sleep 1s
    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
--- a/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
+++ b/ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
@@ -24,7 +24,7 @@ function build_docker_images() {
    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
    popd && sleep 1s
    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
--- a/ChatQnA/tests/test_compose_mariadb_on_xeon.sh
+++ b/ChatQnA/tests/test_compose_mariadb_on_xeon.sh
@@ -140,7 +140,7 @@ function validate_megaservice() {

 function stop_docker() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon
-    docker compose down
+    docker compose -f compose_mariadb.yaml down
 }

 function main() {
--- a/ChatQnA/tests/test_compose_on_gaudi.sh
+++ b/ChatQnA/tests/test_compose_on_gaudi.sh
@@ -24,7 +24,7 @@ function build_docker_images() {
    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
    popd && sleep 1s
    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
--- a/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
+++ b/ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
@@ -24,7 +24,7 @@ function build_docker_images() {
    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
    popd && sleep 1s
    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
--- a/CodeGen/Dockerfile
+++ b/CodeGen/Dockerfile
@@ -1,8 +1,9 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0

+ARG IMAGE_REPO=opea
 ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
+FROM $IMAGE_REPO/comps-base:$BASE_TAG

 COPY ./codegen.py $HOME/codegen.py

--- a/CodeGen/docker_image_build/build.yaml
+++ b/CodeGen/docker_image_build/build.yaml
@@ -5,6 +5,8 @@ services:
  codegen:
    build:
      args:
+        IMAGE_REPO: ${REGISTRY}
+        BASE_TAG: ${TAG}
        http_proxy: ${http_proxy}
        https_proxy: ${https_proxy}
        no_proxy: ${no_proxy}
@@ -39,6 +41,7 @@ services:
    build:
      context: GenAIComps
      dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
+    extends: codegen
    image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
  vllm:
    build:
--- a/CodeGen/tests/test_compose_on_gaudi.sh
+++ b/CodeGen/tests/test_compose_on_gaudi.sh
@@ -27,23 +27,17 @@ export no_proxy=${no_proxy},${ip_address}

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi

    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    # Download Gaudi vllm of latest tag
    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    echo "Check out vLLM tag ${VLLM_FORK_VER}"
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

@@ -250,24 +244,36 @@ function main() {
        stop_docker "${docker_compose_profiles[${i}]}"
    done

-    # build docker images
+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"

    # loop all profiles
    for ((i = 0; i < len_profiles; i++)); do
        echo "Process [${i}]: ${docker_compose_profiles[$i]}, ${docker_llm_container_names[${i}]}"
+
+        echo "::group::start_services"
        start_services "${docker_compose_profiles[${i}]}" "${docker_llm_container_names[${i}]}"
+        echo "::endgroup::"
        docker ps -a

+        echo "::group::validate_microservices"
        validate_microservices "${docker_llm_container_names[${i}]}"
+        echo "::endgroup::"
+
+        echo "::group::validate_megaservice"
        validate_megaservice
+        echo "::endgroup::"
+
+        echo "::group::validate_gradio"
        validate_gradio
+        echo "::endgroup::"

        stop_docker "${docker_compose_profiles[${i}]}"
        sleep 5s
    done

-    echo y | docker system prune
+    docker system prune -f
 }

 main
--- a/CodeGen/tests/test_compose_on_rocm.sh
+++ b/CodeGen/tests/test_compose_on_rocm.sh
@@ -17,19 +17,13 @@ ip_address=$(hostname -I | awk '{print $1}')

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi

    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
    service_list="codegen codegen-ui llm-textgen"
@@ -164,18 +158,35 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::validate_frontend"
+    validate_frontend
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
-    cd $WORKPATH
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/CodeGen/tests/test_compose_on_xeon.sh
+++ b/CodeGen/tests/test_compose_on_xeon.sh
@@ -27,19 +27,13 @@ export no_proxy=${no_proxy},${ip_address}

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi

    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    git clone https://github.com/vllm-project/vllm.git && cd vllm
    VLLM_VER="v0.8.3"
@@ -256,17 +250,28 @@ function main() {
    for ((i = 0; i < len_profiles; i++)); do
        echo "Process [${i}]: ${docker_compose_profiles[$i]}, ${docker_llm_container_names[${i}]}"
        docker ps -a
-        start_services "${docker_compose_profiles[${i}]}" "${docker_llm_container_names[${i}]}"

+        echo "::group::start_services"
+        start_services "${docker_compose_profiles[${i}]}" "${docker_llm_container_names[${i}]}"
+        echo "::endgroup::"
+
+        echo "::group::validate_microservices"
        validate_microservices "${docker_llm_container_names[${i}]}"
+        echo "::endgroup::"
+
+        echo "::group::validate_megaservice"
        validate_megaservice
+        echo "::endgroup::"
+
+        echo "::group::validate_gradio"
        validate_gradio
+        echo "::endgroup::"

        stop_docker "${docker_compose_profiles[${i}]}"
        sleep 5s
    done

-    echo y | docker system prune
+    docker system prune -f
 }

 main
--- a/CodeGen/tests/test_compose_vllm_on_rocm.sh
+++ b/CodeGen/tests/test_compose_vllm_on_rocm.sh
@@ -17,19 +17,13 @@ ip_address=$(hostname -I | awk '{print $1}')

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi

    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
    service_list="vllm-rocm llm-textgen codegen codegen-ui"
@@ -164,17 +158,35 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::validate_frontend"
+    validate_frontend
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
-    cd $WORKPATH
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/CodeTrans/docker_compose/intel/cpu/xeon/README.md
+++ b/CodeTrans/docker_compose/intel/cpu/xeon/README.md
@@ -46,7 +46,7 @@ export http_proxy="Your_HTTP_Proxy"           # http proxy if any
 export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
 export no_proxy=localhost,127.0.0.1,$host_ip  # additional no proxies if needed
 export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
-source ./set_env.sh
+source docker_compose/intel/set_env.sh
 ```

 Consult the section on [CodeTrans Service configuration](#codetrans-configuration) for information on how service specific configuration parameters affect deployments.
--- a/CodeTrans/docker_compose/intel/hpu/gaudi/README.md
+++ b/CodeTrans/docker_compose/intel/hpu/gaudi/README.md
@@ -46,7 +46,7 @@ export http_proxy="Your_HTTP_Proxy"           # http proxy if any
 export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
 export no_proxy=localhost,127.0.0.1,$host_ip  # additional no proxies if needed
 export NGINX_PORT=${your_nginx_port}          # your usable port for nginx, 80 for example
-source ./set_env.sh
+source docker_compose/intel/set_env.sh
 ```

 Consult the section on [CodeTrans Service configuration](#codetrans-configuration) for information on how service specific configuration parameters affect deployments.
--- a/CodeTrans/docker_compose/intel/set_env.sh
+++ b/CodeTrans/docker_compose/intel/set_env.sh
@@ -2,7 +2,7 @@

 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-pushd "../../" > /dev/null
+pushd "../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null

--- a/CodeTrans/tests/test_compose_on_gaudi.sh
+++ b/CodeTrans/tests/test_compose_on_gaudi.sh
@@ -26,7 +26,7 @@ function build_docker_images() {
    popd && sleep 1s

