Provide unified scalable deployment and benchmarking support for exam… (#1315)

Signed-off-by: Cathy Zhang <cathy.zhang@intel.com>
Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
(cherry picked from commit ed163087ba)

.github/CODEOWNERS

@@ -1,17 +1,23 @@
-/AgentQnA/ kaokao.lv@intel.com
-/AudioQnA/ sihan.chen@intel.com
-/ChatQnA/ liang1.lv@intel.com
-/CodeGen/ liang1.lv@intel.com
-/CodeTrans/ sihan.chen@intel.com
-/DocSum/ letong.han@intel.com
+* liang1.lv@intel.com feng.tian@intel.com suyue.chen@intel.com
+/.github/ suyue.chen@intel.com ze.pan@intel.com
+/AgentQnA/ 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 xinyao.wang@intel.com
+/CodeTrans/ sihan.chen@intel.com xinyao.wang@intel.com
+/DBQnA/ supriya.krishnamurthi@intel.com liang1.lv@intel.com
 /DocIndexRetriever/ kaokao.lv@intel.com chendi.xue@intel.com
-/InstructionTuning xinyu.ye@intel.com
-/RerankFinetuning xinyu.ye@intel.com
-/MultimodalQnA tiep.le@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
-/VideoQnA huiling.bao@intel.com
-/*/ liang1.lv@intel.com
+/DocSum/ letong.han@intel.com xinyao.wang@intel.com
+/EdgeCraftRAG/ yongbo.zhu@intel.com mingyuan.qi@intel.com
+/FaqGen/ yogesh.pandey@intel.com xinyao.wang@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 xinyao.wang@intel.com
+/VisualQnA/ liang1.lv@intel.com sihan.chen@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
@@ -65,6 +66,7 @@ body:
       options:
         - label: Pull docker images from hub.docker.com
         - label: Build docker images from source
+        - label: Other
     validations:
       required: true
 
@@ -73,10 +75,11 @@ 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
     validations:
       required: true
 
@@ -87,6 +90,7 @@ body:
       options:
         - Single Node
         - Multiple Nodes
+        - Other
       default: 0
     validations:
       required: true
@@ -126,3 +130,12 @@ 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
@@ -65,6 +66,7 @@ body:
       options:
         - Single Node
         - Multiple Nodes
+        - Other
       default: 0
     validations:
       required: true

.github/license_template.txt

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

.github/workflows/_example-workflow.yml

@@ -28,7 +28,7 @@ on:
         default: false
         required: false
         type: boolean
-      test_k8s:
+      test_helmchart:
         default: false
         required: false
         type: boolean
@@ -74,15 +74,15 @@ jobs:
           cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
           docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
           if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
-              git clone https://github.com/vllm-project/vllm.git
+              git clone --depth 1 https://github.com/vllm-project/vllm.git
               cd vllm && git rev-parse HEAD && cd ../
           fi
-          if [[ $(grep -c "vllm-hpu:" ${docker_compose_path}) != 0 ]]; then
-               git clone https://github.com/HabanaAI/vllm-fork.git
-               cd vllm-fork && git rev-parse HEAD && cd ../
+          if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
+              git clone --depth 1 --branch v0.6.4.post2+Gaudi-1.19.0 https://github.com/HabanaAI/vllm-fork.git
+              sed -i 's/triton/triton==3.1.0/g' vllm-fork/requirements-hpu.txt
           fi
-          git clone https://github.com/opea-project/GenAIComps.git
-          cd GenAIComps && git checkout ${{ inputs.opea_branch }} && git rev-parse HEAD && cd ../
+          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
         if: ${{ fromJSON(inputs.build) }}
@@ -110,16 +110,16 @@ jobs:
 
 
 ####################################################################################################
-# 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 }}
+      mode: "CD"
     secrets: inherit
 
 ####################################################################################################

.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 +1,233 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+name: Helm Chart E2e Test For Call
+permissions: read-all
+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 [[ "$filename" == *"nv"* ]]; then
+                continue
+              else
+                if [[ "${{ 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]
+    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: ${{ inputs.example }}
+        run: |
+          CHART_NAME="${example,,}"  # CodeGen
+          echo "CHART_NAME=$CHART_NAME" >> $GITHUB_ENV
+          echo "RELEASE_NAME=${CHART_NAME}$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV
+          echo "NAMESPACE=${CHART_NAME}-$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV
+          echo "ROLLOUT_TIMEOUT_SECONDS=600s" >> $GITHUB_ENV
+          echo "TEST_TIMEOUT_SECONDS=600s" >> $GITHUB_ENV
+          echo "KUBECTL_TIMEOUT_SECONDS=60s" >> $GITHUB_ENV
+          echo "should_cleanup=false" >> $GITHUB_ENV
+          echo "skip_validate=false" >> $GITHUB_ENV
+          echo "CHART_FOLDER=${example}/kubernetes/helm" >> $GITHUB_ENV
+
+      - 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=${HFTOKEN} \
+            --set global.modelUseHostPath=/home/sdp/.cache/huggingface/hub \
+            --set GOOGLE_API_KEY=${{ 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
-
-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}opea" >> $GITHUB_ENV
-          echo "IMAGE_TAG=${{ 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" >> $GITHUB_ENV
-          echo "NAMESPACE=$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!!!"
-              echo "Check the logs in 'Dump logs when e2e test failed' step!!!"
-              exit 1
-            fi
-          fi
-
-      - name: Dump logs when e2e test failed
-        if: failure()
-        run: |
-          .github/workflows/scripts/k8s-utils.sh dump_all_pod_logs $NAMESPACE
-
-      - 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

@@ -89,7 +89,7 @@ jobs:
           echo "test_cases=$test_cases"
           echo "test_cases=$test_cases" >> $GITHUB_OUTPUT
 
-  run-test:
+  compose-test:
     needs: [get-test-case]
     strategy:
       matrix:
@@ -111,6 +111,17 @@ 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: Run test
         shell: bash
         env:
@@ -121,6 +132,7 @@ jobs:
           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 }}
           IMAGE_REPO: ${{ inputs.registry }}
           IMAGE_TAG: ${{ inputs.tag }}
           example: ${{ inputs.example }}
@@ -131,21 +143,14 @@ jobs:
           if [[ "$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
 
