[CICD enhance] DBQnA run CI with latest base image, group logs in GHA outputs. (#1931)

Signed-off-by: chensuyue <suyue.chen@intel.com>

.github/CODEOWNERS

@@ -1,13 +1,26 @@
-/AgentQnA/ xuhui.ren@intel.com
-/AudioQnA/ sihan.chen@intel.com
-/ChatQnA/ liang1.lv@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/ 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/ abolfazl.shahbazi@intel.com kaokao.lv@intel.com chendi.xue@intel.com
 /DocSum/ letong.han@intel.com
-/DocIndexRetriever/ xuhui.ren@intel.com chendi.xue@intel.com
-/FaqGen/ xinyao.wang@intel.com
-/SearchQnA/ sihan.chen@intel.com
-/Translation/ liang1.lv@intel.com
-/VisualQnA/ liang1.lv@intel.com
-/ProductivitySuite/ hoong.tee.yeoh@intel.com
-/*/ liang1.lv@intel.com
+/EdgeCraftRAG/ yongbo.zhu@intel.com mingyuan.qi@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
+/ProductivitySuite/ jaswanth.karani@intel.com hoong.tee.yeoh@intel.com
+/RerankFinetuning/ xinyu.ye@intel.com kaokao.lv@intel.com
+/SearchQnA/ sihan.chen@intel.com letong.han@intel.com
+/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
+/WorkflowExecAgent/ joshua.jian.ern.liew@intel.com kaokao.lv@intel.com

.github/ISSUE_TEMPLATE/1_bug_template.yml

@@ -4,6 +4,7 @@
 name: Report Bug
 description: Used to report bug
 title: "[Bug]"
+labels: ["bug"]
 body:
   - type: dropdown
     id: priority
@@ -31,6 +32,7 @@ body:
         - Mac
         - BSD
         - Other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -55,6 +57,7 @@ body:
         - GPU-Nvidia
         - GPU-AMD
         - GPU-other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -65,6 +68,8 @@ body:
       options:
         - label: Pull docker images from hub.docker.com
         - label: Build docker images from source
+        - label: Other
+        - label: N/A
     validations:
       required: true
 
@@ -73,10 +78,12 @@ body:
     attributes:
       label: Deploy method
       options:
-        - label: Docker compose
         - label: Docker
-        - label: Kubernetes
-        - label: Helm
+        - label: Docker Compose
+        - label: Kubernetes Helm Charts
+        - label: Kubernetes GMC
+        - label: Other
+        - label: N/A
     validations:
       required: true
 
@@ -87,6 +94,8 @@ body:
       options:
         - Single Node
         - Multiple Nodes
+        - Other
+        - N/A
       default: 0
     validations:
       required: true
@@ -126,3 +135,12 @@ body:
       render: shell
     validations:
       required: false
+
+
+  - type: textarea
+    id: attachments
+    attributes:
+      label: Attachments
+      description: Attach any relevant files or screenshots.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/2_feature_template.yml

@@ -4,6 +4,7 @@
 name: Report Feature
 description: Used to report feature
 title: "[Feature]"
+labels: ["feature"]
 body:
   - type: dropdown
     id: priority
@@ -31,6 +32,7 @@ body:
         - Mac
         - BSD
         - Other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -55,6 +57,7 @@ body:
         - GPU-Nvidia
         - GPU-AMD
         - GPU-other (Please let us know in description)
+        - N/A
     validations:
       required: true
 
@@ -65,6 +68,8 @@ body:
       options:
         - Single Node
         - Multiple Nodes
+        - Other
+        - N/A
       default: 0
     validations:
       required: true

.github/code_spell_ignore.txt

@@ -0,0 +1,3 @@
+ModelIn
+modelin
+pressEnter

.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/license_template.txt

@@ -1,2 +1,2 @@
-Copyright (C) 2024 Intel Corporation
-SPDX-License-Identifier: Apache-2.0
+Copyright (C) 2025 Intel Corporation
+SPDX-License-Identifier: Apache-2.0

.github/workflows/_build_comps_base_image.yml

@@ -0,0 +1,65 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Build Comps Base Image
+permissions: read-all
+on:
+  workflow_call:
+    inputs:
+      node:
+        required: true
+        type: string
+      build:
+        default: true
+        required: false
+        type: boolean
+      tag:
+        default: "latest"
+        required: false
+        type: string
+      opea_branch:
+        default: "main"
+        required: false
+        type: string
+      inject_commit:
+        default: false
+        required: false
+        type: boolean
+
+jobs:
+  pre-build-image-check:
+    runs-on: ubuntu-latest
+    outputs:
+      should_skip: ${{ steps.check-skip.outputs.should_skip }}
+    steps:
+      - name: Check if job should be skipped
+        id: check-skip
+        run: |
+          should_skip=true
+          if [[ "${{ inputs.node }}" == "gaudi" || "${{ inputs.node }}" == "xeon" ]]; then
+            should_skip=false
+          fi
+          echo "should_skip=$should_skip"
+          echo "should_skip=$should_skip" >> $GITHUB_OUTPUT
+
+  build-images:
+    needs: [ pre-build-image-check ]
+    if: ${{ needs.pre-build-image-check.outputs.should_skip == 'false' && fromJSON(inputs.build) }}
+    runs-on: "docker-build-${{ inputs.node }}"
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Clone Required Repo
+        run: |
+          git clone --depth 1 --branch ${{ inputs.opea_branch }} https://github.com/opea-project/GenAIComps.git
+          cd GenAIComps && git rev-parse HEAD && cd ../ && ls -l
+
+      - name: Build Image
+        uses: opea-project/validation/actions/image-build@main
+        with:
+          work_dir: ${{ github.workspace }}/GenAIComps
+          docker_compose_path: ${{ github.workspace }}/GenAIComps/.github/workflows/docker/compose/base-compose.yaml
+          registry: ${OPEA_IMAGE_REPO}opea
+          inject_commit: ${{ inputs.inject_commit }}
+          tag: ${{ inputs.tag }}

.github/workflows/_build_image.yml

@@ -0,0 +1,96 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Build Images
+permissions: read-all
+on:
+  workflow_call:
+    inputs:
+      node:
+        required: true
+        type: string
+      build:
+        default: true
+        required: false
+        type: boolean
+      example:
+        required: true
+        type: string
+      services:
+        default: ""
+        required: false
+        type: string
+      tag:
+        default: "latest"
+        required: false
+        type: string
+      opea_branch:
+        default: "main"
+        required: false
+        type: string
+      inject_commit:
+        default: false
+        required: false
+        type: boolean
+
+jobs:
+  pre-build-image-check:
+    runs-on: ubuntu-latest
+    outputs:
+      should_skip: ${{ steps.check-skip.outputs.should_skip }}
+    steps:
+      - name: Check if job should be skipped
+        id: check-skip
+        run: |
+          should_skip=true
+          if [[ "${{ inputs.node }}" == "gaudi" || "${{ inputs.node }}" == "xeon" ]]; then
+            should_skip=false
+          fi
+          echo "should_skip=$should_skip"
+          echo "should_skip=$should_skip" >> $GITHUB_OUTPUT
+
+  build-images:
+    needs: [ pre-build-image-check ]
+    if: ${{ needs.pre-build-image-check.outputs.should_skip == 'false' && fromJSON(inputs.build) }}
+    runs-on: "docker-build-${{ inputs.node }}"
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Get Checkout Ref
+        run: |
+          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
+            echo "CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge" >> $GITHUB_ENV
+          else
+            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
+          fi
+
+      - name: Checkout out GenAIExamples
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ env.CHECKOUT_REF }}
+          fetch-depth: 0
+
+      - name: Clone Required Repo
+        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 -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 -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 ../
+
+      - name: Build Image
+        uses: opea-project/validation/actions/image-build@main
+        with:
+          work_dir: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
+          docker_compose_path: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
+          service_list: ${{ inputs.services }}
+          registry: ${OPEA_IMAGE_REPO}opea
+          inject_commit: ${{ inputs.inject_commit }}
+          tag: ${{ inputs.tag }}

.github/workflows/_example-workflow.yml

@@ -12,6 +12,10 @@ on:
       example:
         required: true
         type: string
+      services:
+        default: ""
+        required: false
+        type: string
       tag:
         default: "latest"
         required: false
@@ -24,7 +28,7 @@ on:
         default: false
         required: false
         type: boolean
-      test_k8s:
+      test_helmchart:
         default: false
         required: false
         type: boolean
@@ -36,79 +40,57 @@ on:
         default: "main"
         required: false
         type: string
+      inject_commit:
+        default: false
+        required: false
+        type: boolean
+      use_model_cache:
+        default: false
+        required: false
+        type: boolean
+
 jobs:
 ####################################################################################################
 # Image Build
 ####################################################################################################
   build-images:
-    runs-on: "docker-build-${{ inputs.node }}"
-    steps:
-      - name: Clean Up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Get checkout ref
-        run: |
-          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
-            echo "CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge" >> $GITHUB_ENV
-          else
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-          fi
-          echo "checkout ref ${{ env.CHECKOUT_REF }}"
-
-      - name: Checkout out Repo
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ env.CHECKOUT_REF }}
-          fetch-depth: 0
-
-      - name: Clone required Repo
-        run: |
-          cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
-          docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
-          if [[ $(grep -c "tei-gaudi:" ${docker_compose_path}) != 0 ]]; then
-              git clone https://github.com/huggingface/tei-gaudi.git
-          fi
-          if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
-              git clone https://github.com/vllm-project/vllm.git
-          fi
-          git clone https://github.com/opea-project/GenAIComps.git
-          cd GenAIComps && git checkout ${{ inputs.opea_branch }} && cd ../
-
-      - name: Build Image
-        if: ${{ fromJSON(inputs.build) }}
-        uses: opea-project/validation/actions/image-build@main
-        with:
-          work_dir: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
-          docker_compose_path: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
-          registry: ${OPEA_IMAGE_REPO}opea
-          tag: ${{ inputs.tag }}
+    uses: ./.github/workflows/_build_image.yml
+    with:
+      node: ${{ inputs.node }}
+      build: ${{ fromJSON(inputs.build) }}
+      example: ${{ inputs.example }}
+      services: ${{ inputs.services }}
+      tag: ${{ inputs.tag }}
+      opea_branch: ${{ inputs.opea_branch }}
+      inject_commit: ${{ inputs.inject_commit }}
 
 ####################################################################################################
 # Docker Compose Test
 ####################################################################################################
   test-example-compose:
     needs: [build-images]
-    if: ${{ fromJSON(inputs.test_compose) }}
+    if: ${{ inputs.test_compose }}
     uses: ./.github/workflows/_run-docker-compose.yml
     with:
       tag: ${{ inputs.tag }}
       example: ${{ inputs.example }}
       hardware: ${{ inputs.node }}
+      use_model_cache: ${{ inputs.use_model_cache }}
+      opea_branch: ${{ inputs.opea_branch }}
     secrets: inherit
 
 
 ####################################################################################################
-# K8S Test
+# helmchart Test
 ####################################################################################################
-  test-k8s-manifest:
-    needs: [build-images]
-    if: ${{ fromJSON(inputs.test_k8s) }}
-    uses: ./.github/workflows/_manifest-e2e.yml
+  test-helmchart:
+    if: ${{ fromJSON(inputs.test_helmchart) }}
+    uses: ./.github/workflows/_helm-e2e.yml
     with:
       example: ${{ inputs.example }}
       hardware: ${{ inputs.node }}
       tag: ${{ inputs.tag }}
-      context: "CD"
+      mode: "CD"
     secrets: inherit
 
 ####################################################################################################
@@ -116,7 +98,7 @@ jobs:
 ####################################################################################################
   test-gmc-pipeline:
     needs: [build-images]
-    if: ${{ fromJSON(inputs.test_gmc) }}
+    if: false # ${{ fromJSON(inputs.test_gmc) }}
     uses: ./.github/workflows/_gmc-e2e.yml
     with:
       example: ${{ inputs.example }}

.github/workflows/_get-test-matrix.yml

@@ -14,7 +14,7 @@ on:
       test_mode:
         required: false
         type: string
-        default: 'docker_compose'
+        default: 'compose'
     outputs:
       run_matrix:
         description: "The matrix string"
@@ -42,6 +42,12 @@ jobs:
           ref: ${{ env.CHECKOUT_REF }}
           fetch-depth: 0
 
+      - name: Check Dangerous Command Injection
+        if: github.event_name == 'pull_request' || github.event_name == 'pull_request_target'
+        uses: opea-project/validation/actions/check-cmd@main
+        with:
+          work_dir: ${{ github.workspace }}
+
       - name: Get test matrix
         id: get-test-matrix
         run: |
@@ -54,9 +60,11 @@ jobs:
             base_commit=$(git rev-parse HEAD~1) # push event
           fi
           merged_commit=$(git log -1 --format='%H')
+          echo "print all changed files..."
+          git diff --name-only ${base_commit} ${merged_commit}
           changed_files="$(git diff --name-only ${base_commit} ${merged_commit} | \
           grep -vE '${{ inputs.diff_excluded_files }}')" || true
-          echo "changed_files=$changed_files"
+          echo "filtered changed_files=$changed_files"
           export changed_files=$changed_files
           export test_mode=${{ inputs.test_mode }}
           export WORKSPACE=${{ github.workspace }}

.github/workflows/_gmc-workflow.yml

@@ -67,36 +67,6 @@ jobs:
           make docker.build
           make docker.push
 
-      - name: Scan gmcmanager
-        if: ${{ inputs.node == 'gaudi' }}
-        uses: opea-project/validation/actions/trivy-scan@main
-        with:
-          image-ref: ${{ env.DOCKER_REGISTRY }}/gmcmanager:${{ env.VERSION }}
-          output: gmcmanager-scan.txt
-
-      - name: Upload gmcmanager scan result
-        if: ${{ inputs.node == 'gaudi' }}
-        uses: actions/upload-artifact@v4.3.4
-        with:
-          name: gmcmanager-scan
-          path: gmcmanager-scan.txt
-          overwrite: true
-
-      - name: Scan gmcrouter
-        if: ${{ inputs.node == 'gaudi' }}
-        uses: opea-project/validation/actions/trivy-scan@main
-        with:
-          image-ref: ${{ env.DOCKER_REGISTRY }}/gmcrouter:${{ env.VERSION }}
-          output: gmcrouter-scan.txt
-
-      - name: Upload gmcrouter scan result
-        if: ${{ inputs.node == 'gaudi' }}
-        uses: actions/upload-artifact@v4.3.4
-        with:
-          name: gmcrouter-scan
-          path: gmcrouter-scan.txt
-          overwrite: true
-
       - name: Clean up images
         if: always()
         run: |

.github/workflows/_helm-e2e.yml

@@ -0,0 +1,252 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Helm Chart E2e Test For Call
+permissions:
+  contents: read
+
+on:
+  workflow_call:
+    inputs:
+      example:
+        default: "chatqna"
+        required: true
+        type: string
+        description: "example to test, chatqna or common/asr"
+      hardware:
+        default: "xeon"
+        required: true
+        type: string
+      dockerhub:
+        default: "false"
+        required: false
+        type: string
+        description: "Set to true if you want to use released docker images at dockerhub. By default using internal docker registry."
+      mode:
+        default: "CD"
+        description: "Whether the test range is CI, CD or CICD"
+        required: false
+        type: string
+      tag:
+        default: "latest"
+        required: false
+        type: string
+      version:
+        default: "0-latest"
+        required: false
+        type: string
+
+jobs:
+  get-test-case:
+    runs-on: ubuntu-latest
+    outputs:
+      value_files: ${{ steps.get-test-files.outputs.value_files }}
+      CHECKOUT_REF: ${{ steps.get-checkout-ref.outputs.CHECKOUT_REF }}
+    steps:
+      - name: Get checkout ref
+        id: get-checkout-ref
+        run: |
+          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
+            CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge
+          else
+            CHECKOUT_REF=${{ github.ref }}
+          fi
+          echo "CHECKOUT_REF=${CHECKOUT_REF}" >> $GITHUB_OUTPUT
+          echo "checkout ref ${CHECKOUT_REF}"
+
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ steps.get-checkout-ref.outputs.CHECKOUT_REF }}
+          fetch-depth: 0
+
+      - name: Get test Services
+        id: get-test-files
+        run: |
+          set -x
+          if [ "${{ inputs.mode }}" = "CI" ]; then
+            base_commit=${{ github.event.pull_request.base.sha }}
+            merged_commit=$(git log -1 --format='%H')
+            values_files=$(git diff --name-only ${base_commit} ${merged_commit} | \
+            grep "${{ inputs.example }}/kubernetes/helm" | \
+            grep "values.yaml" |\
+            sort -u)
+            echo $values_files
+          elif [ "${{ inputs.mode }}" = "CD" ]; then
+            values_files=$(ls ${{ inputs.example }}/kubernetes/helm/*values.yaml || true)
+          fi
+          value_files="["
+          for file in ${values_files}; do
+            if [ -f "$file" ]; then
+              filename=$(basename "$file")
+              if [[ "$filename" == *"gaudi"* ]]; then
+                if [[ "${{ inputs.hardware }}" == "gaudi" ]]; then
+                  value_files="${value_files}\"${filename}\","
+                fi
+              elif [[ "$filename" == *"rocm"* ]]; then
+                if [[ "${{ inputs.hardware }}" == "rocm" ]]; then
+                  value_files="${value_files}\"${filename}\","
+                fi
+              elif [[ "$filename" == *"nv"* ]]; then
+                continue
+              else
+                if [[ "${{ inputs.hardware }}" == "xeon" ]]; then
+                  value_files="${value_files}\"${filename}\","
+                fi
+              fi
+            fi
+          done
+          value_files="${value_files%,}]"
+
+          echo "value_files=${value_files}"
+          echo "value_files=${value_files}" >> $GITHUB_OUTPUT
+
+  helm-test:
+    needs: [get-test-case]
+    if: ${{ needs.get-test-case.outputs.value_files != '[]' }}
+    strategy:
+      matrix:
+        value_file: ${{ fromJSON(needs.get-test-case.outputs.value_files) }}
+      fail-fast: false
+    runs-on: k8s-${{ inputs.hardware }}
+    continue-on-error: true
+    steps:
+      - name: Clean Up Working Directory
+        run: |
+          echo "value_file=${{ matrix.value_file }}"
+          sudo rm -rf ${{github.workspace}}/*
+
+      - name: Get checkout ref
+        id: get-checkout-ref
+        run: |
+          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
+            CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge
+          else
+            CHECKOUT_REF=${{ github.ref }}
+          fi
+          echo "CHECKOUT_REF=${CHECKOUT_REF}" >> $GITHUB_OUTPUT
+          echo "checkout ref ${CHECKOUT_REF}"
+
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ steps.get-checkout-ref.outputs.CHECKOUT_REF }}
+          fetch-depth: 0
+
+      - name: Set variables
+        env:
+          example: ${{ inputs.example }}
+        run: |
+          if [[ ! "$example" =~ ^[a-zA-Z0-9]{1,20}$ ]] || [[ "$example" =~ \.\. ]] || [[ "$example" == -* || "$example" == *- ]]; then
+            echo "Error: Invalid input - only lowercase alphanumeric and internal hyphens allowed"
+            exit 1
+          fi
+          # SAFE_PREFIX="kb-"
+          CHART_NAME="${SAFE_PREFIX}$(echo "$example" | tr '[:upper:]' '[:lower:]')"
+          RAND_SUFFIX=$(openssl rand -hex 2 | tr -dc 'a-f0-9')
+
+          cat <<EOF >> $GITHUB_ENV
+          CHART_NAME=${CHART_NAME}
+          RELEASE_NAME=${CHART_NAME}-$(date +%s)
+          NAMESPACE=ns-${CHART_NAME}-${RAND_SUFFIX}
+          ROLLOUT_TIMEOUT_SECONDS=600s
+          TEST_TIMEOUT_SECONDS=600s
+          KUBECTL_TIMEOUT_SECONDS=60s
+          should_cleanup=false
+          skip_validate=false
+          CHART_FOLDER=${example}/kubernetes/helm
+          EOF
+
+          echo "Generated safe variables:" >> $GITHUB_STEP_SUMMARY
+          echo "- CHART_NAME: ${CHART_NAME}" >> $GITHUB_STEP_SUMMARY
+
+      - name: Helm install
+        id: install
+        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 }}
+          value_file: ${{ matrix.value_file }}
+        run: |
+          set -xe
+          echo "should_cleanup=true" >> $GITHUB_ENV
+          if [[ ! -f ${{ github.workspace }}/${{ env.CHART_FOLDER }}/${value_file} ]]; then
+            echo "No value file found, exiting test!"
+            echo "skip_validate=true" >> $GITHUB_ENV
+            echo "should_cleanup=false" >> $GITHUB_ENV
+            exit 0
+          fi
+
+          for img in `helm template -n $NAMESPACE $RELEASE_NAME oci://ghcr.io/opea-project/charts/${CHART_NAME} -f ${{ inputs.example }}/kubernetes/helm/${value_file} --version ${{ inputs.version }} | grep 'image:' | grep 'opea/' | awk '{print $2}' | xargs`;
+          do
+            # increase helm install wait for for vllm-gaudi case
+            if [[ $img == *"vllm-gaudi"* ]]; then
+              ROLLOUT_TIMEOUT_SECONDS=900s
+            fi
+          done
+          if ! helm install \
+            --create-namespace \
+            --namespace $NAMESPACE \
+            $RELEASE_NAME \
+            oci://ghcr.io/opea-project/charts/${CHART_NAME} \
+            --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} \
+            --set global.modelUseHostPath=/data2/hf_model \
+            --set GOOGLE_API_KEY=${{ env.GOOGLE_API_KEY}} \
+            --set GOOGLE_CSE_ID=${{ env.GOOGLE_CSE_ID}} \
+            --set web-retriever.GOOGLE_API_KEY=${{ env.GOOGLE_API_KEY}} \
+            --set web-retriever.GOOGLE_CSE_ID=${{ env.GOOGLE_CSE_ID}} \
+            -f ${{ inputs.example }}/kubernetes/helm/${value_file} \
+            --version ${{ inputs.version }} \
+            --wait --timeout "$ROLLOUT_TIMEOUT_SECONDS"; then
+            echo "Failed to install chart ${{ inputs.example }}"
+            echo "skip_validate=true" >> $GITHUB_ENV
+            .github/workflows/scripts/k8s-utils.sh dump_pods_status $NAMESPACE
+            exit 1
+          fi
+
+      - name: Validate e2e test
+        if: always()
+        run: |
+          set -xe
+          if $skip_validate; then
+            echo "Skip validate"
+          else
+            LOG_PATH=/home/$(whoami)/helm-logs
+            chart=${{ env.CHART_NAME }}
+            helm test -n $NAMESPACE $RELEASE_NAME --logs --timeout "$TEST_TIMEOUT_SECONDS" | tee ${LOG_PATH}/charts-${chart}.log
+            exit_code=$?
+            if [ $exit_code -ne 0 ]; then
+                echo "Chart ${chart} test failed, please check the logs in ${LOG_PATH}!"
+                exit 1
+            fi
+
+            echo "Checking response results, make sure the output is reasonable. "
+            teststatus=false
+            if [[ -f $LOG_PATH/charts-${chart}.log ]] && \
+            [[ $(grep -c "^Phase:.*Failed" $LOG_PATH/charts-${chart}.log) != 0 ]]; then
+                teststatus=false
+                ${{ github.workspace }}/.github/workflows/scripts/k8s-utils.sh dump_all_pod_logs $NAMESPACE
+            else
+                teststatus=true
+            fi
+
+            if [ $teststatus == false ]; then
+                echo "Response check failed, please check the logs in artifacts!"
+                exit 1
+            else
+                echo "Response check succeeded!"
+                exit 0
+            fi
+          fi
+
+      - name: Helm uninstall
+        if: always()
+        run: |
+          if $should_cleanup; then
+            helm uninstall $RELEASE_NAME --namespace $NAMESPACE
+            if ! kubectl delete ns $NAMESPACE --timeout=$KUBECTL_TIMEOUT_SECONDS; then
+              kubectl delete pods --namespace $NAMESPACE --force --grace-period=0 --all
+              kubectl delete ns $NAMESPACE --force --grace-period=0 --timeout=$KUBECTL_TIMEOUT_SECONDS
+            fi
+          fi