    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
@@ -37,12 +37,12 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose
+    cd $WORKPATH/docker_compose/intel
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
    export NGINX_PORT=80
    export host_ip=${ip_address}
    source set_env.sh
-    cd intel/hpu/gaudi
+    cd hpu/gaudi

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_on_xeon.sh
+++ b/CodeTrans/tests/test_compose_on_xeon.sh
@@ -39,13 +39,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose
+    cd $WORKPATH/docker_compose/intel
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}

    export NGINX_PORT=80
    export host_ip=${ip_address}
    source set_env.sh
-    cd intel/cpu/xeon/
+    cd cpu/xeon/

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_tgi_on_gaudi.sh
+++ b/CodeTrans/tests/test_compose_tgi_on_gaudi.sh
@@ -34,13 +34,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose
+    cd $WORKPATH/docker_compose/intel
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}

    export NGINX_PORT=80
    export host_ip=${ip_address}
    source set_env.sh
-    cd intel/hpu/gaudi/
+    cd hpu/gaudi/

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/CodeTrans/tests/test_compose_tgi_on_xeon.sh
+++ b/CodeTrans/tests/test_compose_tgi_on_xeon.sh
@@ -34,13 +34,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose
+    cd $WORKPATH/docker_compose/intel
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}

    export NGINX_PORT=80
    export host_ip=${ip_address}
    source set_env.sh
-    cd intel/cpu/xeon/
+    cd cpu/xeon/

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/DocIndexRetriever/Dockerfile
+++ b/DocIndexRetriever/Dockerfile
@@ -1,8 +1,9 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0

+ARG IMAGE_REPO=opea
 ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
+FROM $IMAGE_REPO/comps-base:$BASE_TAG

 COPY ./retrieval_tool.py $HOME/retrieval_tool.py

--- a/DocIndexRetriever/docker_image_build/build.yaml
+++ b/DocIndexRetriever/docker_image_build/build.yaml
@@ -5,6 +5,8 @@ services:
  doc-index-retriever:
    build:
      args:
+        IMAGE_REPO: ${REGISTRY:-opea}
+        BASE_TAG: ${TAG:-latest}
        http_proxy: ${http_proxy}
        https_proxy: ${https_proxy}
        no_proxy: ${no_proxy}
--- a/DocIndexRetriever/tests/test_compose_milvus_on_gaudi.sh
+++ b/DocIndexRetriever/tests/test_compose_milvus_on_gaudi.sh
@@ -20,17 +20,15 @@ function build_docker_images() {
    if [ ! -d "GenAIComps" ] ; then
        git clone --single-branch --branch "${opea_branch:-"main"}" https://github.com/opea-project/GenAIComps.git
    fi
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+
    service_list="dataprep embedding retriever reranking doc-index-retriever"
    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
-    docker pull quay.io/coreos/etcd:v3.5.5
-    docker pull minio/minio:RELEASE.2023-03-20T20-16-18Z
-    docker pull milvusdb/milvus:v2.4.6
    docker images && sleep 1s
-
-    echo "Docker images built!"
 }

 function start_services() {
@@ -112,19 +110,27 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "Dump current docker ps"
-    docker ps
-    start_time=$(date +%s)
-    start_services
-    end_time=$(date +%s)
-    duration=$((end_time-start_time))
-    echo "Mega service start duration is $duration s"
-    validate_megaservice
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/DocIndexRetriever/tests/test_compose_milvus_on_xeon.sh
+++ b/DocIndexRetriever/tests/test_compose_milvus_on_xeon.sh
@@ -20,16 +20,15 @@ function build_docker_images() {
    if [ ! -d "GenAIComps" ] ; then
        git clone --single-branch --branch "${opea_branch:-"main"}" https://github.com/opea-project/GenAIComps.git
    fi
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+
    service_list="dataprep embedding retriever reranking doc-index-retriever"
    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-    docker pull quay.io/coreos/etcd:v3.5.5
-    docker pull minio/minio:RELEASE.2023-03-20T20-16-18Z
-    docker pull milvusdb/milvus:v2.4.6
    docker images && sleep 1s
-
-    echo "Docker images built!"
 }

 function start_services() {
@@ -111,19 +110,27 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "Dump current docker ps"
-    docker ps
-    start_time=$(date +%s)
-    start_services
-    end_time=$(date +%s)
-    duration=$((end_time-start_time))
-    echo "Mega service start duration is $duration s"
-    validate_megaservice
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/DocIndexRetriever/tests/test_compose_on_gaudi.sh
+++ b/DocIndexRetriever/tests/test_compose_on_gaudi.sh
@@ -21,14 +21,15 @@ function build_docker_images() {
    if [ ! -d "GenAIComps" ] ; then
        git clone --single-branch --branch "${opea_branch:-"main"}" https://github.com/opea-project/GenAIComps.git
    fi
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull redis/redis-stack:7.2.0-v9
-    docker pull ghcr.io/huggingface/tei-gaudi:1.5.0
    docker images && sleep 1s
-    echo "Docker images built!"
 }

 function start_services() {
@@ -103,19 +104,27 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "Dump current docker ps"
-    docker ps
-    start_time=$(date +%s)
-    start_services
-    end_time=$(date +%s)
-    duration=$((end_time-start_time))
-    echo "Mega service start duration is $duration s"
-    validate_megaservice
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/DocIndexRetriever/tests/test_compose_on_xeon.sh
+++ b/DocIndexRetriever/tests/test_compose_on_xeon.sh
@@ -21,14 +21,15 @@ function build_docker_images() {
    if [ ! -d "GenAIComps" ] ; then
        git clone --single-branch --branch "${opea_branch:-"main"}" https://github.com/opea-project/GenAIComps.git
    fi
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+
    service_list="dataprep embedding retriever reranking doc-index-retriever"
    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
-    docker pull redis/redis-stack:7.2.0-v9
    docker images && sleep 1s
-
-    echo "Docker images built!"
 }

 function start_services() {
@@ -110,20 +111,27 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "Dump current docker ps"
-    docker ps
+    echo "::endgroup::"

-    start_time=$(date +%s)
+    echo "::group::start_services"
    start_services
-    end_time=$(date +%s)
-    duration=$((end_time-start_time))
-    echo "Mega service start duration is $duration s"
-    validate_megaservice
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh
+++ b/DocIndexRetriever/tests/test_compose_without_rerank_on_xeon.sh
@@ -21,6 +21,11 @@ function build_docker_images() {
    if [ ! -d "GenAIComps" ] ; then
        git clone --single-branch --branch "${opea_branch:-"main"}" https://github.com/opea-project/GenAIComps.git
    fi
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+
    service_list="dataprep embedding retriever doc-index-retriever"
    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