-      - name: Clean up container
+      - name: Clean up container after test
         shell: bash
         if: cancelled() || failure()
         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 $yaml_file
-          container_list=$(cat $yaml_file | grep container_name | cut -d':' -f2)
-          for container_name in $container_list; do
-              cid=$(docker ps -aq --filter "name=$container_name")
-              if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
-          done
+          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"
           docker system prune -f
           docker rmi $(docker images --filter reference="*:5000/*/*" -q) || true
 

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

@@ -13,7 +13,7 @@ on:
 
 jobs:
   build:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
 
     - name: Checkout

.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-example-workflow.yml

@@ -12,7 +12,7 @@ on:
         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:
@@ -35,9 +35,9 @@ on:
         description: 'Test examples with docker compose'
         required: false
         type: boolean
-      test_k8s:
-        default: false
-        description: 'Test examples with k8s'
+      test_helmchart:
+        default: true
+        description: 'Test examples with helm charts'
         required: false
         type: boolean
       test_gmc:
@@ -51,7 +51,7 @@ on:
         required: false
         type: string
       inject_commit:
-        default: true
+        default: false
         description: "inject commit to docker images true or false"
         required: false
         type: string
@@ -103,7 +103,7 @@ jobs:
       tag: ${{ inputs.tag }}
       build: ${{ fromJSON(inputs.build) }}
       test_compose: ${{ fromJSON(inputs.test_compose) }}
-      test_k8s: ${{ fromJSON(inputs.test_k8s) }}
+      test_helmchart: ${{ fromJSON(inputs.test_helmchart) }}
       test_gmc: ${{ fromJSON(inputs.test_gmc) }}
       opea_branch: ${{ inputs.opea_branch }}
       inject_commit: ${{ inputs.inject_commit }}

.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
@@ -23,10 +23,6 @@ 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"
@@ -35,9 +31,10 @@ jobs:
 
       - 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

@@ -12,7 +12,7 @@ on:
         type: string
       example:
         default: "ChatQnA"
-        description: 'Build images belong to which example?'
+        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:
@@ -31,7 +31,7 @@ on:
         required: false
         type: string
       inject_commit:
-        default: true
+        default: false
         description: "inject commit to docker images true or false"
         required: false
         type: string

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

@@ -0,0 +1,59 @@
+# 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
+    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]
+    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

@@ -5,11 +5,11 @@ name: Nightly build/publish latest docker images
 
 on:
   schedule:
-    - cron: "30 13 * * *" # UTC time
+    - cron: "30 14 * * *" # UTC time
   workflow_dispatch:
 
 env:
-  EXAMPLES: "AgentQnA,AudioQnA,ChatQnA,CodeGen,CodeTrans,DocIndexRetriever,DocSum,FaqGen,InstructionTuning,MultimodalQnA,ProductivitySuite,RerankFinetuning,SearchQnA,Translation,VideoQnA,VisualQnA"
+  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
   TAG: "latest"
   PUBLISH_TAGS: "latest"
 
@@ -32,7 +32,7 @@ jobs:
           echo "TAG=$TAG" >> $GITHUB_OUTPUT
           echo "PUBLISH_TAGS=$PUBLISH_TAGS" >> $GITHUB_OUTPUT
 
-  build:
+  build-and-test:
     needs: get-build-matrix
     strategy:
       matrix:
@@ -42,6 +42,7 @@ jobs:
     with:
       node: gaudi
       example: ${{ matrix.example }}
+      test_compose: true
     secrets: inherit
 
   get-image-list:
@@ -51,7 +52,7 @@ jobs:
       examples: ${{ needs.get-build-matrix.outputs.EXAMPLES }}
 
   publish:
-    needs: [get-build-matrix, get-image-list, build]
+    needs: [get-build-matrix, get-image-list, build-and-test]
     strategy:
       matrix:
         image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}

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

@@ -0,0 +1,76 @@
+# 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
+    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" == *"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() && ${{ needs.job1.outputs.run_matrix.example.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

@@ -28,7 +28,7 @@ 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]
@@ -42,5 +42,5 @@ jobs:
       tag: "ci"
       example: ${{ matrix.example }}
       hardware: ${{ matrix.hardware }}
-      diff_excluded_files: '.github|*.md|*.txt|kubernetes|manifest|gmc|assets|benchmark'
+      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/**/manifest/**"
 
 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

@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-name: Check Paths and Hyperlinks
+name: Check hyperlinks and relative path validity
 
 on:
   pull_request:
@@ -9,39 +9,6 @@ on:
     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:

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

@@ -1,42 +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:
-      - "**/Dockerfile**"
-      - "**.py"
-      - "**/kubernetes/**/manifest/**"
-      - "**/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/push-image-build.yml

@@ -8,7 +8,9 @@ on:
     branches: [ 'main' ]
     paths:
       - "**.py"
-      - "**Dockerfile"
+      - "**Dockerfile*"
+      - "**docker_image_build/build.yaml"
+      - "**/ui/**"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}-on-push
@@ -18,7 +20,7 @@ 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

.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/docker_compose_clean_up.sh

@@ -0,0 +1,48 @@
+#!/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 [[ $port =~ [a-zA-Z_-] ]]; then
+            port=$(grep -E "export $port=" tests/$test_case | cut -d'=' -f2)
+          fi
+          if [[ $port =~ [0-9] ]]; then
+            if [[ $port == 5000 ]]; then
+              echo "Error: Port 5000 is used by local docker registry, please DO NOT use it in docker compose deployment!!!"
+              exit 1
+            fi
+            cid=$(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

@@ -16,11 +16,16 @@ for example in ${examples}; do
     if [[ ! $(find . -type f | grep ${test_mode}) ]]; then continue; fi
     cd tests
     ls -l
-    hardware_list=$(find . -type f -name "test_compose*_on_*.sh" | cut -d/ -f2 | cut -d. -f1 | awk -F'_on_' '{print $2}'| sort -u)
-    echo "Test supported hardware list = ${hardware_list}"
+    if [[ "$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
+    if [[ $(printf '%s\n' "${changed_files[@]}" | grep ${example} | cut -d'/' -f2 | grep -E '\.py|Dockerfile*|ui|docker_image_build' ) ]]; then
         # run test on all hardware if megaservice or ui code change
         run_hardware=$hardware_list
     else

.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

.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))$
@@ -100,18 +100,18 @@ repos:
           - prettier@3.2.5
 
   - repo: https://github.com/psf/black.git
-    rev: 24.4.2
+    rev: 24.10.0
     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
@@ -122,7 +122,7 @@ repos:
           - tomli
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.0
+    rev: v0.8.6
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix, --no-cache]

.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

@@ -2,8 +2,8 @@
 
 ## 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 is shown below. The supervisor agent interfaces with the user and dispatch 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 the knowledge base (a vector database). The worker SQL agent retrieve relevant data from the SQL database. Although not included in this example, but 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)
 
 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.
 