.github/workflows/_manifest-e2e.yml

@@ -1,111 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Single Kubernetes Manifest E2e Test For Call
-on:
-  workflow_call:
-    inputs:
-      example:
-        default: "ChatQnA"
-        description: "The example to test on K8s"
-        required: true
-        type: string
-      hardware:
-        default: "xeon"
-        description: "Nodes to run the test, xeon or gaudi"
-        required: true
-        type: string
-      tag:
-        default: "latest"
-        description: "Tag to apply to images, default is latest"
-        required: false
-        type: string
-      context:
-        default: "CI"
-        description: "CI or CD"
-        required: false
-        type: string
-
-jobs:
-  manifest-test:
-    runs-on: "k8s-${{ inputs.hardware }}"
-    continue-on-error: true
-    steps:
-      - name: Clean Up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Get checkout ref
-        run: |
-          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
-            echo "CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge" >> $GITHUB_ENV
-          else
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-          fi
-          echo "checkout ref ${{ env.CHECKOUT_REF }}"
-
-      - name: Checkout out Repo
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ env.CHECKOUT_REF }}
-          fetch-depth: 0
-
-      - name: Set variables
-        run: |
-          echo "IMAGE_REPO=$OPEA_IMAGE_REPO" >> $GITHUB_ENV
-          echo "IMAGE_TAG=${{ inputs.tag }}" >> $GITHUB_ENV
-          lower_example=$(echo "${{ inputs.example }}" | tr '[:upper:]' '[:lower:]')
-          echo "NAMESPACE=$lower_example-$(tr -dc a-z0-9 </dev/urandom | head -c 16)" >> $GITHUB_ENV
-          echo "ROLLOUT_TIMEOUT_SECONDS=1800s" >> $GITHUB_ENV
-          echo "KUBECTL_TIMEOUT_SECONDS=60s" >> $GITHUB_ENV
-          echo "continue_test=true" >> $GITHUB_ENV
-          echo "should_cleanup=false" >> $GITHUB_ENV
-          echo "skip_validate=true" >> $GITHUB_ENV
-          echo "CONTEXT=${{ inputs.context }}" >> $GITHUB_ENV
-          echo "NAMESPACE=$NAMESPACE"
-
-      - name: Kubectl install
-        id: install
-        run: |
-          if [[ ! -f ${{ github.workspace }}/${{ inputs.example }}/tests/test_manifest_on_${{ inputs.hardware }}.sh ]]; then
-            echo "No test script found, exist test!"
-            exit 0
-          else
-            ${{ github.workspace }}/${{ inputs.example }}/tests/test_manifest_on_${{ inputs.hardware }}.sh init_${{ inputs.example }}
-            echo "should_cleanup=true" >> $GITHUB_ENV
-            kubectl create ns $NAMESPACE
-            ${{ github.workspace }}/${{ inputs.example }}/tests/test_manifest_on_${{ inputs.hardware }}.sh install_${{ inputs.example }} $NAMESPACE
-            echo "Testing ${{ inputs.example }}, waiting for pod ready..."
-            if kubectl rollout status deployment --namespace "$NAMESPACE" --timeout "$ROLLOUT_TIMEOUT_SECONDS"; then
-              echo "Testing manifests ${{ inputs.example }}, waiting for pod ready done!"
-              echo "skip_validate=false" >> $GITHUB_ENV
-            else
-              echo "Timeout waiting for pods in namespace $NAMESPACE to be ready!"
-              .github/workflows/scripts/k8s-utils.sh dump_pods_status $NAMESPACE
-              exit 1
-            fi
-            sleep 60
-          fi
-
-      - name: Validate e2e test
-        if: always()
-        run: |
-          if $skip_validate; then
-            echo "Skip validate"
-          else
-            if ${{ github.workspace }}/${{ inputs.example }}/tests/test_manifest_on_${{ inputs.hardware }}.sh validate_${{ inputs.example }} $NAMESPACE ; then
-              echo "Validate ${{ inputs.example }} successful!"
-            else
-              echo "Validate ${{ inputs.example }} failure!!!"
-              .github/workflows/scripts/k8s-utils.sh dump_all_pod_logs $NAMESPACE
-            fi
-          fi
-
-      - name: Kubectl uninstall
-        if: always()
-        run: |
-          if $should_cleanup; then
-            if ! kubectl delete ns $NAMESPACE --timeout=$KUBECTL_TIMEOUT_SECONDS; then
-              kubectl delete pods --namespace $NAMESPACE --force --grace-period=0 --all
-              kubectl delete ns $NAMESPACE --force --grace-period=0 --timeout=$KUBECTL_TIMEOUT_SECONDS
-            fi
-          fi

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

@@ -28,6 +28,14 @@ on:
         required: false
         type: string
         default: ""
+      use_model_cache:
+        required: false
+        type: boolean
+        default: false
+      opea_branch:
+        default: "main"
+        required: false
+        type: string
 jobs:
   get-test-case:
     runs-on: ubuntu-latest
@@ -60,9 +68,16 @@ jobs:
           cd ${{ github.workspace }}/${{ inputs.example }}/tests
           run_test_cases=""
 
-          default_test_case=$(find . -type f -name "test_compose_on_${{ inputs.hardware }}.sh" | cut -d/ -f2)
+          if [[ "${{ inputs.hardware }}" == "gaudi"* ]]; then
+            hardware="gaudi"
+          elif [[ "${{ inputs.hardware }}" == "xeon"* ]]; then
+            hardware="xeon"
+          else
+            hardware="${{ inputs.hardware }}"
+          fi
+          default_test_case=$(find . -type f -name "test_compose_on_$hardware.sh" | cut -d/ -f2)
           if [ "$default_test_case" ]; then run_test_cases="$default_test_case"; fi
-          other_test_cases=$(find . -type f -name "test_compose_*_on_${{ inputs.hardware }}.sh" | cut -d/ -f2)
+          other_test_cases=$(find . -type f -name "test_compose_*_on_$hardware.sh" | cut -d/ -f2)
           echo "default_test_case=$default_test_case"
           echo "other_test_cases=$other_test_cases"
 
@@ -85,12 +100,17 @@ jobs:
               fi
           done
 
+          if [ -z "$run_test_cases" ] && [[ $(printf '%s\n' "${changed_files[@]}" | grep ${{ inputs.example }} | grep /tests/) ]]; then
+              run_test_cases=$other_test_cases
+          fi
+
           test_cases=$(echo $run_test_cases | tr ' ' '\n' | sort -u | jq -R '.' | jq -sc '.')
           echo "test_cases=$test_cases"
           echo "test_cases=$test_cases" >> $GITHUB_OUTPUT
 
-  run-test:
+  compose-test:
     needs: [get-test-case]
+    if: ${{ needs.get-test-case.outputs.test_cases != '[""]' }}
     strategy:
       matrix:
         test_case: ${{ fromJSON(needs.get-test-case.outputs.test_cases) }}
@@ -101,9 +121,18 @@ jobs:
       - name: Clean up Working Directory
         run: |
           sudo rm -rf ${{github.workspace}}/* || true
+
+          echo "Cleaning up containers using ports..."
+          cid=$(docker ps --format '{{.Names}} : {{.Ports}}' | grep -v ' : $' | grep -v 0.0.0.0:5000 | awk -F' : ' '{print $1}')
+          if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
           docker system prune -f
-          docker rmi $(docker images --filter reference="*/*/*:latest" -q) || true
-          docker rmi $(docker images --filter reference="*/*:ci" -q) || true
+
+          echo "Cleaning up images ..."
+          docker images --filter reference="*/*/*:latest" -q | xargs -r docker rmi && sleep 1s
+          docker images --filter reference="*/*:ci" -q | xargs -r docker rmi && sleep 1s
+          docker images --filter reference="*:5000/*/*" -q | xargs -r docker rmi && sleep 1s
+          docker images --filter reference="opea/comps-base" -q | xargs -r docker rmi && sleep 1s
+          docker images
 
       - name: Checkout out Repo
         uses: actions/checkout@v4
@@ -111,40 +140,84 @@ jobs:
           ref: ${{ needs.get-test-case.outputs.CHECKOUT_REF }}
           fetch-depth: 0
 
+      - name: Clean up container before test
+        shell: bash
+        run: |
+          docker ps
+          cd ${{ github.workspace }}/${{ inputs.example }}
+          export test_case=${{ matrix.test_case }}
+          export hardware=${{ inputs.hardware }}
+          bash ${{ github.workspace }}/.github/workflows/scripts/docker_compose_clean_up.sh "containers"
+          bash ${{ github.workspace }}/.github/workflows/scripts/docker_compose_clean_up.sh "ports"
+          docker ps
+
+      - name: Log in DockerHub
+        uses: docker/login-action@v3.2.0
+        with:
+          username: ${{ secrets.DOCKERHUB_USER }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
       - name: Run test
         shell: bash
         env:
           HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
+          HF_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           PINECONE_KEY: ${{ secrets.PINECONE_KEY }}
+          PINECONE_KEY_LANGCHAIN_TEST: ${{ secrets.PINECONE_KEY_LANGCHAIN_TEST }}
+          SDK_BASE_URL: ${{ secrets.SDK_BASE_URL }}
+          SERVING_TOKEN: ${{ secrets.SERVING_TOKEN }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          FINNHUB_API_KEY: ${{ secrets.FINNHUB_API_KEY }}
+          FINANCIAL_DATASETS_API_KEY: ${{ secrets.FINANCIAL_DATASETS_API_KEY }}
           IMAGE_REPO: ${{ inputs.registry }}
           IMAGE_TAG: ${{ inputs.tag }}
+          opea_branch: ${{ inputs.opea_branch }}
           example: ${{ inputs.example }}
           hardware: ${{ inputs.hardware }}
           test_case: ${{ matrix.test_case }}
+          use_model_cache: ${{ inputs.use_model_cache }}
         run: |
           cd ${{ github.workspace }}/$example/tests
           if [[ "$IMAGE_REPO" == "" ]]; then export IMAGE_REPO="${OPEA_IMAGE_REPO}opea"; fi
-          if [ -f ${test_case} ]; then timeout 30m bash ${test_case}; else echo "Test script {${test_case}} not found, skip test!"; fi
+          if [[ "$use_model_cache" == "true" ]]; then
+            if [ -d "/data2/hf_model" ]; then
+              export model_cache="/data2/hf_model"
+            else
+              echo "Model cache directory /data2/hf_model does not exist"
+              export model_cache="$HOME/.cache/huggingface/hub"
+            fi
+            if [[ "$test_case" == *"rocm"* ]]; then
+              export model_cache="/var/lib/GenAI/data"
+            fi
+          fi
+          if [ -f "${test_case}" ]; then timeout 60m bash "${test_case}"; else echo "Test script {${test_case}} not found, skip test!"; fi
 
-      - name: Clean up container
-        shell: bash
-        if: cancelled() || failure()
+      - name: Clean up container after test
+        if: always()
         run: |
-          cd ${{ github.workspace }}/${{ inputs.example }}/docker_compose
-          test_case=${{ matrix.test_case }}
-          flag=${test_case%_on_*}
-          flag=${flag#test_}
-          yaml_file=$(find . -type f -wholename "*${{ inputs.hardware }}/${flag}.yaml")
-          echo $yaml_file
-          docker compose -f $yaml_file stop && docker compose -f $yaml_file rm -f || true
-          docker system prune -f
-          docker rmi $(docker images --filter reference="*:5000/*/*" -q) || true
+          set -x
+
+          echo "Cleaning up containers using ports..."
+          cid=$(docker ps --format '{{.Names}} : {{.Ports}}' | grep -v ' : $' | grep -v 0.0.0.0:5000 | awk -F' : ' '{print $1}')
+          if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
+
+          echo "Cleaning up images ..."
+          if [[ "${{ inputs.hardware }}" == "xeon"* ]]; then
+              docker system prune -a -f
+          else
+              docker images --filter reference="*/*/*:latest" -q | xargs -r docker rmi && sleep 1s
+              docker images --filter reference="*/*:ci" -q | xargs -r docker rmi && sleep 1s
+              docker images --filter reference="*:5000/*/*" -q | xargs -r docker rmi && sleep 1s
+              docker images --filter reference="opea/comps-base" -q | xargs -r docker rmi && sleep 1s
+              docker system prune -f
+          fi
+          docker images
 
       - name: Publish pipeline artifact
         if: ${{ !cancelled() }}
         uses: actions/upload-artifact@v4
         with:
-          name: ${{ inputs.example }}_${{ matrix.test_case }}
+          name: ${{ inputs.hardware }}_${{ inputs.example }}_${{ matrix.test_case }}
           path: ${{ github.workspace }}/${{ inputs.example }}/tests/*.log

.github/workflows/check-online-doc-build.yml

@@ -0,0 +1,35 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check Online Document Building
+permissions: {}
+
+on:
+  pull_request:
+    branches: [main]
+    paths:
+      - "**.md"
+      - "**.rst"
+
+jobs:
+  build:
+    runs-on: ubuntu-22.04
+    steps:
+
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        path: GenAIExamples
+
+    - name: Checkout docs
+      uses: actions/checkout@v4
+      with:
+        repository: opea-project/docs
+        path: docs
+
+    - name: Build Online Document
+      shell: bash
+      run: |
+        echo "build online doc"
+        cd docs
+        bash scripts/build.sh

.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

@@ -0,0 +1,29 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check stale issue and pr
+
+on:
+  schedule:
+    - cron: "30 22 * * *"
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v9
+        with:
+          days-before-issue-stale: 30
+          days-before-pr-stale: 30
+          days-before-issue-close: 7
+          days-before-pr-close: 7
+          stale-issue-message: "This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days."
+          stale-pr-message: "This PR is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days."
+          close-issue-message: "This issue was closed because it has been stalled for 7 days with no activity."
+          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/dockerhub-description.yml

@@ -0,0 +1,117 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Update Docker Hub Description
+on:
+  schedule:
+    - cron: "0 0 * * 0"
+  workflow_dispatch:
+
+jobs:
+  get-images-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      examples_json: ${{ steps.extract.outputs.examples_json }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Extract images info and generate JSON matrix
+        id: extract
+        run: |
+          #!/bin/bash
+          set -e
+          images=$(awk -F'|' '/^\| *\[opea\// {
+            gsub(/^ +| +$/, "", $2);
+            gsub(/^ +| +$/, "", $4);
+            gsub(/^ +| +$/, "", $5);
+
+            # Extract the path portion of the dockerHub link from the Example Images column
+            match($2, /\(https:\/\/hub\.docker\.com\/r\/[^)]*\)/);
+            repository = substr($2, RSTART, RLENGTH);
+            # Remove the prefix and the trailing right bracket
+            sub(/^\(https:\/\/hub\.docker\.com\/r\//, "", repository);
+            sub(/\)$/, "", repository);
+
+            # Description Direct assignment
+            description = $4;
+
+            # Extract the content of the github link from the Readme column
+            match($5, /\(https:\/\/github\.com\/[^)]*\)/);
+            readme_url = substr($5, RSTART, RLENGTH);
+            # Remove the prefix and the trailing right bracket
+            sub(/^\(https:\/\/github\.com\//, "", readme_url);
+            sub(/\)$/, "", readme_url);
+            # Remove blob information, such as "blob/main/" or "blob/habana_main/"
+            gsub(/blob\/[^/]+\//, "", readme_url);
+            # Remove the organization name and keep only the file path, such as changing "opea-project/GenAIExamples/AudioQnA/README.md" to "GenAIExamples/AudioQnA/README.md"
+            sub(/^[^\/]+\//, "", readme_url);
+
+            # Generate JSON object string
+            printf "{\"repository\":\"%s\",\"short-description\":\"%s\",\"readme-filepath\":\"%s\"}\n", repository, description, readme_url;
+          }' docker_images_list.md)
+
+          # Concatenate all JSON objects into a JSON array, using paste to separate them with commas
+          json="[$(echo "$images" | paste -sd, -)]"
+          echo "$json"
+          # Set as output variable for subsequent jobs to use
+          echo "::set-output name=examples_json::$json"
+
+  check-images-matrix:
+    runs-on: ubuntu-latest
+    needs: get-images-matrix
+    if: ${{ needs.get-images-matrix.outputs.examples_json != '' }}
+    strategy:
+      matrix:
+        image: ${{ fromJSON(needs.get-images-matrix.outputs.examples_json) }}
+      fail-fast: false
+    steps:
+    - name: Check dockerhub description
+      run: |
+        echo "dockerhub description for ${{ matrix.image.repository }}"
+        echo "short-description: ${{ matrix.image.short-description }}"
+        echo "readme-filepath: ${{ matrix.image.readme-filepath }}"
+
+  dockerHubDescription:
+    runs-on: ubuntu-latest
+    needs: get-images-matrix
+    if: ${{ needs.get-images-matrix.outputs.examples_json != '' }}
+    strategy:
+      matrix:
+        image: ${{ fromJSON(needs.get-images-matrix.outputs.examples_json) }}
+      fail-fast: false
+    steps:
+    - name: Checkout GenAIExamples
+      uses: actions/checkout@v4
+      with:
+        repository: opea-project/GenAIExamples
+        path: GenAIExamples
+
+    - name: Checkout GenAIComps
+      uses: actions/checkout@v4
+      with:
+        repository: opea-project/GenAIComps
+        path: GenAIComps
+
+    - name: Checkout vllm-openvino
+      uses: actions/checkout@v4
+      with:
+        repository: vllm-project/vllm
+        path: vllm
+
+    - name: Checkout vllm-gaudi
+      uses: actions/checkout@v4
+      with:
+        repository: HabanaAI/vllm-fork
+        ref: habana_main
+        path: vllm-fork
+
+    - name: add dockerhub description
+      uses: peter-evans/dockerhub-description@v4
+      with:
+        username: ${{ secrets.DOCKERHUB_USER }}
+        password: ${{ secrets.DOCKERHUB_TOKEN }}
+        repository: ${{ matrix.image.repository }}
+        short-description: ${{ matrix.image.short-description }}
+        readme-filepath: ${{ matrix.image.readme-filepath }}
+        enable-url-completion: false

.github/workflows/manual-docker-clean.yml

@@ -0,0 +1,31 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Clean up container on manual event
+on:
+  workflow_dispatch:
+    inputs:
+      node:
+        default: "rocm"
+        description: "Hardware to clean"
+        required: true
+        type: string
+      clean_list:
+        default: ""
+        description: "docker command to clean"
+        required: false
+        type: string
+
+jobs:
+  clean:
+    runs-on: "${{ inputs.node }}"
+    steps:
+      - name: Clean up container
+        run: |
+          docker ps
+          if [ "${{ inputs.clean_list }}" ]; then
+            echo "----------stop and remove containers----------"
+            docker stop ${{ inputs.clean_list }} && docker rm ${{ inputs.clean_list }}
+            echo "----------container removed----------"
+            docker ps
+          fi