@@ -114,19 +119,27 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    echo "Dump current docker ps"
-    docker ps
-    start_time=$(date +%s)
-    start_services
-    end_time=$(date +%s)
-    duration=$((end_time-start_time))
-    echo "Mega service start duration is $duration s"
-    validate_megaservice
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
+    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/DocSum/docker_compose/intel/cpu/xeon/README.md
+++ b/DocSum/docker_compose/intel/cpu/xeon/README.md
@@ -27,9 +27,9 @@ Clone the GenAIExample repository and access the ChatQnA Intel Xeon platform Doc

 ```bash
 git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/DocSum/docker_compose
+cd GenAIExamples/DocSum/docker_compose/intel
 source set_env.sh
-cd intel/cpu/xeon/
+cd cpu/xeon/
 ```

 NOTE: by default vLLM does "warmup" at start, to optimize its performance for the specified model and the underlying platform, which can take long time. For development (and e.g. autoscaling) it can be skipped with `export VLLM_SKIP_WARMUP=true`.
@@ -49,6 +49,7 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 To deploy the DocSum services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute:

 ```bash
+cd cpu/xeon/
 docker compose up -d
 ```

--- a/DocSum/docker_compose/intel/hpu/gaudi/README.md
+++ b/DocSum/docker_compose/intel/hpu/gaudi/README.md
@@ -29,9 +29,9 @@ Clone the GenAIExample repository and access the DocSum Intel® Gaudi® platform

 ```bash
 git clone https://github.com/opea-project/GenAIExamples.git
-cd GenAIExamples/DocSum/docker_compose
+cd GenAIExamples/DocSum/docker_compose/intel
 source set_env.sh
-cd intel/hpu/gaudi/
+cd hpu/gaudi/
 ```

 NOTE: by default vLLM does "warmup" at start, to optimize its performance for the specified model and the underlying platform, which can take long time. For development (and e.g. autoscaling) it can be skipped with `export VLLM_SKIP_WARMUP=true`.
@@ -51,6 +51,7 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 To deploy the DocSum services, execute the `docker compose up` command with the appropriate arguments. For a default deployment, execute:

 ```bash
+cd hpu/gaudi/
 docker compose up -d
 ```

--- a/DocSum/docker_compose/intel/set_env.sh
+++ b/DocSum/docker_compose/intel/set_env.sh
--- a/DocSum/tests/test_compose_on_gaudi.sh
+++ b/DocSum/tests/test_compose_on_gaudi.sh
@@ -16,7 +16,7 @@ echo "REGISTRY=IMAGE_REPO=${IMAGE_REPO}"
 echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}
-source $WORKPATH/docker_compose/set_env.sh
+source $WORKPATH/docker_compose/intel/set_env.sh

 export MODEL_CACHE=${model_cache:-"./data"}

@@ -50,7 +50,7 @@ function build_docker_images() {
    popd && sleep 1s

    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
--- a/DocSum/tests/test_compose_on_xeon.sh
+++ b/DocSum/tests/test_compose_on_xeon.sh
@@ -17,7 +17,7 @@ echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}

-source $WORKPATH/docker_compose/set_env.sh
+source $WORKPATH/docker_compose/intel/set_env.sh
 export MODEL_CACHE=${model_cache:-"./data"}

 export MAX_INPUT_TOKENS=2048
--- a/DocSum/tests/test_compose_tgi_on_gaudi.sh
+++ b/DocSum/tests/test_compose_tgi_on_gaudi.sh
@@ -16,7 +16,7 @@ echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}

-source $WORKPATH/docker_compose/set_env.sh
+source $WORKPATH/docker_compose/intel/set_env.sh
 export MODEL_CACHE=${model_cache:-"./data"}

 export MAX_INPUT_TOKENS=2048
--- a/DocSum/tests/test_compose_tgi_on_xeon.sh
+++ b/DocSum/tests/test_compose_tgi_on_xeon.sh
@@ -16,7 +16,7 @@ echo "TAG=IMAGE_TAG=${IMAGE_TAG}"
 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}

-source $WORKPATH/docker_compose/set_env.sh
+source $WORKPATH/docker_compose/intel/set_env.sh
 export MODEL_CACHE=${model_cache:-"./data"}

 export MAX_INPUT_TOKENS=2048
--- a/EdgeCraftRAG/docker_compose/intel/gpu/arc/set_env.sh
+++ b/EdgeCraftRAG/docker_compose/intel/gpu/arc/set_env.sh
@@ -5,3 +5,13 @@
 pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
+
+export MODEL_PATH=${MODEL_PATH}
+export DOC_PATH=${DOC_PATH}
+export UI_TMPFILE_PATH=${UI_TMPFILE_PATH}
+export HOST_IP=${HOST_IP}
+export LLM_MODEL=${LLM_MODEL}
+export HF_ENDPOINT=${HF_ENDPOINT}
+export vLLM_ENDPOINT=${vLLM_ENDPOINT}
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export no_proxy="localhost, 127.0.0.1, 192.168.1.1"
--- a/EdgeCraftRAG/tests/README.md
+++ b/EdgeCraftRAG/tests/README.md
@@ -0,0 +1,21 @@
+# EdgeCraftRAG E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel ARC with TGI:
+
+```bash
+bash test_compose_on_arc.sh
+```
+
+On Intel ARC with vLLM:
+
+```bash
+bash test_compose_vllm_on_arc.sh
+```
--- a/EdgeCraftRAG/tests/test_compose_on_arc.sh
+++ b/EdgeCraftRAG/tests/test_compose_on_arc.sh
@@ -46,18 +46,10 @@ function build_docker_images() {
 }

 function start_services() {
-    export MODEL_PATH=${MODEL_PATH}
-    export DOC_PATH=${DOC_PATH}
    export UI_UPLOAD_PATH=${UI_UPLOAD_PATH}
-    export HOST_IP=${HOST_IP}
-    export LLM_MODEL=${LLM_MODEL}
-    export HF_ENDPOINT=${HF_ENDPOINT}
-    export vLLM_ENDPOINT=${vLLM_ENDPOINT}
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export no_proxy="localhost, 127.0.0.1, 192.168.1.1"

    cd $WORKPATH/docker_compose/intel/gpu/arc
-
+    source set_env.sh
    # Start Docker Containers
    docker compose -f $COMPOSE_FILE up -d > ${LOG_PATH}/start_services_with_compose.log
    sleep 20
--- a/EdgeCraftRAG/tests/test_compose_vllm_on_arc.sh
+++ b/EdgeCraftRAG/tests/test_compose_vllm_on_arc.sh
@@ -53,17 +53,8 @@ function build_docker_images() {
 }

 function start_services() {
-    export MODEL_PATH=${MODEL_PATH}
-    export DOC_PATH=${DOC_PATH}
-    export UI_TMPFILE_PATH=${UI_TMPFILE_PATH}
-    export HOST_IP=${HOST_IP}
-    export LLM_MODEL=${LLM_MODEL}
-    export HF_ENDPOINT=${HF_ENDPOINT}
-    export vLLM_ENDPOINT=${vLLM_ENDPOINT}
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export no_proxy="localhost, 127.0.0.1, 192.168.1.1"
-
    cd $WORKPATH/docker_compose/intel/gpu/arc
+    source set_env.sh