@@ -38,6 +38,7 @@ flowchart LR
     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>}}
@@ -51,6 +52,7 @@ flowchart LR
     direction LR
     a[User Input Query] --> AG_REACT
     AG_REACT --> AG_RAG
+    AG_REACT --> AG_SQL
     AG_RAG --> DocIndexRetriever-MegaService
     EM ==> RET
     RET ==> RER
@@ -59,6 +61,7 @@ flowchart LR
     %% Embedding service flow
     direction LR
     AG_RAG <-.-> LLM_gen
+    AG_SQL <-.-> LLM_gen
     AG_REACT <-.-> LLM_gen
     EM <-.-> TEI_EM
     RET <-.-> R_RET
@@ -75,37 +78,40 @@ flowchart LR
 ### Why Agent for question answering?
 
 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.
+   RAG 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. Expand scope of the agent.
+   The supervisor agent can interact with multiple worker agents that specialize in different domains with different skills (e.g., retrieve documents, write SQL queries, etc.), and thus can answer questions in multiple domains.
+3. Hierarchical multi-agents can improve performance.
+   Expert worker agents, such as RAG agent and SQL agent, 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. If we only use one agent and provide all the tools to this single agent, it may get overwhelmed and not able to provide accurate answers.
 
 ## Deployment with docker
 
-1. Build agent docker image
+1. Build agent docker image [Optional]
 
-   Note: this is optional. The docker images will be automatically pulled when running the docker compose commands. This step is only needed if pulling images failed.
+> [!NOTE]
+> the step is optional. The docker images will be automatically pulled when running the docker compose commands. This step is only needed if pulling images failed.
 
-   First, clone the opea GenAIComps repo.
+First, clone the opea GenAIComps repo.
 
-   ```
-   export WORKDIR=<your-work-directory>
-   cd $WORKDIR
-   git clone https://github.com/opea-project/GenAIComps.git
-   ```
+```
+export WORKDIR=<your-work-directory>
+cd $WORKDIR
+git clone https://github.com/opea-project/GenAIComps.git
+```
 
-   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.
+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.
 
-   ```
-   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 .
-   ```
+```
+cd GenAIComps
+docker build -t opea/agent:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/agent/src/Dockerfile .
+```
 
 2. Set up environment for this example </br>
+
    First, clone this repo.
 
    ```
+   export WORKDIR=<your-work-directory>
    cd $WORKDIR
    git clone https://github.com/opea-project/GenAIExamples.git
    ```
@@ -113,6 +119,14 @@ flowchart LR
    Second, set up env vars.
 
    ```
+   # Example: host_ip="192.168.1.1" or export host_ip="External_Public_IP"
+   export host_ip=$(hostname -I | awk '{print $1}')
+   # if you are in a proxy environment, also set the proxy-related environment variables
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+
    export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
    # for using open-source llms
    export HUGGINGFACEHUB_API_TOKEN=<your-HF-token>
@@ -137,38 +151,86 @@ flowchart LR
    bash run_ingest_data.sh
    ```
 
-4. Launch other tools. </br>
+4. Prepare SQL database
+   In this example, we will use the Chinook SQLite database. Run the commands below.
+
+   ```
+   # Download data
+   cd $WORKDIR
+   git clone https://github.com/lerocha/chinook-database.git
+   cp chinook-database/ChinookDatabase/DataSources/Chinook_Sqlite.sqlite $WORKDIR/GenAIExamples/AgentQnA/tests/
+   ```
+
+5. Launch other tools. </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
    ```
 
-5. Launch agent services</br>
-   We provide two options for `llm_engine` of the agents: 1. open-source LLMs, 2. OpenAI models via API calls.
+6. Launch multi-agent system. </br>
+   We provide two options for `llm_engine` of the agents: 1. open-source LLMs on Intel Gaudi2, 2. OpenAI models via API calls.
 
-   To use open-source LLMs on Gaudi2, run commands below.
+   ::::{tab-set}
+   :::{tab-item} Gaudi
+   :sync: Gaudi
 
+   On Gaudi2 we will serve `meta-llama/Meta-Llama-3.1-70B-Instruct` using vllm.
+
+   First build vllm-gaudi docker image.
+
+   ```bash
+   cd $WORKDIR
+   git clone https://github.com/vllm-project/vllm.git
+   cd ./vllm
+   git checkout v0.6.6
+   docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:latest --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
    ```
-   cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi
-   bash launch_tgi_gaudi.sh
-   bash launch_agent_service_tgi_gaudi.sh
+
+   Then launch vllm on Gaudi2 with the command below.
+
+   ```bash
+   vllm_port=8086
+   model="meta-llama/Meta-Llama-3.1-70B-Instruct"
+   docker run -d --runtime=habana --rm --name "vllm-gaudi-server" -e HABANA_VISIBLE_DEVICES=0,1,2,3 -p $vllm_port:8000 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host opea/vllm-gaudi:latest --model ${model} --max-seq-len-to-capture 16384 --tensor-parallel-size 4
    ```
 
+   Then launch Agent microservices.
+
+   ```bash
+   cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
+   bash launch_agent_service_gaudi.sh
+   ```
+
+   :::
+   :::{tab-item} Xeon
+   :sync: Xeon
+
    To use OpenAI models, run commands below.
 
