update secrets token name

Signed-off-by: ZePan110 <ze.pan@intel.com>

.github/CODEOWNERS

@@ -1,16 +1,18 @@
-* liang1.lv@intel.com feng.tian@intel.com suyue.chen@intel.com
+# Code owners will review PRs within their respective folders.
+
+* liang1.lv@intel.com feng.tian@intel.com suyue.chen@intel.com kaokao.lv@intel.com minmin.hou@intel.com rita.brugarolas.brufau@intel.com
 /.github/ suyue.chen@intel.com ze.pan@intel.com
-/AgentQnA/ kaokao.lv@intel.com minmin.hou@intel.com
+/AgentQnA/ abolfazl.shahbazi@intel.com kaokao.lv@intel.com minmin.hou@intel.com
 /AudioQnA/ sihan.chen@intel.com wenjiao.yue@intel.com
 /AvatarChatbot/ chun.tao@intel.com kaokao.lv@intel.com
 /ChatQnA/ liang1.lv@intel.com letong.han@intel.com
 /CodeGen/ liang1.lv@intel.com
 /CodeTrans/ sihan.chen@intel.com
 /DBQnA/ supriya.krishnamurthi@intel.com liang1.lv@intel.com
-/DocIndexRetriever/ kaokao.lv@intel.com chendi.xue@intel.com
+/DocIndexRetriever/ abolfazl.shahbazi@intel.com kaokao.lv@intel.com chendi.xue@intel.com
 /DocSum/ letong.han@intel.com
 /EdgeCraftRAG/ yongbo.zhu@intel.com mingyuan.qi@intel.com
-/FaqGen/ yogesh.pandey@intel.com
+/FinanceAgent/ abolfazl.shahbazi@intel.com kaokao.lv@intel.com minmin.hou@intel.com rita.brugarolas.brufau@intel.com
 /GraphRAG/ rita.brugarolas.brufau@intel.com abolfazl.shahbazi@intel.com
 /InstructionTuning/ xinyu.ye@intel.com kaokao.lv@intel.com
 /MultimodalQnA/ melanie.h.buehler@intel.com tiep.le@intel.com
@@ -20,4 +22,5 @@
 /Text2Image/ wenjiao.yue@intel.com xinyu.ye@intel.com
 /Translation/ liang1.lv@intel.com sihan.chen@intel.com
 /VideoQnA/ huiling.bao@intel.com
-/VisualQnA/ liang1.lv@intel.com sihan.chen@intel.com
+/VisualQnA/ liang1.lv@intel.com sihan.chen@intel.com
+/WorkflowExecAgent/ joshua.jian.ern.liew@intel.com kaokao.lv@intel.com

.github/env/_build_image.sh

@@ -0,0 +1,5 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+export VLLM_VER=v0.8.3
+export VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0

.github/workflows/_build_image.yml

@@ -75,17 +75,12 @@ jobs:
         run: |
           cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
           docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
+          source ${{ github.workspace }}/.github/env/_build_image.sh
           if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
-              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 ../
+              git clone -b ${VLLM_VER} --single-branch https://github.com/vllm-project/vllm.git
           fi
           if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
-              git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-              VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
-              echo "Check out vLLM tag ${VLLM_VER}"
-              git checkout ${VLLM_VER} &> /dev/null && cd ../
+              git clone -b ${VLLM_FORK_VER} --single-branch https://github.com/HabanaAI/vllm-fork.git
           fi
           git clone --depth 1 --branch ${{ inputs.opea_branch }} https://github.com/opea-project/GenAIComps.git
           cd GenAIComps && git rev-parse HEAD && cd ../

.github/workflows/_gmc-e2e.yml

@@ -55,7 +55,7 @@ jobs:
       - name: Run tests
         id: run-test
         env:
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HF_TOKEN }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
         run: |

.github/workflows/_helm-e2e.yml

@@ -137,7 +137,7 @@ jobs:
         env:
           example: ${{ inputs.example }}
         run: |
-          if [[ ! "$example" =~ ^[a-zA-Z]{1,20}$ ]] || [[ "$example" =~ \.\. ]] || [[ "$example" == -* || "$example" == *- ]]; then
+          if [[ ! "$example" =~ ^[a-zA-Z0-9]{1,20}$ ]] || [[ "$example" =~ \.\. ]] || [[ "$example" == -* || "$example" == *- ]]; then
             echo "Error: Invalid input - only lowercase alphanumeric and internal hyphens allowed"
             exit 1
           fi
@@ -165,8 +165,8 @@ jobs:
         env:
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          HFTOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HF_TOKEN }}
+          HFTOKEN: ${{ secrets.HF_TOKEN }}
           value_file: ${{ matrix.value_file }}
         run: |
           set -xe

.github/workflows/_run-docker-compose.yml

@@ -160,8 +160,8 @@ jobs:
       - name: Run test
         shell: bash
         env:
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          HF_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           PINECONE_KEY: ${{ secrets.PINECONE_KEY }}
@@ -204,6 +204,10 @@ jobs:
           if [[ ! -z "$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() }}

.github/workflows/daily-update-vllm-version.yml

@@ -0,0 +1,94 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Daily update vLLM & vLLM-fork version
+
+on:
+  schedule:
+    - cron: "30 22 * * *"
+  workflow_dispatch:
+
+env:
+  BRANCH_NAME: "update"
+  USER_NAME: "CICD-at-OPEA"
+  USER_EMAIL: "CICD@opea.dev"
+
+jobs:
+  freeze-tag:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - repo: vLLM
+            repo_name: vllm-project/vllm
+            ver_name: VLLM_VER
+          - repo: vLLM-fork
+            repo_name: HabanaAI/vllm-fork
+            ver_name: VLLM_FORK_VER
+      fail-fast: false
+    permissions:
+      contents: write
+      pull-requests: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          ref: ${{ github.ref }}
+
+      - name: Set up Git
+        run: |
+          git config --global user.name ${{ env.USER_NAME }}
+          git config --global user.email ${{ env.USER_EMAIL }}
+          git remote set-url origin https://${{ env.USER_NAME }}:"${{ secrets.ACTION_TOKEN }}"@github.com/${{ github.repository }}.git
+          git fetch
+
+          if git ls-remote https://github.com/${{ github.repository }}.git "refs/heads/${{ env.BRANCH_NAME }}_${{ matrix.repo }}" | grep -q "refs/heads/${{ env.BRANCH_NAME }}_${{ matrix.repo }}"; then
+            echo "branch ${{ env.BRANCH_NAME }}_${{ matrix.repo }} exists"
+            git checkout ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
+          else
+            echo "branch ${{ env.BRANCH_NAME }}_${{ matrix.repo }} not exists"
+            git checkout -b ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
+            git push origin ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
+            echo "branch ${{ env.BRANCH_NAME }}_${{ matrix.repo }} created successfully"
+          fi
+
+      - name: Run script
+        run: |
+          latest_vllm_ver=$(curl -s "https://api.github.com/repos/${{ matrix.repo_name }}/tags" | jq '.[0].name' -)
+          latest_vllm_ver=$(echo "$latest_vllm_ver" | sed 's/"//g')
+          echo "latest_vllm_ver=${latest_vllm_ver}" >> "$GITHUB_ENV"
+          find . -type f -name "*.sh" -exec sed -i "s/${{ matrix.ver_name }}=.*/${{ matrix.ver_name }}=${latest_vllm_ver}/" {} \;
+
+      - name: Commit changes
+        run: |
+          git add .
+          if git diff-index --quiet HEAD --; then
+            echo "No changes detected, skipping commit."
+            exit 1
+          else
+            git commit -s -m "Update ${{ matrix.repo }} version to ${latest_vllm_ver}"
+            git push --set-upstream origin ${{ env.BRANCH_NAME }}_${{ matrix.repo }}
+          fi
+
+      - name: Create Pull Request
+        env:
+          GH_TOKEN: ${{ secrets.ACTION_TOKEN }}
+        run: |
+          pr_count=$(curl -H "Authorization: token ${{ secrets.ACTION_TOKEN }}" -s "https://api.github.com/repos/${{ github.repository }}/pulls?state=all&head=${{ env.USER_NAME }}:${{ env.BRANCH_NAME }}_${{ matrix.repo }}" | jq '. | length')
+          if [ $pr_count -gt 0 ]; then
+            echo "Pull Request exists"
+            pr_number=$(curl -H "Authorization: token ${{ secrets.ACTION_TOKEN }}" -s "https://api.github.com/repos/${{ github.repository }}/pulls?state=all&head=${{ env.USER_NAME }}:${{ env.BRANCH_NAME }}_${{ matrix.repo }}" | jq '.[0].number')
+            gh pr edit ${pr_number} \
+              --title "Update ${{ matrix.repo }} version to ${latest_vllm_ver}" \
+              --body "Update ${{ matrix.repo }} version to ${latest_vllm_ver}"
+            echo "Pull Request updated successfully"
+          else
+            echo "Pull Request does not exists..."
+            gh pr create \
+              -B main \
+              -H ${{ env.BRANCH_NAME }}_${{ matrix.repo }} \
+              --title "Update ${{ matrix.repo }} version to ${latest_vllm_ver}" \
+              --body "Update ${{ matrix.repo }} version to ${latest_vllm_ver}"
+            echo "Pull Request created successfully"
+          fi