    # Start Docker Containers
    docker compose -f $COMPOSE_FILE up -d > ${LOG_PATH}/start_services_with_compose.log
--- a/FinanceAgent/tests/test_compose_on_gaudi.sh
+++ b/FinanceAgent/tests/test_compose_on_gaudi.sh
@@ -60,7 +60,7 @@ function build_vllm_docker_image() {
    fi
    cd ./vllm-fork

-    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
    git checkout ${VLLM_FORK_VER} &> /dev/null
    docker build --no-cache -f Dockerfile.hpu -t $vllm_image --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
    if [ $? -ne 0 ]; then
--- a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md
+++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md
@@ -137,7 +137,6 @@ export BACKEND_SERVICE_ENDPOINT_DOCSUM="http://${host_ip}:8890/v1/docsum"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
 export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get"
 export CHAT_HISTORY_CREATE_ENDPOINT="http://${host_ip}:6012/v1/chathistory/create"
-export CHAT_HISTORY_CREATE_ENDPOINT="http://${host_ip}:6012/v1/chathistory/create"
 export CHAT_HISTORY_DELETE_ENDPOINT="http://${host_ip}:6012/v1/chathistory/delete"
 export CHAT_HISTORY_GET_ENDPOINT="http://${host_ip}:6012/v1/chathistory/get"
 export PROMPT_SERVICE_GET_ENDPOINT="http://${host_ip}:6018/v1/prompt/get"
--- a/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh
+++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh
@@ -18,7 +18,6 @@ export BACKEND_SERVICE_ENDPOINT_DOCSUM="http://${host_ip}:8890/v1/docsum"
 export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
 export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get"
 export CHAT_HISTORY_CREATE_ENDPOINT="http://${host_ip}:6012/v1/chathistory/create"
-export CHAT_HISTORY_CREATE_ENDPOINT="http://${host_ip}:6012/v1/chathistory/create"
 export CHAT_HISTORY_DELETE_ENDPOINT="http://${host_ip}:6012/v1/chathistory/delete"
 export CHAT_HISTORY_GET_ENDPOINT="http://${host_ip}:6012/v1/chathistory/get"
 export PROMPT_SERVICE_GET_ENDPOINT="http://${host_ip}:6018/v1/prompt/get"
--- a/ProductivitySuite/tests/README.md
+++ b/ProductivitySuite/tests/README.md
@@ -0,0 +1,15 @@
+# ProductivitySuite E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon with TGI:
+
+```bash
+bash test_compose_on_xeon.sh
+```
--- a/ProductivitySuite/tests/test_compose_on_xeon.sh
+++ b/ProductivitySuite/tests/test_compose_on_xeon.sh
@@ -29,33 +29,12 @@ function build_docker_images() {

 function start_services() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon/
-
-    export DB_NAME="opea"
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-    export LLM_MODEL_ID_CODEGEN="Intel/neural-chat-7b-v3-3"
-    export INDEX_NAME="rag-redis"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export BACKEND_SERVICE_ENDPOINT_CHATQNA="http://${ip_address}:8888/v1/chatqna"
-    export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/delete"
-    export BACKEND_SERVICE_ENDPOINT_CODEGEN="http://${ip_address}:7778/v1/codegen"
-    export BACKEND_SERVICE_ENDPOINT_DOCSUM="http://${ip_address}:8890/v1/docsum"
-    export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/ingest"
-    export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/get"
-    export CHAT_HISTORY_CREATE_ENDPOINT="http://${ip_address}:6012/v1/chathistory/create"
-    export CHAT_HISTORY_CREATE_ENDPOINT="http://${ip_address}:6012/v1/chathistory/create"
-    export CHAT_HISTORY_DELETE_ENDPOINT="http://${ip_address}:6012/v1/chathistory/delete"
-    export CHAT_HISTORY_GET_ENDPOINT="http://${ip_address}:6012/v1/chathistory/get"
-    export PROMPT_SERVICE_GET_ENDPOINT="http://${ip_address}:6018/v1/prompt/get"
-    export PROMPT_SERVICE_CREATE_ENDPOINT="http://${ip_address}:6018/v1/prompt/create"
-    export PROMPT_SERVICE_DELETE_ENDPOINT="http://${ip_address}:6018/v1/prompt/delete"
-    export KEYCLOAK_SERVICE_ENDPOINT="http://${ip_address}:8080"
-    export DocSum_COMPONENT_NAME="OpeaDocSumTgi"
    export host_ip=${ip_address}
    export LOGFLAG=True
    export no_proxy="$no_proxy,tgi_service_codegen,llm_codegen,tei-embedding-service,tei-reranking-service,chatqna-xeon-backend-server,retriever,tgi-service,redis-vector-db,whisper,llm-docsum-tgi,docsum-xeon-backend-server,mongo,codegen"

+    source set_env.sh
+
    # Start Docker Containers
    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
    sleep 30s
--- a/SearchQnA/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/SearchQnA/docker_compose/amd/gpu/rocm/set_env.sh
@@ -2,8 +2,8 @@

 # Copyright (C) 2025 Advanced Micro Devices, Inc.

-export HOST_IP=''
-export EXTERNAL_HOST_IP=''
+export HOST_IP=${ip_address}
+export EXTERNAL_HOST_IP=${ip_address}

 export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
 export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
@@ -12,9 +12,9 @@ export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
 export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'

-export SEARCH_BACKEND_SERVICE_PORT=18142
+export SEARCH_BACKEND_SERVICE_PORT=3008
 export SEARCH_EMBEDDING_SERVICE_PORT=3002
-export SEARCH_FRONTEND_SERVICE_PORT=18143
+export SEARCH_FRONTEND_SERVICE_PORT=5173
 export SEARCH_LLM_SERVICE_PORT=3007
 export SEARCH_RERANK_SERVICE_PORT=3005
 export SEARCH_TEI_EMBEDDING_PORT=3001
--- a/SearchQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh
+++ b/SearchQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh
@@ -2,8 +2,8 @@

 # Copyright (C) 2025 Advanced Micro Devices, Inc.

-export HOST_IP=''
-export EXTERNAL_HOST_IP=''
+export HOST_IP=${ip_address}
+export EXTERNAL_HOST_IP=${ip_address}

 export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
 export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
@@ -12,11 +12,11 @@ export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
 export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'

-export MODEL_PATH="./data"
+export MODEL_CACHE="./data"

-export SEARCH_BACKEND_SERVICE_PORT=18142
+export SEARCH_BACKEND_SERVICE_PORT=3008
 export SEARCH_EMBEDDING_SERVICE_PORT=3002
-export SEARCH_FRONTEND_SERVICE_PORT=18143
+export SEARCH_FRONTEND_SERVICE_PORT=5173
 export SEARCH_LLM_SERVICE_PORT=3007
 export SEARCH_RERANK_SERVICE_PORT=3005
 export SEARCH_TEI_EMBEDDING_PORT=3001
--- a/SearchQnA/docker_compose/intel/set_env.sh
+++ b/SearchQnA/docker_compose/intel/set_env.sh
@@ -2,11 +2,13 @@

 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-pushd "../../" > /dev/null
+pushd "../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null