    ```
+   export OPENAI_API_KEY=<your-openai-key>
    cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
    bash launch_agent_service_openai.sh
    ```
 
+   :::
+   ::::
+
+## Deploy using Helm Chart
+
+Refer to the [AgentQnA helm chart](./kubernetes/helm/README.md) for instructions on deploying AgentQnA on Kubernetes.
+
 ## Validate services
 
 First look at logs of the agent docker containers:
 
 ```
-# worker agent
+# worker RAG agent
 docker logs rag-agent-endpoint
+
+# worker SQL agent
+docker logs sql-agent-endpoint
 ```
 
 ```
@@ -178,22 +240,36 @@ docker logs react-agent-endpoint
 
 You should see something like "HTTP server setup successful" if the docker containers are started successfully.</p>
 
-Second, validate worker agent:
+Second, validate worker RAG agent:
 
 ```
-curl http://${ip_address}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Most recent album by Taylor Swift"
+curl http://${host_ip}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "Michael Jackson song Thriller"
     }'
 ```
 
-Third, validate supervisor agent:
+Third, validate worker SQL agent:
 
 ```
-curl http://${ip_address}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
-     "query": "Most recent album by Taylor Swift"
+curl http://${host_ip}:9096/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "How many employees are in the company"
     }'
 ```
 
+Finally, validate supervisor agent:
+
+```
+curl http://${host_ip}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "How many albums does Iron Maiden have?"
+    }'
+```
+
+## Deploy AgentQnA UI
+
+The AgentQnA UI can be deployed locally or using Docker.
+
+For detailed instructions on deploying AgentQnA UI, refer to the [AgentQnA UI Guide](./ui/svelte/README.md).
+
 ## How to register your own tools with agent
 
-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/README.md).
+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/src/README.md).

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

@@ -0,0 +1,101 @@
+# Single node on-prem deployment with Docker Compose on AMD GPU
+
+This example showcases a hierarchical multi-agent system for question-answering applications. We deploy the example on Xeon. For LLMs, we use OpenAI models via API calls. For instructions on using open-source LLMs, please refer to the deployment guide [here](../../../../README.md).
+
+## Deployment with docker
+
+1. First, clone this repo.
+   ```
+   export WORKDIR=<your-work-directory>
+   cd $WORKDIR
+   git clone https://github.com/opea-project/GenAIExamples.git
+   ```
+2. Set up environment for this example </br>
+
+   ```
+   # Example: host_ip="192.168.1.1" or export host_ip="External_Public_IP"
+   export host_ip=$(hostname -I | awk '{print $1}')
+   # if you are in a proxy environment, also set the proxy-related environment variables
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+
+   export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+   #OPANAI_API_KEY if you want to use OpenAI models
+   export OPENAI_API_KEY=<your-openai-key>
+   # Set AMD GPU settings
+   export AGENTQNA_CARD_ID="card1"
+   export AGENTQNA_RENDER_ID="renderD136"
+   ```
+
+3. Deploy the retrieval tool (i.e., DocIndexRetriever mega-service)
+
+   First, launch the mega-service.
+
+   ```
+   cd $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool
+   bash launch_retrieval_tool.sh
+   ```
+
+   Then, ingest data into the vector database. Here we provide an example. You can ingest your own data.
+
+   ```
+   bash run_ingest_data.sh
+   ```
+
+4. Launch Tool service
+   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
+   ```
+5. Launch `Agent` service
+
+   ```
+   cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/amd/gpu/rocm
+   bash launch_agent_service_tgi_rocm.sh
+   ```
+
+6. [Optional] Build `Agent` docker image if pulling images failed.
+
+   ```
+   git clone https://github.com/opea-project/GenAIComps.git
+   cd GenAIComps
+   docker build -t opea/agent:latest -f comps/agent/src/Dockerfile .
+   ```
+
+## Validate services
+
+First look at logs of the agent docker containers:
+
+```
+# worker agent
+docker logs rag-agent-endpoint
+```
+
+```
+# supervisor agent
+docker logs react-agent-endpoint
+```
+
+You should see something like "HTTP server setup successful" if the docker containers are started successfully.</p>
+
+Second, validate worker agent:
+
+```
+curl http://${host_ip}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "query": "Most recent album by Taylor Swift"
+    }'
+```
+
+Third, validate supervisor agent:
+
+```
+curl http://${host_ip}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "query": "Most recent album by Taylor Swift"
+    }'
+```
+
+## How to register your own tools with agent
+
+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/src/README.md).

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

@@ -0,0 +1,97 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  agent-tgi-server:
+    image: ${AGENTQNA_TGI_IMAGE}
+    container_name: agent-tgi-server
+    ports:
+      - "${AGENTQNA_TGI_SERVICE_PORT-8085}:80"
+    volumes:
+      - /var/opea/agent-service/:/data
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: "http://${HOST_IP}:${AGENTQNA_TGI_SERVICE_PORT}"
+      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+    shm_size: 1g
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/${AGENTQNA_CARD_ID}:/dev/dri/${AGENTQNA_CARD_ID}
+      - /dev/dri/${AGENTQNA_RENDER_ID}:/dev/dri/${AGENTQNA_RENDER_ID}
+    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: opea/agent:latest
+    container_name: rag-agent-endpoint
+    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_llama
+      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
+
+  supervisor-react-agent:
+    image: opea/agent:latest
+    container_name: react-agent-endpoint
+    depends_on:
+      - agent-tgi-server
+      - worker-rag-agent
+    volumes:
+      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
+      - ${TOOLSET_PATH}:/home/user/tools/
+    ports:
+      - "${AGENTQNA_FRONTEND_PORT}:9090"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: react_langgraph
+      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: false
+      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
+      port: 9090

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

@@ -0,0 +1,47 @@
+# 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:2.3.1-rocm
+export AGENTQNA_TGI_SERVICE_PORT="8085"
+
+# LLM related environment variables
+export AGENTQNA_CARD_ID="card1"
+export AGENTQNA_RENDER_ID="renderD136"
+export HF_CACHE_DIR=${HF_CACHE_DIR}
+ls $HF_CACHE_DIR
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+#export NUM_SHARDS=4
+export LLM_ENDPOINT_URL="http://${ip_address}:${AGENTQNA_TGI_SERVICE_PORT}"
+export temperature=0.01
+export max_new_tokens=512
+
+# agent related environment variables
+export AGENTQNA_WORKER_AGENT_SERVICE_PORT="9095"
+export TOOLSET_PATH=/home/huggingface/datamonsters/amd-opea/GenAIExamples/AgentQnA/tools/
+echo "TOOLSET_PATH=${TOOLSET_PATH}"
+export recursion_limit_worker=12
+export recursion_limit_supervisor=10
+export WORKER_AGENT_URL="http://${ip_address}:${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="9090"
+
+#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"
+
+docker compose -f compose.yaml up -d