.github/workflows/daily_check_issue_and_pr.yml

@@ -26,3 +26,4 @@ jobs:
           close-pr-message: "This PR was closed because it has been stalled for 7 days with no activity."
           repo-token: ${{ secrets.ACTION_TOKEN }}
           start-date: "2025-03-01T00:00:00Z"
+          exempt-issue-labels: "Backlog"

.github/workflows/pr-link-path-scan.yml

@@ -23,6 +23,7 @@ jobs:
       - name: Check the Validity of Hyperlinks
         run: |
           cd ${{github.workspace}}
+          delay=15
           fail="FALSE"
           merged_commit=$(git log -1 --format='%H')
           changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
@@ -35,15 +36,20 @@ jobs:
                   # echo $url_line
                   url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
                   path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
-                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
-                  if [ "$response" -ne 200 ]; then
-                    echo "**********Validation failed, try again**********"
-                    response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
-                    if [ "$response_retry" -eq 200 ]; then
-                      echo "*****Retry successfully*****"
-                    else
-                      echo "Invalid link from ${{github.workspace}}/$path: $url"
-                      fail="TRUE"
+                  if [[ "$url" == "https://platform.openai.com/api-keys"* ]]; then
+                    echo "Link "$url" from ${{github.workspace}}/$path needs to be verified by a real person."
+                  else
+                    sleep $delay
+                    response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
+                    if [ "$response" -ne 200 ]; then
+                      echo "**********Validation failed ($response), try again**********"
+                      response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
+                      if [ "$response_retry" -eq 200 ]; then
+                        echo "*****Retry successfully*****"
+                      else
+                        echo "Invalid link ($response_retry) from ${{github.workspace}}/$path: $url"
+                        fail="TRUE"
+                      fi
                     fi
                   fi
                 done
@@ -74,6 +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 }}"
@@ -105,14 +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

AgentQnA/README.md

@@ -99,7 +99,7 @@ flowchart LR
 
 #### First, clone the `GenAIExamples` repo.
 
-```
+```bash
 export WORKDIR=<your-work-directory>
 cd $WORKDIR
 git clone https://github.com/opea-project/GenAIExamples.git
@@ -109,7 +109,7 @@ git clone https://github.com/opea-project/GenAIExamples.git
 
 ##### For proxy environments only
 
-```
+```bash
 export http_proxy="Your_HTTP_Proxy"
 export https_proxy="Your_HTTPs_Proxy"
 # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
@@ -118,14 +118,24 @@ export no_proxy="Your_No_Proxy"
 
 ##### For using open-source llms
 
-```
+Set up a [HuggingFace](https://huggingface.co/) account and generate a [user access token](https://huggingface.co/docs/transformers.js/en/guides/private#step-1-generating-a-user-access-token).
+
+Then set an environment variable with the token and another for a directory to download the models:
+
+```bash
 export HUGGINGFACEHUB_API_TOKEN=<your-HF-token>
-export HF_CACHE_DIR=<directory-where-llms-are-downloaded> #so that no need to redownload every time
+export HF_CACHE_DIR=<directory-where-llms-are-downloaded> #  to avoid redownloading models
 ```
 
-##### [Optional] OPANAI_API_KEY to use OpenAI models
+##### [Optional] OPENAI_API_KEY to use OpenAI models or Intel® AI for Enterprise Inference
 
-```
+To use OpenAI models, generate a key following these [instructions](https://platform.openai.com/api-keys).
+
+To use a remote server running Intel® AI for Enterprise Inference, contact the cloud service provider or owner of the on-prem machine for a key to access the desired model on the server.
+
+Then set the environment variable `OPENAI_API_KEY` with the key contents:
+
+```bash
 export OPENAI_API_KEY=<your-openai-key>
 ```
 
@@ -133,16 +143,18 @@ export OPENAI_API_KEY=<your-openai-key>
 
 ##### Gaudi
 
-```
+```bash
 source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh
 ```
 
 ##### Xeon
 
-```
+```bash
 source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon/set_env.sh
 ```
 
+For running
+
 ### 2. Launch the multi-agent system. </br>
 
 We make it convenient to launch the whole system with docker compose, which includes microservices for LLM, agents, UI, retrieval tool, vector database, dataprep, and telemetry. There are 3 docker compose files, which make it easy for users to pick and choose. Users can choose a different retrieval tool other than the `DocIndexRetriever` example provided in our GenAIExamples repo. Users can choose not to launch the telemetry containers.
@@ -184,14 +196,37 @@ docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/
 
 #### Launch on Xeon
 
-On Xeon, only OpenAI models are supported. The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
+On Xeon, OpenAI models and models deployed on a remote server are supported. Both methods require an API key.
 
 ```bash
 export OPENAI_API_KEY=<your-openai-key>
 cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
+```
+
+##### OpenAI Models
+
+The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
+
+```bash
 docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose_openai.yaml up -d
 ```
 
+##### Models on Remote Server
+
+When models are deployed on a remote server with Intel® AI for Enterprise Inference, a base URL and an API key are required to access them. To run the Agent microservice on Xeon while using models deployed on a remote server, add `compose_remote.yaml` to the `docker compose` command and set additional environment variables.
+
+###### Notes
+
+- `OPENAI_API_KEY` is already set in a previous step.
+- `model` is used to overwrite the value set for this environment variable in `set_env.sh`.
+- `LLM_ENDPOINT_URL` is the base URL given from the owner of the on-prem machine or cloud service provider. It will follow this format: "https://<DNS>". Here is an example: "https://api.inference.example.com".
+
+```bash
+export model=<name-of-model-card>
+export LLM_ENDPOINT_URL=<http-endpoint-of-remote-server>
+docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose_openai.yaml -f compose_remote.yaml up -d
+```
+
 ### 3. Ingest Data into the vector database
 
 The `run_ingest_data.sh` script will use an example jsonl file to ingest example documents into a vector database. Other ways to ingest data and other types of documents supported can be found in the OPEA dataprep microservice located in the opea-project/GenAIComps repo.
@@ -208,12 +243,18 @@ bash run_ingest_data.sh
 The UI microservice is launched in the previous step with the other microservices.
 To see the UI, open a web browser to `http://${ip_address}:5173` to access the UI. Note the `ip_address` here is the host IP of the UI microservice.
 
-1. `create Admin Account` with a random value
-2. add opea agent endpoint `http://$ip_address:9090/v1` which is a openai compatible api
+1. Click on the arrow above `Get started`. Create an admin account with a name, email, and password.
+2. Add an OpenAI-compatible API endpoint. In the upper right, click on the circle button with the user's initial, go to `Admin Settings`->`Connections`. Under `Manage OpenAI API Connections`, click on the `+` to add a connection. Fill in these fields:
+
+- **URL**: `http://${ip_address}:9090/v1`, do not forget the `v1`
+- **Key**: any value
+- **Model IDs**: any name i.e. `opea-agent`, then press `+` to add it
+
+Click "Save".
 
 ![opea-agent-setting](assets/img/opea-agent-setting.png)
 
-3. test opea agent with ui
+3. Test OPEA agent with UI. Return to `New Chat` and ensure the model (i.e. `opea-agent`) is selected near the upper left. Enter in any prompt to interact with the agent.
 