-
+export GOOGLE_CSE_ID=$GOOGLE_CSE_ID
+export GOOGLE_API_KEY=$GOOGLE_API_KEY
+export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
 export EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
 export TEI_EMBEDDING_ENDPOINT=http://${host_ip}:3001
 export RERANK_MODEL_ID=BAAI/bge-reranker-base
--- a/SearchQnA/tests/README.md
+++ b/SearchQnA/tests/README.md
@@ -0,0 +1,33 @@
+# SearchQnA E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon with TGI:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_on_gaudi.sh
+```
+
+On AMD ROCm with TGI:
+
+```bash
+bash test_compose_on_rocm.sh
+```
+
+On AMD ROCm with vLLM:
+
+```bash
+bash test_compose_vllm_on_rocm.sh
+```
--- a/SearchQnA/tests/test_compose_on_gaudi.sh
+++ b/SearchQnA/tests/test_compose_on_gaudi.sh
@@ -43,34 +43,13 @@ function build_docker_images() {

 function start_services() {

-    cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export GOOGLE_CSE_ID=$GOOGLE_CSE_ID
-    export GOOGLE_API_KEY=$GOOGLE_API_KEY
-    export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
-
-    export EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
-    export TEI_EMBEDDING_ENDPOINT=http://$ip_address:3001
-    export RERANK_MODEL_ID=BAAI/bge-reranker-base
+    cd $WORKPATH/docker_compose/intel/
    export RERANK_TYPE="tei"
-    export TEI_RERANKING_ENDPOINT=http://$ip_address:3004
-
-    export TGI_LLM_ENDPOINT=http://$ip_address:3006
-    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
-    export WEB_RETRIEVER_SERVICE_HOST_IP=${ip_address}
-    export RERANK_SERVICE_HOST_IP=${ip_address}
-    export LLM_SERVICE_HOST_IP=${ip_address}
-
-    export EMBEDDING_SERVICE_PORT=3002
-    export WEB_RETRIEVER_SERVICE_PORT=3003
-    export RERANK_SERVICE_PORT=3005
-    export LLM_SERVICE_PORT=3007
    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:3008/v1/searchqna"
    export host_ip=${ip_address}
    export LOGFLAG=true
-
+    source ./set_env.sh
+    cd hpu/gaudi

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/SearchQnA/tests/test_compose_on_rocm.sh
+++ b/SearchQnA/tests/test_compose_on_rocm.sh
@@ -30,36 +30,7 @@ function build_docker_images() {

 function start_services() {
    cd $WORKPATH/docker_compose/amd/gpu/rocm/
-
-    export HOST_IP=${ip_address}
-    export EXTERNAL_HOST_IP=${ip_address}
-
-    export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
-    export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
-    export SEARCH_GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
-    export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
-    export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'
-
-    export SEARCH_BACKEND_SERVICE_PORT=3008
-    export SEARCH_EMBEDDING_SERVICE_PORT=3002
-    export SEARCH_FRONTEND_SERVICE_PORT=5173
-    export SEARCH_LLM_SERVICE_PORT=3007
-    export SEARCH_RERANK_SERVICE_PORT=3005
-    export SEARCH_TEI_EMBEDDING_PORT=3001
-    export SEARCH_TEI_RERANKING_PORT=3004
-    export SEARCH_TGI_SERVICE_PORT=3006
-    export SEARCH_WEB_RETRIEVER_SERVICE_PORT=3003
-
-    export SEARCH_BACKEND_SERVICE_ENDPOINT=http://${EXTERNAL_HOST_IP}:${SEARCH_BACKEND_SERVICE_PORT}/v1/searchqna
-    export SEARCH_EMBEDDING_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_LLM_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_MEGA_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_RERANK_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_TEI_EMBEDDING_ENDPOINT=http://${HOST_IP}:${SEARCH_TEI_EMBEDDING_PORT}
-    export SEARCH_TEI_RERANKING_ENDPOINT=http://${HOST_IP}:${SEARCH_TEI_RERANKING_PORT}
-    export SEARCH_TGI_LLM_ENDPOINT=http://${HOST_IP}:${SEARCH_TGI_SERVICE_PORT}
-    export SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP=${HOST_IP}
+    source ./set_env.sh

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/SearchQnA/tests/test_compose_on_xeon.sh
+++ b/SearchQnA/tests/test_compose_on_xeon.sh
@@ -41,34 +41,13 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export GOOGLE_CSE_ID=$GOOGLE_CSE_ID
-    export GOOGLE_API_KEY=$GOOGLE_API_KEY
-    export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
-
-    export EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
-    export TEI_EMBEDDING_ENDPOINT=http://$ip_address:3001
-    export RERANK_MODEL_ID=BAAI/bge-reranker-base
+    cd $WORKPATH/docker_compose/intel/
    export RERANK_TYPE="tei"
-    export TEI_RERANKING_ENDPOINT=http://$ip_address:3004
-
-    export TGI_LLM_ENDPOINT=http://$ip_address:3006
-    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export EMBEDDING_SERVICE_HOST_IP=${ip_address}
-    export WEB_RETRIEVER_SERVICE_HOST_IP=${ip_address}
-    export RERANK_SERVICE_HOST_IP=${ip_address}
-    export LLM_SERVICE_HOST_IP=${ip_address}
-
-    export EMBEDDING_SERVICE_PORT=3002
-    export WEB_RETRIEVER_SERVICE_PORT=3003
-    export RERANK_SERVICE_PORT=3005
-    export LLM_SERVICE_PORT=3007
    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:3008/v1/searchqna"
    export host_ip=${ip_address}
    export LOGFLAG=true
-
+    source ./set_env.sh
+    cd cpu/xeon

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/SearchQnA/tests/test_compose_vllm_on_rocm.sh
+++ b/SearchQnA/tests/test_compose_vllm_on_rocm.sh
@@ -31,36 +31,8 @@ function start_services() {
    cd $WORKPATH/docker_compose/amd/gpu/rocm/

    export HOST_IP=${ip_address}
-    export EXTERNAL_HOST_IP=${ip_address}
-
-    export SEARCH_EMBEDDING_MODEL_ID='BAAI/bge-base-en-v1.5'
-    export SEARCH_GOOGLE_API_KEY=${GOOGLE_API_KEY}
-    export SEARCH_GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
-    export SEARCH_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export SEARCH_LLM_MODEL_ID='Intel/neural-chat-7b-v3-3'
-    export SEARCH_RERANK_MODEL_ID='BAAI/bge-reranker-base'
-
-    export MODEL_CACHE="./data"
-
-    export SEARCH_BACKEND_SERVICE_PORT=3008
-    export SEARCH_EMBEDDING_SERVICE_PORT=3002
-    export SEARCH_FRONTEND_SERVICE_PORT=5173
-    export SEARCH_LLM_SERVICE_PORT=3007
-    export SEARCH_RERANK_SERVICE_PORT=3005
-    export SEARCH_TEI_EMBEDDING_PORT=3001
-    export SEARCH_TEI_RERANKING_PORT=3004
-    export SEARCH_VLLM_SERVICE_PORT=3080
-    export SEARCH_WEB_RETRIEVER_SERVICE_PORT=3003
-
-    export SEARCH_BACKEND_SERVICE_ENDPOINT=http://${EXTERNAL_HOST_IP}:${SEARCH_BACKEND_SERVICE_PORT}/v1/searchqna
-    export SEARCH_EMBEDDING_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_LLM_ENDPOINT=http://${HOST_IP}:${SEARCH_VLLM_SERVICE_PORT}
-    export SEARCH_LLM_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_MEGA_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_RERANK_SERVICE_HOST_IP=${HOST_IP}
-    export SEARCH_TEI_EMBEDDING_ENDPOINT=http://${HOST_IP}:${SEARCH_TEI_EMBEDDING_PORT}
-    export SEARCH_TEI_RERANKING_ENDPOINT=http://${HOST_IP}:${SEARCH_TEI_RERANKING_PORT}
-    export SEARCH_WEB_RETRIEVER_SERVICE_HOST_IP=${HOST_IP}
+    # export SEARCH_BACKEND_SERVICE_PORT=3008
+    source ./set_env_vllm.sh