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

@@ -0,0 +1,46 @@
+#!/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:2.3.1-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 $HF_CACHE_DIR
+export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
+export NUM_SHARDS=4
+export LLM_ENDPOINT_URL="http://${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"

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

@@ -1,3 +1,123 @@
-# Deployment on Xeon
+# Single node on-prem deployment with Docker Compose on Xeon Scalable processors
 
-We deploy the retrieval tool on Xeon. For LLMs, we support OpenAI models via API calls. For instructions on using open-source LLMs, please refer to the deployment guide [here](../../../../README.md).
+This example showcases a hierarchical multi-agent system for question-answering applications. We deploy the example on Xeon. For LLMs, we use OpenAI models via API calls. For instructions on using open-source LLMs, please refer to the deployment guide [here](../../../../README.md).
+
+## Deployment with docker
+
+1. First, clone this repo.
+   ```
+   export WORKDIR=<your-work-directory>
+   cd $WORKDIR
+   git clone https://github.com/opea-project/GenAIExamples.git
+   ```
+2. Set up environment for this example </br>
+
+   ```
+   # Example: host_ip="192.168.1.1" or export host_ip="External_Public_IP"
+   export host_ip=$(hostname -I | awk '{print $1}')
+   # if you are in a proxy environment, also set the proxy-related environment variables
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+
+   export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+   #OPANAI_API_KEY if you want to use OpenAI models
+   export OPENAI_API_KEY=<your-openai-key>
+   ```
+
+3. Deploy the retrieval tool (i.e., DocIndexRetriever mega-service)
+
+   First, launch the mega-service.
+
+   ```
+   cd $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool
+   bash launch_retrieval_tool.sh
+   ```
+
+   Then, ingest data into the vector database. Here we provide an example. You can ingest your own data.
+
+   ```
+   bash run_ingest_data.sh
+   ```
+
+4. Prepare SQL database
+   In this example, we will use the SQLite database provided in the [TAG-Bench](https://github.com/TAG-Research/TAG-Bench/tree/main). Run the commands below.
+
+   ```
+   # Download data
+   cd $WORKDIR
+   git clone https://github.com/TAG-Research/TAG-Bench.git
+   cd TAG-Bench/setup
+   chmod +x get_dbs.sh
+   ./get_dbs.sh
+   ```
+
+5. Launch Tool service
+   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
+   ```
+6. Launch multi-agent system
+
+   The configurations of the supervisor agent and the worker agents are defined in the docker-compose yaml file. We currently use openAI GPT-4o-mini as LLM.
+
+   ```
+   cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
+   bash launch_agent_service_openai.sh
+   ```
+
+7. [Optional] Build `Agent` docker image if pulling images failed.
+
+   ```
+   git clone https://github.com/opea-project/GenAIComps.git
+   cd GenAIComps
+   docker build -t opea/agent:latest -f comps/agent/src/Dockerfile .
+   ```
+
+## Validate services
+
+First look at logs of the agent docker containers:
+
+```
+# worker RAG agent
+docker logs rag-agent-endpoint
+
+# worker SQL agent
+docker logs sql-agent-endpoint
+```
+
+```
+# supervisor agent
+docker logs react-agent-endpoint
+```
+
+You should see something like "HTTP server setup successful" if the docker containers are started successfully.</p>
+
+Second, validate worker RAG agent:
+
+```
+curl http://${host_ip}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "Michael Jackson song Thriller"
+    }'
+```
+
+Third, validate worker SQL agent:
+
+```
+curl http://${host_ip}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "How many employees are in the company?"
+    }'
+```
+
+Finally, validate supervisor agent:
+
+```
+curl http://${host_ip}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "How many albums does Iron Maiden have?"
+    }'
+```
+
+## How to register your own tools with agent
+
+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/src/README.md).

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

@@ -3,7 +3,7 @@
 
 services:
   worker-rag-agent:
-    image: opea/agent-langchain:latest
+    image: opea/agent:latest
     container_name: rag-agent-endpoint
     volumes:
       - ${TOOLSET_PATH}:/home/user/tools/
@@ -19,7 +19,7 @@ services:
       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}
@@ -31,9 +31,36 @@ services:
       LANGCHAIN_PROJECT: "opea-worker-agent-service"
       port: 9095
 
+  worker-sql-agent:
+    image: opea/agent:latest
+    container_name: sql-agent-endpoint
+    volumes:
+      - ${WORKDIR}/TAG-Bench/:/home/user/TAG-Bench # SQL database
+    ports:
+      - "9096:9096"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: sql_agent
+      db_name: ${db_name}
+      db_path: ${db_path}
+      use_hints: false
+      hints_file: /home/user/TAG-Bench/${db_name}_hints.csv
+      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
@@ -51,7 +78,7 @@ services:
       model: ${model}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      streaming: false
+      stream: false
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}

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

@@ -1,6 +1,9 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+pushd "../../../../../" > /dev/null
+source .set_env.sh
+popd > /dev/null
 export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
 export ip_address=$(hostname -I | awk '{print $1}')
 export recursion_limit_worker=12
@@ -10,7 +13,10 @@ export temperature=0
 export max_new_tokens=4096
 export OPENAI_API_KEY=${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=california_schools
+export db_path="sqlite:////home/user/TAG-Bench/dev_folder/dev_databases/${db_name}/${db_name}.sqlite"
 
 docker compose -f compose_openai.yaml up -d

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

@@ -0,0 +1,147 @@
+# Single node on-prem deployment AgentQnA on Gaudi
+
+This example showcases a hierarchical multi-agent system for question-answering applications. We deploy the example on Gaudi using open-source LLMs.
+For more details, please refer to the deployment guide [here](../../../../README.md).
+
+## Deployment with docker
+
+1. First, clone this repo.
+   ```
+   export WORKDIR=<your-work-directory>
+   cd $WORKDIR
+   git clone https://github.com/opea-project/GenAIExamples.git
+   ```
+2. Set up environment for this example </br>
+
+   ```
+   # Example: host_ip="192.168.1.1" or export host_ip="External_Public_IP"
+   export host_ip=$(hostname -I | awk '{print $1}')
+   # if you are in a proxy environment, also set the proxy-related environment variables
+   export http_proxy="Your_HTTP_Proxy"
+   export https_proxy="Your_HTTPs_Proxy"
+   # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
+   export no_proxy="Your_No_Proxy"
+
+   export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+   # for using open-source llms
+   export HUGGINGFACEHUB_API_TOKEN=<your-HF-token>
+   # Example export HF_CACHE_DIR=$WORKDIR so that no need to redownload every time
+   export HF_CACHE_DIR=<directory-where-llms-are-downloaded>
+
+   ```
+
+3. Deploy the retrieval tool (i.e., DocIndexRetriever mega-service)
+
+   First, launch the mega-service.
+
+   ```
+   cd $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool
+   bash launch_retrieval_tool.sh
+   ```
+
+   Then, ingest data into the vector database. Here we provide an example. You can ingest your own data.
+
+   ```
+   bash run_ingest_data.sh
+   ```
+
+4. Prepare SQL database
+   In this example, we will use the Chinook SQLite database. Run the commands below.
+
+   ```
+   # Download data
+   cd $WORKDIR
+   git clone https://github.com/lerocha/chinook-database.git
+   cp chinook-database/ChinookDatabase/DataSources/Chinook_Sqlite.sqlite $WORKDIR/GenAIExamples/AgentQnA/tests/
+   ```
+
+5. Launch Tool service
+   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
+   ```
+6. Launch multi-agent system
+
+   On Gaudi2 we will serve `meta-llama/Meta-Llama-3.1-70B-Instruct` using vllm.
+
+   First build vllm-gaudi docker image.
+
+   ```bash
+   cd $WORKDIR
+   git clone https://github.com/vllm-project/vllm.git
+   cd ./vllm
+   git checkout v0.6.6
+   docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:latest --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
+   ```
+
+   Then launch vllm on Gaudi2 with the command below.
+
+   ```bash
+   vllm_port=8086
+   model="meta-llama/Meta-Llama-3.1-70B-Instruct"
+   docker run -d --runtime=habana --rm --name "vllm-gaudi-server" -e HABANA_VISIBLE_DEVICES=0,1,2,3 -p $vllm_port:8000 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host opea/vllm-gaudi:latest --model ${model} --max-seq-len-to-capture 16384 --tensor-parallel-size 4
+   ```
+
+   Then launch Agent microservices.
+
+   ```bash
+   cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
+   bash launch_agent_service_gaudi.sh
+   ```
+
+7. [Optional] Build `Agent` docker image if pulling images failed.
+
+   If docker image pulling failed in Step 6 above, build the agent docker image with the commands below. After image build, try Step 6 again.
+
+   ```
+   git clone https://github.com/opea-project/GenAIComps.git
+   cd GenAIComps
+   docker build -t opea/agent:latest -f comps/agent/src/Dockerfile .
+   ```
+
+## Validate services
+
+First look at logs of the agent docker containers:
+
+```
+# worker RAG agent
+docker logs rag-agent-endpoint
+
+# worker SQL agent
+docker logs sql-agent-endpoint
+```
+
+```
+# supervisor agent
+docker logs react-agent-endpoint
+```
+
+You should see something like "HTTP server setup successful" if the docker containers are started successfully.</p>
+
+Second, validate worker RAG agent:
+
+```
+curl http://${host_ip}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "Michael Jackson song Thriller"
+    }'
+```
+
+Third, validate worker SQL agent:
+
+```
+curl http://${host_ip}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "How many employees are in the company?"
+    }'
+```
+
+Finally, validate supervisor agent:
+
+```
+curl http://${host_ip}:9090/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "messages": "How many albums does Iron Maiden have?"
+    }'
+```
+
+## How to register your own tools with agent
+
+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/src/README.md).