 ![opea-agent-test](assets/img/opea-agent-test.png)
 

AgentQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -13,8 +13,8 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       TGI_LLM_ENDPOINT: "http://${ip_address}:${TGI_SERVICE_PORT}"
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     shm_size: 32g
     devices:
       - /dev/kfd:/dev/kfd
@@ -42,7 +42,7 @@ services:
       with_memory: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: tgi
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -76,7 +76,7 @@ services:
       use_hints: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -104,7 +104,7 @@ services:
       with_memory: true
       recursion_limit: ${recursion_limit_supervisor}
       llm_engine: tgi
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}

AgentQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml

@@ -10,8 +10,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       WILM_USE_TRITON_FLASH_ATTENTION: 0
@@ -46,7 +46,7 @@ services:
       with_memory: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -80,7 +80,7 @@ services:
       use_hints: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -108,7 +108,7 @@ services:
       with_memory: true
       recursion_limit: ${recursion_limit_supervisor}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}

AgentQnA/docker_compose/amd/gpu/rocm/launch_agent_service_tgi_rocm.sh

@@ -19,7 +19,7 @@ export CRAG_SERVER_PORT="18114"
 
 export WORKPATH=$(dirname "$PWD")
 export WORKDIR=${WORKPATH}/../../../
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export HF_CACHE_DIR="./data"
 export MODEL_CACHE="./data"
@@ -39,7 +39,7 @@ export CRAG_SERVER=http://${ip_address}:${CRAG_SERVER_PORT}
 export WORKER_AGENT_URL="http://${ip_address}:${WORKER_RAG_AGENT_PORT}/v1/chat/completions"
 export SQL_AGENT_URL="http://${ip_address}:${WORKER_SQL_AGENT_PORT}/v1/chat/completions"
 export HF_CACHE_DIR=${HF_CACHE_DIR}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export no_proxy=${no_proxy}
 export http_proxy=${http_proxy}
 export https_proxy=${https_proxy}

AgentQnA/docker_compose/amd/gpu/rocm/launch_agent_service_vllm_rocm.sh

@@ -19,7 +19,7 @@ export CRAG_SERVER_PORT="18114"
 
 export WORKPATH=$(dirname "$PWD")
 export WORKDIR=${WORKPATH}/../../../
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export VLLM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export HF_CACHE_DIR="./data"
 export MODEL_CACHE="./data"
@@ -40,7 +40,7 @@ export CRAG_SERVER=http://${ip_address}:${CRAG_SERVER_PORT}
 export WORKER_AGENT_URL="http://${ip_address}:${WORKER_RAG_AGENT_PORT}/v1/chat/completions"
 export SQL_AGENT_URL="http://${ip_address}:${WORKER_SQL_AGENT_PORT}/v1/chat/completions"
 export HF_CACHE_DIR=${HF_CACHE_DIR}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export no_proxy=${no_proxy}
 export http_proxy=${http_proxy}
 export https_proxy=${https_proxy}

AgentQnA/docker_compose/amd/gpu/rocm/stop_agent_service_vllm_rocm.sh

@@ -20,8 +20,8 @@ export CRAG_SERVER_PORT="18114"
 
 export WORKPATH=$(dirname "$PWD")
 export WORKDIR=${WORKPATH}/../../../
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export VLLM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export HF_CACHE_DIR="./data"
 export MODEL_CACHE="./data"
@@ -42,7 +42,7 @@ export CRAG_SERVER=http://${ip_address}:${CRAG_SERVER_PORT}
 export WORKER_AGENT_URL="http://${ip_address}:${WORKER_RAG_AGENT_PORT}/v1/chat/completions"
 export SQL_AGENT_URL="http://${ip_address}:${WORKER_SQL_AGENT_PORT}/v1/chat/completions"
 export HF_CACHE_DIR=${HF_CACHE_DIR}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export no_proxy=${no_proxy}
 export http_proxy=${http_proxy}
 export https_proxy=${https_proxy}

AgentQnA/docker_compose/intel/cpu/xeon/compose_remote.yaml

@@ -0,0 +1,18 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  worker-rag-agent:
+    environment:
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      api_key: ${OPENAI_API_KEY}
+
+  worker-sql-agent:
+    environment:
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      api_key: ${OPENAI_API_KEY}
+
+  supervisor-react-agent:
+    environment:
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      api_key: ${OPENAI_API_KEY}

AgentQnA/docker_compose/intel/cpu/xeon/set_env.sh

@@ -33,7 +33,7 @@ fi
 # retriever
 export host_ip=$(hostname -I | awk '{print $1}')
 export HF_CACHE_DIR=${HF_CACHE_DIR}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export no_proxy=${no_proxy}
 export http_proxy=${http_proxy}
 export https_proxy=${https_proxy}

AgentQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -16,7 +16,7 @@ services:
       with_memory: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -50,7 +50,7 @@ services:
       use_hints: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -79,7 +79,7 @@ services:
       with_memory: true
       recursion_limit: ${recursion_limit_supervisor}
       llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
@@ -122,7 +122,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}

AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh

@@ -16,8 +16,8 @@ export ip_address=$(hostname -I | awk '{print $1}')
 # LLM related environment variables
 export HF_CACHE_DIR=${HF_CACHE_DIR}
 ls $HF_CACHE_DIR
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
 export LLM_MODEL_ID="meta-llama/Llama-3.3-70B-Instruct"
 export NUM_SHARDS=4
 export LLM_ENDPOINT_URL="http://${ip_address}:8086"

AgentQnA/docker_compose/intel/hpu/gaudi/tgi_gaudi.yaml

@@ -13,7 +13,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all

AgentQnA/retrieval_tool/launch_retrieval_tool.sh

@@ -3,7 +3,7 @@
 
 host_ip=$(hostname -I | awk '{print $1}')
 export HF_CACHE_DIR=${HF_CACHE_DIR}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export no_proxy=${no_proxy}
 export http_proxy=${http_proxy}
 export https_proxy=${https_proxy}

AgentQnA/tests/step1_build_images.sh

@@ -37,8 +37,8 @@ function build_agent_docker_image_gaudi_vllm() {
     get_genai_comps
 
     git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_VER} &> /dev/null && cd ../
+    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build agent image with --no-cache..."
     service_list="agent agent-ui vllm-gaudi"

AgentQnA/tests/step2_start_retrieval_tool_rocm_vllm.sh

@@ -20,7 +20,7 @@ function start_retrieval_tool() {
     cd $WORKPATH/../DocIndexRetriever/docker_compose/intel/cpu/xeon
     host_ip=$(hostname -I | awk '{print $1}')
     export HF_CACHE_DIR=${HF_CACHE_DIR}
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
     export no_proxy=${no_proxy}
     export http_proxy=${http_proxy}
     export https_proxy=${https_proxy}

AgentQnA/tests/step4_launch_and_validate_agent_gaudi.sh

@@ -11,8 +11,8 @@ export ip_address=$(hostname -I | awk '{print $1}')
 export host_ip=$ip_address
 echo "ip_address=${ip_address}"
 export TOOLSET_PATH=$WORKPATH/tools/
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
+HF_TOKEN=${HF_TOKEN}
 model="meta-llama/Llama-3.3-70B-Instruct" #"meta-llama/Meta-Llama-3.1-70B-Instruct"
 
 export HF_CACHE_DIR=${model_cache:-"/data2/huggingface"}

AgentQnA/tests/test_compose_on_gaudi.sh

@@ -7,7 +7,7 @@ WORKPATH=$(dirname "$PWD")
 export WORKDIR=$WORKPATH/../../
 echo "WORKDIR=${WORKDIR}"
 export ip_address=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
 export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui,vllm-gaudi-server,jaeger,grafana,prometheus,127.0.0.1,localhost,0.0.0.0,$ip_address"
 IMAGE_REPO=${IMAGE_REPO:-"opea"}

AgentQnA/tests/test_compose_on_rocm.sh

@@ -9,7 +9,7 @@ ls $WORKPATH
 export WORKDIR=$WORKPATH/../../
 echo "WORKDIR=${WORKDIR}"
 export ip_address=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export TOOLSET_PATH=$WORKPATH/tools/
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}

AgentQnA/tests/test_compose_vllm_on_rocm.sh

@@ -8,7 +8,7 @@ WORKPATH=$(dirname "$PWD")
 export WORKDIR=${WORKPATH}/../../
 echo "WORKDIR=${WORKDIR}"
 export ip_address=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export TOOLSET_PATH=$WORKPATH/tools/
 IMAGE_REPO=${IMAGE_REPO:-"opea"}
 IMAGE_TAG=${IMAGE_TAG:-"latest"}

AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -40,7 +40,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${LLM_MODEL_ID}

AudioQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml

@@ -35,8 +35,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       WILM_USE_TRITON_FLASH_ATTENTION: 0

AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh

@@ -6,8 +6,8 @@
 
 # export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
 
-export host_ip="192.165.1.21"
-export HUGGINGFACEHUB_API_TOKEN=${YOUR_HUGGINGFACEHUB_API_TOKEN}
+export host_ip=${ip_address}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 # <token>
 
 export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3

AudioQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh

@@ -6,9 +6,9 @@
 
 # export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
 
-export host_ip=""
-export external_host_ip=""
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export host_ip=${ip_address}
+export external_host_ip=${ip_address}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export HF_CACHE_DIR="./data"
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export VLLM_SERVICE_PORT="8081"

AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml

@@ -36,7 +36,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}

AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml

@@ -40,7 +40,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}

AudioQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml

@@ -36,7 +36,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1"]

AudioQnA/docker_compose/intel/cpu/xeon/set_env.sh

@@ -5,7 +5,7 @@
 
 # export host_ip=<your External Public IP>
 export host_ip=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 # <token>
 
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
@@ -14,7 +14,8 @@ export MEGA_SERVICE_HOST_IP=${host_ip}
 export WHISPER_SERVER_HOST_IP=${host_ip}
 export SPEECHT5_SERVER_HOST_IP=${host_ip}
 export LLM_SERVER_HOST_IP=${host_ip}
-
+export GPT_SOVITS_SERVER_HOST_IP=${host_ip}
+export GPT_SOVITS_SERVER_PORT=9880
 export WHISPER_SERVER_PORT=7066
 export SPEECHT5_SERVER_PORT=7055
 export LLM_SERVER_PORT=3006

AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -45,7 +45,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all

AudioQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml

@@ -45,7 +45,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all

AudioQnA/docker_compose/intel/hpu/gaudi/set_env.sh

@@ -5,7 +5,7 @@
 
 # export host_ip=<your External Public IP>
 export host_ip=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 # <token>
 
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"

AudioQnA/tests/README.md

@@ -0,0 +1,45 @@
+# AudioQnA 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_tgi_on_xeon.sh
+```
+
+On Intel Xeon with vLLM:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_tgi_on_gaudi.sh
+```
+
+On Intel Gaudi with vLLM:
+
+```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
+```

AudioQnA/tests/test_compose_multilang_on_xeon.sh

@@ -40,21 +40,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export WHISPER_SERVER_HOST_IP=${ip_address}
-    export GPT_SOVITS_SERVER_HOST_IP=${ip_address}
-    export LLM_SERVER_HOST_IP=${ip_address}
-
-    export WHISPER_SERVER_PORT=7066
-    export GPT_SOVITS_SERVER_PORT=9880
-    export LLM_SERVER_PORT=3006
-
-    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-
+    source set_env.sh
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AudioQnA/tests/test_compose_on_gaudi.sh

@@ -27,9 +27,9 @@ function build_docker_images() {
 
     git clone https://github.com/HabanaAI/vllm-fork.git
     cd vllm-fork/
-    VLLM_VER=v0.6.6.post1+Gaudi-1.20.0
-    echo "Check out vLLM tag ${VLLM_VER}"
-    git checkout ${VLLM_VER} &> /dev/null && cd ../
+    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    echo "Check out vLLM tag ${VLLM_FORK_VER}"
+    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="audioqna audioqna-ui whisper-gaudi speecht5-gaudi vllm-gaudi"
@@ -40,24 +40,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
-    export NUM_CARDS=1
-    export BLOCK_SIZE=128
-    export MAX_NUM_SEQS=256
-    export MAX_SEQ_LEN_TO_CAPTURE=2048
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export WHISPER_SERVER_HOST_IP=${ip_address}
-    export SPEECHT5_SERVER_HOST_IP=${ip_address}
-    export LLM_SERVER_HOST_IP=${ip_address}
-
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_PORT=3006
-
-    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
+    source set_env.sh
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AudioQnA/tests/test_compose_on_rocm.sh

@@ -35,20 +35,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export WHISPER_SERVER_HOST_IP=${ip_address}
-    export SPEECHT5_SERVER_HOST_IP=${ip_address}
-    export LLM_SERVER_HOST_IP=${ip_address}
-
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_PORT=3006
-
-    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
-
+    source set_env.sh
     # Start Docker Containers
     docker compose up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0

AudioQnA/tests/test_compose_on_xeon.sh

@@ -40,21 +40,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export WHISPER_SERVER_HOST_IP=${ip_address}
-    export SPEECHT5_SERVER_HOST_IP=${ip_address}
-    export LLM_SERVER_HOST_IP=${ip_address}
-
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_PORT=3006
-
-    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-
+    source set_env.sh
     # sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AudioQnA/tests/test_compose_tgi_on_gaudi.sh

@@ -34,21 +34,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export WHISPER_SERVER_HOST_IP=${ip_address}
-    export SPEECHT5_SERVER_HOST_IP=${ip_address}
-    export LLM_SERVER_HOST_IP=${ip_address}
-
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_PORT=3006
-
-    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-
+    source set_env.sh
     # Start Docker Containers
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0

AudioQnA/tests/test_compose_tgi_on_xeon.sh

@@ -34,21 +34,8 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/cpu/xeon/
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export LLM_MODEL_ID=meta-llama/Meta-Llama-3-8B-Instruct
-
-    export MEGA_SERVICE_HOST_IP=${ip_address}
-    export WHISPER_SERVER_HOST_IP=${ip_address}
-    export SPEECHT5_SERVER_HOST_IP=${ip_address}
-    export LLM_SERVER_HOST_IP=${ip_address}
-
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_PORT=3006
-
-    export BACKEND_SERVICE_ENDPOINT=http://${ip_address}:3008/v1/audioqna
     export host_ip=${ip_address}
-
+    source set_env.sh
     # Start Docker Containers
     docker compose -f compose_tgi.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
     n=0

AudioQnA/tests/test_compose_vllm_on_rocm.sh

@@ -33,27 +33,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm/
-
-    export host_ip=${ip_address}
-    export external_host_ip=${ip_address}
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-    export HF_CACHE_DIR="./data"
-    export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
-    export VLLM_SERVICE_PORT="8081"
-
-    export MEGA_SERVICE_HOST_IP=${host_ip}
-    export WHISPER_SERVER_HOST_IP=${host_ip}
-    export SPEECHT5_SERVER_HOST_IP=${host_ip}
-    export LLM_SERVER_HOST_IP=${host_ip}
-
-    export WHISPER_SERVER_PORT=7066
-    export SPEECHT5_SERVER_PORT=7055
-    export LLM_SERVER_PORT=${VLLM_SERVICE_PORT}
-    export BACKEND_SERVICE_PORT=3008
-    export FRONTEND_SERVICE_PORT=5173
-
-    export BACKEND_SERVICE_ENDPOINT=http://${external_host_ip}:${BACKEND_SERVICE_PORT}/v1/audioqna
-
+    source set_env_vllm.sh
     sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
 
     # Start Docker Containers

AvatarChatbot/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 ./avatarchatbot.py $HOME/avatarchatbot.py
 