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/Translation/docker_compose/intel/cpu/xeon/README.md
+++ b/Translation/docker_compose/intel/cpu/xeon/README.md
@@ -42,9 +42,9 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 To set up environment variables for deploying Translation service, source the set_env.sh script in this directory:

 ```
-cd ../../../
+cd ../../
 source set_env.sh
-cd intel/cpu/xeon
+cd cpu/xeon
 ```

 The set_env.sh script will prompt for required and optional environment variables used to configure the Translation service. If a value is not entered, the script will use a default value for the same. It will also generate a env file defining the desired configuration. Consult the section on [Translation Service configuration](#translation-service-configuration) for information on how service specific configuration parameters affect deployments.
--- a/Translation/docker_compose/intel/hpu/gaudi/README.md
+++ b/Translation/docker_compose/intel/hpu/gaudi/README.md
@@ -42,9 +42,9 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 To set up environment variables for deploying Translation service, source the _set_env.sh_ script in this directory:

 ```
-cd ../../../
+cd ../../
 source set_env.sh
-cd intel/hpu/gaudi/
+cd hpu/gaudi/
 ```

 The set_env.sh script will prompt for required and optional environment variables used to configure the Translation service. If a value is not entered, the script will use a default value for the same. It will also generate a env file defining the desired configuration. Consult the section on [Translation Service configuration](#translation-service-configuration) for information on how service specific configuration parameters affect deployments.
--- a/Translation/docker_compose/intel/set_env.sh
+++ b/Translation/docker_compose/intel/set_env.sh
@@ -2,7 +2,7 @@

 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-pushd "../../" > /dev/null
+pushd "../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null

--- a/Translation/tests/test_compose_on_gaudi.sh
+++ b/Translation/tests/test_compose_on_gaudi.sh
@@ -40,10 +40,10 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose
+    cd $WORKPATH/docker_compose/intel
    export host_ip=${ip_address}
    source set_env.sh
-    cd intel/hpu/gaudi
+    cd hpu/gaudi

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/Translation/tests/test_compose_on_xeon.sh
+++ b/Translation/tests/test_compose_on_xeon.sh
@@ -40,10 +40,10 @@ function build_docker_images() {
 }

 function start_services() {
-    cd $WORKPATH/docker_compose
+    cd $WORKPATH/docker_compose/intel
    export host_ip=${ip_address}
    source set_env.sh
-    cd intel/cpu/xeon
+    cd cpu/xeon

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

--- a/VisualQnA/Dockerfile
+++ b/VisualQnA/Dockerfile
@@ -1,8 +1,9 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0

+ARG IMAGE_REPO=opea
 ARG BASE_TAG=latest
-FROM opea/comps-base:$BASE_TAG
+FROM $IMAGE_REPO/comps-base:$BASE_TAG

 COPY ./visualqna.py $HOME/visualqna.py

--- a/VisualQnA/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/VisualQnA/docker_compose/amd/gpu/rocm/set_env.sh
@@ -6,7 +6,7 @@
 export HOST_IP=${host_ip}
 export EXTERNAL_HOST_IP=${host_ip}
 export VISUALQNA_TGI_SERVICE_PORT="8399"
-export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${Your_HUGGINGFACEHUB_API_TOKEN}
+export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export VISUALQNA_CARD_ID="card1"
 export VISUALQNA_RENDER_ID="renderD136"
 export LVM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
@@ -16,8 +16,8 @@ export MEGA_SERVICE_HOST_IP=${HOST_IP}
 export LVM_SERVICE_HOST_IP=${HOST_IP}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/visualqna"
 export FRONTEND_SERVICE_IP=${HOST_IP}
-export FRONTEND_SERVICE_PORT=18001
+export FRONTEND_SERVICE_PORT=5173
 export BACKEND_SERVICE_NAME=visualqna
 export BACKEND_SERVICE_IP=${HOST_IP}
-export BACKEND_SERVICE_PORT=18002
+export BACKEND_SERVICE_PORT=8888
 export NGINX_PORT=18003
--- a/VisualQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh
+++ b/VisualQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh
@@ -6,7 +6,7 @@
 export HOST_IP=${host_ip}
 export EXTERNAL_HOST_IP=${host_ip}
 export VISUALQNA_VLLM_SERVICE_PORT="8081"
-export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${Your_HUGGINGFACEHUB_API_TOKEN}
+export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export VISUALQNA_CARD_ID="card1"
 export VISUALQNA_RENDER_ID="renderD136"
 export VISUALQNA_LVM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
@@ -16,8 +16,8 @@ export MEGA_SERVICE_HOST_IP=${HOST_IP}
 export LVM_SERVICE_HOST_IP=${HOST_IP}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:${BACKEND_SERVICE_PORT}/v1/visualqna"
 export FRONTEND_SERVICE_IP=${HOST_IP}
-export FRONTEND_SERVICE_PORT=18001
+export FRONTEND_SERVICE_PORT=5173
 export BACKEND_SERVICE_NAME=visualqna
 export BACKEND_SERVICE_IP=${HOST_IP}
-export BACKEND_SERVICE_PORT=18002
+export BACKEND_SERVICE_PORT=8888
 export NGINX_PORT=18003
--- a/VisualQnA/docker_image_build/build.yaml
+++ b/VisualQnA/docker_image_build/build.yaml
@@ -5,6 +5,8 @@ services:
  visualqna:
    build:
      args:
+        IMAGE_REPO: ${REGISTRY:-opea}
+        BASE_TAG: ${TAG:-latest}
        http_proxy: ${http_proxy}
        https_proxy: ${https_proxy}
        no_proxy: ${no_proxy}
@@ -33,4 +35,17 @@ services:
    build:
      context: GenAIComps
      dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
+    extends: visualqna
    image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
+  vllm:
+    build:
+      context: vllm
+      dockerfile: docker/Dockerfile.cpu
+    extends: visualqna
+    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
+  vllm-gaudi:
+    build:
+      context: vllm-fork
+      dockerfile: Dockerfile.hpu
+    extends: visualqna
+    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
--- a/VisualQnA/tests/README.md
+++ b/VisualQnA/tests/README.md
@@ -0,0 +1,45 @@
+# VisualQnA E2E test scripts
+
+## Set the required environment variable
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+## Run test
+
+On Intel Xeon with Vllm:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Gaudi with Vllm:
+
+```bash
+bash test_compose_on_gaudi.sh
+```
+
+On Intel Xeon with TGI:
+
+```bash
+bash test_compose_tgi_on_xeon.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_tgi_on_gaudi.sh
+```
+
+On AMD ROCm with TGI:
+
+```bash
+bash test_compose_on_rocm.sh
+```
+
+On AMD ROCm with vLLM:
+
+```bash
+bash test_compose_vllm_on_rocm.sh
+```
--- a/VisualQnA/tests/test_compose_on_gaudi.sh
+++ b/VisualQnA/tests/test_compose_on_gaudi.sh
@@ -18,16 +18,20 @@ LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')

 function build_docker_images() {
+    opea_branch=${opea_branch:-"main"}
    cd $WORKPATH/docker_image_build
-    git clone --depth 1 --branch main https://github.com/opea-project/GenAIComps.git
-    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
+    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