.github/workflows/manual-docker-publish.yml

@@ -11,23 +11,23 @@ on:
         required: true
         type: string
       examples:
-        default: "Translation"
-        description: 'List of examples to publish [AudioQnA,ChatQnA,CodeGen,CodeTrans,DocSum,FaqGen,SearchQnA,Translation]'
+        default: ""
+        description: 'List of examples to publish [AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA]'
         required: false
         type: string
       images:
-        default: "gmcmanager,gmcrouter"
-        description: 'List of images to publish [gmcmanager,gmcrouter, ...]'
+        default: ""
+        description: 'List of images to publish [gmcmanager,gmcrouter]'
         required: false
         type: string
       tag:
-        default: "v0.9"
-        description: "Tag to publish"
+        default: "rc"
+        description: "Tag to publish, like [1.0rc]"
         required: true
         type: string
       publish_tags:
-        default: "latest,v0.9"
-        description: 'Tag list apply to publish images'
+        default: "latest,1.x"
+        description: "Tag list apply to publish images, like [latest,1.0]"
         required: false
         type: string
 
@@ -41,9 +41,11 @@ jobs:
 
   publish:
     needs: [get-image-list]
+    if: ${{ needs.get-image-list.outputs.matrix != '' }}
     strategy:
       matrix:
         image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}
+      fail-fast: false
     runs-on: "docker-build-${{ inputs.node }}"
     steps:
       - uses: docker/login-action@v3.2.0

.github/workflows/manual-docker-scan.yml

@@ -11,13 +11,13 @@ on:
         required: true
         type: string
       examples:
-        default: "ChatQnA"
-        description: 'List of examples to scan [AudioQnA,ChatQnA,CodeGen,CodeTrans,DocSum,FaqGen,SearchQnA,Translation]'
+        default: ""
+        description: 'List of examples to publish "AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA"'
         required: false
         type: string
       images:
-        default: "gmcmanager,gmcrouter"
-        description: 'List of images to scan [gmcmanager,gmcrouter, ...]'
+        default: ""
+        description: 'List of images to publish "gmcmanager,gmcrouter"'
         required: false
         type: string
       tag:
@@ -47,6 +47,7 @@ jobs:
   scan-docker:
     needs: get-image-list
     runs-on: "docker-build-${{ inputs.node }}"
+    if: ${{ needs.get-image-list.outputs.matrix != '' }}
     strategy:
       matrix:
         image: ${{ fromJson(needs.get-image-list.outputs.matrix) }}

.github/workflows/manual-example-workflow.yml

@@ -7,12 +7,12 @@ on:
     inputs:
       nodes:
         default: "gaudi,xeon"
-        description: "Hardware to run test"
+        description: "Hardware to run test gaudi,xeon,rocm,arc,gaudi3,xeon-gnr"
         required: true
         type: string
       examples:
         default: "ChatQnA"
-        description: 'List of examples to test [AudioQnA,ChatQnA,CodeGen,CodeTrans,DocSum,FaqGen,SearchQnA,Translation]'
+        description: 'List of examples to test [AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA,AvatarChatbot,Text2Image,WorkflowExecAgent,DBQnA,EdgeCraftRAG,GraphRAG]'
         required: true
         type: string
       tag:
@@ -20,11 +20,6 @@ on:
         description: "Tag to apply to images"
         required: true
         type: string
-      deploy_gmc:
-        default: false
-        description: 'Whether to deploy gmc'
-        required: true
-        type: boolean
       build:
         default: true
         description: 'Build test required images for Examples'
@@ -35,14 +30,9 @@ on:
         description: 'Test examples with docker compose'
         required: false
         type: boolean
-      test_k8s:
-        default: false
-        description: 'Test examples with k8s'
-        required: false
-        type: boolean
-      test_gmc:
-        default: false
-        description: 'Test examples with gmc'
+      test_helmchart:
+        default: true
+        description: 'Test examples with helm charts'
         required: false
         type: boolean
       opea_branch:
@@ -50,6 +40,16 @@ on:
         description: 'OPEA branch for image build'
         required: false
         type: string
+      inject_commit:
+        default: false
+        description: "inject commit to docker images"
+        required: false
+        type: boolean
+      use_model_cache:
+        default: false
+        description: "use model cache"
+        required: false
+        type: boolean
 
 permissions: read-all
 jobs:
@@ -69,23 +69,20 @@ jobs:
         nodes_json=$(printf '%s\n' "${nodes[@]}" | sort -u | jq -R '.' | jq -sc '.')
         echo "nodes=$nodes_json" >> $GITHUB_OUTPUT
 
-  build-deploy-gmc:
+  build-comps-base:
     needs: [get-test-matrix]
-    if: ${{ fromJSON(inputs.deploy_gmc) }}
     strategy:
       matrix:
         node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
-      fail-fast: false
-    uses: ./.github/workflows/_gmc-workflow.yml
+    uses: ./.github/workflows/_build_comps_base_image.yml
     with:
       node: ${{ matrix.node }}
+      build: ${{ fromJSON(inputs.build) }}
       tag: ${{ inputs.tag }}
       opea_branch: ${{ inputs.opea_branch }}
-    secrets: inherit
 
   run-examples:
-    needs: [get-test-matrix, build-deploy-gmc]
-    if: always()
+    needs: [get-test-matrix, build-comps-base]
     strategy:
       matrix:
         example: ${{ fromJson(needs.get-test-matrix.outputs.examples) }}
@@ -98,7 +95,8 @@ jobs:
       tag: ${{ inputs.tag }}
       build: ${{ fromJSON(inputs.build) }}
       test_compose: ${{ fromJSON(inputs.test_compose) }}
-      test_k8s: ${{ fromJSON(inputs.test_k8s) }}
-      test_gmc: ${{ fromJSON(inputs.test_gmc) }}
+      test_helmchart: ${{ fromJSON(inputs.test_helmchart) }}
       opea_branch: ${{ inputs.opea_branch }}
+      inject_commit: ${{ inputs.inject_commit }}
+      use_model_cache: ${{ inputs.use_model_cache }}
     secrets: inherit

.github/workflows/manual-freeze-tag.yml

@@ -1,13 +1,13 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-name: Freeze OPEA images release tag in readme on manual event
+name: Freeze OPEA images release tag
 
 on:
   workflow_dispatch:
     inputs:
       tag:
-        default: "latest"
+        default: "1.1.0"
         description: "Tag to apply to images"
         required: true
         type: string
@@ -23,21 +23,18 @@ jobs:
           fetch-depth: 0
           ref: ${{ github.ref }}
 
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.10"
-
       - name: Set up Git
         run: |
-          git config --global user.name "NeuralChatBot"
-          git config --global user.email "grp_neural_chat_bot@intel.com"
-          git remote set-url origin https://NeuralChatBot:"${{ secrets.ACTION_TOKEN }}"@github.com/opea-project/GenAIExamples.git
+          git config --global user.name "CICD-at-OPEA"
+          git config --global user.email "CICD@opea.dev"
+          git remote set-url origin https://CICD-at-OPEA:"${{ secrets.ACTION_TOKEN }}"@github.com/opea-project/GenAIExamples.git
 
       - name: Run script
         run: |
-          find . -name "*.md" | xargs sed -i "s|^docker\ compose|TAG=${{ github.event.inputs.tag }}\ docker\ compose|g"
-          find . -type f -name "*.yaml" \( -path "*/benchmark/*" -o -path "*/kubernetes/*" \) | xargs sed -i -E 's/(opea\/[A-Za-z0-9\-]*:)latest/\1${{ github.event.inputs.tag }}/g'
-          find . -type f -name "*.md" \( -path "*/benchmark/*" -o -path "*/kubernetes/*" \) | xargs sed -i -E 's/(opea\/[A-Za-z0-9\-]*:)latest/\1${{ github.event.inputs.tag }}/g'
+          IFS='.' read -r major minor patch <<< "${{ github.event.inputs.tag }}"
+          echo "VERSION_MAJOR ${major}"  > version.txt
+          echo "VERSION_MINOR ${minor}" >> version.txt
+          echo "VERSION_PATCH ${patch}" >> version.txt
 
       - name: Commit changes
         run: |

.github/workflows/manual-image-build.yml

@@ -0,0 +1,67 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Build specific images on manual event
+on:
+  workflow_dispatch:
+    inputs:
+      nodes:
+        default: "gaudi,xeon"
+        description: "Hardware to run test"
+        required: true
+        type: string
+      example:
+        default: "ChatQnA"
+        description: 'Build images belong to which example? [AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA,AvatarChatbot,Text2Image,WorkflowExecAgent,DBQnA,EdgeCraftRAG,GraphRAG]'
+        required: true
+        type: string
+      services:
+        default: "chatqna,chatqna-without-rerank"
+        description: 'Service list to build'
+        required: true
+        type: string
+      tag:
+        default: "latest"
+        description: "Tag to apply to images"
+        required: true
+        type: string
+      opea_branch:
+        default: "main"
+        description: 'OPEA branch for image build'
+        required: false
+        type: string
+      inject_commit:
+        default: false
+        description: "inject commit to docker images"
+        required: false
+        type: boolean
+
+jobs:
+  get-test-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      nodes: ${{ steps.get-matrix.outputs.nodes }}
+    steps:
+      - name: Create Matrix
+        id: get-matrix
+        run: |
+          nodes=($(echo ${{ inputs.nodes }} | tr ',' ' '))
+          nodes_json=$(printf '%s\n' "${nodes[@]}" | sort -u | jq -R '.' | jq -sc '.')
+          echo "nodes=$nodes_json" >> $GITHUB_OUTPUT
+
+  image-build:
+    needs: get-test-matrix
+    if: ${{ needs.get-test-matrix.outputs.nodes != '' }}
+    strategy:
+      matrix:
+        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
+      fail-fast: false
+    uses: ./.github/workflows/_example-workflow.yml
+    with:
+      node: ${{ matrix.node }}
+      example: ${{ inputs.example }}
+      services: ${{ inputs.services }}
+      tag: ${{ inputs.tag }}
+      opea_branch: ${{ inputs.opea_branch }}
+      inject_commit: ${{ inputs.inject_commit }}
+    secrets: inherit

.github/workflows/manual-reset-local-registry.yml

@@ -0,0 +1,61 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Clean up Local Registry on manual event
+on:
+  workflow_dispatch:
+    inputs:
+      nodes:
+        default: "gaudi,xeon"
+        description: "Hardware to clean up"
+        required: true
+        type: string
+
+env:
+  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
+
+jobs:
+  get-build-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      examples: ${{ steps.get-matrix.outputs.examples }}
+      nodes: ${{ steps.get-matrix.outputs.nodes }}
+    steps:
+    - name: Create Matrix
+      id: get-matrix
+      run: |
+        examples=($(echo ${EXAMPLES} | tr ',' ' '))
+        examples_json=$(printf '%s\n' "${examples[@]}" | sort -u | jq -R '.' | jq -sc '.')
+        echo "examples=$examples_json" >> $GITHUB_OUTPUT
+        nodes=($(echo ${{ inputs.nodes }} | tr ',' ' '))
+        nodes_json=$(printf '%s\n' "${nodes[@]}" | sort -u | jq -R '.' | jq -sc '.')
+        echo "nodes=$nodes_json" >> $GITHUB_OUTPUT
+
+  clean-up:
+    needs: get-build-matrix
+    if: ${{ needs.get-image-list.outputs.matrix != '' }}
+    strategy:
+      matrix:
+        node: ${{ fromJson(needs.get-build-matrix.outputs.nodes) }}
+      fail-fast: false
+    runs-on: "docker-build-${{ matrix.node }}"
+    steps:
+      - name: Clean Up Local Registry
+        run: |
+          echo "Cleaning up local registry on ${{ matrix.node }}"
+          bash /home/sdp/workspace/fully_registry_cleanup.sh
+          docker ps | grep registry
+
+  build:
+    needs: [get-build-matrix, clean-up]
+    if: ${{ needs.get-image-list.outputs.matrix != '' }}
+    strategy:
+      matrix:
+        example: ${{ fromJson(needs.get-build-matrix.outputs.examples) }}
+        node: ${{ fromJson(needs.get-build-matrix.outputs.nodes) }}
+      fail-fast: false
+    uses: ./.github/workflows/_example-workflow.yml
+    with:
+      node: ${{ matrix.node }}
+      example: ${{ matrix.example }}
+    secrets: inherit

.github/workflows/nightly-docker-build-publish.yml

@@ -0,0 +1,95 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Nightly build/publish latest docker images
+
+on:
+  schedule:
+    - cron: "30 14 * * 1-5" # UTC time
+  workflow_dispatch:
+
+env:
+  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
+  TAG: "latest"
+  PUBLISH_TAGS: "latest"
+
+jobs:
+  get-build-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      examples_json: ${{ steps.get-matrix.outputs.examples_json }}
+      EXAMPLES: ${{ steps.get-matrix.outputs.EXAMPLES }}
+      TAG: ${{ steps.get-matrix.outputs.TAG }}
+      PUBLISH_TAGS: ${{ steps.get-matrix.outputs.PUBLISH_TAGS }}
+    steps:
+      - name: Create Matrix
+        id: get-matrix
+        run: |
+          examples=($(echo ${EXAMPLES} | tr ',' ' '))
+          examples_json=$(printf '%s\n' "${examples[@]}" | sort -u | jq -R '.' | jq -sc '.')
+          echo "examples_json=$examples_json" >> $GITHUB_OUTPUT
+          echo "EXAMPLES=$EXAMPLES" >> $GITHUB_OUTPUT
+          echo "TAG=$TAG" >> $GITHUB_OUTPUT
+          echo "PUBLISH_TAGS=$PUBLISH_TAGS" >> $GITHUB_OUTPUT
+
+  build-comps-base:
+    needs: [get-build-matrix]
+    uses: ./.github/workflows/_build_comps_base_image.yml
+    with:
+      node: gaudi
+
+  build-images:
+    needs: [get-build-matrix, build-comps-base]
+    strategy:
+      matrix:
+        example: ${{ fromJSON(needs.get-build-matrix.outputs.examples_json) }}
+      fail-fast: false
+    uses: ./.github/workflows/_build_image.yml
+    with:
+      node: gaudi
+      example: ${{ matrix.example }}
+      inject_commit: true
+    secrets: inherit
+
+  test-example:
+    needs: [get-build-matrix]
+    if: ${{ needs.get-build-matrix.outputs.examples_json != '' }}
+    strategy:
+      matrix:
+        example: ${{ fromJSON(needs.get-build-matrix.outputs.examples_json) }}
+      fail-fast: false
+    uses: ./.github/workflows/_example-workflow.yml
+    with:
+      node: xeon
+      build: false
+      example: ${{ matrix.example }}
+      test_compose: true
+      inject_commit: true
+    secrets: inherit
+
+  get-image-list:
+    needs: [get-build-matrix]
+    uses: ./.github/workflows/_get-image-list.yml
+    with:
+      examples: ${{ needs.get-build-matrix.outputs.EXAMPLES }}
+
+  publish:
+    needs: [get-build-matrix, get-image-list, build-images]
+    if: always()
+    strategy:
+      matrix:
+        image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}
+      fail-fast: false
+    runs-on: "docker-build-gaudi"
+    steps:
+      - uses: docker/login-action@v3.2.0
+        with:
+          username: ${{ secrets.DOCKERHUB_USER }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Image Publish
+        uses: opea-project/validation/actions/image-publish@main
+        with:
+          local_image_ref: ${OPEA_IMAGE_REPO}opea/${{ matrix.image }}:${{ needs.get-build-matrix.outputs.TAG }}
+          image_name: opea/${{ matrix.image }}
+          publish_tags: ${{ needs.get-build-matrix.outputs.PUBLISH_TAGS }}

.github/workflows/pr-bum_list_check.yml

@@ -1,50 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Check Requirements
-
-on: [pull_request]
-
-jobs:
-  check-requirements:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout PR branch
-        uses: actions/checkout@v4
-
-      - name: Save PR requirements
-        run: |
-          find . -name "requirements.txt" -exec cat {} \; | \
-              grep -v '^\s*#' | \
-              grep -v '^\s*$' | \
-              grep -v '^\s*-' | \
-              sed 's/^\s*//' | \
-              awk -F'[>=<]' '{print $1}' | \
-              sort -u > pr-requirements.txt
-          cat pr-requirements.txt
-
-      - name: Checkout main branch
-        uses: actions/checkout@v4
-        with:
-          ref: main
-          path: main-branch
-
-      - name: Save main branch requirements
-        run: |
-          find ./main-branch -name "requirements.txt" -exec cat {} \; | \
-              grep -v '^\s*#' | \
-              grep -v '^\s*$' | \
-              grep -v '^\s*-' | \
-              sed 's/^\s*//' | \
-              awk -F'[>=<]' '{print $1}' | \
-              sort -u > main-requirements.txt
-          cat main-requirements.txt
-
-      - name: Compare requirements
-        run: |
-          comm -23 pr-requirements.txt main-requirements.txt > added-packages.txt
-          if [ -s added-packages.txt ]; then
-            echo "New packages found in PR:" && cat added-packages.txt
-          else
-            echo "No new packages found😊."
-          fi

.github/workflows/pr-chart-e2e.yml

@@ -0,0 +1,81 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: E2E Test with Helm Charts
+
+on:
+  pull_request_target:
+    branches: [main]
+    types: [opened, reopened, ready_for_review, synchronize] # added `ready_for_review` since draft is skipped
+    paths:
+      - "!**.md"
+      - "**/helm/**"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  job1:
+    name: Get-Test-Matrix
+    permissions:
+      contents: read
+      pull-requests: read
+    runs-on: ubuntu-latest
+    outputs:
+      run_matrix: ${{ steps.get-test-matrix.outputs.run_matrix }}
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+        with:
+          ref: "refs/pull/${{ github.event.number }}/merge"
+          fetch-depth: 0
+
+      - name: Get Test Matrix
+        id: get-test-matrix
+        run: |
+          set -x
+          echo "base_commit=${{ github.event.pull_request.base.sha }}"
+          base_commit=${{ github.event.pull_request.base.sha }}
+          merged_commit=$(git log -1 --format='%H')
+          values_files=$(git diff --name-only ${base_commit} ${merged_commit} | \
+          grep "values.yaml" | \
+          sort -u ) #CodeGen/kubernetes/helm/cpu-values.yaml
+          run_matrix="{\"include\":["
+          for values_file in ${values_files}; do
+            if [ -f "$values_file" ]; then
+              valuefile=$(basename "$values_file")   # cpu-values.yaml
+              example=$(echo "$values_file" | cut -d'/' -f1) # CodeGen
+              if [[ "$valuefile" == *"gaudi"* ]]; then
+                hardware="gaudi"
+              elif [[ "$valuefile" == *"rocm"* ]]; then
+                hardware="rocm"
+              elif [[ "$valuefile" == *"nv"* ]]; then
+                continue
+              else
+                hardware="xeon"
+              fi
+              echo "example=${example}, hardware=${hardware}, valuefile=${valuefile}"
+              if [[ $(echo ${run_matrix} | grep -c "{\"example\":\"${example}\",\"hardware\":\"${hardware}\"},") == 0 ]]; then
+                run_matrix="${run_matrix}{\"example\":\"${example}\",\"hardware\":\"${hardware}\"},"
+                echo "------------------ add one values file ------------------"
+              fi
+            fi
+          done
+          run_matrix="${run_matrix%,}"
+          run_matrix=$run_matrix"]}"
+          echo "run_matrix="${run_matrix}""
+          echo "run_matrix="${run_matrix}"" >> $GITHUB_OUTPUT
+
+  helm-chart-test:
+    needs: [job1]
+    if: always() && ${{ fromJSON(needs.job1.outputs.run_matrix).length != 0 }}
+    uses: ./.github/workflows/_helm-e2e.yml
+    strategy:
+      matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }}
+    with:
+      example: ${{ matrix.example }}
+      hardware: ${{ matrix.hardware }}
+      mode: "CI"
+    secrets: inherit

.github/workflows/pr-check-duplicated-image.yml

@@ -0,0 +1,40 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check Duplicated Images
+
+on:
+  pull_request:
+    branches: [main]
+    types: [opened, reopened, ready_for_review, synchronize]
+    paths:
+      - "**/docker_image_build/*.yaml"
+      - ".github/workflows/pr-check-duplicated-image.yml"
+      - ".github/workflows/scripts/check_duplicated_image.py"
+  workflow_dispatch:
+
+# If there is a new commit, the previous jobs will be canceled
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  check-duplicated-image:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - name: Check all the docker image build files
+        run: |
+          pip install PyYAML
+          cd ${{github.workspace}}
+          build_files=""
+          for f in `find . -path "*/docker_image_build/build.yaml"`; do
+              build_files="$build_files $f"
+          done
+          python3 .github/workflows/scripts/check_duplicated_image.py $build_files
+        shell: bash

.github/workflows/pr-code-scan.yml

@@ -34,6 +34,11 @@ jobs:
       - name: Checkout out Repo
         uses: actions/checkout@v4
 
+      - name: Check Dangerous Command Injection
+        uses: opea-project/validation/actions/check-cmd@main
+        with:
+          work_dir: ${{ github.workspace }}
+
       - name: Docker Build
         run: |
           docker build -f ${{ github.workspace }}/.github/workflows/docker/${{ env.DOCKER_FILE_NAME }}.dockerfile -t ${{ env.REPO_NAME }}:${{ env.REPO_TAG }} .