AvatarChatbot/docker_compose/amd/gpu/rocm/README.md

@@ -68,7 +68,7 @@ Then run the command `docker images`, you will have following images ready:
 Before starting the services with `docker compose`, you have to recheck the following environment variables.
 
 ```bash
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export host_ip=$(hostname -I | awk '{print $1}')
 
 export TGI_SERVICE_PORT=3006

AvatarChatbot/docker_compose/amd/gpu/rocm/compose.yaml

@@ -52,8 +52,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     shm_size: 1g
     devices:
       - /dev/kfd:/dev/kfd

AvatarChatbot/docker_compose/amd/gpu/rocm/set_env.sh

@@ -3,7 +3,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export OPENAI_API_KEY=${OPENAI_API_KEY}
 export host_ip=$(hostname -I | awk '{print $1}')
 
@@ -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

AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml

@@ -37,7 +37,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://${host_ip}:3006/health || exit 1"]
       interval: 10s

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=${HF_TOKEN}
+export host_ip=$(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

AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -48,7 +48,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all

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=${HF_TOKEN}
+export host_ip=$(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

AvatarChatbot/docker_image_build/build.yaml

@@ -5,6 +5,8 @@ services:
   avatarchatbot:
     build:
       args:
+        IMAGE_REPO: ${REGISTRY:-opea}
+        BASE_TAG: ${TAG:-latest}
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}

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
+```

AvatarChatbot/tests/test_compose_on_gaudi.sh

@@ -24,19 +24,13 @@ 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="avatarchatbot whisper-gaudi speecht5-gaudi wav2lip-gaudi animation"
@@ -51,37 +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
@@ -128,19 +92,29 @@ function stop_docker() {
 
 
 function main() {
+    echo "::group::stop_docker"
     stop_docker
-    echo y | docker builder prune --all
-    echo y | docker image prune
+    echo "::endgroup::"
+    docker builder prune --all -f
+    docker image prune -f
 
+    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    validate_megaservice
-    # validate_frontend
+    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 builder prune --all
-    echo y | docker image prune
+    echo "::endgroup::"
+    docker builder prune --all -f
+    docker image prune -f
 
 }
 

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=${IMAGE_REPO}"
@@ -25,6 +25,10 @@ ip_address=$(hostname -I | awk '{print $1}')
 function build_docker_images() {
     cd $WORKPATH/docker_image_build
     git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
+    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="avatarchatbot whisper asr speecht5 tts wav2lip animation"
@@ -38,48 +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
@@ -138,11 +102,6 @@ function validate_megaservice() {
 }
 
 
-#function validate_frontend() {
-
-#}
-
-
 function stop_docker() {
     cd $WORKPATH/docker_compose/amd/gpu/rocm
     docker compose down && docker compose rm -f
@@ -151,19 +110,27 @@ function stop_docker() {
 
 function main() {
 
-    echo $OPENAI_API_KEY
-    echo $OPENAI_KEY
-
+    echo "::group::stop_docker"
     stop_docker
+    echo "::endgroup::"
+
+    echo "::group::build_docker_images"
     if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    sleep 30
-    validate_megaservice
-    # validate_frontend
-    stop_docker
+    echo "::endgroup::"
 
-    echo y | docker system prune
+    echo "::group::start_services"
+    start_services
+    echo "::endgroup::"
+
+    echo "::group::validate_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
+    stop_docker
+    echo "::endgroup::"
+
+    docker system prune -f
 
 }
 

AvatarChatbot/tests/test_compose_on_xeon.sh

@@ -24,19 +24,13 @@ 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="avatarchatbot whisper speecht5 wav2lip animation"
@@ -51,37 +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
@@ -127,16 +91,28 @@ function stop_docker() {
 
 
 function main() {
-    stop_docker
-    if [[ "$IMAGE_REPO" == "opea" ]]; then build_docker_images; fi
-    start_services
-    # validate_microservices
-    validate_megaservice
-    # validate_frontend
-    stop_docker
 
-    echo y | docker builder prune --all
-    echo y | docker image prune
+    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_megaservice"
+    validate_megaservice
+    echo "::endgroup::"
+
+    echo "::group::stop_docker"
+    stop_docker
+    echo "::endgroup::"
+
+    docker system prune -f
 
 }
 

ChatQnA/benchmark_chatqna.yaml

@@ -37,7 +37,7 @@ deploy:
 
     llm:
       engine: vllm  # or tgi
-      model_id: "meta-llama/Llama-3.1-8B-Instruct" # mandatory
+      model_id: "meta-llama/Meta-Llama-3-8B-Instruct" # mandatory
       replicaCount:
         with_teirerank: [7, 15, 31, 63]     # When teirerank.enabled is True
         without_teirerank: [8, 16, 32, 64]   # When teirerank.enabled is False

ChatQnA/docker_compose/amd/gpu/rocm/compose.yaml

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen.yaml

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

ChatQnA/docker_compose/amd/gpu/rocm/compose_faqgen_vllm.yaml

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

ChatQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml

@@ -16,7 +16,7 @@ services:
       - chatqna-redis-vector-db
       - chatqna-tei-embedding-service
     ports:
-      - "${CHATQNA_REDIS_DATAPREP_PORT:-5000}:5000"
+      - "${CHATQNA_REDIS_DATAPREP_PORT:-18103}:5000"
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}

ChatQnA/docker_compose/amd/gpu/rocm/set_env.sh

@@ -2,17 +2,17 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/amd/gpu/rocm/set_env_faqgen.sh

@@ -2,18 +2,18 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
 export CHATQNA_LLM_FAQGEN_PORT=18011
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/amd/gpu/rocm/set_env_faqgen_vllm.sh

@@ -2,18 +2,18 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
 export CHATQNA_LLM_FAQGEN_PORT=18011
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh

@@ -2,17 +2,17 @@
 
 # Copyright (C) 2025 Advanced Micro Devices, Inc.
 
-export HOST_IP=''
-export HOST_IP_EXTERNAL=''
+export HOST_IP=${ip_address}
+export HOST_IP_EXTERNAL=${ip_address}
 
 export CHATQNA_EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CHATQNA_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export CHATQNA_LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
 export CHATQNA_RERANK_MODEL_ID="BAAI/bge-reranker-base"
 
-export CHATQNA_BACKEND_SERVICE_PORT=18102
-export CHATQNA_FRONTEND_SERVICE_PORT=18101
-export CHATQNA_NGINX_PORT=18104
+export CHATQNA_BACKEND_SERVICE_PORT=8888
+export CHATQNA_FRONTEND_SERVICE_PORT=5173
+export CHATQNA_NGINX_PORT=80
 export CHATQNA_REDIS_DATAPREP_PORT=18103
 export CHATQNA_REDIS_RETRIEVER_PORT=7000
 export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8001

ChatQnA/docker_compose/install_docker.sh

@@ -1,35 +0,0 @@
-#!/bin/bash
-
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-# Update the package index
-sudo apt-get -y update
-
-# Install prerequisites
-sudo apt-get -y install ca-certificates curl
-
-# Create the directory for the Docker GPG key
-sudo install -m 0755 -d /etc/apt/keyrings
-
-# Add Docker's official GPG key
-sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
-
-# Set permissions for the GPG key
-sudo chmod a+r /etc/apt/keyrings/docker.asc
-
-# Add Docker repository to the sources list
-echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
-  $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
-
-# Update the package index with Docker packages
-sudo apt-get -y update
-
-# Install Docker packages
-sudo apt-get -y install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
-
-# add existing user
-sudo usermod -aG docker $USER
-
-# Optional: Verify that Docker is installed correctly
-sudo docker --version

ChatQnA/docker_compose/intel/cpu/aipc/README.md

@@ -183,7 +183,7 @@ export https_proxy=${your_http_proxy}
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export RERANK_MODEL_ID="BAAI/bge-reranker-base"
 export INDEX_NAME="rag-redis"
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export OLLAMA_HOST=${host_ip}
 export OLLAMA_MODEL="llama3.2"
 ```
@@ -194,7 +194,7 @@ export OLLAMA_MODEL="llama3.2"
 set EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
 set RERANK_MODEL_ID=BAAI/bge-reranker-base
 set INDEX_NAME=rag-redis
-set HUGGINGFACEHUB_API_TOKEN=%HUGGINGFACEHUB_API_TOKEN%
+set HUGGINGFACEHUB_API_TOKEN=%HF_TOKEN%
 set OLLAMA_HOST=host.docker.internal
 set OLLAMA_MODEL="llama3.2"
 ```

ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate

ChatQnA/docker_compose/intel/cpu/aipc/set_env.sh

@@ -9,7 +9,7 @@ popd > /dev/null
 
 export host_ip=$(hostname -I | awk '{print $1}')
 
-if [ -z "${HUGGINGFACEHUB_API_TOKEN}" ]; then
+if [ -z "${HF_TOKEN}" ]; then
     echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set HUGGINGFACEHUB_API_TOKEN."
 fi
 
@@ -17,7 +17,7 @@ if [ -z "${host_ip}" ]; then
     echo "Error: host_ip is not set. Please set host_ip first."
 fi
 
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export RERANK_MODEL_ID="BAAI/bge-reranker-base"
 export INDEX_NAME="rag-redis"

ChatQnA/docker_compose/intel/cpu/xeon/README.md

@@ -156,6 +156,7 @@ In the context of deploying a ChatQnA pipeline on an Intel® Xeon® platform, we
 | [compose_faqgen_tgi.yaml](./compose_faqgen_tgi.yaml)         | Enables FAQ generation using TGI as the LLM serving framework. For more details, refer to [README_faqgen.md](./README_faqgen.md).                                     |
 | [compose.telemetry.yaml](./compose.telemetry.yaml)           | Helper file for telemetry features for vllm. Can be used along with any compose files that serves vllm                                                                |
 | [compose_tgi.telemetry.yaml](./compose_tgi.telemetry.yaml)   | Helper file for telemetry features for tgi. Can be used along with any compose files that serves tgi                                                                  |
+| [compose_mariadb.yaml](./compose_mariadb.yaml)               | Uses MariaDB Server as the vector database. All other configurations remain the same as the default                                                                   |
 
 ## ChatQnA with Conversational UI (Optional)
 

ChatQnA/docker_compose/intel/cpu/xeon/README_mariadb.md

@@ -0,0 +1,259 @@
+# Deploying ChatQnA with MariaDB Vector on Intel® Xeon® Processors
+
+This document outlines the deployment process for a ChatQnA application utilizing the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline on Intel® Xeon® servers. The pipeline integrates **MariaDB Vector** as the vector database and includes microservices such as `embedding`, `retriever`, `rerank`, and `llm`.
+
+---
+
+## Table of Contents
+
+1. [Build Docker Images](#build-docker-images)
+2. [Validate Microservices](#validate-microservices)
+3. [Launch the UI](#launch-the-ui)
+4. [Launch the Conversational UI (Optional)](#launch-the-conversational-ui-optional)
+
+---
+
+## Build Docker Images
+
+First of all, you need to build Docker Images locally and install the python package of it.
+
+```bash
+git clone https://github.com/opea-project/GenAIComps.git
+cd GenAIComps
+```
+
+### 1. Build Retriever Image
+
+```bash
+docker build --no-cache -t opea/retriever:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/retrievers/src/Dockerfile .
+```
+
+### 2. Build Dataprep Image
+
+```bash
+docker build --no-cache -t opea/dataprep:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/dataprep/src/Dockerfile .
+cd ..
+```
+
+### 3. Build MegaService Docker Image
+
+To construct the Mega Service, we utilize the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice pipeline within the `chatqna.py` Python script. Build MegaService Docker image via below command:
+
+```bash
+git clone https://github.com/opea-project/GenAIExamples.git
+cd GenAIExamples/ChatQnA/
+docker build --no-cache -t opea/chatqna:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+cd ../..
+```
+
+### 4. Build UI Docker Image
+
+Build frontend Docker image via below command:
+
+```bash
+cd GenAIExamples/ChatQnA/ui
+docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
+cd ../../..
+```
+
+### 5. Build Conversational React UI Docker Image (Optional)
+
+Build frontend Docker image that enables Conversational experience with ChatQnA megaservice via below command:
+
+**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
+
+```bash
+cd GenAIExamples/ChatQnA/ui
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8912/v1/chatqna"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6043/v1/dataprep/ingest"
+docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy --build-arg BACKEND_SERVICE_ENDPOINT=$BACKEND_SERVICE_ENDPOINT --build-arg DATAPREP_SERVICE_ENDPOINT=$DATAPREP_SERVICE_ENDPOINT -f ./docker/Dockerfile.react .
+cd ../../..
+```
+
+### 6. Build Nginx Docker Image
+
+```bash
+cd GenAIComps
+docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/third_parties/nginx/src/Dockerfile .
+```
+
+Then run the command `docker images`, you will have the following 5 Docker Images:
+
+1. `opea/dataprep:latest`
+2. `opea/retriever:latest`
+3. `opea/chatqna:latest`
+4. `opea/chatqna-ui:latest`
+5. `opea/nginx:latest`
+
+## Start Microservices
+
+### Required Models
+
+By default, the embedding, reranking and LLM models are set to a default value as listed below:
+
+| Service   | Model                               |
+| --------- | ----------------------------------- |
+| Embedding | BAAI/bge-base-en-v1.5               |
+| Reranking | BAAI/bge-reranker-base              |
+| LLM       | meta-llama/Meta-Llama-3-8B-Instruct |
+
+Change the `xxx_MODEL_ID` below for your needs.
+
+### Setup Environment Variables
+
+Since the `compose.yaml` will consume some environment variables, you need to set them up in advance as below.
+
+**Export the value of the public IP address of your Xeon server to the `host_ip` environment variable**
+