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

@@ -3,10 +3,9 @@
 
 services:
   worker-rag-agent:
-    image: opea/agent-langchain:latest
+    image: opea/agent:latest
     container_name: rag-agent-endpoint
     volumes:
-      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9095:9095"
@@ -15,13 +14,13 @@ services:
       ip_address: ${ip_address}
       strategy: rag_agent_llama
       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}
@@ -33,14 +32,41 @@ 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 # test db
+    ports:
+      - "9096:9096"
+    ipc: host
+    environment:
+      ip_address: ${ip_address}
+      strategy: sql_agent_llama
+      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: opea/agent:latest
     container_name: react-agent-endpoint
     depends_on:
       - 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"
@@ -49,13 +75,13 @@ services:
       ip_address: ${ip_address}
       strategy: react_llama
       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: false
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}
@@ -66,4 +92,5 @@ 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

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

@@ -1,6 +1,9 @@
 # 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=$WORKPATH/../../
 echo "WORKDIR=${WORKDIR}"
@@ -13,8 +16,8 @@ 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://${ip_address}:8085"
-export temperature=0.01
+export LLM_ENDPOINT_URL="http://${ip_address}:8086"
+export temperature=0
 export max_new_tokens=4096
 
 # agent related environment variables
@@ -23,7 +26,11 @@ 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"
+
 docker compose -f compose.yaml up -d

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

@@ -3,7 +3,7 @@
 
 services:
   tgi-server:
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.5
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
     container_name: tgi-server
     ports:
       - "8085:80"

AgentQnA/docker_image_build/build.yaml

@@ -2,12 +2,18 @@
 # 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}

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/gaudi-values.yaml

@@ -0,0 +1,16 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Accelerate inferencing in heaviest components to improve performance
+# by overriding their subchart values
+
+vllm:
+  enabled: true
+  image:
+    repository: opea/vllm-gaudi
+supervisor:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+ragagent:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm
+sqlagent:
+  llm_endpoint_url: http://{{ .Release.Name }}-vllm

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/tests/_test_compose_openai_on_xeon.sh