-    git clone https://github.com/HabanaAI/vllm-fork.git
-    cd ./vllm-fork/
-    docker build -f Dockerfile.hpu -t opea/vllm-gaudi:${TAG} --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
-    cd ..
-    rm -rf vllm-fork
+    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
+    VLLM_FORK_VER=v0.7.2+Gaudi-1.21.0
+    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../

+    service_list="visualqna visualqna-ui lvm nginx vllm-gaudi"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
    docker images && sleep 1s
 }

@@ -186,17 +190,31 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    #validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/VisualQnA/tests/test_compose_on_rocm.sh
+++ b/VisualQnA/tests/test_compose_on_rocm.sh
@@ -15,47 +15,24 @@ ip_address=$(hostname -I | awk '{print $1}')
 export MODEL_CACHE=${model_cache:-"/var/lib/GenAI/data"}
 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}
-export HOST_IP=${ip_address}
-export VISUALQNA_TGI_SERVICE_PORT="8399"
-export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export VISUALQNA_CARD_ID="card1"
-export VISUALQNA_RENDER_ID="renderD136"
-export LVM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
+export host_ip=${ip_address}
 export MODEL="llava-hf/llava-v1.6-mistral-7b-hf"
-export LVM_ENDPOINT="http://${HOST_IP}:8399"
-export LVM_SERVICE_PORT=9399
-export MEGA_SERVICE_HOST_IP=${HOST_IP}
-export LVM_SERVICE_HOST_IP=${HOST_IP}
-export BACKEND_SERVICE_ENDPOINT="http://${HOST_IP}:${BACKEND_SERVICE_PORT}/v1/visualqna"
-export FRONTEND_SERVICE_IP=${HOST_IP}
-export FRONTEND_SERVICE_PORT=5173
-export BACKEND_SERVICE_NAME=visualqna
-export BACKEND_SERVICE_IP=${HOST_IP}
-export BACKEND_SERVICE_PORT=8888
-export NGINX_PORT=18003
 export PATH="~/miniconda3/bin:$PATH"
-export MODEL_CACHE=${model_cache:-"/var/opea/multimodalqna-service/data"}
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env.sh

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi
-
    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
+    service_list="visualqna visualqna-ui lvm nginx"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull ghcr.io/huggingface/text-generation-inference:2.4.1-rocm
    docker images && sleep 1s
 }

@@ -209,17 +186,31 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    #validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/VisualQnA/tests/test_compose_on_xeon.sh
+++ b/VisualQnA/tests/test_compose_on_xeon.sh
@@ -17,22 +17,28 @@ LOG_PATH="$WORKPATH/tests"
 ip_address=$(hostname -I | awk '{print $1}')

 function build_docker_images() {
+    opea_branch=${opea_branch:-"main"}
    cd $WORKPATH/docker_image_build
-    git clone --depth 1 --branch main https://github.com/opea-project/GenAIComps.git
-    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
+    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s
+    git clone https://github.com/vllm-project/vllm.git && cd vllm
+    VLLM_VER="v0.8.3"
+    echo "Check out vLLM tag ${VLLM_VER}"
+    git checkout ${VLLM_VER} &> /dev/null
+    cd ../

-    docker pull opea/vllm:latest
-    docker tag opea/vllm:latest opea/vllm:${TAG}
+    service_list="visualqna visualqna-ui lvm nginx vllm"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log
    docker images && sleep 1s
 }

 function start_services() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon/
-
    source ./set_env.sh
-
    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
-
    # Start Docker Containers
    docker compose up -d > ${LOG_PATH}/start_services_with_compose.log

@@ -179,17 +185,31 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    #validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/VisualQnA/tests/test_compose_tgi_on_gaudi.sh
+++ b/VisualQnA/tests/test_compose_tgi_on_gaudi.sh
@@ -17,44 +17,28 @@ ip_address=$(hostname -I | awk '{print $1}')

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi
-
    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
+    service_list="visualqna visualqna-ui lvm nginx"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull ghcr.io/huggingface/tgi-gaudi:2.0.6
    docker images && sleep 1s
 }

 function start_services() {
    cd $WORKPATH/docker_compose/intel/hpu/gaudi

-    export LVM_MODEL_ID="llava-hf/llava-v1.6-mistral-7b-hf"
-    export LVM_ENDPOINT="http://${ip_address}:8399"
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LVM_SERVICE_PORT=9399
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export LVM_SERVICE_HOST_IP=${ip_address}
-    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/visualqna"
-    export FRONTEND_SERVICE_IP=${ip_address}
-    export FRONTEND_SERVICE_PORT=5173
-    export BACKEND_SERVICE_NAME=visualqna
-    export BACKEND_SERVICE_IP=${ip_address}
-    export BACKEND_SERVICE_PORT=8888
    export NGINX_PORT=80
    export host_ip=${ip_address}
+    source ./set_env.sh
+    export LVM_MODEL_ID="llava-hf/llava-v1.6-mistral-7b-hf"

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

@@ -200,22 +184,36 @@ function validate_frontend() {

 function stop_docker() {
    cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    docker compose stop && docker compose rm -f
+    docker compose -f compose_tgi.yaml down
 }

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    # validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/VisualQnA/tests/test_compose_tgi_on_xeon.sh
+++ b/VisualQnA/tests/test_compose_tgi_on_xeon.sh
@@ -17,44 +17,27 @@ ip_address=$(hostname -I | awk '{print $1}')

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi
-
    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
+    service_list="visualqna visualqna-ui lvm nginx"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

-    docker pull ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
    docker images && sleep 1s
 }

 function start_services() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon/

-    export LVM_MODEL_ID="llava-hf/llava-v1.6-mistral-7b-hf"
-    export LVM_ENDPOINT="http://${ip_address}:8399"
    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LVM_SERVICE_PORT=9399
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export LVM_SERVICE_HOST_IP=${ip_address}
-    export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/visualqna"
-    export FRONTEND_SERVICE_IP=${ip_address}
-    export FRONTEND_SERVICE_PORT=5173
-    export BACKEND_SERVICE_NAME=visualqna
-    export BACKEND_SERVICE_IP=${ip_address}
-    export BACKEND_SERVICE_PORT=8888
    export NGINX_PORT=80
    export host_ip=${ip_address}
+    source ./set_env.sh

    sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

@@ -200,22 +183,36 @@ function validate_frontend() {

 function stop_docker() {
    cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    docker compose stop && docker compose rm -f
+    docker compose -f compose_tgi.yaml down
 }