+> Change the External_Public_IP below with the actual IPV4 value
+
+```bash
+export host_ip="External_Public_IP"
+```
+
+> Change to your actual Huggingface API Token value
+
+```bash
+export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+```
+
+**Append the value of the public IP address to the no_proxy list if you are in a proxy environment**
+
+```bash
+export no_proxy=${your_no_proxy},chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-mariadb-vector,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service
+```
+
+```bash
+export no_proxy=${your_no_proxy}
+export http_proxy=${your_http_proxy}
+export https_proxy=${your_http_proxy}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export MARIADB_DATABASE="vectordb"
+export MARIADB_USER="chatqna"
+export MARIADB_PASSWORD="password"
+```
+
+Note: Please replace with `host_ip` with you external IP address, do not use localhost.
+
+### Start all the services Docker Containers
+
+> Before running the docker compose command, you need to be in the folder that has the docker compose yaml file
+
+```bash
+cd GenAIExamples/ChatQnA/docker_compose/intel/cpu/xeon/
+docker compose -f compose_mariadb.yaml up -d
+```
+
+### Validate Microservices
+
+Follow the instructions to validate MicroServices.
+For details on how to verify the correctness of the response, refer to [how-to-validate_service](../../hpu/gaudi/how_to_validate_service.md).
+
+1. TEI Embedding Service
+
+   ```bash
+   curl ${host_ip}:6040/embed \
+       -X POST \
+       -d '{"inputs":"What is Deep Learning?"}' \
+       -H 'Content-Type: application/json'
+   ```
+
+2. Retriever Microservice
+
+   To consume the retriever microservice, you need to generate a mock embedding vector by Python script. The length of embedding vector
+   is determined by the embedding model.
+   Here we use the model `EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"`, which vector size is 768.
+
+   Check the vector dimension of your embedding model, set `your_embedding` dimension equals to it.
+
+   ```bash
+   export your_embedding=$(python3 -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)")
+   curl http://${host_ip}:6045/v1/retrieval \
+     -X POST \
+     -d '{"text":"What is the revenue of Nike in 2023?","embedding":"'"${your_embedding}"'"}' \
+     -H 'Content-Type: application/json'
+   ```
+
+3. TEI Reranking Service
+
+   ```bash
+   curl http://${host_ip}:6041/rerank \
+       -X POST \
+       -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
+       -H 'Content-Type: application/json'
+   ```
+
+4. LLM Backend Service
+
+   In the first startup, this service will take more time to download, load and warm up the model. After it's finished, the service will be ready.
+
+   Try the command below to check whether the LLM service is ready.
+
+   ```bash
+   docker logs vllm-service 2>&1 | grep complete
+   ```
+
+   If the service is ready, you will get the response like below.
+
+   ```text
+   INFO: Application startup complete.
+   ```
+
+   Then try the `cURL` command below to validate vLLM service.
+
+   ```bash
+   curl http://${host_ip}:6042/v1/chat/completions \
+     -X POST \
+     -d '{"model": "meta-llama/Meta-Llama-3-8B-Instruct", "messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens":17}' \
+     -H 'Content-Type: application/json'
+   ```
+
+5. MegaService
+
+   ```bash
+   curl http://${host_ip}:8912/v1/chatqna -H "Content-Type: application/json" -d '{
+        "messages": "What is the revenue of Nike in 2023?"
+        }'
+   ```
+
+6. Dataprep Microservice（Optional）
+
+   If you want to update the default knowledge base, you can use the following commands:
+
+   Update Knowledge Base via Local File Upload:
+
+   ```bash
+   curl -X POST "http://${host_ip}:6043/v1/dataprep/ingest" \
+        -H "Content-Type: multipart/form-data" \
+        -F "files=@./your_file.pdf"
+   ```
+
+   This command updates a knowledge base by uploading a local file for processing. Update the file path according to your environment.
+
+   Add Knowledge Base via HTTP Links:
+
+   ```bash
+   curl -X POST "http://${host_ip}:6043/v1/dataprep/ingest" \
+        -H "Content-Type: multipart/form-data" \
+        -F 'link_list=["https://opea.dev"]'
+   ```
+
+## Launch the UI
+
+To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
+
+```yaml
+  chatqna-xeon-ui-server:
+    image: opea/chatqna-ui:latest
+    ...
+    ports:
+      - "80:5173"
+```
+
+![project-screenshot](../../../../assets/img/chat_ui_init.png)
+
+Here is an example of running ChatQnA:
+
+![project-screenshot](../../../../assets/img/chat_ui_response.png)

ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml

@@ -31,7 +31,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -67,7 +67,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -83,7 +83,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
@@ -99,7 +99,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       VLLM_CPU_KVCACHE_SPACE: 40

ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate

ChatQnA/docker_compose/intel/cpu/xeon/compose_faqgen_tgi.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate

ChatQnA/docker_compose/intel/cpu/xeon/compose_mariadb.yaml

@@ -0,0 +1,185 @@
+# Copyright (C) 2025 MariaDB Foundation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  mariadb-server:
+    image: mariadb:latest
+    container_name: mariadb-server
+    ports:
+      - "3306:3306"
+    environment:
+      - MARIADB_DATABASE=${MARIADB_DATABASE}
+      - MARIADB_USER=${MARIADB_USER}
+      - MARIADB_PASSWORD=${MARIADB_PASSWORD}
+      - MARIADB_RANDOM_ROOT_PASSWORD=1
+    healthcheck:
+      test: ["CMD", "healthcheck.sh", "--connect", "--innodb_initialized"]
+      start_period: 10s
+      interval: 10s
+      timeout: 5s
+      retries: 3
+  dataprep-mariadb-vector:
+    image: ${REGISTRY:-opea}/dataprep:${TAG:-latest}
+    container_name: dataprep-mariadb-vector
+    depends_on:
+      mariadb-server:
+        condition: service_healthy
+      tei-embedding-service:
+        condition: service_started
+    ports:
+      - "6007:5000"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_MARIADBVECTOR"
+      MARIADB_CONNECTION_URL: mariadb+mariadbconnector://${MARIADB_USER}:${MARIADB_PASSWORD}@mariadb-server:3306/${MARIADB_DATABASE}
+      TEI_ENDPOINT: http://tei-embedding-service:80
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 50
+    restart: unless-stopped
+  tei-embedding-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    container_name: tei-embedding-server
+    ports:
+      - "6006:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
+  retriever:
+    image: ${REGISTRY:-opea}/retriever:${TAG:-latest}
+    container_name: retriever-mariadb-vector
+    depends_on:
+      mariadb-server:
+        condition: service_healthy
+    ports:
+      - "7000:7000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      MARIADB_CONNECTION_URL: mariadb+mariadbconnector://${MARIADB_USER}:${MARIADB_PASSWORD}@mariadb-server:3306/${MARIADB_DATABASE}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+      LOGFLAG: ${LOGFLAG}
+      RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_MARIADBVECTOR"
+    restart: unless-stopped
+  tei-reranking-service:
+    image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+    container_name: tei-reranking-server
+    ports:
+      - "8808:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate
+  vllm-service:
+    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
+    container_name: vllm-service
+    ports:
+      - "9009:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
+    shm_size: 128g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HF_TOKEN}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
+      VLLM_TORCH_PROFILER_DIR: "/mnt"
+      VLLM_CPU_KVCACHE_SPACE: 40
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:9009/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
+    command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
+  chatqna-xeon-backend-server:
+    image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
+    container_name: chatqna-xeon-backend-server
+    depends_on:
+      mariadb-server:
+        condition: service_healthy
+      dataprep-mariadb-vector:
+        condition: service_healthy
+      tei-embedding-service:
+        condition: service_started
+      retriever:
+        condition: service_started
+      tei-reranking-service:
+        condition: service_started
+      vllm-service:
+        condition: service_healthy
+    ports:
+      - "8888:8888"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
+      - EMBEDDING_SERVER_HOST_IP=tei-embedding-service
+      - EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
+      - RETRIEVER_SERVICE_HOST_IP=retriever
+      - RERANK_SERVER_HOST_IP=tei-reranking-service
+      - RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
+      - LLM_SERVER_HOST_IP=vllm-service
+      - LLM_SERVER_PORT=80
+      - LLM_MODEL=${LLM_MODEL_ID}
+      - LOGFLAG=${LOGFLAG}
+    ipc: host
+    restart: always
+  chatqna-xeon-ui-server:
+    image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
+    container_name: chatqna-xeon-ui-server
+    depends_on:
+      - chatqna-xeon-backend-server
+    ports:
+      - "5173:5173"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+    ipc: host
+    restart: always
+  chatqna-xeon-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: chatqna-xeon-nginx-server
+    depends_on:
+      - chatqna-xeon-backend-server
+      - chatqna-xeon-ui-server
+    ports:
+      - "${NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=chatqna-xeon-ui-server
+      - FRONTEND_SERVICE_PORT=5173
+      - BACKEND_SERVICE_NAME=chatqna
+      - BACKEND_SERVICE_IP=chatqna-xeon-backend-server
+      - BACKEND_SERVICE_PORT=8888
+      - DATAPREP_SERVICE_IP=dataprep-mariadb-vector
+      - DATAPREP_SERVICE_PORT=5000
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge

ChatQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml

@@ -75,7 +75,7 @@ services:
       MILVUS_HOST: ${host_ip}
       MILVUS_PORT: 19530
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       EMBEDDING_MODEL_ID: ${EMBEDDING_MODEL_ID}
       LOGFLAG: ${LOGFLAG}
     healthcheck:
@@ -107,7 +107,7 @@ services:
       MILVUS_HOST: ${host_ip}
       MILVUS_PORT: 19530
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_MILVUS"
     restart: unless-stopped
@@ -138,7 +138,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
@@ -155,7 +155,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:

ChatQnA/docker_compose/intel/cpu/xeon/compose_pinecone.yaml

@@ -20,7 +20,7 @@ services:
       PINECONE_INDEX_NAME: ${PINECONE_INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
       LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_PINECONE"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
@@ -55,7 +55,7 @@ services:
       PINECONE_INDEX_NAME: ${PINECONE_INDEX_NAME}
       LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_PINECONE"
     restart: unless-stopped
@@ -71,7 +71,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
@@ -87,7 +87,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80

ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml

@@ -24,7 +24,7 @@ services:
       QDRANT_PORT: 6333
       QDRANT_INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_QDRANT"
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
@@ -92,7 +92,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80

ChatQnA/docker_compose/intel/cpu/xeon/compose_remote.yaml

@@ -31,7 +31,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
     container_name: tei-embedding-server
@@ -61,7 +61,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -77,7 +77,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate

ChatQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
@@ -92,7 +92,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0

ChatQnA/docker_compose/intel/cpu/xeon/compose_without_rerank.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
     command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80

ChatQnA/docker_compose/intel/cpu/xeon/grafana/dashboards/download_opea_dashboard.sh

@@ -1,6 +1,8 @@
 # Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-rm *.json
+if ls *.json 1> /dev/null 2>&1; then
+    rm *.json
+fi
 wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/chatqna_megaservice_grafana.json
 wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/qdrant_grafana.json
 wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/milvus_grafana.json

ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh

@@ -7,6 +7,9 @@ pushd "../../../../../" > /dev/null
 source .set_env.sh
 popd > /dev/null
 
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
+export host_ip=${ip_address}
 export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
 export RERANK_MODEL_ID="BAAI/bge-reranker-base"
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"

ChatQnA/docker_compose/intel/cpu/xeon/set_env_mariadb.sh

@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2025 MariaDB Foundation
+# SPDX-License-Identifier: Apache-2.0
+
+pushd "../../../../../" > /dev/null
+source .set_env.sh
+popd > /dev/null
+
+if [ -z "${HF_TOKEN}" ]; then
+    echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set HUGGINGFACEHUB_API_TOKEN."
+fi
+
+export host_ip=$(hostname -I | awk '{print $1}')
+export MARIADB_DATABASE="vectordb"
+export MARIADB_USER="chatqna"
+export MARIADB_PASSWORD="password"
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export LOGFLAG=""
+export no_proxy="$no_proxy,chatqna-xeon-ui-server,chatqna-xeon-backend-server,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,jaeger,prometheus,grafana,node-exporter"
+export LLM_SERVER_PORT=9000
+export NGINX_PORT=80

ChatQnA/docker_compose/intel/hpu/gaudi/README.md

@@ -43,7 +43,7 @@ Some HuggingFace resources, such as some models, are only accessible if you have
 
 ### Configure the Deployment Environment
 
-To set up environment variables for deploying ChatQnA services, source the _setup_env.sh_ script in this directory:
+To set up environment variables for deploying ChatQnA services, source the _setup_env.sh_ script in this directory (If using faqgen or guardrails, source the _set_env_faqgen.sh_):
 