.github/workflows/pr-dependency-review.yml

@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 name: "Dependency Review"
-on: [pull_request]
+on: [pull_request_target]
 
 permissions:
   contents: read

.github/workflows/pr-docker-compose-e2e.yml

@@ -28,19 +28,20 @@ jobs:
     if: ${{ !github.event.pull_request.draft }}
     uses: ./.github/workflows/_get-test-matrix.yml
     with:
-      diff_excluded_files: '.github|*.md|*.txt|kubernetes|manifest|gmc|assets|benchmark'
+      diff_excluded_files: '\.github|\.md|\.txt|kubernetes|gmc|assets|benchmark'
 
   example-test:
     needs: [get-test-matrix]
+    if: ${{ needs.get-test-matrix.outputs.run_matrix != '' }}
     strategy:
       matrix: ${{ fromJSON(needs.get-test-matrix.outputs.run_matrix) }}
       fail-fast: false
-    if: ${{ !github.event.pull_request.draft }}
     uses: ./.github/workflows/_run-docker-compose.yml
     with:
       registry: "opea"
       tag: "ci"
       example: ${{ matrix.example }}
       hardware: ${{ matrix.hardware }}
-      diff_excluded_files: '.github|*.md|*.txt|kubernetes|manifest|gmc|assets|benchmark'
+      use_model_cache: true
+      diff_excluded_files: '\.github|\.md|\.txt|kubernetes|gmc|assets|benchmark'
     secrets: inherit

.github/workflows/pr-dockerfile-path-and-build-yaml-scan.yml

@@ -0,0 +1,109 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Compose file and dockerfile path checking
+
+on:
+  pull_request:
+    branches: [main]
+    types: [opened, reopened, ready_for_review, synchronize]
+
+jobs:
+  check-dockerfile-paths-in-README:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo GenAIExamples
+        uses: actions/checkout@v4
+
+      - name: Clone Repo GenAIComps
+        run: |
+          cd ..
+          git clone --depth 1 https://github.com/opea-project/GenAIComps.git
+
+      - name: Check for Missing Dockerfile Paths in GenAIComps
+        run: |
+          cd ${{github.workspace}}
+          miss="FALSE"
+          while IFS=: read -r file line content; do
+              dockerfile_path=$(echo "$content" | awk -F '-f ' '{print $2}' | awk '{print $1}')
+              if [[ ! -f "../GenAIComps/${dockerfile_path}" ]]; then
+                  miss="TRUE"
+                  echo "Missing Dockerfile: GenAIComps/${dockerfile_path} (Referenced in GenAIExamples/${file}:${line})"
+              fi
+          done < <(grep -Ern 'docker build .* -f comps/.+/Dockerfile' --include='*.md' .)
+
+
+          if [[ "$miss" == "TRUE" ]]; then
+            exit 1
+          fi
+
+        shell: bash
+
+  check-Dockerfile-in-build-yamls:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo GenAIExamples
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check Dockerfile path included in image build yaml
+        if: always()
+        run: |
+          set -e
+          shopt -s globstar
+          no_add="FALSE"
+          cd ${{github.workspace}}
+          Dockerfiles=$(realpath $(find ./ -name '*Dockerfile*' ! -path '*/tests/*'))
+          if [ -n "$Dockerfiles" ]; then
+            for dockerfile in $Dockerfiles; do
+              service=$(echo "$dockerfile" | awk -F '/GenAIExamples/' '{print $2}' | awk -F '/' '{print $2}')
+              cd ${{github.workspace}}/$service/docker_image_build
+              all_paths=$(realpath $(awk '  /context:/ { context = $2 }  /dockerfile:/ { dockerfile = $2; combined = context "/" dockerfile; gsub(/\/+/, "/", combined); if  (index(context, ".") > 0) {print combined}}' build.yaml) 2> /dev/null || true  )
+              if ! echo "$all_paths" | grep -q "$dockerfile"; then
+                echo "AR: Update $dockerfile to GenAIExamples/$service/docker_image_build/build.yaml. The yaml is used for release images build."
+                no_add="TRUE"
+              fi
+            done
+          fi
+
+          if [[ "$no_add" == "TRUE" ]]; then
+            exit 1
+          fi
+
+  check-image-and-service-names-in-build-yaml:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo GenAIExamples
+        uses: actions/checkout@v4
+
+      - name: Check name agreement in build.yaml
+        run: |
+          pip install ruamel.yaml
+          cd ${{github.workspace}}
+          consistency="TRUE"
+          build_yamls=$(find . -name 'build.yaml')
+          for build_yaml in $build_yamls; do
+            message=$(python3 .github/workflows/scripts/check-name-agreement.py "$build_yaml")
+            if [[ "$message" != *"consistent"* ]]; then
+              consistency="FALSE"
+              echo "Inconsistent service name and image name found in file $build_yaml."
+              echo "$message"
+            fi
+          done
+
+          if [[ "$consistency" == "FALSE" ]]; then
+            echo "Please ensure that the service and image names are consistent in build.yaml, otherwise we cannot guarantee that your image will be published correctly."
+            exit 1
+          fi
+
+        shell: bash

.github/workflows/pr-gmc-e2e.yaml.disabled

@@ -8,11 +8,10 @@ on:
     branches: ["main", "*rc"]
     types: [opened, reopened, ready_for_review, synchronize] # added `ready_for_review` since draft is skipped
     paths:
-      - "**/kubernetes/**/gmc/**"
+      - "**/kubernetes/gmc/**"
       - "**/tests/test_gmc**"
       - "!**.md"
       - "!**.txt"
-      - "!**/kubernetes/**/manifests/**"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
@@ -22,7 +21,7 @@ jobs:
   job1:
     uses: ./.github/workflows/_get-test-matrix.yml
     with:
-      diff_excluded_files: '.github|docker_compose|manifest|assets|*.md|*.txt'
+      diff_excluded_files: '\.github|docker_compose|assets|\.md|\.txt'
       test_mode: "gmc"
 
   gmc-test:

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

@@ -0,0 +1,141 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Check hyperlinks and relative path validity
+
+on:
+  pull_request:
+    branches: [main]
+    types: [opened, reopened, ready_for_review, synchronize]
+
+jobs:
+  check-the-validity-of-hyperlinks-in-README:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo GenAIExamples
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - 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 $NF}')"
+          if  [ -n "$changed_files" ]; then
+            for changed_file in $changed_files; do
+              # echo $changed_file
+              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file" | grep -Ev 'GenAIExamples/blob/main') || true
+              if [ -n "$url_lines" ]; then
+                for url_line in $url_lines; do
+                  # 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-)
+                  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: $url"
+                        fail="TRUE"
+                      fi
+                    fi
+                  fi
+                done
+              fi
+            done
+          else
+            echo "No changed .md file."
+          fi
+
+          if [[ "$fail" == "TRUE" ]]; then
+            exit 1
+          else
+            echo "All hyperlinks are valid."
+          fi
+        shell: bash
+
+  check-the-validity-of-relative-path:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clean up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Checkout Repo GenAIExamples
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Checking Relative Path Validity
+        run: |
+          cd ${{github.workspace}}
+          fail="FALSE"
+          repo_name=${{ github.event.pull_request.head.repo.full_name }}
+          branch="https://github.com/$repo_name/blob/${{ github.event.pull_request.head.ref }}"
+
+          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 $NF}')"
+          png_lines=$(grep -Eo '\]\([^)]+\)' --include='*.md' -r .|grep -Ev 'http')
+          if [ -n "$png_lines" ]; then
+            for png_line in $png_lines; do
+              refer_path=$(echo "$png_line"|cut -d':' -f1 | cut -d'/' -f2-)
+              png_path=$(echo "$png_line"|cut -d '(' -f2 | cut -d ')' -f1)
+
+              if [[ "${png_path:0:1}" == "/" ]]; then
+                check_path=$png_path
+              elif [[ "$png_path" == *#* ]]; then
+                relative_path=$(echo "$png_path" | cut -d '#' -f1)
+                if [ -n "$relative_path" ]; then
+                  check_path=$(dirname "$refer_path")/$relative_path
+                  png_path=$(echo "$png_path" | awk -F'#' '{print "#" $2}')
+                else
+                  check_path=$refer_path
+                fi
+              else
+                check_path=$(dirname "$refer_path")/$png_path
+              fi
+
+              if [ -e "$check_path" ]; then
+                real_path=$(realpath $check_path)
+                if [[ "$png_line" == *#* ]]; then
+                  if [ -n "changed_files" ] && echo "$changed_files" | grep -q "^${refer_path}$"; then
+                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIExamples||')$png_path
+                    response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
+                    if [ "$response" -ne 200 ]; then
+                      echo "**********Validation failed, 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"
+                        fail="TRUE"
+                      fi
+                    else
+                      echo "Validation succeed $png_line"
+                    fi
+                  fi
+                fi
+              else
+                echo "${{github.workspace}}/$refer_path:$png_path does not exist"
+                fail="TRUE"
+              fi
+            done
+          fi
+
+          if [[ "$fail" == "TRUE" ]]; then
+            exit 1
+          else
+            echo "All hyperlinks are valid."
+          fi
+        shell: bash

.github/workflows/pr-manifest-e2e.yml

@@ -1,40 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: E2E test with manifests
-
-on:
-  pull_request_target:
-    branches: ["main", "*rc"]
-    types: [opened, reopened, ready_for_review, synchronize] # added `ready_for_review` since draft is skipped
-    paths:
-      - "**/kubernetes/**/manifests/**"
-      - "**/tests/test_manifest**"
-      - "!**.md"
-      - "!**.txt"
-      - "!**/kubernetes/**/gmc/**"
-  workflow_dispatch:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  job1:
-    uses: ./.github/workflows/_get-test-matrix.yml
-    with:
-      diff_excluded_files: '.github|docker_compose|gmc|assets|*.md|*.txt|benchmark'
-      test_mode: "manifest"
-
-  run-example:
-    needs: job1
-    strategy:
-      matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }}
-      fail-fast: false
-    uses: ./.github/workflows/_example-workflow.yml
-    with:
-      node: ${{ matrix.hardware }}
-      example: ${{ matrix.example }}
-      tag: ${{ github.event.pull_request.head.sha }}
-      test_k8s: true
-    secrets: inherit

.github/workflows/pr-manifest-validate.yml

@@ -1,54 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Manifests Validate
-
-on:
-  pull_request:
-    branches: [main]
-    types: [opened, reopened, ready_for_review, synchronize] # added `ready_for_review` since draft is skipped
-    paths:
-      - "**/kubernetes/manifests/**"
-      - .github/workflows/manifest-validate.yml
-  workflow_dispatch:
-
-# If there is a new commit, the previous jobs will be canceled
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-env:
-  MANIFEST_DIR: "manifests"
-
-jobs:
-  manifests-validate:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout out Repo
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: changed files
-        id: changed_files
-        run: |
-          set -xe
-          changed_folder=$(git diff --name-only ${{ github.event.pull_request.base.sha }} ${{ github.event.pull_request.head.sha }} | \
-          grep "kubernetes/manifests" | grep -vE '.github|README.md|*.txt|*.sh' | cut -d'/' -f1 | sort -u )
-          echo "changed_folder: $changed_folder"
-          if [ -z "$changed_folder" ]; then
-              echo "No changes in manifests folder"
-              echo "SKIP=true" >> $GITHUB_OUTPUT
-              exit 0
-          fi
-          echo "SKIP=false" >> $GITHUB_OUTPUT
-          for folder in $changed_folder; do
-              folder_str="$folder_str $folder/kubernetes/manifests/"
-          done
-          echo "folder_str=$folder_str"
-          echo "folder_str=$folder_str" >> $GITHUB_ENV
-
-      - uses: docker://ghcr.io/yannh/kubeconform:latest
-        if: steps.changed_files.outputs.SKIP == 'false'
-        with:
-          args: "-summary -output json ${{env.folder_str}}"

.github/workflows/pr-path-detection.yml

@@ -1,156 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Check Paths and Hyperlinks
-
-on:
-  pull_request:
-    branches: [main]
-    types: [opened, reopened, ready_for_review, synchronize]
-
-jobs:
-  check-dockerfile-paths:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clean Up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Checkout Repo GenAIExamples
-        uses: actions/checkout@v4
-
-      - name: Clone Repo GenAIComps
-        run: |
-          cd ..
-          git clone https://github.com/opea-project/GenAIComps.git
-
-      - name: Check for Missing Dockerfile Paths in GenAIComps
-        run: |
-          cd ${{github.workspace}}
-          miss="FALSE"
-          while IFS=: read -r file line content; do
-              dockerfile_path=$(echo "$content" | awk -F '-f ' '{print $2}' | awk '{print $1}')
-              if [[ ! -f "../GenAIComps/${dockerfile_path}" ]]; then
-                  miss="TRUE"
-                  echo "Missing Dockerfile: GenAIComps/${dockerfile_path} (Referenced in GenAIExamples/${file}:${line})"
-              fi
-          done < <(grep -Ern 'docker build .* -f comps/.+/Dockerfile' --include='*.md' .)
-
-
-          if [[ "$miss" == "TRUE" ]]; then
-            exit 1
-          fi
-
-        shell: bash
-
-  check-the-validity-of-hyperlinks-in-README:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clean Up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Checkout Repo GenAIExamples
-        uses: actions/checkout@v4
-
-      - name: Check the Validity of Hyperlinks
-        run: |
-          cd ${{github.workspace}}
-          fail="FALSE"
-          url_lines=$(grep -Eo '\]\(http[s]?://[^)]+\)' --include='*.md' -r .)
-          if [ -n "$url_lines" ]; then
-            for url_line in $url_lines; do
-              url=$(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")
-              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: $url"
-                  fail="TRUE"
-                fi
-              fi
-            done
-          fi
-
-          if [[ "$fail" == "TRUE" ]]; then
-            exit 1
-          else
-            echo "All hyperlinks are valid."
-          fi
-        shell: bash
-
-  check-the-validity-of-relative-path:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Clean up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Checkout Repo GenAIExamples
-        uses: actions/checkout@v4
-
-      - name: Checking Relative Path Validity
-        run: |
-          cd ${{github.workspace}}
-          fail="FALSE"
-          repo_name=${{ github.event.pull_request.head.repo.full_name }}
-          if [ "$(echo "$repo_name"|cut -d'/' -f1)" != "opea-project" ]; then
-            owner=$(echo "${{ github.event.pull_request.head.repo.full_name }}" |cut -d'/' -f1)
-            branch="https://github.com/$owner/GenAIExamples/tree/${{ github.event.pull_request.head.ref }}"
-          else
-            branch="https://github.com/opea-project/GenAIExamples/blob/${{ github.event.pull_request.head.ref }}"
-          fi
-          link_head="https://github.com/opea-project/GenAIExamples/blob/main"
-          png_lines=$(grep -Eo '\]\([^)]+\)' --include='*.md' -r .|grep -Ev 'http')
-          if [ -n "$png_lines" ]; then
-            for png_line in $png_lines; do
-              refer_path=$(echo "$png_line"|cut -d':' -f1 | cut -d'/' -f2-)
-              png_path=$(echo "$png_line"|cut -d '(' -f2 | cut -d ')' -f1)
-              if [[ "${png_path:0:1}" == "/" ]]; then
-                check_path=${{github.workspace}}$png_path
-              elif [[ "${png_path:0:1}" == "#" ]]; then
-                check_path=${{github.workspace}}/$refer_path$png_path
-              else
-                check_path=${{github.workspace}}/$(dirname "$refer_path")/$png_path
-              fi
-              real_path=$(realpath $check_path)
-              if [ $? -ne 0 ]; then
-                echo "Path $png_path in file ${{github.workspace}}/$refer_path does not exist"
-                fail="TRUE"
-              else
-                url=$link_head$(echo "$real_path" | sed 's|.*/GenAIExamples||')
-                response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url")
-                if [ "$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 "Retry failed. Check branch ${{ github.event.pull_request.head.ref }}"
-                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIExamples||')
-                    response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
-                    if [ "$response" -ne 200 ]; then
-                      echo "**********Validation failed, try again**********"
-                      response_retry=$(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"
-                        fail="TRUE"
-                      fi
-                    else
-                      echo "Check branch ${{ github.event.pull_request.head.ref }} successfully."
-                    fi
-                  fi
-                fi
-              fi
-            done
-          fi
-
-          if [[ "$fail" == "TRUE" ]]; then
-            exit 1
-          else
-            echo "All hyperlinks are valid."
-          fi
-        shell: bash

.github/workflows/push-image-build.yml

@@ -8,8 +8,9 @@ on:
     branches: [ 'main' ]
     paths:
       - "**.py"
-      - "**Dockerfile"
-  workflow_dispatch:
+      - "**Dockerfile*"
+      - "**docker_image_build/build.yaml"
+      - "**/ui/**"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}-on-push
@@ -19,17 +20,16 @@ jobs:
   job1:
     uses: ./.github/workflows/_get-test-matrix.yml
     with:
-      test_mode: "docker_image_build/build.yaml"
+      test_mode: "docker_image_build"
 
   image-build:
     needs: job1
+    if: ${{ needs.job1.outputs.run_matrix != '{"include":[]}' }}
     strategy:
-      matrix:
-        example: ${{ fromJSON(needs.job1.outputs.run_matrix).include.*.example }}
-        node: ["gaudi","xeon"]
+      matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }}
       fail-fast: false
     uses: ./.github/workflows/_example-workflow.yml
     with:
-      node: ${{ matrix.node }}
+      node: ${{ matrix.hardware }}
       example: ${{ matrix.example }}
     secrets: inherit

.github/workflows/push-infra-issue-creation.yml

@@ -40,7 +40,7 @@ jobs:
       - name: Create Issue
         uses: daisy-ycguo/create-issue-action@stable
         with:
-          token: ${{ secrets.Infra_Issue_Token }}
+          token: ${{ secrets.ACTION_TOKEN }}
           owner: opea-project
           repo: GenAIInfra
           title: |
@@ -54,6 +54,6 @@ jobs:
 
             ${{ env.changed_files }}
 
-            Please verify if the helm charts and manifests need to be changed accordingly.
+            Please verify if the helm charts need to be changed accordingly.
 
             > This issue was created automatically by CI.

.github/workflows/scripts/check-name-agreement.py

@@ -0,0 +1,46 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import argparse
+
+from ruamel.yaml import YAML
+
+
+def parse_yaml_file(file_path):
+    yaml = YAML()
+    with open(file_path, "r") as file:
+        data = yaml.load(file)
+    return data
+
+
+def check_service_image_consistency(data):
+    inconsistencies = []
+    for service_name, service_details in data.get("services", {}).items():
+        image_name = service_details.get("image", "")
+        # Extract the image name part after the last '/'
+        image_name_part = image_name.split("/")[-1].split(":")[0]
+        # Check if the service name is a substring of the image name part
+        if service_name not in image_name_part:
+            # Get the line number of the service name
+            line_number = service_details.lc.line + 1
+            inconsistencies.append((service_name, image_name, line_number))
+    return inconsistencies
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Check service name and image name consistency in a YAML file.")
+    parser.add_argument("file_path", type=str, help="The path to the YAML file.")
+    args = parser.parse_args()
+
+    data = parse_yaml_file(args.file_path)
+
+    inconsistencies = check_service_image_consistency(data)
+    if inconsistencies:
+        for service_name, image_name, line_number in inconsistencies:
+            print(f"Service name: {service_name}, Image name: {image_name}, Line number: {line_number}")
+    else:
+        print("All consistent")
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/scripts/check_duplicated_image.py

@@ -0,0 +1,79 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import argparse
+import os.path
+import subprocess
+import sys
+
+import yaml
+
+images = {}
+dockerfiles = {}
+errors = []
+
+
+def check_docker_compose_build_definition(file_path):
+    with open(file_path, "r") as f:
+        data = yaml.load(f, Loader=yaml.FullLoader)
+        for service in data["services"]:
+            if "build" in data["services"][service] and "image" in data["services"][service]:
+                bash_command = "echo " + data["services"][service]["image"]
+                image = (
+                    subprocess.run(["bash", "-c", bash_command], check=True, capture_output=True)
+                    .stdout.decode("utf-8")
+                    .strip()
+                )
+                build = data["services"][service]["build"]
+                context = build.get("context", "")
+                dockerfile = os.path.normpath(
+                    os.path.join(os.path.dirname(file_path), context, build.get("dockerfile", ""))
+                )
+                if not os.path.isfile(dockerfile):
+                    # dockerfile not exists in the current repo context, assume it's in 3rd party context
+                    dockerfile = os.path.normpath(os.path.join(context, build.get("dockerfile", "")))
+                item = {"file_path": file_path, "service": service, "dockerfile": dockerfile, "image": image}
+                if image in images and dockerfile != images[image]["dockerfile"]:
+                    errors.append(
+                        f"ERROR: !!! Found Conflicts !!!\n"
+                        f"Image: {image}, Dockerfile: {dockerfile}, defined in Service: {service}, File: {file_path}\n"
+                        f"Image: {image}, Dockerfile: {images[image]['dockerfile']}, defined in Service: {images[image]['service']}, File: {images[image]['file_path']}"
+                    )
+                else:
+                    # print(f"Add Image: {image} Dockerfile: {dockerfile}")
+                    images[image] = item
+
+                if dockerfile in dockerfiles and image != dockerfiles[dockerfile]["image"]:
+                    errors.append(
+                        f"WARNING: Different images using the same Dockerfile\n"
+                        f"Dockerfile: {dockerfile}, Image: {image}, defined in Service: {service}, File: {file_path}\n"
+                        f"Dockerfile: {dockerfile}, Image: {dockerfiles[dockerfile]['image']}, defined in Service: {dockerfiles[dockerfile]['service']}, File: {dockerfiles[dockerfile]['file_path']}"
+                    )
+                else:
+                    dockerfiles[dockerfile] = item
+
+
+def parse_arg():
+    parser = argparse.ArgumentParser(
+        description="Check for conflicts in image build definition in docker-compose.yml files"
+    )
+    parser.add_argument("files", nargs="+", help="list of files to be checked")
+    return parser.parse_args()
+
+
+def main():
+    args = parse_arg()
+    for file_path in args.files:
+        check_docker_compose_build_definition(file_path)
+    print("SUCCESS: No Conlicts Found.")
+    if errors:
+        for error in errors:
+            print(error)
+        sys.exit(1)
+    else:
+        print("SUCCESS: No Conflicts Found.")
+    return 0
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/scripts/codeScan/hadolint.sh