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    # validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }

--- a/VisualQnA/tests/test_compose_vllm_on_rocm.sh
+++ b/VisualQnA/tests/test_compose_vllm_on_rocm.sh
@@ -14,45 +14,24 @@ ip_address=$(hostname -I | awk '{print $1}')

 export REGISTRY=${IMAGE_REPO}
 export TAG=${IMAGE_TAG}
-export HOST_IP=${ip_address}
-export VISUALQNA_VLLM_SERVICE_PORT="8081"
-export VISUALQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export VISUALQNA_CARD_ID="card1"
-export VISUALQNA_RENDER_ID="renderD136"
-export VISUALQNA_LVM_MODEL_ID="Xkev/Llama-3.2V-11B-cot"
+export host_ip=${ip_address}
 export MODEL="llava-hf/llava-v1.6-mistral-7b-hf"
-export LVM_ENDPOINT="http://${HOST_IP}:${VISUALQNA_VLLM_SERVICE_PORT}"
-export LVM_SERVICE_PORT=9399
-export MEGA_SERVICE_HOST_IP=${HOST_IP}
-export LVM_SERVICE_HOST_IP=${HOST_IP}
-export BACKEND_SERVICE_ENDPOINT="http://${HOST_IP}:${BACKEND_SERVICE_PORT}/v1/visualqna"
-export FRONTEND_SERVICE_IP=${HOST_IP}
-export FRONTEND_SERVICE_PORT=5173
-export BACKEND_SERVICE_NAME=visualqna
-export BACKEND_SERVICE_IP=${HOST_IP}
-export BACKEND_SERVICE_PORT=8888
-export NGINX_PORT=18003
 export PATH="~/miniconda3/bin:$PATH"
 export MODEL_CACHE=${model_cache:-"/var/opea/multimodalqna-service/data"}
+source $WORKPATH/docker_compose/amd/gpu/rocm/set_env_vllm.sh

 function build_docker_images() {
    opea_branch=${opea_branch:-"main"}
-    # If the opea_branch isn't main, replace the git clone branch in Dockerfile.
-    if [[ "${opea_branch}" != "main" ]]; then
-        cd $WORKPATH
-        OLD_STRING="RUN git clone --depth 1 https://github.com/opea-project/GenAIComps.git"
-        NEW_STRING="RUN git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git"
-        find . -type f -name "Dockerfile*" | while read -r file; do
-            echo "Processing file: $file"
-            sed -i "s|$OLD_STRING|$NEW_STRING|g" "$file"
-        done
-    fi
-
    cd $WORKPATH/docker_image_build
    git clone --depth 1 --branch ${opea_branch} https://github.com/opea-project/GenAIComps.git
+    pushd GenAIComps
+    echo "GenAIComps test commit is $(git rev-parse HEAD)"
+    docker build --no-cache -t ${REGISTRY}/comps-base:${TAG} --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+    popd && sleep 1s

    echo "Build all the images with --no-cache, check docker_image_build.log for details..."
-    docker compose -f build.yaml build --no-cache > ${LOG_PATH}/docker_image_build.log
+    service_list="visualqna visualqna-ui lvm nginx vllm-rocm"
+    docker compose -f build.yaml build ${service_list} --no-cache > ${LOG_PATH}/docker_image_build.log

    docker images && sleep 1s
 }
@@ -207,17 +186,31 @@ function stop_docker() {

 function main() {

+    echo "::group::stop_docker"
    stop_docker
+    echo "::endgroup::"

+    echo "::group::build_docker_images"
    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
+    echo "::endgroup::"
+
+    echo "::group::start_services"
    start_services
+    echo "::endgroup::"

+    echo "::group::validate_microservices"
    validate_microservices
-    validate_megaservice
-    #validate_frontend
+    echo "::endgroup::"

+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
    stop_docker
-    echo y | docker system prune
+    echo "::endgroup::"
+
+    docker system prune -f

 }
Author	SHA1	Message	Date
CICD-at-OPEA	c712c01829	Update vLLM-fork version to v0.7.2+Gaudi-1.21.0 Signed-off-by: CICD-at-OPEA <CICD@opea.dev>	2025-05-20 22:41:44 +00:00
chen, suyue	66ecaf2e6f	Merge branch 'main' into update_vLLM-fork	2025-05-20 10:54:35 +08:00
ZePan110	8a9f3f4351	Organize set_env.sh paths and update README.md (#1920 ) Signed-off-by: ZePan110 <ze.pan@intel.com> Co-authored-by: chen, suyue <suyue.chen@intel.com> Co-authored-by: Ying Hu <ying.hu@intel.com>	2025-05-20 10:05:00 +08:00
chen, suyue	09d93ecce6	[CICD enhance] CodeGen run CI with latest base image, group logs in GHA outputs. (#1928 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-05-19 09:31:56 +08:00
ZePan110	ed918bcef1	Integrate EdgeCraftRAG set_env to ut scripts and add README.md for UT scripts. (#1963 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-05-16 15:19:36 +08:00
ZePan110	1c0b1731c5	Integrate VisualQnA set_env to ut scripts. (#1947 ) Signed-off-by: ZePan110 <ze.pan@intel.com> Co-authored-by: chen, suyue <suyue.chen@intel.com>	2025-05-16 15:19:07 +08:00
ZePan110	22174e68a5	Integrate AvatarChatbot set_env to ut scripts. (#1961 ) Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-05-16 15:18:06 +08:00
ZePan110	c8abbc4958	Integrate ProductivitySuite set_env to ut scripts and add README.md for UT scripts. (#1966 ) Signed-off-by: ZePan110 <ze.pan@intel.com> Co-authored-by: Ying Hu <ying.hu@intel.com>	2025-05-16 15:16:38 +08:00
chen, suyue	7ee6f3657c	[CICD enhance] DocIndexRetriever run CI with latest base image, group logs in GHA outputs. (#1932 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-05-16 15:16:02 +08:00
ZePan110	11b04b38db	Integrate SearchQnA set_env to ut scripts. (#1950 ) Integrate SearchQnA set_env to ut scripts. Add README.md for UT scripts. Signed-off-by: ZePan110 <ze.pan@intel.com>	2025-05-16 15:09:07 +08:00
chen, suyue	7f55b5a100	Specify image build list for VisualQnA (#1967 ) Signed-off-by: chensuyue <suyue.chen@intel.com>	2025-05-16 14:44:17 +08:00
xiguiw	46fab4a736	Merge branch 'main' into update_vLLM-fork	2025-05-16 09:34:11 +08:00
CICD-at-OPEA	8ba40a5bff	Update vLLM-fork version to v0.7.2+Gaudi-1.21.0 Signed-off-by: CICD-at-OPEA <CICD@opea.dev>	2025-05-08 08:37:52 +00:00