 ```
 source ./set_env.sh

ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -31,7 +31,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -67,7 +67,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
   tei-reranking-service:
     image: ghcr.io/huggingface/tei-gaudi:1.5.0
@@ -101,7 +101,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}

ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
@@ -61,7 +61,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
   tei-reranking-service:
     image: ghcr.io/huggingface/tei-gaudi:1.5.0

ChatQnA/docker_compose/intel/hpu/gaudi/compose_faqgen_tgi.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
@@ -61,7 +61,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
   tei-reranking-service:
     image: ghcr.io/huggingface/tei-gaudi:1.5.0
@@ -95,7 +95,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all

ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -42,7 +42,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       GURADRAILS_MODEL_ID: ${GURADRAILS_MODEL_ID}
@@ -73,7 +73,7 @@ services:
       https_proxy: ${https_proxy}
       SAFETY_GUARD_MODEL_ID: ${GURADRAILS_MODEL_ID}
       SAFETY_GUARD_ENDPOINT: http://vllm-guardrails-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
   tei-embedding-service:
     image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -104,7 +104,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -140,7 +140,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}

ChatQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -96,7 +96,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all

ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -60,7 +60,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
     restart: unless-stopped
@@ -75,7 +75,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       LLM_MODEL_ID: ${LLM_MODEL_ID}

ChatQnA/docker_compose/intel/hpu/gaudi/how_to_validate_service.md

@@ -123,7 +123,7 @@ View the docker input parameters in `./ChatQnA/docker_compose/intel/hpu/gaudi/co
     environment:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       ENABLE_HPU_GRAPH: true

ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh

@@ -4,12 +4,20 @@
 # SPDX-License-Identifier: Apache-2.0
 
 # Function to prompt for input and set environment variables
+NON_INTERACTIVE=${NON_INTERACTIVE:-false}
+
 prompt_for_env_var() {
   local var_name="$1"
   local prompt_message="$2"
   local default_value="$3"
   local mandatory="$4"
 
+  if [[ "$NON_INTERACTIVE" == "true" ]]; then
+    echo "Non-interactive environment detected. Setting $var_name to default: $default_value"
+    export "$var_name"="$default_value"
+    return
+  fi
+
   if [[ "$mandatory" == "true" ]]; then
     while [[ -z "$value" ]]; do
       read -p "$prompt_message [default: \"${default_value}\"]: " value
@@ -34,7 +42,7 @@ popd > /dev/null
 
 # Prompt the user for each required environment variable
 prompt_for_env_var "EMBEDDING_MODEL_ID" "Enter the EMBEDDING_MODEL_ID" "BAAI/bge-base-en-v1.5" false
-prompt_for_env_var "HUGGINGFACEHUB_API_TOKEN" "Enter the HUGGINGFACEHUB_API_TOKEN" "" true
+prompt_for_env_var "HUGGINGFACEHUB_API_TOKEN" "Enter the HUGGINGFACEHUB_API_TOKEN" "${HF_TOKEN}" true
 prompt_for_env_var "RERANK_MODEL_ID" "Enter the RERANK_MODEL_ID" "BAAI/bge-reranker-base" false
 prompt_for_env_var "LLM_MODEL_ID" "Enter the LLM_MODEL_ID" "meta-llama/Meta-Llama-3-8B-Instruct" false
 prompt_for_env_var "INDEX_NAME" "Enter the INDEX_NAME" "rag-redis" false
@@ -42,34 +50,40 @@ prompt_for_env_var "NUM_CARDS" "Enter the number of Gaudi devices" "1" false
 prompt_for_env_var "host_ip" "Enter the host_ip" "$(curl ifconfig.me)" false
 