@@ -15,7 +15,7 @@ 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() {

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

@@ -11,17 +11,16 @@ 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 ../
+        git clone --depth 1 --branch ${opea_branch:-"main"} https://github.com/opea-project/GenAIComps.git
     fi
 }
 
 
 function build_docker_images_for_retrieval_tool(){
     cd $WORKDIR/GenAIExamples/DocIndexRetriever/docker_image_build/
-    # git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${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"
+    service_list="doc-index-retriever dataprep embedding retriever reranking"
     docker compose -f build.yaml build ${service_list} --no-cache
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
 
@@ -35,6 +34,26 @@ function build_agent_docker_image() {
     docker compose -f build.yaml build --no-cache
 }
 
+function build_vllm_docker_image() {
+    echo "Building the vllm docker image"
+    cd $WORKPATH
+    echo $WORKPATH
+    if [ ! -d "./vllm-fork" ]; then
+        git clone https://github.com/HabanaAI/vllm-fork.git
+    fi
+    cd ./vllm-fork
+    git checkout v0.6.4.post2+Gaudi-1.19.0
+    sed -i 's/triton/triton==3.1.0/g' requirements-hpu.txt
+    docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:ci --shm-size=128g . --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy
+    if [ $? -ne 0 ]; then
+        echo "opea/vllm-gaudi:ci failed"
+        exit 1
+    else
+        echo "opea/vllm-gaudi:ci successful"
+    fi
+}
+
+
 function main() {
     echo "==================== Build docker images for retrieval tool ===================="
     build_docker_images_for_retrieval_tool
@@ -43,6 +62,12 @@ function main() {
     echo "==================== Build agent docker image ===================="
     build_agent_docker_image
     echo "==================== Build agent docker image completed ===================="
+
+    echo "==================== Build vllm docker image ===================="
+    build_vllm_docker_image
+    echo "==================== Build vllm docker image completed ===================="
+
+    docker image ls | grep vllm
 }
 
 main

AgentQnA/tests/step2_start_retrieval_tool.sh

@@ -7,6 +7,7 @@ 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=$WORKDIR/hf_cache
 if [ ! -d "$HF_CACHE_DIR" ]; then

AgentQnA/tests/step4_launch_and_validate_agent_tgi.sh

@@ -8,15 +8,22 @@ 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 TOOLSET_PATH=$WORKPATH/tools/
 export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+model="meta-llama/Meta-Llama-3.1-70B-Instruct"
 
-export HF_CACHE_DIR=$WORKDIR/hf_cache
+export HF_CACHE_DIR=/data2/huggingface
 if [ ! -d "$HF_CACHE_DIR" ]; then
+    HF_CACHE_DIR=$WORKDIR/hf_cache
     mkdir -p "$HF_CACHE_DIR"
 fi
+echo  "HF_CACHE_DIR=$HF_CACHE_DIR"
 ls $HF_CACHE_DIR
 
+vllm_port=8086
+vllm_volume=${HF_CACHE_DIR}
+
 function start_tgi(){
     echo "Starting tgi-gaudi server"
     cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi
@@ -24,14 +31,67 @@ function start_tgi(){
 
 }
 
+function start_vllm_service_70B() {
+
+    echo "token is ${HF_TOKEN}"
+
+    echo "start vllm gaudi service"
+    echo "**************model is $model**************"
+    vllm_image=opea/vllm-gaudi:ci
+    docker run -d --runtime=habana --rm --name "vllm-gaudi-server" -e HABANA_VISIBLE_DEVICES=0,1,2,3 -p $vllm_port:8000 -v $vllm_volume:/data -e HF_TOKEN=$HF_TOKEN -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_HOME=/data -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e PT_HPU_ENABLE_LAZY_COLLECTIVES=true -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e no_proxy=$no_proxy -e VLLM_SKIP_WARMUP=true --cap-add=sys_nice --ipc=host $vllm_image --model ${model} --max-seq-len-to-capture 16384 --tensor-parallel-size 4
+    sleep 5s
+    echo "Waiting vllm gaudi ready"
+    n=0
+    LOG_PATH=$PWD
+    until [[ "$n" -ge 100 ]] || [[ $ready == true ]]; do
+        docker logs vllm-gaudi-server
+        docker logs vllm-gaudi-server &> ${LOG_PATH}/vllm-gaudi-service.log
+        n=$((n+1))
+        if grep -q "Uvicorn running on" ${LOG_PATH}/vllm-gaudi-service.log; then
+            break
+        fi
+        if grep -q "No such container" ${LOG_PATH}/vllm-gaudi-service.log; then
+            echo "container vllm-gaudi-server not found"
+            exit 1
+        fi
+        sleep 5s
+    done
+    sleep 5s
+    echo "Service started successfully"
+}
+
+
+function prepare_data() {
+    cd $WORKDIR
+
+    echo "Downloading data..."
+    git clone https://github.com/TAG-Research/TAG-Bench.git
+    cd TAG-Bench/setup
+    chmod +x get_dbs.sh
+    ./get_dbs.sh
+
+    echo "Split data..."
+    cd $WORKPATH/tests/sql_agent_test
+    bash run_data_split.sh
+
+    echo "Data preparation done!"
+}
+
+function download_chinook_data(){
+    echo "Downloading chinook data..."
+    cd $WORKDIR
+    git clone https://github.com/lerocha/chinook-database.git
+    cp chinook-database/ChinookDatabase/DataSources/Chinook_Sqlite.sqlite $WORKDIR/GenAIExamples/AgentQnA/tests/
+}
+
 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
-    sleep 10
+    bash launch_agent_service_gaudi.sh
+    sleep 2m
 }
 