@@ -7,7 +7,7 @@ source /GenAIExamples/.github/workflows/scripts/change_color
 log_dir=/GenAIExamples/.github/workflows/scripts/codeScan
 ERROR_WARN=false
 
-find . -type f \( -name "Dockerfile*" \) -print -exec hadolint --ignore DL3006 --ignore DL3007 --ignore DL3008 --ignore DL3013 {} \; > ${log_dir}/hadolint.log
+find . -type f \( -name "Dockerfile*" \) -print -exec hadolint --ignore DL3006 --ignore DL3007 --ignore DL3008 --ignore DL3013 --ignore DL3018 --ignore DL3016 {} \; > ${log_dir}/hadolint.log
 
 if [[ $(grep -c "error" ${log_dir}/hadolint.log) != 0 ]]; then
     $BOLD_RED && echo "Error!! Please Click on the artifact button to download and check error details." && $RESET

.github/workflows/scripts/docker_compose_clean_up.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# The test machine used by several opea projects, so the test scripts can't use `docker compose down` to clean up
+# the all the containers, ports and networks directly.
+# So we need to use the following script to minimize the impact of the clean up.
+
+test_case=${test_case:-"test_compose_on_gaudi.sh"}
+hardware=${hardware:-"gaudi"}
+flag=${test_case%_on_*}
+flag=${flag#test_}
+yaml_file=$(find . -type f -wholename "*${hardware}/${flag}.yaml")
+echo $yaml_file
+
+case "$1" in
+    containers)
+        echo "Stop and remove all containers used by the services in $yaml_file ..."
+        containers=$(cat $yaml_file | grep container_name | cut -d':' -f2)
+        for container_name in $containers; do
+            cid=$(docker ps -aq --filter "name=$container_name")
+            if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
+        done
+        ;;
+    ports)
+        echo "Release all ports used by the services in $yaml_file ..."
+        pip install jq yq
+        ports=$(yq '.services[].ports[] | split(":")[0]' $yaml_file | grep -o '[0-9a-zA-Z_-]\+')
+        echo "All ports list..."
+        echo "$ports"
+        for port in $ports; do
+          if [[ $port =~ [a-zA-Z_-] ]]; then
+            echo "Search port value $port from the test case..."
+            port_fix=$(grep -E "export $port=" tests/$test_case | cut -d'=' -f2)
+            if [[ "$port_fix" == "" ]]; then
+              echo "Can't find the port value from the test case, use the default value in yaml..."
+              port_fix=$(yq '.services[].ports[]' $yaml_file | grep $port | cut -d':' -f2 |  grep -o '[0-9a-zA-Z]\+')
+            fi
+            port=$port_fix
+          fi
+          if [[ $port =~ [0-9] ]]; then
+            if [[ $port == 5000 ]]; then
+              echo "Error: Port 5000 is used by local docker registry, please DO NOT use it in docker compose deployment!!!"
+              exit 1
+            fi
+            echo "Check port $port..."
+            cid=$(docker ps --filter "publish=${port}" --format "{{.ID}}")
+            if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && echo "release $port"; fi
+          fi
+        done
+        ;;
+    *)
+        echo "Unknown function: $1"
+        ;;
+esac

.github/workflows/scripts/get_test_matrix.sh

@@ -9,16 +9,28 @@ set -e
 changed_files=$changed_files
 test_mode=$test_mode
 run_matrix="{\"include\":["
-hardware_list="xeon gaudi" # current support hardware list
 
 examples=$(printf '%s\n' "${changed_files[@]}" | grep '/' | cut -d'/' -f1 | sort -u)
 for example in ${examples}; do
+    if [[ ! -d $WORKSPACE/$example ]]; then continue; fi
     cd $WORKSPACE/$example
     if [[ ! $(find . -type f | grep ${test_mode}) ]]; then continue; fi
+    cd tests
+    ls -l
+    if [[ "$test_mode" == "docker_image_build" ]]; then
+        hardware_list="gaudi xeon"
+    else
+        find_name="test_${test_mode}*_on_*.sh"
+        hardware_list=$(find . -type f -name "${find_name}" | cut -d/ -f2 | cut -d. -f1 | awk -F'_on_' '{print $2}'| sort -u)
+    fi
+    echo -e "Test supported hardware list: \n${hardware_list}"
 
     run_hardware=""
-    if [[ $(printf '%s\n' "${changed_files[@]}" | grep ${example} | cut -d'/' -f2 | grep -E '*.py|Dockerfile*|ui|docker_image_build' ) ]]; then
-        # run test on all hardware if megaservice or ui code change
+    if [[ $(printf '%s\n' "${changed_files[@]}" | grep ${example} | cut -d'/' -f2 | grep -E '\.py|Dockerfile*|ui|docker_image_build' ) ]]; then
+        echo "run test on all hardware if megaservice or ui code change..."
+        run_hardware=$hardware_list
+    elif [[ $(printf '%s\n' "${changed_files[@]}" | grep ${example} | grep 'tests'| cut -d'/' -f3 | grep -vE '^test_|^_test' ) ]]; then
+        echo "run test on all hardware if common test scripts change..."
         run_hardware=$hardware_list
     else
         for hardware in ${hardware_list}; do

.github/workflows/scripts/k8s-utils.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-#set -xe
+set -e
 
 function dump_pod_log() {
     pod_name=$1
@@ -12,7 +12,7 @@ function dump_pod_log() {
     kubectl describe pod $pod_name -n $namespace
     echo "-----------------------------------"
     echo "#kubectl logs $pod_name -n $namespace"
-    kubectl logs $pod_name -n $namespace
+    kubectl logs $pod_name -n $namespace --all-containers --prefix=true
     echo "-----------------------------------"
 }
 
@@ -44,8 +44,13 @@ function dump_pods_status() {
 
 function dump_all_pod_logs() {
     namespace=$1
+    echo "------SUMMARY of POD STATUS in NS $namespace------"
+    kubectl get pods -n $namespace -o wide
+    echo "------SUMMARY of SVC STATUS in NS $namespace------"
+    kubectl get services -n $namespace -o wide
+    echo "------SUMMARY of endpoint STATUS in NS $namespace------"
+    kubectl get endpoints -n $namespace -o wide
     echo "-----DUMP POD STATUS AND LOG in NS $namespace------"
-
     pods=$(kubectl get pods -n $namespace -o jsonpath='{.items[*].metadata.name}')
     for pod_name in $pods
     do

.github/workflows/weekly-example-test.yml

@@ -0,0 +1,55 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Weekly test all examples on multiple HWs
+
+on:
+  schedule:
+    - cron: "30 2 * * 6" # UTC time
+  workflow_dispatch:
+
+env:
+  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
+  NODES: "gaudi,xeon,rocm,arc"
+
+jobs:
+  get-test-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      examples: ${{ steps.get-matrix.outputs.examples }}
+      nodes: ${{ steps.get-matrix.outputs.nodes }}
+    steps:
+      - name: Create Matrix
+        id: get-matrix
+        run: |
+          examples=($(echo ${EXAMPLES} | tr ',' ' '))
+          examples_json=$(printf '%s\n' "${examples[@]}" | sort -u | jq -R '.' | jq -sc '.')
+          echo "examples=$examples_json" >> $GITHUB_OUTPUT
+          nodes=($(echo ${NODES} | tr ',' ' '))
+          nodes_json=$(printf '%s\n' "${nodes[@]}" | sort -u | jq -R '.' | jq -sc '.')
+          echo "nodes=$nodes_json" >> $GITHUB_OUTPUT
+
+  build-comps-base:
+    needs: [get-test-matrix]
+    strategy:
+      matrix:
+        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
+    uses: ./.github/workflows/_build_comps_base_image.yml
+    with:
+      node: ${{ matrix.node }}
+
+  run-examples:
+    needs: [get-test-matrix, build-comps-base]
+    strategy:
+      matrix:
+        example: ${{ fromJson(needs.get-test-matrix.outputs.examples) }}
+        node: ${{ fromJson(needs.get-test-matrix.outputs.nodes) }}
+      fail-fast: false
+    uses: ./.github/workflows/_example-workflow.yml
+    with:
+      node: ${{ matrix.node }}
+      example: ${{ matrix.example }}
+      build: true
+      test_compose: true
+      test_helmchart: true
+    secrets: inherit

.github/workflows/weekly-update-images.yml

@@ -1,11 +1,9 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-name: Weekly update base images and 3rd party images
+name: Weekly update 3rd party images
 
 on:
-  schedule:
-    - cron: "0 0 * * 0"
   workflow_dispatch:
 
 permissions:
@@ -16,8 +14,8 @@ jobs:
   freeze-images:
     runs-on: ubuntu-latest
     env:
-      USER_NAME: "NeuralChatBot"
-      USER_EMAIL: "grp_neural_chat_bot@intel.com"
+      USER_NAME: "CICD-at-OPEA"
+      USER_EMAIL: "CICD@opea.dev"
       BRANCH_NAME: "update_images_tag"
     steps:
       - name: Checkout repository

.gitignore

@@ -5,4 +5,4 @@
 **/playwright/.cache/
 **/test-results/
 
-__pycache__/
+__pycache__/

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: end-of-file-fixer
         files: (.*\.(py|md|rst|yaml|yml|json|ts|js|html|svelte|sh))$
@@ -18,8 +18,6 @@ repos:
               SearchQnA/ui/svelte/tsconfig.json|
               DocSum/ui/svelte/tsconfig.json
           )$
-      - id: check-yaml
-        args: [--allow-multiple-documents]
       - id: debug-statements
       - id: requirements-txt-fixer
       - id: trailing-whitespace
@@ -76,12 +74,12 @@ repos:
         name: Unused noqa
 
   - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+    rev: 6.0.1
     hooks:
       - id: isort
 
   - repo: https://github.com/PyCQA/docformatter
-    rev: v1.7.5
+    rev: 06907d0
     hooks:
       - id: docformatter
         args: [
@@ -102,21 +100,21 @@ repos:
           - prettier@3.2.5
 
   - repo: https://github.com/psf/black.git
-    rev: 24.4.2
+    rev: 25.1.0
     hooks:
       - id: black
         files: (.*\.py)$
 
   - repo: https://github.com/asottile/blacken-docs
-    rev: 1.18.0
+    rev: 1.19.1
     hooks:
       - id: blacken-docs
         args: [--line-length=120, --skip-errors]
         additional_dependencies:
-          - black==24.4.2
+          - black==24.10.0
 
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
       - id: codespell
         args: [-w]
@@ -124,7 +122,7 @@ repos:
           - tomli
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.0
+    rev: v0.11.4
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix, --no-cache]

.prettierignore

@@ -1 +1 @@
-**/kubernetes/
+**/kubernetes/

.set_env.sh

@@ -0,0 +1,16 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+#
+#To anounce the version of the codes, please create a version.txt and have following format.
+#VERSION_MAJOR 1
+#VERSION_MINOR 0
+#VERSION_PATCH 0
+
+VERSION_FILE="version.txt"
+if [ -f $VERSION_FILE ]; then
+    VER_OPEA_MAJOR=$(grep "VERSION_MAJOR" $VERSION_FILE | cut -d " " -f 2)
+    VER_OPEA_MINOR=$(grep "VERSION_MINOR" $VERSION_FILE | cut -d " " -f 2)
+    VER_OPEA_PATCH=$(grep "VERSION_PATCH" $VERSION_FILE | cut -d " " -f 2)
+    export TAG=$VER_OPEA_MAJOR.$VER_OPEA_MINOR
+    echo OPEA Version:$TAG
+fi

AgentQnA/README.md

@@ -1,106 +1,302 @@
 # Agents for Question Answering
 
+## Table of contents
+
+1. [Overview](#overview)
+2. [Deploy with Docker](#deploy-with-docker)
+3. [How to interact with the agent system with UI](#how-to-interact-with-the-agent-system-with-ui)
+4. [Validate Services](#validate-services)
+5. [Register Tools](#how-to-register-other-tools-with-the-ai-agent)
+6. [Monitoring and Tracing](#monitor-and-tracing)
+
 ## Overview
 
-This example showcases a hierarchical multi-agent system for question-answering applications. The architecture diagram is shown below. The supervisor agent interfaces with the user and dispatch tasks to the worker agent and other tools to gather information and come up with answers. The worker agent uses the retrieval tool to generate answers to the queries posted by the supervisor agent. Other tools used by the supervisor agent may include APIs to interface knowledge graphs, SQL databases, external knowledge bases, etc.
-![Architecture Overview](assets/agent_qna_arch.png)
+This example showcases a hierarchical multi-agent system for question-answering applications. The architecture diagram below shows a supervisor agent that interfaces with the user and dispatches tasks to two worker agents to gather information and come up with answers. The worker RAG agent uses the retrieval tool to retrieve relevant documents from a knowledge base - a vector database. The worker SQL agent retrieves relevant data from a SQL database. Although not included in this example by default, other tools such as a web search tool or a knowledge graph query tool can be used by the supervisor agent to gather information from additional sources.
+![Architecture Overview](assets/img/agent_qna_arch.png)
 
-### Why Agent for question answering?
+The AgentQnA example is implemented using the component-level microservices defined in [GenAIComps](https://github.com/opea-project/GenAIComps). The flow chart below shows the information flow between different microservices for this example.
 
-1. Improve relevancy of retrieved context.
-   Agent can rephrase user queries, decompose user queries, and iterate to get the most relevant context for answering user's questions. Compared to conventional RAG, RAG agent can significantly improve the correctness and relevancy of the answer.
-2. Use tools to get additional knowledge.
-   For example, knowledge graphs and SQL databases can be exposed as APIs for Agents to gather knowledge that may be missing in the retrieval vector database.
-3. Hierarchical agent can further improve performance.
-   Expert worker agents, such as retrieval agent, knowledge graph agent, SQL agent, etc., can provide high-quality output for different aspects of a complex query, and the supervisor agent can aggregate the information together to provide a comprehensive answer.
+```mermaid
+---
+config:
+  flowchart:
+    nodeSpacing: 400
+    rankSpacing: 100
+    curve: linear
+  themeVariables:
+    fontSize: 50px
+---
+flowchart LR
+    %% Colors %%
+    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
+    classDef invisible fill:transparent,stroke:transparent;
 
-### Roadmap
+    %% Subgraphs %%
+    subgraph DocIndexRetriever-MegaService["DocIndexRetriever MegaService "]
+        direction LR
+        EM([Embedding MicroService]):::blue
+        RET([Retrieval MicroService]):::blue
+        RER([Rerank MicroService]):::blue
+    end
+    subgraph UserInput[" User Input "]
+        direction LR
+        a([User Input Query]):::orchid
+        Ingest([Ingest data]):::orchid
+    end
+    AG_REACT([Agent MicroService - react]):::blue
+    AG_RAG([Agent MicroService - rag]):::blue
+    AG_SQL([Agent MicroService - sql]):::blue
+    LLM_gen{{LLM Service <br>}}
+    DP([Data Preparation MicroService]):::blue
+    TEI_RER{{Reranking service<br>}}
+    TEI_EM{{Embedding service <br>}}
+    VDB{{Vector DB<br><br>}}
+    R_RET{{Retriever service <br>}}
 
-- v0.9: Worker agent uses open-source websearch tool (duckduckgo), agents use OpenAI GPT-4o-mini as llm backend.
-- v1.0: Worker agent uses OPEA retrieval megaservice as tool.
-- v1.0 or later: agents use open-source llm backend.
-- v1.1 or later: add safeguards
 
-## Getting started
 
-1. Build agent docker image </br>
-   First, clone the opea GenAIComps repo
+    %% Questions interaction
+    direction LR
+    a[User Input Query] --> AG_REACT
+    AG_REACT --> AG_RAG
+    AG_REACT --> AG_SQL
+    AG_RAG --> DocIndexRetriever-MegaService
+    EM ==> RET
+    RET ==> RER
+    Ingest[Ingest data] --> DP
 
-   ```
-   export WORKDIR=<your-work-directory>
-   cd $WORKDIR
-   git clone https://github.com/opea-project/GenAIComps.git
-   ```
+    %% Embedding service flow
+    direction LR
+    AG_RAG <-.-> LLM_gen
+    AG_SQL <-.-> LLM_gen
+    AG_REACT <-.-> LLM_gen
+    EM <-.-> TEI_EM
+    RET <-.-> R_RET
+    RER <-.-> TEI_RER
 
-   Then build the agent docker image. Both the supervisor agent and the worker agent will use the same docker image, but when we launch the two agents we will specify different strategies and register different tools.
+    direction TB
+    %% Vector DB interaction
+    R_RET <-.-> VDB
+    DP <-.-> VDB
 
-   ```
-   cd GenAIComps
-   docker build -t opea/agent-langchain:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/agent/langchain/Dockerfile .
-   ```
-
-2. Launch tool services </br>
-   In this example, we will use some of the mock APIs provided in the Meta CRAG KDD Challenge to demonstrate the benefits of gaining additional context from mock knowledge graphs.
-
-   ```
-   docker run -d -p=8080:8000 docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
-   ```
-
-3. Set up environment for this example </br>
-   First, clone this repo
-
-   ```
-   cd $WORKDIR
-   git clone https://github.com/opea-project/GenAIExamples.git
-   ```
-
-   Second, set up env vars
-
-   ```
-   export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-   # optional: OPANAI_API_KEY
-   export OPENAI_API_KEY=<your-openai-key>
-   ```
-
-4. Launch agent services</br>
-   The configurations of the supervisor agent and the worker agent are defined in the docker-compose yaml file. We currently use openAI GPT-4o-mini as LLM, and we plan to add support for llama3.1-70B-instruct (served by TGI-Gaudi) in a subsequent release.
-   To use openai llm, run command below.
-
-   ```
-   cd docker_compose/intel/cpu/xeon
-   bash launch_agent_service_openai.sh
-   ```
-
-## Validate services
-
-First look at logs of the agent docker containers:
 
 ```
-docker logs docgrader-agent-endpoint
+
+### Why should AI Agents be used for question-answering?
+
+1. **Improve relevancy of retrieved context.**
+   RAG agents can rephrase user queries, decompose user queries, and iterate to get the most relevant context for answering a user's question. Compared to conventional RAG, RAG agents significantly improve the correctness and relevancy of the answer because of the iterations it goes through.
+2. **Expand scope of skills.**
+   The supervisor agent interacts with multiple worker agents that specialize in different skills (e.g., retrieve documents, write SQL queries, etc.). Thus, it can answer questions with different methods.
+3. **Hierarchical multi-agents improve performance.**
+   Expert worker agents, such as RAG agents and SQL agents, can provide high-quality output for different aspects of a complex query, and the supervisor agent can aggregate the information to provide a comprehensive answer. If only one agent is used and all tools are provided to this single agent, it can lead to large overhead or not use the best tool to provide accurate answers.
+
+## Deploy with docker
+
+### 1. Set up environment </br>
+
+#### First, clone the `GenAIExamples` repo.
+
+```bash
+export WORKDIR=<your-work-directory>
+cd $WORKDIR
+git clone https://github.com/opea-project/GenAIExamples.git
 ```
 
+#### Second, set up environment variables.
+
+##### 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"
+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> #  to avoid redownloading 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>
+```
+
+#### Third, set up environment variables for the selected hardware using the corresponding `set_env.sh`
+
+##### 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.
+
+#### Launch on Gaudi
+
+On Gaudi, `meta-llama/Meta-Llama-3.3-70B-Instruct` will be served using vllm. The command below will launch the multi-agent system with the `DocIndexRetriever` as the retrieval tool for the Worker RAG agent.
+
+```bash
+cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
+docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml up -d
+```
+
+> **Note**: To enable the web search tool, skip this step and proceed to the "[Optional] Web Search Tool Support" section.
+
+To enable Open Telemetry Tracing, compose.telemetry.yaml file need to be merged along with default compose.yaml file.
+Gaudi example with Open Telemetry feature:
+
+```bash
+cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
+docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml -f compose.telemetry.yaml up -d
+```
+
+##### [Optional] Web Search Tool Support
+
+<details>
+<summary> Instructions </summary>
+A web search tool is supported in this example and can be enabled by running docker compose with the `compose.webtool.yaml` file.
+The Google Search API is used. Follow the [instructions](https://python.langchain.com/docs/integrations/tools/google_search) to create an API key and enable the Custom Search API on a Google account. The environment variables `GOOGLE_CSE_ID` and `GOOGLE_API_KEY` need to be set.
+
+```bash
+cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
+export GOOGLE_CSE_ID="YOUR_ID"
+export GOOGLE_API_KEY="YOUR_API_KEY"
+docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml -f compose.webtool.yaml up -d
+```
+
+</details>
+
+#### Launch on Xeon
+
+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.
+
+```bash
+cd  $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool/
+bash run_ingest_data.sh
+```
+
+> **Note**: This is a one-time operation.
+
+## How to interact with the agent system with UI
+
+The UI microservice is launched in the previous step with the other microservices.
+To see the UI, open a web browser to `http://${ip_address}:5173` to access the UI. Note the `ip_address` here is the host IP of the UI microservice.
+
+1. 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. 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)
+
+## [Optional] Deploy using Helm Charts
+
+Refer to the [AgentQnA helm chart](./kubernetes/helm/README.md) for instructions on deploying AgentQnA on Kubernetes.
+
+## Validate Services
+
+1. First look at logs for each of the agent docker containers:
+
+```bash
+# worker RAG agent
+docker logs rag-agent-endpoint
+
+# worker SQL agent
+docker logs sql-agent-endpoint
+
+# supervisor agent
 docker logs react-agent-endpoint
 ```
 
-You should see something like "HTTP server setup successful" if the docker containers are started successfully.</p>
+Look for the message "HTTP server setup successful" to confirm the agent docker container has started successfully.</p>
 
-Second, validate worker agent:
+2. Use python to validate each agent is working properly:
 
-```
-curl http://${ip_address}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Most recent album by Taylor Swift"
-    }'
+```bash
+# RAG worker agent
+python $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "Tell me about Michael Jackson song Thriller" --agent_role "worker" --ext_port 9095
+
+# SQL agent
+python $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "How many employees in company" --agent_role "worker" --ext_port 9096
+
+# supervisor agent: this will test a two-turn conversation
+python $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --agent_role "supervisor" --ext_port 9090
 ```
 
-Third, validate supervisor agent:
+## How to register other tools with the AI agent
 
-```
-curl http://${ip_address}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Most recent album by Taylor Swift"
-    }'
-```
+The [tools](./tools) folder contains YAML and Python files for additional tools for the supervisor and worker agents. Refer to the "Provide your own tools" section in the instructions [here](https://github.com/opea-project/GenAIComps/tree/main/comps/agent/src/README.md) to add tools and customize the AI agents.
 