 #Query for enabling http_proxy
-prompt_for_env_var "http_proxy" "Enter the http_proxy." "" false
+prompt_for_env_var "http_proxy" "Enter the http_proxy." "${http_proxy}" false
 
 #Query for enabling https_proxy
-prompt_for_env_var "https_proxy" "Enter the https_proxy." "" false
+prompt_for_env_var "http_proxy" "Enter the http_proxy." "${https_proxy}" false
 
 #Query for enabling no_proxy
-prompt_for_env_var "no_proxy" "Enter the no_proxy." "" false
+prompt_for_env_var "no_proxy" "Enter the no_proxy." "${no_proxy}" false
 
 # Query for enabling logging
-read -p "Enable logging? (yes/no): " logging && logging=$(echo "$logging" | tr '[:upper:]' '[:lower:]')
-if [[ "$logging" == "yes" || "$logging" == "y" ]]; then
-  export LOGFLAG=true
+if [[ "$NON_INTERACTIVE" == "true" ]]; then
+  # Query for enabling logging
+  prompt_for_env_var "LOGFLAG" "Enable logging? (yes/no): " "true" false
+  export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
+  export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
+  export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
+  telemetry_flag=true
 else
-  export LOGFLAG=false
-fi
-
-# Query for enabling OpenTelemetry Tracing Endpoint
-read -p "Enable OpenTelemetry Tracing Endpoint? (yes/no): " telemetry && telemetry=$(echo "$telemetry" | tr '[:upper:]' '[:lower:]')
-if [[ "$telemetry" == "yes" || "$telemetry" == "y" ]]; then
-    export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
-    export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
-    export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
-    telemetry_flag=true
-    pushd "grafana/dashboards" > /dev/null
-    source download_opea_dashboard.sh
-    popd > /dev/null
-else
-    telemetry_flag=false
+  # Query for enabling logging
+  read -p "Enable logging? (yes/no): " logging && logging=$(echo "$logging" | tr '[:upper:]' '[:lower:]')
+  if [[ "$logging" == "yes" || "$logging" == "y" ]]; then
+    export LOGFLAG=true
+  else
+    export LOGFLAG=false
+  fi
+  # Query for enabling OpenTelemetry Tracing Endpoint
+  read -p "Enable OpenTelemetry Tracing Endpoint? (yes/no): " telemetry && telemetry=$(echo "$telemetry" | tr '[:upper:]' '[:lower:]')
+  if [[ "$telemetry" == "yes" || "$telemetry" == "y" ]]; then
+      export JAEGER_IP=$(ip route get 8.8.8.8 | grep -oP 'src \K[^ ]+')
+      export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=grpc://$JAEGER_IP:4317
+      export TELEMETRY_ENDPOINT=http://$JAEGER_IP:4318/v1/traces
+      telemetry_flag=true
+  else
+      telemetry_flag=false
+  fi
 fi
 
 # Generate the .env file
@@ -78,7 +92,7 @@ cat <<EOF > .env
 # Set all required ENV values
 export TAG=${TAG}
 export EMBEDDING_MODEL_ID=${EMBEDDING_MODEL_ID}
-export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 export RERANK_MODEL_ID=${RERANK_MODEL_ID}
 export LLM_MODEL_ID=${LLM_MODEL_ID}
 export INDEX_NAME=${INDEX_NAME}

ChatQnA/docker_compose/intel/hpu/gaudi/set_env_faqgen.sh

@@ -0,0 +1,32 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+pushd "../../../../../" > /dev/null
+source .set_env.sh
+popd > /dev/null
+
+export HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
+export host_ip=${ip_address}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export INDEX_NAME="rag-redis"
+export NUM_CARDS=1
+export VLLM_SKIP_WARMUP=true
+export LOGFLAG=True
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
+
+export LLM_ENDPOINT_PORT=8010
+export LLM_SERVER_PORT=9001
+export CHATQNA_BACKEND_PORT=8888
+export CHATQNA_REDIS_VECTOR_PORT=6377
+export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
+export CHATQNA_FRONTEND_SERVICE_PORT=5175
+export NGINX_PORT=80
+export FAQGen_COMPONENT_NAME="OpeaFaqGenvLLM"
+export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"

ChatQnA/docker_compose/nvidia/gpu/compose.yaml

@@ -24,7 +24,7 @@ services:
       REDIS_HOST: redis-vector-db
       INDEX_NAME: ${INDEX_NAME}
       TEI_ENDPOINT: http://tei-embedding-service:80
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
       interval: 10s
@@ -76,7 +76,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${RERANK_MODEL_ID} --auto-truncate
@@ -98,7 +98,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     ipc: host

ChatQnA/tests/README.md

@@ -0,0 +1,123 @@
+# ChatQnA 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_tgi_on_xeon.sh
+```
+
+On Intel Xeon with vLLM:
+
+```bash
+bash test_compose_on_xeon.sh
+```
+
+On Intel Xeon with MariaDB Vector:
+
+```bash
+bash test_compose_mariadb_on_xeon.sh
+```
+
+On Intel Xeon with Pinecone:
+
+```bash
+bash test_compose_pinecone_on_xeon.sh
+```
+
+On Intel Xeon with Milvus
+
+```bash
+bash test_compose_milvus_on_xeon.sh
+```
+
+On Intel Xeon with Qdrant
+
+```bash
+bash test_compose_qdrant_on_xeon.sh
+```
+
+On Intel Xeon without Rerank:
+
+```bash
+bash test_compose_without_rerank_on_xeon.sh
+```
+
+On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_tgi_on_gaudi.sh
+```
+
+On Intel Gaudi with vLLM:
+
+```bash
+bash test_compose_on_gaudi.sh
+```
+
+On Intel Gaudi with Guardrails:
+
+```bash
+bash test_compose_guardrails_on_gaudi.sh
+```
+
+On Intel Gaudi without Rerank:
+
+```bash
+bash test_compose_without_rerank_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
+```
+
+Test FAQ Generation On Intel Xeon with TGI:
+
+```bash
+bash test_compose_faqgen_tgi_on_xeon.sh
+```
+
+Test FAQ Generation On Intel Xeon with vLLM:
+
+```bash
+bash test_compose_faqgen_on_xeon.sh
+```
+
+Test FAQ Generation On Intel Gaudi with TGI:
+
+```bash
+bash test_compose_faqgen_tgi_on_gaudi.sh
+```
+
+Test FAQ Generation On Intel Gaudi with vLLM:
+
+```bash
+bash test_compose_faqgen_on_gaudi.sh
+```
+
+Test FAQ Generation On AMD ROCm with TGI:
+
+```bash
+bash test_compose_faqgen_on_rocm.sh
+```
+
+Test FAQ Generation On AMD ROCm with vLLM:
+
+```bash
+bash test_compose_faqgen_vllm_on_rocm.sh
+```

ChatQnA/tests/test_compose_faqgen_on_gaudi.sh

@@ -24,8 +24,8 @@ 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_VER=v0.6.6.post1+Gaudi-1.20.0
-    git checkout ${VLLM_VER} &> /dev/null && cd ../
+    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
 
     echo "Build all the images with --no-cache, check docker_image_build.log for details..."
     service_list="chatqna chatqna-ui dataprep retriever llm-faqgen vllm-gaudi nginx"
@@ -36,27 +36,7 @@ function build_docker_images() {
 
 function start_services() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi
-    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-    export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
-    export NUM_CARDS=1
-    export INDEX_NAME="rag-redis"
-    export host_ip=${ip_address}
-    export LLM_ENDPOINT_PORT=8010
-    export LLM_SERVER_PORT=9001
-    export CHATQNA_BACKEND_PORT=8888
-    export CHATQNA_REDIS_VECTOR_PORT=6377
-    export CHATQNA_REDIS_VECTOR_INSIGHT_PORT=8006
-    export CHATQNA_FRONTEND_SERVICE_PORT=5175
-    export NGINX_PORT=80
-    export FAQGen_COMPONENT_NAME="OpeaFaqGenvLLM"
-    export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"
-    export HF_TOKEN=${HF_TOKEN}
-    export VLLM_SKIP_WARMUP=true
-    export LOGFLAG=True
-    export http_proxy=${http_proxy}
-    export https_proxy=${https_proxy}
-    export no_proxy="${ip_address},redis-vector-db,dataprep-redis-service,tei-embedding-service,retriever,tei-reranking-service,tgi-service,vllm-service,guardrails,llm-faqgen,chatqna-gaudi-backend-server,chatqna-gaudi-ui-server,chatqna-gaudi-nginx-server"
+    source set_env_faqgen.sh
 
     # Start Docker Containers
     docker compose -f compose_faqgen.yaml up -d > ${LOG_PATH}/start_services_with_compose.log