-## How to register your own tools with agent
+## Monitor and Tracing
 
-You can take a look at the tools yaml and python files in this example. For more details, please refer to the "Provide your own tools" section in the instructions [here](https://github.com/opea-project/GenAIComps/tree/main/comps/agent/langchain#5-customize-agent-strategy).
+Follow [OpenTelemetry OPEA Guide](https://opea-project.github.io/latest/tutorial/OpenTelemetry/OpenTelemetry_OPEA_Guide.html) to understand how to use OpenTelemetry tracing and metrics in OPEA.  
+For AgentQnA specific tracing and metrics monitoring, follow [OpenTelemetry on AgentQnA](https://opea-project.github.io/latest/tutorial/OpenTelemetry/deploy/AgentQnA.html) section.

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

@@ -0,0 +1,342 @@
+# Build Mega Service of AgentQnA on AMD ROCm GPU
+
+## Build Docker Images
+
+### 1. Build Docker Image
+
+- #### Create application install directory and go to it:
+
+  ```bash
+  mkdir ~/agentqna-install && cd agentqna-install
+  ```
+
+- #### Clone the repository GenAIExamples (the default repository branch "main" is used here):
+
+  ```bash
+  git clone https://github.com/opea-project/GenAIExamples.git
+  ```
+
+  If you need to use a specific branch/tag of the GenAIExamples repository, then (v1.3 replace with its own value):
+
+  ```bash
+  git clone https://github.com/opea-project/GenAIExamples.git && cd GenAIExamples && git checkout v1.3
+  ```
+
+  We remind you that when using a specific version of the code, you need to use the README from this version:
+
+- #### Go to build directory:
+
+  ```bash
+  cd ~/agentqna-install/GenAIExamples/AgentQnA/docker_image_build
+  ```
+
+- Cleaning up the GenAIComps repository if it was previously cloned in this directory.
+  This is necessary if the build was performed earlier and the GenAIComps folder exists and is not empty:
+
+  ```bash
+  echo Y | rm -R GenAIComps
+  ```
+
+- #### Clone the repository GenAIComps (the default repository branch "main" is used here):
+
+```bash
+git clone https://github.com/opea-project/GenAIComps.git
+```
+
+We remind you that when using a specific version of the code, you need to use the README from this version.
+
+- #### Setting the list of images for the build (from the build file.yaml)
+
+  If you want to deploy a vLLM-based or TGI-based application, then the set of services is installed as follows:
+
+  #### vLLM-based application
+
+  ```bash
+  service_list="vllm-rocm agent agent-ui"
+  ```
+
+  #### TGI-based application
+
+  ```bash
+  service_list="agent agent-ui"
+  ```
+
+- #### Optional. Pull TGI Docker Image (Do this if you want to use TGI)
+
+  ```bash
+  docker pull ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+  ```
+
+- #### Build Docker Images
+
+  ```bash
+  docker compose -f build.yaml build ${service_list} --no-cache
+  ```
+
+- #### Build DocIndexRetriever Docker Images
+
+  ```bash
+  cd ~/agentqna-install/GenAIExamples/DocIndexRetriever/docker_image_build/
+  git clone https://github.com/opea-project/GenAIComps.git
+  service_list="doc-index-retriever dataprep embedding retriever reranking"
+  docker compose -f build.yaml build ${service_list} --no-cache
+  ```
+
+- #### Pull DocIndexRetriever Docker Images
+
+  ```bash
+  docker pull redis/redis-stack:7.2.0-v9
+  docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+  ```
+
+  After the build, we check the list of images with the command:
+
+  ```bash
+  docker image ls
+  ```
+
+  The list of images should include:
+
+  ##### vLLM-based application:
+
+  - opea/vllm-rocm:latest
+  - opea/agent:latest
+  - redis/redis-stack:7.2.0-v9
+  - ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+  - opea/embedding:latest
+  - opea/retriever:latest
+  - opea/reranking:latest
+  - opea/doc-index-retriever:latest
+
+  ##### TGI-based application:
+
+  - ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+  - opea/agent:latest
+  - redis/redis-stack:7.2.0-v9
+  - ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
+  - opea/embedding:latest
+  - opea/retriever:latest
+  - opea/reranking:latest
+  - opea/doc-index-retriever:latest
+
+---
+
+## Deploy the AgentQnA Application
+
+### Docker Compose Configuration for AMD GPUs
+
+To enable GPU support for AMD GPUs, the following configuration is added to the Docker Compose file:
+
+- compose_vllm.yaml - for vLLM-based application
+- compose.yaml - for TGI-based
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri:/dev/dri
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+This configuration forwards all available GPUs to the container. To use a specific GPU, specify its `cardN` and `renderN` device IDs. For example:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/card0:/dev/dri/card0
+  - /dev/dri/render128:/dev/dri/render128
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+**How to Identify GPU Device IDs:**
+Use AMD GPU driver utilities to determine the correct `cardN` and `renderN` IDs for your GPU.
+
+### Set deploy environment variables
+
+#### Setting variables in the operating system environment:
+
+```bash
+### Replace the string 'server_address' with your local server IP address
+export host_ip='server_address'
+### Replace the string 'your_huggingfacehub_token' with your HuggingFacehub repository access token.
+export HUGGINGFACEHUB_API_TOKEN='your_huggingfacehub_token'
+### Replace the string 'your_langchain_api_key' with your LANGCHAIN API KEY.
+export LANGCHAIN_API_KEY='your_langchain_api_key'
+export LANGCHAIN_TRACING_V2=""
+```
+
+### Start the services:
+
+#### If you use vLLM
+
+```bash
+cd ~/agentqna-install/GenAIExamples/AgentQnA/docker_compose/amd/gpu/rocm
+bash launch_agent_service_vllm_rocm.sh
+```
+
+#### If you use TGI
+
+```bash
+cd ~/agentqna-install/GenAIExamples/AgentQnA/docker_compose/amd/gpu/rocm
+bash launch_agent_service_tgi_rocm.sh
+```
+
+All containers should be running and should not restart:
+
+##### If you use vLLM:
+
+- dataprep-redis-server
+- doc-index-retriever-server
+- embedding-server
+- rag-agent-endpoint
+- react-agent-endpoint
+- redis-vector-db
+- reranking-tei-xeon-server
+- retriever-redis-server
+- sql-agent-endpoint
+- tei-embedding-server
+- tei-reranking-server
+- vllm-service
+
+##### If you use TGI:
+
+- dataprep-redis-server
+- doc-index-retriever-server
+- embedding-server
+- rag-agent-endpoint
+- react-agent-endpoint
+- redis-vector-db
+- reranking-tei-xeon-server
+- retriever-redis-server
+- sql-agent-endpoint
+- tei-embedding-server
+- tei-reranking-server
+- tgi-service
+
+---
+
+## Validate the Services
+
+### 1. Validate the vLLM/TGI Service
+
+#### If you use vLLM:
+
+```bash
+DATA='{"model": "Intel/neural-chat-7b-v3-3t", '\
+'"messages": [{"role": "user", "content": "What is Deep Learning?"}], "max_tokens": 256}'
+
+curl http://${HOST_IP}:${VLLM_SERVICE_PORT}/v1/chat/completions \
+  -X POST \
+  -d "$DATA" \
+  -H 'Content-Type: application/json'
+```
+
+Checking the response from the service. The response should be similar to JSON:
+
+```json
+{
+  "id": "chatcmpl-142f34ef35b64a8db3deedd170fed951",
+  "object": "chat.completion",
+  "created": 1742270316,
+  "model": "Intel/neural-chat-7b-v3-3",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "",
+        "tool_calls": []
+      },
+      "logprobs": null,
+      "finish_reason": "length",
+      "stop_reason": null
+    }
+  ],
+  "usage": { "prompt_tokens": 66, "total_tokens": 322, "completion_tokens": 256, "prompt_tokens_details": null },
+  "prompt_logprobs": null
+}
+```
+
+If the service response has a meaningful response in the value of the "choices.message.content" key,
+then we consider the vLLM service to be successfully launched
+
+#### If you use TGI:
+
+```bash
+DATA='{"inputs":"What is Deep Learning?",'\
+'"parameters":{"max_new_tokens":256,"do_sample": true}}'
+
+curl http://${HOST_IP}:${TGI_SERVICE_PORT}/generate \
+  -X POST \
+  -d "$DATA" \
+  -H 'Content-Type: application/json'
+```
+
+Checking the response from the service. The response should be similar to JSON:
+
+```json
+{
+  "generated_text": " "
+}
+```
+
+If the service response has a meaningful response in the value of the "generated_text" key,
+then we consider the TGI service to be successfully launched
+
+### 2. Validate Agent Services
+
+#### Validate Rag Agent Service
+
+```bash
+export agent_port=${WORKER_RAG_AGENT_PORT}
+prompt="Tell me about Michael Jackson song Thriller"
+python3 ~/agentqna-install/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt" --agent_role "worker" --ext_port $agent_port
+```
+
+The response must contain the meaningful text of the response to the request from the "prompt" variable
+
+#### Validate Sql Agent Service
+
+```bash
+export agent_port=${WORKER_SQL_AGENT_PORT}
+prompt="How many employees are there in the company?"
+python3 ~/agentqna-install/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt" --agent_role "worker" --ext_port $agent_port
+```
+
+The answer should make sense - "8 employees in the company"
+
+#### Validate React (Supervisor) Agent Service
+
+```bash
+export agent_port=${SUPERVISOR_REACT_AGENT_PORT}
+python3 ~/agentqna-install/GenAIExamples/AgentQnA/tests/test.py --agent_role "supervisor" --ext_port $agent_port --stream
+```
+
+The response should contain "Iron Maiden"
+
+### 3. Stop application
+
+#### If you use vLLM
+
+```bash
+cd ~/agentqna-install/GenAIExamples/AgentQnA/docker_compose/amd/gpu/rocm
+bash stop_agent_service_vllm_rocm.sh
+```
+
+#### If you use TGI
+
+```bash
+cd ~/agentqna-install/GenAIExamples/AgentQnA/docker_compose/amd/gpu/rocm
+bash stop_agent_service_tgi_rocm.sh
+```

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

@@ -0,0 +1,124 @@
+# Copyright (C) 2025 Advanced Micro Devices, Inc.
+
+services:
+  tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:3.0.0-rocm
+    container_name: tgi-service
+    ports:
+      - "${TGI_SERVICE_PORT-8085}:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/data"
+    environment:
+      no_proxy: ${no_proxy}
+      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}
+    shm_size: 32g
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    cap_add:
+      - SYS_PTRACE
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+    ipc: host
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192
+
+  worker-rag-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: rag-agent-endpoint
+    volumes:
+      - "${TOOLSET_PATH}:/home/user/tools/"
+    ports:
+      - "${WORKER_RAG_AGENT_PORT:-9095}:9095"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: rag_agent_llama
+      with_memory: false
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: tgi
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: false
+      tools: /home/user/tools/worker_agent_tools.yaml
+      require_human_feedback: false
+      RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
+      LANGCHAIN_PROJECT: "opea-worker-agent-service"
+      port: 9095
+
+  worker-sql-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: sql-agent-endpoint
+    volumes:
+      - "${WORKDIR}/tests/Chinook_Sqlite.sqlite:/home/user/chinook-db/Chinook_Sqlite.sqlite:rw"
+    ports:
+      - "${WORKER_SQL_AGENT_PORT:-9096}:9096"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: sql_agent_llama
+      with_memory: false
+      db_name: ${db_name}
+      db_path: ${db_path}
+      use_hints: false
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: vllm
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: false
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      port: 9096
+
+  supervisor-react-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: react-agent-endpoint
+    depends_on:
+      - worker-rag-agent
+    volumes:
+      - "${TOOLSET_PATH}:/home/user/tools/"
+    ports:
+      - "${SUPERVISOR_REACT_AGENT_PORT:-9090}:9090"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: react_llama
+      with_memory: true
+      recursion_limit: ${recursion_limit_supervisor}
+      llm_engine: tgi
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: true
+      tools: /home/user/tools/supervisor_agent_tools.yaml
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
+      LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
+      CRAG_SERVER: ${CRAG_SERVER}
+      WORKER_AGENT_URL: ${WORKER_AGENT_URL}
+      SQL_AGENT_URL: ${SQL_AGENT_URL}
+      port: 9090

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

@@ -0,0 +1,128 @@
+# Copyright (C) 2025 Advanced Micro Devices, Inc.
+
+services:
+  vllm-service:
+    image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
+    container_name: vllm-service
+    ports:
+      - "${VLLM_SERVICE_PORT:-8081}:8011"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+      WILM_USE_TRITON_FLASH_ATTENTION: 0
+      PYTORCH_JIT: 0
+    volumes:
+      - "${MODEL_CACHE:-./data}:/data"
+    shm_size: 20G
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/:/dev/dri/
+    cap_add:
+      - SYS_PTRACE
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+      - apparmor=unconfined
+    command: "--model ${VLLM_LLM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 4 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
+    ipc: host
+
+  worker-rag-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: rag-agent-endpoint
+    volumes:
+      - ${TOOLSET_PATH}:/home/user/tools/
+    ports:
+      - "${WORKER_RAG_AGENT_PORT:-9095}:9095"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: rag_agent_llama
+      with_memory: false
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: vllm
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: false
+      tools: /home/user/tools/worker_agent_tools.yaml
+      require_human_feedback: false
+      RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
+      LANGCHAIN_PROJECT: "opea-worker-agent-service"
+      port: 9095
+
+  worker-sql-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: sql-agent-endpoint
+    volumes:
+      - "${WORKDIR}/tests/Chinook_Sqlite.sqlite:/home/user/chinook-db/Chinook_Sqlite.sqlite:rw"
+    ports:
+      - "${WORKER_SQL_AGENT_PORT:-9096}:9096"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: sql_agent_llama
+      with_memory: false
+      db_name: ${db_name}
+      db_path: ${db_path}
+      use_hints: false
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: vllm
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: false
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      port: 9096
+
+  supervisor-react-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: react-agent-endpoint
+    depends_on:
+      - worker-rag-agent
+    volumes:
+      - ${TOOLSET_PATH}:/home/user/tools/
+    ports:
+      - "${SUPERVISOR_REACT_AGENT_PORT:-9090}:9090"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: react_llama
+      with_memory: true
+      recursion_limit: ${recursion_limit_supervisor}
+      llm_engine: vllm
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: true
+      tools: /home/user/tools/supervisor_agent_tools.yaml
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
+      LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
+      LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
+      CRAG_SERVER: ${CRAG_SERVER}
+      WORKER_AGENT_URL: ${WORKER_AGENT_URL}
+      SQL_AGENT_URL: ${SQL_AGENT_URL}
+      port: 9090

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

@@ -0,0 +1,87 @@
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+# Before start script:
+# export host_ip="your_host_ip_or_host_name"
+# export HUGGINGFACEHUB_API_TOKEN="your_huggingface_api_token"
+# export LANGCHAIN_API_KEY="your_langchain_api_key"
+# export LANGCHAIN_TRACING_V2=""
+
+# Set server hostname or IP address
+export ip_address=${host_ip}
+
+# Set services IP ports
+export TGI_SERVICE_PORT="18110"
+export WORKER_RAG_AGENT_PORT="18111"
+export WORKER_SQL_AGENT_PORT="18112"
+export SUPERVISOR_REACT_AGENT_PORT="18113"
+export CRAG_SERVER_PORT="18114"
+
+export WORKPATH=$(dirname "$PWD")
+export WORKDIR=${WORKPATH}/../../../
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export HF_CACHE_DIR="./data"
+export MODEL_CACHE="./data"
+export TOOLSET_PATH=${WORKPATH}/../../../tools/
+export recursion_limit_worker=12
+export LLM_ENDPOINT_URL=http://${ip_address}:${TGI_SERVICE_PORT}
+export temperature=0.01
+export max_new_tokens=512
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export LANGCHAIN_API_KEY=${LANGCHAIN_API_KEY}
+export LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2}
+export db_name=Chinook
+export db_path="sqlite:////home/user/chinook-db/Chinook_Sqlite.sqlite"
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export CRAG_SERVER=http://${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=${HUGGINGFACEHUB_API_TOKEN}
+export no_proxy=${no_proxy}
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+export REDIS_URL="redis://${host_ip}:6379"
+export INDEX_NAME="rag-redis"
+export RERANK_TYPE="tei"
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export RERANK_SERVICE_HOST_IP=${host_ip}
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+
+echo ${WORKER_RAG_AGENT_PORT} > ${WORKPATH}/WORKER_RAG_AGENT_PORT_tmp
+echo ${WORKER_SQL_AGENT_PORT} > ${WORKPATH}/WORKER_SQL_AGENT_PORT_tmp
+echo ${SUPERVISOR_REACT_AGENT_PORT} > ${WORKPATH}/SUPERVISOR_REACT_AGENT_PORT_tmp
+echo ${CRAG_SERVER_PORT} > ${WORKPATH}/CRAG_SERVER_PORT_tmp
+
+echo "Downloading chinook data..."
+echo Y | rm -R chinook-database
+git clone https://github.com/lerocha/chinook-database.git
+echo Y | rm -R ../../../../../AgentQnA/tests/Chinook_Sqlite.sqlite
+cp chinook-database/ChinookDatabase/DataSources/Chinook_Sqlite.sqlite ../../../../../AgentQnA/tests
+
+docker compose -f ../../../../../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml up -d
+docker compose -f compose.yaml up -d
+
+n=0
+until [[ "$n" -ge 100 ]]; do
+    docker logs tgi-service > ${WORKPATH}/tgi_service_start.log
+    if grep -q Connected ${WORKPATH}/tgi_service_start.log; then
+        break
+    fi
+    sleep 10s
+    n=$((n+1))
+done
+
+echo "Starting CRAG server"
+docker run -d --runtime=runc --name=kdd-cup-24-crag-service -p=${CRAG_SERVER_PORT}:8000 docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0

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

@@ -0,0 +1,88 @@
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+# Before start script:
+# export host_ip="your_host_ip_or_host_name"
+# export HUGGINGFACEHUB_API_TOKEN="your_huggingface_api_token"
+# export LANGCHAIN_API_KEY="your_langchain_api_key"
+# export LANGCHAIN_TRACING_V2=""
+
+# Set server hostname or IP address
+export ip_address=${host_ip}
+
+# Set services IP ports
+export VLLM_SERVICE_PORT="18110"
+export WORKER_RAG_AGENT_PORT="18111"
+export WORKER_SQL_AGENT_PORT="18112"
+export SUPERVISOR_REACT_AGENT_PORT="18113"
+export CRAG_SERVER_PORT="18114"
+
+export WORKPATH=$(dirname "$PWD")
+export WORKDIR=${WORKPATH}/../../../
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export VLLM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export HF_CACHE_DIR="./data"
+export MODEL_CACHE="./data"
+export TOOLSET_PATH=${WORKPATH}/../../../tools/
+export recursion_limit_worker=12
+export LLM_ENDPOINT_URL=http://${ip_address}:${VLLM_SERVICE_PORT}
+export LLM_MODEL_ID=${VLLM_LLM_MODEL_ID}
+export temperature=0.01
+export max_new_tokens=512
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export LANGCHAIN_API_KEY=${LANGCHAIN_API_KEY}
+export LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2}
+export db_name=Chinook
+export db_path="sqlite:////home/user/chinook-db/Chinook_Sqlite.sqlite"
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+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 no_proxy=${no_proxy}
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+export REDIS_URL="redis://${host_ip}:6379"
+export INDEX_NAME="rag-redis"
+export RERANK_TYPE="tei"
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export RERANK_SERVICE_HOST_IP=${host_ip}
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+
+echo ${WORKER_RAG_AGENT_PORT} > ${WORKPATH}/WORKER_RAG_AGENT_PORT_tmp
+echo ${WORKER_SQL_AGENT_PORT} > ${WORKPATH}/WORKER_SQL_AGENT_PORT_tmp
+echo ${SUPERVISOR_REACT_AGENT_PORT} > ${WORKPATH}/SUPERVISOR_REACT_AGENT_PORT_tmp
+echo ${CRAG_SERVER_PORT} > ${WORKPATH}/CRAG_SERVER_PORT_tmp
+
+echo "Downloading chinook data..."
+echo Y | rm -R chinook-database
+git clone https://github.com/lerocha/chinook-database.git
+echo Y | rm -R ../../../../../AgentQnA/tests/Chinook_Sqlite.sqlite
+cp chinook-database/ChinookDatabase/DataSources/Chinook_Sqlite.sqlite ../../../../../AgentQnA/tests
+
+docker compose -f ../../../../../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml up -d
+docker compose -f compose_vllm.yaml up -d
+
+n=0
+until [[ "$n" -ge 500 ]]; do
+    docker logs vllm-service >& "${WORKPATH}"/vllm-service_start.log
+    if grep -q "Application startup complete" "${WORKPATH}"/vllm-service_start.log; then
+        break
+    fi
+    sleep 20s
+    n=$((n+1))
+done
+
+echo "Starting CRAG server"
+docker run -d --runtime=runc --name=kdd-cup-24-crag-service -p=${CRAG_SERVER_PORT}:8000 docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0

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

@@ -0,0 +1,62 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+WORKPATH=$(dirname "$PWD")/..
+export ip_address=${host_ip}
+export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export AGENTQNA_TGI_IMAGE=ghcr.io/huggingface/text-generation-inference:2.4.1-rocm
+export AGENTQNA_TGI_SERVICE_PORT="19001"
+
+# LLM related environment variables
+export AGENTQNA_CARD_ID="card1"
+export AGENTQNA_RENDER_ID="renderD136"
+export HF_CACHE_DIR=${HF_CACHE_DIR}
+ls $HF_CACHE_DIR
+export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export NUM_SHARDS=4
+export LLM_ENDPOINT_URL="http://${ip_address}:${AGENTQNA_TGI_SERVICE_PORT}"
+export temperature=0.01
+export max_new_tokens=512
+
+# agent related environment variables
+export AGENTQNA_WORKER_AGENT_SERVICE_PORT="9095"
+export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export WORKER_AGENT_URL="http://${ip_address}:${AGENTQNA_WORKER_AGENT_SERVICE_PORT}/v1/chat/completions"
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export CRAG_SERVER=http://${ip_address}:18881
+
+export AGENTQNA_FRONTEND_PORT="15557"
+
+#retrieval_tool
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+export REDIS_URL="redis://${host_ip}:26379"
+export INDEX_NAME="rag-redis"
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export RERANK_SERVICE_HOST_IP=${host_ip}
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete"
+
+echo "Removing chinook data..."
+echo Y | rm -R chinook-database
+if [ -d "chinook-database" ]; then
+    rm -rf chinook-database
+fi
+echo "Chinook data removed!"
+
+echo "Stopping CRAG server"
+docker rm kdd-cup-24-crag-service --force
+
+echo "Stopping Agent services"
+docker compose -f compose.yaml down
+
+echo "Stopping Retrieval services"
+docker compose -f ../../../../../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml down

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

@@ -0,0 +1,84 @@
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+
+# Before start script:
+# export host_ip="your_host_ip_or_host_name"
+# export HUGGINGFACEHUB_API_TOKEN="your_huggingface_api_token"
+# export LANGCHAIN_API_KEY="your_langchain_api_key"
+# export LANGCHAIN_TRACING_V2=""
+
+# Set server hostname or IP address
+export ip_address=${host_ip}
+
+# Set services IP ports
+export VLLM_SERVICE_PORT="18110"
+export WORKER_RAG_AGENT_PORT="18111"
+export WORKER_SQL_AGENT_PORT="18112"
+export SUPERVISOR_REACT_AGENT_PORT="18113"
+export CRAG_SERVER_PORT="18114"
+
+export WORKPATH=$(dirname "$PWD")
+export WORKDIR=${WORKPATH}/../../../
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export VLLM_LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
+export HF_CACHE_DIR="./data"
+export MODEL_CACHE="./data"
+export TOOLSET_PATH=${WORKPATH}/../../../tools/
+export recursion_limit_worker=12
+export LLM_ENDPOINT_URL=http://${ip_address}:${VLLM_SERVICE_PORT}
+export LLM_MODEL_ID=${VLLM_LLM_MODEL_ID}
+export temperature=0.01
+export max_new_tokens=512
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export LANGCHAIN_API_KEY=${LANGCHAIN_API_KEY}
+export LANGCHAIN_TRACING_V2=${LANGCHAIN_TRACING_V2}
+export db_name=Chinook
+export db_path="sqlite:////home/user/chinook-db/Chinook_Sqlite.sqlite"
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export CRAG_SERVER=http://${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=${HUGGINGFACEHUB_API_TOKEN}
+export no_proxy=${no_proxy}
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+export REDIS_URL="redis://${host_ip}:6379"
+export INDEX_NAME="rag-redis"
+export RERANK_TYPE="tei"
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export RERANK_SERVICE_HOST_IP=${host_ip}
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+
+echo ${WORKER_RAG_AGENT_PORT} > ${WORKPATH}/WORKER_RAG_AGENT_PORT_tmp
+echo ${WORKER_SQL_AGENT_PORT} > ${WORKPATH}/WORKER_SQL_AGENT_PORT_tmp
+echo ${SUPERVISOR_REACT_AGENT_PORT} > ${WORKPATH}/SUPERVISOR_REACT_AGENT_PORT_tmp
+echo ${CRAG_SERVER_PORT} > ${WORKPATH}/CRAG_SERVER_PORT_tmp
+
+echo "Removing chinook data..."
+echo Y | rm -R chinook-database
+if [ -d "chinook-database" ]; then
+    rm -rf chinook-database
+fi
+echo "Chinook data removed!"
+
+echo "Stopping CRAG server"
+docker rm kdd-cup-24-crag-service --force
+
+echo "Stopping Agent services"
+docker compose -f compose_vllm.yaml down
+
+echo "Stopping Retrieval services"
+docker compose -f ../../../../../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml down

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

@@ -0,0 +1,3 @@
+# Single node on-prem deployment with Docker Compose on Xeon Scalable processors
+
+This example showcases a hierarchical multi-agent system for question-answering applications. To deploy the example on Xeon, OpenAI LLM models via API calls are used. For instructions, refer to the deployment guide [here](../../../../README.md).

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

@@ -2,11 +2,10 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  worker-docgrader-agent:
-    image: opea/agent-langchain:latest
-    container_name: docgrader-agent-endpoint
+  worker-rag-agent:
+    image: opea/agent:latest
+    container_name: rag-agent-endpoint
     volumes:
-      - ${WORKDIR}/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9095:9095"
@@ -14,13 +13,14 @@ services:
     environment:
       ip_address: ${ip_address}
       strategy: rag_agent
+      with_memory: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: openai
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       model: ${model}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      streaming: false
+      stream: false
       tools: /home/user/tools/worker_agent_tools.yaml
       require_human_feedback: false
       RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
@@ -32,26 +32,56 @@ services:
       LANGCHAIN_PROJECT: "opea-worker-agent-service"
       port: 9095
 
+  worker-sql-agent:
+    image: opea/agent:latest
+    container_name: sql-agent-endpoint
+    volumes:
+      - ${WORKDIR}/GenAIExamples/AgentQnA/tests:/home/user/chinook-db # SQL database
+    ports:
+      - "9096:9096"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: sql_agent
+      with_memory: false
+      db_name: ${db_name}
+      db_path: ${db_path}
+      use_hints: false
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: openai
+      OPENAI_API_KEY: ${OPENAI_API_KEY}
+      model: ${model}
+      temperature: 0
+      max_new_tokens: ${max_new_tokens}
+      stream: false
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      port: 9096
 
   supervisor-react-agent:
-    image: opea/agent-langchain:latest
+    image: opea/agent:latest
     container_name: react-agent-endpoint
+    depends_on:
+      - worker-rag-agent
+      - worker-sql-agent
     volumes:
-      - ${WORKDIR}/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9090:9090"
     ipc: host
     environment:
       ip_address: ${ip_address}
-      strategy: react_langgraph
+      strategy: react_llama
+      with_memory: true
       recursion_limit: ${recursion_limit_supervisor}
       llm_engine: openai
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       model: ${model}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      streaming: false
+      stream: true
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}
@@ -62,4 +92,21 @@ services:
       LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
       CRAG_SERVER: $CRAG_SERVER
       WORKER_AGENT_URL: $WORKER_AGENT_URL
+      SQL_AGENT_URL: $SQL_AGENT_URL
       port: 9090
+  mock-api:
+    image: docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
+    container_name: mock-api
+    ports:
+      - "8080:8000"
+    ipc: host
+  agent-ui:
+    image: opea/agent-ui
+    container_name: agent-ui
+    ports:
+      - "5173:8080"
+    ipc: host
+
+networks:
+  default:
+    driver: bridge

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/launch_agent_service_openai.sh

@@ -1,16 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-export ip_address=$(hostname -I | awk '{print $1}')
-export recursion_limit_worker=12
-export recursion_limit_supervisor=10
-export model="gpt-4o-mini-2024-07-18"
-export temperature=0
-export max_new_tokens=512
-export OPENAI_API_KEY=${OPENAI_API_KEY}
-export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
-export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
-export CRAG_SERVER=http://${ip_address}:8080
-
-docker compose -f compose_openai.yaml up -d

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

@@ -0,0 +1,57 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+pushd "../../../../../" > /dev/null
+source .set_env.sh
+popd > /dev/null
+
+if [[ -z "${WORKDIR}" ]]; then
+	echo "Please set WORKDIR environment variable"
+	exit 0
+fi
+echo "WORKDIR=${WORKDIR}"
+export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+export ip_address=$(hostname -I | awk '{print $1}')
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export model="gpt-4o-mini-2024-07-18"
+export temperature=0
+export max_new_tokens=4096
+export OPENAI_API_KEY=${OPENAI_API_KEY}
+export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
+export SQL_AGENT_URL="http://${ip_address}:9096/v1/chat/completions"
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export CRAG_SERVER=http://${ip_address}:8080
+export db_name=Chinook
+export db_path="sqlite:////home/user/chinook-db/Chinook_Sqlite.sqlite"
+
+if [ ! -f $WORKDIR/GenAIExamples/AgentQnA/tests/Chinook_Sqlite.sqlite ]; then
+    echo "Download Chinook_Sqlite!"
+    wget  -O $WORKDIR/GenAIExamples/AgentQnA/tests/Chinook_Sqlite.sqlite  https://github.com/lerocha/chinook-database/releases/download/v1.4.5/Chinook_Sqlite.sqlite
+fi
+
+# retriever
+export host_ip=$(hostname -I | awk '{print $1}')
+export HF_CACHE_DIR=${HF_CACHE_DIR}
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export no_proxy=${no_proxy}
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+export REDIS_URL="redis://${host_ip}:6379"
+export INDEX_NAME="rag-redis"
+export RERANK_TYPE="tei"
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export RERANK_SERVICE_HOST_IP=${host_ip}
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+
+
+export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui"

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

@@ -0,0 +1,3 @@
+# Single node on-prem deployment AgentQnA on Gaudi
+
+This example showcases a hierarchical multi-agent system for question-answering applications. To deploy the example on Gaudi using open-source LLMs, refer to the deployment guide [here](../../../../README.md).

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

@@ -0,0 +1,93 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  tei-embedding-service:
+    command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
+  tei-reranking-service:
+    command: --model-id ${RERANK_MODEL_ID} --auto-truncate --otlp-endpoint $OTEL_EXPORTER_OTLP_TRACES_ENDPOINT
+  jaeger:
+    image: jaegertracing/all-in-one:1.67.0
+    container_name: jaeger
+    ports:
+      - "16686:16686"
+      - "4317:4317"
+      - "4318:4318"
+      - "9411:9411"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      COLLECTOR_ZIPKIN_HOST_PORT: 9411
+    restart: unless-stopped
+  prometheus:
+    image: prom/prometheus:v2.52.0
+    container_name: prometheus
+    user: root
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus/prometheus.yaml
+      - ./prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yaml'
+    ports:
+      - '9091:9090'
+    ipc: host
+    restart: unless-stopped
+  grafana:
+    image: grafana/grafana:11.0.0
+    container_name: grafana
+    volumes:
+      - ./grafana_data:/var/lib/grafana
+      - ./grafana/dashboards:/var/lib/grafana/dashboards
+      - ./grafana/provisioning:/etc/grafana/provisioning
+    user: root
+    environment:
+      GF_SECURITY_ADMIN_PASSWORD: admin
+      GF_RENDERING_CALLBACK_URL: http://grafana:3000/
+      GF_LOG_FILTERS: rendering:debug
+    depends_on:
+      - prometheus
+    ports:
+      - '3000:3000'
+    ipc: host
+    restart: unless-stopped
+  node-exporter:
+    image: prom/node-exporter
+    container_name: node-exporter
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - --collector.filesystem.ignored-mount-points
+      - "^/(sys|proc|dev|host|etc|rootfs/var/lib/docker/containers|rootfs/var/lib/docker/overlay2|rootfs/run/docker/netns|rootfs/var/lib/docker/aufs)($$|/)"
+    ports:
+      - 9100:9100
+    restart: always
+    deploy:
+      mode: global
+  gaudi-exporter:
+    image: vault.habana.ai/gaudi-metric-exporter/metric-exporter:1.19.2-32
+    container_name: gaudi-exporter
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+      - /dev:/dev
+    ports:
+      - 41612:41611
+    restart: always
+    deploy:
+      mode: global
+  worker-rag-agent:
+    environment:
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
+  worker-sql-agent:
+    environment:
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}
+  supervisor-react-agent:
+    environment:
+      - TELEMETRY_ENDPOINT=${TELEMETRY_ENDPOINT}

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

@@ -0,0 +1,9 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  supervisor-react-agent:
+    environment:
+      - tools=/home/user/tools/supervisor_agent_webtools.yaml
+      - GOOGLE_CSE_ID=${GOOGLE_CSE_ID}
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY}

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

@@ -2,50 +2,26 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  tgi-server:
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.4
-    container_name: tgi-server
-    ports:
-      - "8085:80"
+  worker-rag-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: rag-agent-endpoint
     volumes:
-      - ${HF_CACHE_DIR}:/data
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_HUB_DISABLE_PROGRESS_BARS: 1
-      HF_HUB_ENABLE_HF_TRANSFER: 0
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}
-  worker-docgrader-agent:
-    image: opea/agent-langchain:latest
-    container_name: docgrader-agent-endpoint
-    depends_on:
-      - tgi-server
-    volumes:
-      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9095:9095"
     ipc: host
     environment:
       ip_address: ${ip_address}
-      strategy: rag_agent
+      strategy: rag_agent_llama
+      with_memory: false
       recursion_limit: ${recursion_limit_worker}
-      llm_engine: tgi
+      llm_engine: vllm
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      streaming: false
+      stream: false
       tools: /home/user/tools/worker_agent_tools.yaml
       require_human_feedback: false
       RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
@@ -57,30 +33,58 @@ services:
       LANGCHAIN_PROJECT: "opea-worker-agent-service"
       port: 9095
 
+  worker-sql-agent:
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+    container_name: sql-agent-endpoint
+    volumes:
+      - ${WORKDIR}/GenAIExamples/AgentQnA/tests:/home/user/chinook-db # test db
+    ports:
+      - "9096:9096"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: sql_agent_llama
+      with_memory: false
+      db_name: ${db_name}
+      db_path: ${db_path}
+      use_hints: false
+      recursion_limit: ${recursion_limit_worker}
+      llm_engine: vllm
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      llm_endpoint_url: ${LLM_ENDPOINT_URL}
+      model: ${LLM_MODEL_ID}
+      temperature: ${temperature}
+      max_new_tokens: ${max_new_tokens}
+      stream: false
+      require_human_feedback: false
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      port: 9096
 
   supervisor-react-agent:
-    image: opea/agent-langchain:latest
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
     container_name: react-agent-endpoint
     depends_on:
-      - tgi-server
-      - worker-docgrader-agent
+      - worker-rag-agent
+      - worker-sql-agent
     volumes:
-      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9090:9090"
     ipc: host
     environment:
       ip_address: ${ip_address}
-      strategy: react_langgraph
+      strategy: react_llama
+      with_memory: true
       recursion_limit: ${recursion_limit_supervisor}
-      llm_engine: tgi
+      llm_engine: vllm
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      streaming: false
+      stream: true
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}
@@ -91,4 +95,47 @@ services:
       LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
       CRAG_SERVER: $CRAG_SERVER
       WORKER_AGENT_URL: $WORKER_AGENT_URL
+      SQL_AGENT_URL: $SQL_AGENT_URL
       port: 9090
+  mock-api:
+    image: docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
+    container_name: mock-api
+    ports:
+      - "8080:8000"
+    ipc: host
+  agent-ui:
+    image: ${REGISTRY:-opea}/agent-ui:${TAG:-latest}
+    container_name: agent-ui
+    environment:
+      host_ip: ${host_ip}
+    ports:
+      - "5173:8080"
+    ipc: host
+  vllm-service:
+    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
+    container_name: vllm-gaudi-server
+    ports:
+      - "8086:8000"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/data"
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
+      VLLM_TORCH_PROFILER_DIR: "/mnt"
+      VLLM_SKIP_WARMUP: true
+      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8086/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    command: --model $LLM_MODEL_ID --tensor-parallel-size 4 --host 0.0.0.0 --port 8000 --block-size 128 --max-num-seqs 256 --max-seq-len-to-capture 16384

AgentQnA/docker_compose/intel/hpu/gaudi/grafana/dashboards/download_opea_dashboard.sh

@@ -0,0 +1,10 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+rm *.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/chatqna_megaservice_grafana.json
+mv chatqna_megaservice_grafana.json agentqna_microervices_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/vllm_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/tgi_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/node_grafana.json
+wget https://raw.githubusercontent.com/opea-project/GenAIEval/refs/heads/main/evals/benchmark/grafana/gaudi_grafana.json

AgentQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/dashboards/local.yaml

@@ -0,0 +1,14 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: 1
+
+providers:
+- name: 'default'
+  orgId: 1
+  folder: ''
+  type: file
+  disableDeletion: false
+  updateIntervalSeconds: 10 #how often Grafana will scan for changed dashboards
+  options:
+    path: /var/lib/grafana/dashboards

AgentQnA/docker_compose/intel/hpu/gaudi/grafana/provisioning/datasources/datasource.yml

@@ -0,0 +1,54 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# config file version
+apiVersion: 1
+
+# list of datasources that should be deleted from the database
+deleteDatasources:
+  - name: Prometheus
+    orgId: 1
+
+# list of datasources to insert/update depending
+# what's available in the database
+datasources:
+  # <string, required> name of the datasource. Required
+- name: Prometheus
+  # <string, required> datasource type. Required
+  type: prometheus
+  # <string, required> access mode. direct or proxy. Required
+  access: proxy
+  # <int> org id. will default to orgId 1 if not specified
+  orgId: 1
+  # <string> url
+  url: http://prometheus:9090
+  # <string> database password, if used
+  password:
+  # <string> database user, if used
+  user:
+  # <string> database name, if used
+  database:
+  # <bool> enable/disable basic auth
+  basicAuth: false
+  # <string> basic auth username, if used
+  basicAuthUser:
+  # <string> basic auth password, if used
+  basicAuthPassword:
+  # <bool> enable/disable with credentials headers
+  withCredentials:
+  # <bool> mark as default datasource. Max one per org
+  isDefault: true
+  # <map> fields that will be converted to json and stored in json_data
+  jsonData:
+     httpMethod: GET
+     graphiteVersion: "1.1"
+     tlsAuth: false
+     tlsAuthWithCACert: false
+  # <string> json object of data that will be encrypted.
+  secureJsonData:
+    tlsCACert: "..."
+    tlsClientCert: "..."
+    tlsClientKey: "..."
+  version: 1
+  # <bool> allow users to edit datasources from the UI.
+  editable: true

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

@@ -1,43 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-WORKPATH=$(dirname "$PWD")/..
-# export WORKDIR=$WORKPATH/../../
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-
-# LLM related environment variables
-export HF_CACHE_DIR=${HF_CACHE_DIR}
-ls $HF_CACHE_DIR
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-70B-Instruct"
-export NUM_SHARDS=4
-export LLM_ENDPOINT_URL="http://${ip_address}:8085"
-export temperature=0.01
-export max_new_tokens=512
-
-# agent related environment variables
-export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-echo "TOOLSET_PATH=${TOOLSET_PATH}"
-export recursion_limit_worker=12
-export recursion_limit_supervisor=10
-export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
-export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
-export CRAG_SERVER=http://${ip_address}:8080
-
-docker compose -f compose.yaml up -d
-
-sleep 5s
-echo "Waiting tgi gaudi ready"
-n=0
-until [[ "$n" -ge 100 ]] || [[ $ready == true ]]; do
-    docker logs tgi-server &> tgi-gaudi-service.log
-    n=$((n+1))
-    if grep -q Connected tgi-gaudi-service.log; then
-        break
-    fi
-    sleep 5s
-done
-sleep 5s
-echo "Service started successfully"

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

@@ -0,0 +1,55 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+global:
+  scrape_interval: 5s
+  external_labels:
+    monitor: "my-monitor"
+scrape_configs:
+  - job_name: "prometheus"
+    static_configs:
+      - targets: ["prometheus:9090"]
+  - job_name: "vllm"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["vllm-gaudi-server:8000"]
+  - job_name: "tgi"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["tgi-gaudi-server:80"]
+  - job_name: "tei-embedding"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["tei-embedding-server:80"]
+  - job_name: "tei-reranking"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["tei-reranking-server:80"]
+  - job_name: "retriever"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["retriever:7000"]
+  - job_name: "dataprep-redis-service"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["dataprep-redis-service:5000"]
+  - job_name: "prometheus-node-exporter"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["node-exporter:9100"]
+  - job_name: "prometheus-gaudi-exporter"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["gaudi-exporter:41611"]
+  - job_name: "supervisor-react-agent"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["react-agent-endpoint:9090"]
+  - job_name: "worker-rag-agent"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["rag-agent-endpoint:9095"]
+  - job_name: "worker-sql-agent"
+    metrics_path: /metrics
+    static_configs:
+      - targets: ["sql-agent-endpoint:9096"]

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

@@ -0,0 +1,72 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+pushd "../../../../../" > /dev/null
+source .set_env.sh
+popd > /dev/null
+WORKPATH=$(dirname "$PWD")/..
+# export WORKDIR=$WORKPATH/../../
+if [[ -z "${WORKDIR}" ]]; then
+	echo "Please set WORKDIR environment variable"
+	exit 0
+fi
+echo "WORKDIR=${WORKDIR}"
+export ip_address=$(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=${HUGGINGFACEHUB_API_TOKEN}
+export LLM_MODEL_ID="meta-llama/Llama-3.3-70B-Instruct"
+export NUM_SHARDS=4
+export LLM_ENDPOINT_URL="http://${ip_address}:8086"
+export temperature=0
+export max_new_tokens=4096
+
+# agent related environment variables
+export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+echo "TOOLSET_PATH=${TOOLSET_PATH}"
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
+export SQL_AGENT_URL="http://${ip_address}:9096/v1/chat/completions"
+export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
+export CRAG_SERVER=http://${ip_address}:8080
+
+export db_name=Chinook
+export db_path="sqlite:////home/user/chinook-db/Chinook_Sqlite.sqlite"
+if [ ! -f $WORKDIR/GenAIExamples/AgentQnA/tests/Chinook_Sqlite.sqlite ]; then
+    echo "Download Chinook_Sqlite!"
+    wget  -O $WORKDIR/GenAIExamples/AgentQnA/tests/Chinook_Sqlite.sqlite  https://github.com/lerocha/chinook-database/releases/download/v1.4.5/Chinook_Sqlite.sqlite
+fi
+
+# configure agent ui
+# echo "AGENT_URL = 'http://$ip_address:9090/v1/chat/completions'" | tee ${WORKDIR}/GenAIExamples/AgentQnA/ui/svelte/.env
+
+# retriever
+export host_ip=$(hostname -I | awk '{print $1}')
+export no_proxy=${no_proxy}
+export http_proxy=${http_proxy}
+export https_proxy=${https_proxy}
+export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+export REDIS_URL="redis://${host_ip}:6379"
+export INDEX_NAME="rag-redis"
+export RERANK_TYPE="tei"
+export MEGA_SERVICE_HOST_IP=${host_ip}
+export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+export RERANK_SERVICE_HOST_IP=${host_ip}
+export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+# Set OpenTelemetry Tracing Endpoint
+export JAEGER_IP=$(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
+
+export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui,vllm-gaudi-server,jaeger,grafana,prometheus,node-exporter,gaudi-exporter,127.0.0.1,localhost,0.0.0.0,$host_ip,,$JAEGER_IP"

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

@@ -0,0 +1,30 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  tgi-server:
+    image: ghcr.io/huggingface/tgi-gaudi:2.3.1
+    container_name: tgi-server
+    ports:
+      - "8085:80"
+    volumes:
+      - ${HF_CACHE_DIR}:/data
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
+      ENABLE_HPU_GRAPH: true
+      LIMIT_HPU_GRAPH: true
+      USE_FLASH_ATTENTION: true
+      FLASH_ATTENTION_RECOMPUTE: true
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}

AgentQnA/docker_image_build/build.yaml

@@ -2,12 +2,30 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  agent-langchain:
+  agent:
     build:
       context: GenAIComps
-      dockerfile: comps/agent/langchain/Dockerfile
+      dockerfile: comps/agent/src/Dockerfile
       args:
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}
-    image: ${REGISTRY:-opea}/agent-langchain:${TAG:-latest}
+    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
+  agent-ui:
+    build:
+      context: ../ui
+      dockerfile: ./docker/Dockerfile
+    extends: agent
+    image: ${REGISTRY:-opea}/agent-ui:${TAG:-latest}
+  vllm-gaudi:
+    build:
+      context: vllm-fork
+      dockerfile: Dockerfile.hpu
+    extends: agent
+    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
+  vllm-rocm:
+    build:
+      context: GenAIComps
+      dockerfile: comps/third_parties/vllm/src/Dockerfile.amd_gpu
+    extends: agent
+    image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}

AgentQnA/kubernetes/helm/README.md

@@ -0,0 +1,11 @@
+# Deploy AgentQnA on Kubernetes cluster
+
+- You should have Helm (version >= 3.15) installed. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
+- For more deploy options, refer to [helm charts README](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts#readme).
+
+## Deploy on Gaudi
+
+```
+export HFTOKEN="insert-your-huggingface-token-here"
+helm install agentqna oci://ghcr.io/opea-project/charts/agentqna  --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} -f gaudi-values.yaml
+```

AgentQnA/kubernetes/helm/cpu-values.yaml

@@ -0,0 +1,22 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+tgi:
+  enabled: false
+vllm:
+  enabled: true
+  LLM_MODEL_ID: "meta-llama/Meta-Llama-3-8B-Instruct"
+  extraCmdArgs: ["--max-seq-len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
+
+supervisor:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+  llm_engine: vllm
+  model: "meta-llama/Meta-Llama-3-8B-Instruct"
+ragagent:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+  llm_engine: vllm
+  model: "meta-llama/Meta-Llama-3-8B-Instruct"
+sqlagent:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+  llm_engine: vllm
+  model: "meta-llama/Meta-Llama-3-8B-Instruct"

AgentQnA/kubernetes/helm/gaudi-values.yaml

@@ -0,0 +1,35 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Accelerate inferencing in heaviest components to improve performance
+# by overriding their subchart values
+
+tgi:
+  enabled: false
+vllm:
+  enabled: true
+  accelDevice: "gaudi"
+  image:
+    repository: opea/vllm-gaudi
+  resources:
+    limits:
+      habana.ai/gaudi: 4
+  LLM_MODEL_ID: "meta-llama/Llama-3.3-70B-Instruct"
+  OMPI_MCA_btl_vader_single_copy_mechanism: none
+  PT_HPU_ENABLE_LAZY_COLLECTIVES: true
+  VLLM_SKIP_WARMUP: true
+  shmSize: 16Gi
+  extraCmdArgs: ["--tensor-parallel-size", "4", "--max-seq-len-to-capture", "16384", "--enable-auto-tool-choice", "--tool-call-parser", "llama3_json"]
+
+supervisor:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+  llm_engine: vllm
+  model: "meta-llama/Llama-3.3-70B-Instruct"
+ragagent:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+  llm_engine: vllm
+  model: "meta-llama/Llama-3.3-70B-Instruct"
+sqlagent:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+  llm_engine: vllm
+  model: "meta-llama/Llama-3.3-70B-Instruct"

AgentQnA/retrieval_tool/index_data.py

@@ -53,7 +53,7 @@ def main():
     host_ip = args.host_ip
     port = args.port
     proxies = {"http": ""}
-    url = "http://{host_ip}:{port}/v1/dataprep".format(host_ip=host_ip, port=port)
+    url = "http://{host_ip}:{port}/v1/dataprep/ingest".format(host_ip=host_ip, port=port)
 
     # Split jsonl file into json files
     files = split_jsonl_into_txts(os.path.join(args.filedir, args.filename))

AgentQnA/retrieval_tool/launch_retrieval_tool.sh

@@ -13,13 +13,14 @@ export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
 export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
 export REDIS_URL="redis://${host_ip}:6379"
 export INDEX_NAME="rag-redis"
+export RERANK_TYPE="tei"
 export MEGA_SERVICE_HOST_IP=${host_ip}
 export EMBEDDING_SERVICE_HOST_IP=${host_ip}
 export RETRIEVER_SERVICE_HOST_IP=${host_ip}
 export RERANK_SERVICE_HOST_IP=${host_ip}
 export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
-export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get_file"
-export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete_file"
+export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
 
 docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml up -d

AgentQnA/retrieval_tool/run_ingest_data.sh

@@ -1,7 +1,22 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+host_ip=$(hostname -I | awk '{print $1}')
+port=6007
 FILEDIR=${WORKDIR}/GenAIExamples/AgentQnA/example_data/
 FILENAME=test_docs_music.jsonl
 
-python3 index_data.py --filedir ${FILEDIR} --filename ${FILENAME} --host_ip $host_ip
+# AgentQnA ingestion script requires following packages
+packages=("requests" "tqdm")
+
+# Check if packages are installed
+for package in "${packages[@]}"; do
+  if pip freeze | grep -q "$package="; then
+    echo "$package is installed"
+  else
+    echo "$package is not installed"
+    pip install --no-cache-dir "$package"
+  fi
+done
+
+python3 index_data.py --filedir ${FILEDIR} --filename ${FILENAME} --host_ip $host_ip --port $port

AgentQnA/tests/1_build_images.sh

@@ -1,48 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -e
-WORKPATH=$(dirname "$PWD")
-export WORKDIR=$WORKPATH/../../
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-
-
-function get_genai_comps() {
-    if [ ! -d "GenAIComps" ] ; then
-        git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
-    fi
-}
-
-
-function build_docker_images_for_retrieval_tool(){
-    cd $WORKDIR/GenAIExamples/DocIndexRetriever/docker_image_build/
-    # git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
-    get_genai_comps
-    echo "Build all the images with --no-cache..."
-    service_list="doc-index-retriever dataprep-redis embedding-tei retriever-redis reranking-tei"
-    docker compose -f build.yaml build ${service_list} --no-cache
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
-
-    docker images && sleep 1s
-}
-
-function build_agent_docker_image() {
-    cd $WORKDIR/GenAIExamples/AgentQnA/docker_image_build/
-    get_genai_comps
-    echo "Build agent image with --no-cache..."
-    docker compose -f build.yaml build --no-cache
-}
-
-function main() {
-    echo "==================== Build docker images for retrieval tool ===================="
-    build_docker_images_for_retrieval_tool
-    echo "==================== Build docker images for retrieval tool completed ===================="
-
-    echo "==================== Build agent docker image ===================="
-    build_agent_docker_image
-    echo "==================== Build agent docker image completed ===================="
-}
-
-main

AgentQnA/tests/4_launch_and_validate_agent_openai.sh

@@ -1,60 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -e
-echo "OPENAI_API_KEY=${OPENAI_API_KEY}"
-
-WORKPATH=$(dirname "$PWD")
-export WORKDIR=$WORKPATH/../../
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-
-function start_agent_and_api_server() {
-    echo "Starting CRAG server"
-    docker run -d --runtime=runc --name=kdd-cup-24-crag-service -p=8080:8000 docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
-
-    echo "Starting Agent services"
-    cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
-    bash launch_agent_service_openai.sh
-}
-
-function validate() {
-    local CONTENT="$1"
-    local EXPECTED_RESULT="$2"
-    local SERVICE_NAME="$3"
-
-    if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
-        echo "[ $SERVICE_NAME ] Content is as expected: $CONTENT"
-        echo 0
-    else
-        echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
-        echo 1
-    fi
-}
-
-function validate_agent_service() {
-    echo "----------------Test agent ----------------"
-    local CONTENT=$(http_proxy="" curl http://${ip_address}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Tell me about Michael Jackson song thriller"
-    }')
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "react-agent-endpoint")
-    docker logs react-agent-endpoint
-    if [ "$EXIT_CODE" == "1" ]; then
-        exit 1
-    fi
-
-}
-
-function main() {
-    echo "==================== Start agent ===================="
-    start_agent_and_api_server
-    echo "==================== Agent started ===================="
-
-    echo "==================== Validate agent service ===================="
-    validate_agent_service
-    echo "==================== Agent service validated ===================="
-}
-
-main

AgentQnA/tests/4_launch_and_validate_agent_tgi.sh

@@ -1,76 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -e
-
-WORKPATH=$(dirname "$PWD")
-export WORKDIR=$WORKPATH/../../
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-
-export HF_CACHE_DIR=$WORKDIR/hf_cache
-if [ ! -d "$HF_CACHE_DIR" ]; then
-    mkdir -p "$HF_CACHE_DIR"
-fi
-ls $HF_CACHE_DIR
-
-
-function start_agent_and_api_server() {
-    echo "Starting CRAG server"
-    docker run -d --runtime=runc --name=kdd-cup-24-crag-service -p=8080:8000 docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
-
-    echo "Starting Agent services"
-    cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi
-    bash launch_agent_service_tgi_gaudi.sh
-}
-
-function validate() {
-    local CONTENT="$1"
-    local EXPECTED_RESULT="$2"
-    local SERVICE_NAME="$3"
-
-    if echo "$CONTENT" | grep -q "$EXPECTED_RESULT"; then
-        echo "[ $SERVICE_NAME ] Content is as expected: $CONTENT"
-        echo 0
-    else
-        echo "[ $SERVICE_NAME ] Content does not match the expected result: $CONTENT"
-        echo 1
-    fi
-}
-
-function validate_agent_service() {
-    echo "----------------Test agent ----------------"
-    local CONTENT=$(http_proxy="" curl http://${ip_address}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Tell me about Michael Jackson song thriller"
-    }')
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "react-agent-endpoint")
-    docker logs docgrader-agent-endpoint
-    if [ "$EXIT_CODE" == "1" ]; then
-        exit 1
-    fi
-
-    local CONTENT=$(http_proxy="" curl http://${ip_address}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Tell me about Michael Jackson song thriller"
-    }')
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "react-agent-endpoint")
-    docker logs react-agent-endpoint
-    if [ "$EXIT_CODE" == "1" ]; then
-        exit 1
-    fi
-
-}
-
-function main() {
-    echo "==================== Start agent ===================="
-    start_agent_and_api_server
-    echo "==================== Agent started ===================="
-
-    echo "==================== Validate agent service ===================="
-    validate_agent_service
-    echo "==================== Agent service validated ===================="
-}
-
-main

AgentQnA/tests/_test_compose_openai_on_xeon.sh

@@ -15,28 +15,35 @@ function stop_agent_and_api_server() {
     echo "Stopping CRAG server"
     docker stop $(docker ps -q --filter ancestor=docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0)
     echo "Stopping Agent services"
-    docker stop $(docker ps -q --filter ancestor=opea/agent-langchain:latest)
+    docker stop $(docker ps -q --filter ancestor=opea/agent:latest)
 }
 
 function stop_retrieval_tool() {
     echo "Stopping Retrieval tool"
-    docker compose -f $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool/docker/docker-compose-retrieval-tool.yaml down
+    local RETRIEVAL_TOOL_PATH=$WORKPATH/../DocIndexRetriever
+    cd $RETRIEVAL_TOOL_PATH/docker_compose/intel/cpu/xeon/
+    container_list=$(cat compose.yaml | grep container_name | cut -d':' -f2)
+    for container_name in $container_list; do
+        cid=$(docker ps -aq --filter "name=$container_name")
+        echo "Stopping container $container_name"
+        if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
+    done
 }
 
 echo "=================== #1 Building docker images===================="
-bash 1_build_images.sh
+bash step1_build_images.sh xeon
 echo "=================== #1 Building docker images completed===================="
 
 echo "=================== #2 Start retrieval tool===================="
-bash 2_start_retrieval_tool.sh
+bash step2_start_retrieval_tool.sh
 echo "=================== #2 Retrieval tool started===================="
 
 echo "=================== #3 Ingest data and validate retrieval===================="
-bash 3_ingest_data_and_validate_retrieval.sh
+bash step3_ingest_data_and_validate_retrieval.sh
 echo "=================== #3 Data ingestion and validation completed===================="
 
 echo "=================== #4 Start agent and API server===================="
-bash 4_launch_and_validate_agent_openai.sh
+bash step4_launch_and_validate_agent_openai.sh
 echo "=================== #4 Agent test passed ===================="
 
 echo "=================== #5 Stop agent and API server===================="

AgentQnA/tests/sql_agent_test/run_data_split.sh

@@ -0,0 +1,6 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+DATAPATH=$WORKDIR/TAG-Bench/tag_queries.csv
+OUTFOLDER=$WORKDIR/TAG-Bench/query_by_db
+python3 split_data.py --path $DATAPATH --output $OUTFOLDER

AgentQnA/tests/sql_agent_test/split_data.py

@@ -0,0 +1,27 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import argparse
+import os
+
+import pandas as pd
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--path", type=str, required=True)
+    parser.add_argument("--output", type=str, required=True)
+    args = parser.parse_args()
+
+    # if output folder does not exist, create it
+    if not os.path.exists(args.output):
+        os.makedirs(args.output)
+
+    # Load the data
+    data = pd.read_csv(args.path)
+
+    # Split the data by domain
+    domains = data["DB used"].unique()
+    for domain in domains:
+        domain_data = data[data["DB used"] == domain]
+        out = os.path.join(args.output, f"query_{domain}.csv")
+        domain_data.to_csv(out, index=False)

AgentQnA/tests/step1_build_images.sh

@@ -0,0 +1,100 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -e
+WORKPATH=$(dirname "$PWD")
+export WORKDIR=$WORKPATH/../../
+echo "WORKDIR=${WORKDIR}"
+export ip_address=$(hostname -I | awk '{print $1}')
+
+
+function get_genai_comps() {
+    if [ ! -d "GenAIComps" ] ; then
+        git clone --depth 1 --branch ${opea_branch:-"main"} https://github.com/opea-project/GenAIComps.git
+    fi
+}
+
+function build_docker_images_for_retrieval_tool(){
+    cd $WORKDIR/GenAIExamples/DocIndexRetriever/docker_image_build/
+    get_genai_comps
+    echo "Build all the images with --no-cache..."
+    docker compose -f build.yaml build --no-cache
+    docker images && sleep 1s
+}
+
+function build_agent_docker_image_xeon() {
+    cd $WORKDIR/GenAIExamples/AgentQnA/docker_image_build/
+    get_genai_comps
+
+    echo "Build agent image with --no-cache..."
+    service_list="agent agent-ui"
+    docker compose -f build.yaml build ${service_list} --no-cache
+}
+
+function build_agent_docker_image_gaudi_vllm() {
+    cd $WORKDIR/GenAIExamples/AgentQnA/docker_image_build/
+    get_genai_comps
+
+    git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
+    VLLM_FORK_VER=v0.6.6.post1+Gaudi-1.20.0
+    git checkout ${VLLM_FORK_VER} &> /dev/null && cd ../
+
+    echo "Build agent image with --no-cache..."
+    service_list="agent agent-ui vllm-gaudi"
+    docker compose -f build.yaml build ${service_list} --no-cache
+}
+
+function build_agent_docker_image_rocm() {
+    cd $WORKDIR/GenAIExamples/AgentQnA/docker_image_build/
+    get_genai_comps
+
+    echo "Build agent image with --no-cache..."
+    service_list="agent agent-ui"
+    docker compose -f build.yaml build ${service_list} --no-cache
+}
+
+function build_agent_docker_image_rocm_vllm() {
+    cd $WORKDIR/GenAIExamples/AgentQnA/docker_image_build/
+    get_genai_comps
+
+    echo "Build agent image with --no-cache..."
+    service_list="agent agent-ui vllm-rocm"
+    docker compose -f build.yaml build ${service_list} --no-cache
+}
+
+
+function main() {
+    echo "==================== Build docker images for retrieval tool ===================="
+    build_docker_images_for_retrieval_tool
+    echo "==================== Build docker images for retrieval tool completed ===================="
+
+    sleep 3s
+
+    case $1 in
+        "rocm")
+            echo "==================== Build agent docker image for ROCm ===================="
+            build_agent_docker_image_rocm
+            ;;
+        "rocm_vllm")
+            echo "==================== Build agent docker image for ROCm VLLM ===================="
+            build_agent_docker_image_rocm_vllm
+            ;;
+        "gaudi_vllm")
+            echo "==================== Build agent docker image for Gaudi ===================="
+            build_agent_docker_image_gaudi_vllm
+            ;;
+        "xeon")
+            echo "==================== Build agent docker image for Xeon ===================="
+            build_agent_docker_image_xeon
+            ;;
+        *)
+            echo "Invalid argument"
+            exit 1
+            ;;
+    esac
+
+    docker image ls | grep vllm
+}
+
+main $1

AgentQnA/tests/step2_start_retrieval_tool.sh

@@ -7,8 +7,9 @@ WORKPATH=$(dirname "$PWD")
 export WORKDIR=$WORKPATH/../../
 echo "WORKDIR=${WORKDIR}"
 export ip_address=$(hostname -I | awk '{print $1}')
+export host_ip=${ip_address}
 
-export HF_CACHE_DIR=$WORKDIR/hf_cache
+export HF_CACHE_DIR=${model_cache:-"$WORKDIR/hf_cache"}
 if [ ! -d "$HF_CACHE_DIR" ]; then
     echo "Creating HF_CACHE directory"
     mkdir -p "$HF_CACHE_DIR"

AgentQnA/tests/step2_start_retrieval_tool_rocm_vllm.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -e
+WORKPATH=$(dirname "$PWD")
+export WORKDIR=$WORKPATH/../
+echo "WORKDIR=${WORKDIR}"
+export ip_address=$(hostname -I | awk '{print $1}')
+export host_ip=${ip_address}
+
+export HF_CACHE_DIR=$WORKPATH/hf_cache
+if [ ! -d "$HF_CACHE_DIR" ]; then
+    echo "Creating HF_CACHE directory"
+    mkdir -p "$HF_CACHE_DIR"
+fi
+
+function start_retrieval_tool() {
+    echo "Starting 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=${HUGGINGFACEHUB_API_TOKEN}
+    export no_proxy=${no_proxy}
+    export http_proxy=${http_proxy}
+    export https_proxy=${https_proxy}
+    export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
+    export RERANK_MODEL_ID="BAAI/bge-reranker-base"
+    export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
+    export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
+    export REDIS_URL="redis://${host_ip}:6379"
+    export INDEX_NAME="rag-redis"
+    export RERANK_TYPE="tei"
+    export MEGA_SERVICE_HOST_IP=${host_ip}
+    export EMBEDDING_SERVICE_HOST_IP=${host_ip}
+    export RETRIEVER_SERVICE_HOST_IP=${host_ip}
+    export RERANK_SERVICE_HOST_IP=${host_ip}
+    export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
+    export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
+    export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
+    export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
+
+    docker compose -f compose.yaml up -d
+}
+
+echo "==================== Start retrieval tool ===================="
+start_retrieval_tool
+sleep 20 # needed for downloading the models
+echo "==================== Retrieval tool started ===================="