 function validate() {
@@ -49,35 +109,76 @@ function validate() {
 }
 
 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"
-    # }')
+    # # test worker rag agent
+    echo "======================Testing worker rag agent======================"
     export agent_port="9095"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py)
+    prompt="Tell me about Michael Jackson song Thriller"
+    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt")
+    # echo $CONTENT
     local EXIT_CODE=$(validate "$CONTENT" "Thriller" "rag-agent-endpoint")
-    docker logs rag-agent-endpoint
+    echo $EXIT_CODE
+    local EXIT_CODE="${EXIT_CODE:0-1}"
     if [ "$EXIT_CODE" == "1" ]; then
+        docker logs rag-agent-endpoint
         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"
-    # }')
-    export agent_port="9090"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py)
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "react-agent-endpoint")
-    docker logs react-agent-endpoint
+    # # test worker sql agent
+    echo "======================Testing worker sql agent======================"
+    export agent_port="9096"
+    prompt="How many employees are there in the company?"
+    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt")
+    local EXIT_CODE=$(validate "$CONTENT" "8" "sql-agent-endpoint")
+    echo $CONTENT
+    # echo $EXIT_CODE
+    local EXIT_CODE="${EXIT_CODE:0-1}"
     if [ "$EXIT_CODE" == "1" ]; then
+        docker logs sql-agent-endpoint
+        exit 1
+    fi
+
+    # test supervisor react agent
+    echo "======================Testing supervisor react agent======================"
+    export agent_port="9090"
+    prompt="How many albums does Iron Maiden have?"
+    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt")
+    local EXIT_CODE=$(validate "$CONTENT" "21" "react-agent-endpoint")
+    # echo $CONTENT
+    echo $EXIT_CODE
+    local EXIT_CODE="${EXIT_CODE:0-1}"
+    if [ "$EXIT_CODE" == "1" ]; then
+        docker logs react-agent-endpoint
         exit 1
     fi
 
 }
 
+function remove_data() {
+    echo "Removing data..."
+    cd $WORKDIR
+    if [ -d "TAG-Bench" ]; then
+        rm -rf TAG-Bench
+    fi
+    echo "Data removed!"
+}
+
+function remove_chinook_data(){
+    echo "Removing chinook data..."
+    cd $WORKDIR
+    if [ -d "chinook-database" ]; then
+        rm -rf chinook-database
+    fi
+    echo "Chinook data removed!"
+}
+
 function main() {
-    echo "==================== Start TGI ===================="
-    start_tgi
-    echo "==================== TGI started ===================="
+    echo "==================== Prepare data ===================="
+    download_chinook_data
+    echo "==================== Data prepare done ===================="
+
+    echo "==================== Start VLLM service ===================="
+    start_vllm_service_70B
+    echo "==================== VLLM service started ===================="
 
     echo "==================== Start agent ===================="
     start_agent_and_api_server
@@ -88,4 +189,8 @@ function main() {
     echo "==================== Agent service validated ===================="
 }
 
+remove_data
+remove_chinook_data
 main
+remove_data
+remove_chinook_data

AgentQnA/tests/step4a_launch_and_validate_agent_tgi_on_rocm.sh

@@ -0,0 +1,76 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -ex
+
+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/amd/gpu/rocm
+    bash launch_agent_service_tgi_rocm.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 "$CONTENT" "Thriller" "react-agent-endpoint")
+    docker logs rag-agent-endpoint
+    if [ "$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.py

@@ -1,6 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+import argparse
 import os
 
 import requests
@@ -9,17 +10,47 @@ import requests
 def generate_answer_agent_api(url, prompt):
     proxies = {"http": ""}
     payload = {
-        "query": prompt,
+        "messages": prompt,
     }
     response = requests.post(url, json=payload, proxies=proxies)
     answer = response.json()["text"]
     return answer
 
 
+def process_request(url, query, is_stream=False):
+    proxies = {"http": ""}
+
+    payload = {
+        "messages": query,
+    }
+
+    try:
+        resp = requests.post(url=url, json=payload, proxies=proxies, stream=is_stream)
+        if not is_stream:
+            ret = resp.json()["text"]
+            print(ret)
+        else:
+            for line in resp.iter_lines(decode_unicode=True):
+                print(line)
+            ret = None
+
+        resp.raise_for_status()  # Raise an exception for unsuccessful HTTP status codes
+        return ret
+    except requests.exceptions.RequestException as e:
+        ret = f"An error occurred:{e}"
+        print(ret)
+        return False
+
+
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--prompt", type=str)
+    parser.add_argument("--stream", action="store_true")
+    args = parser.parse_args()
+
     ip_address = os.getenv("ip_address", "localhost")
-    agent_port = os.getenv("agent_port", "9095")
+    agent_port = os.getenv("agent_port", "9090")
     url = f"http://{ip_address}:{agent_port}/v1/chat/completions"
-    prompt = "Tell me about Michael Jackson song thriller"
-    answer = generate_answer_agent_api(url, prompt)
-    print(answer)
+    prompt = args.prompt
+
+    process_request(url, prompt, args.stream)

AgentQnA/tests/test_compose_on_gaudi.sh

@@ -1,8 +1,7 @@
 #!/bin/bash
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-
-set -e
+set -xe
 
 WORKPATH=$(dirname "$PWD")
 export WORKDIR=$WORKPATH/../../
@@ -27,7 +26,7 @@ function stop_agent_docker() {
     done
 }
 
-function stop_tgi(){
+function stop_llm(){
     cd $WORKPATH/docker_compose/intel/hpu/gaudi/
     container_list=$(cat tgi_gaudi.yaml | grep container_name | cut -d':' -f2)
     for container_name in $container_list; do
@@ -36,6 +35,14 @@ function stop_tgi(){
         if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
     done
 
+    cid=$(docker ps -aq --filter "name=vllm-gaudi-server")
+    echo "Stopping container $cid"
+    if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
+
+    cid=$(docker ps -aq --filter "name=test-comps-vllm-gaudi-service")
+    echo "Stopping container $cid"
+    if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
+
 }
 
 function stop_retrieval_tool() {
@@ -52,7 +59,7 @@ function stop_retrieval_tool() {
 echo "workpath: $WORKPATH"
 echo "=================== Stop containers ===================="
 stop_crag
-stop_tgi
+stop_llm
 stop_agent_docker
 stop_retrieval_tool
 
@@ -78,8 +85,9 @@ echo "=================== #5 Stop agent and API server===================="
 stop_crag
 stop_agent_docker
 stop_retrieval_tool
+stop_llm
 echo "=================== #5 Agent and API server stopped===================="
 
 echo y | docker system prune
 
-echo "ALL DONE!"
+echo "ALL DONE!!"

AgentQnA/tests/test_compose_on_rocm.sh

@@ -0,0 +1,75 @@
+#!/bin/bash
+# Copyright (C) 2024 Advanced Micro Devices, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+set -xe
+
+WORKPATH=$(dirname "$PWD")
+export WORKDIR=$WORKPATH/../../
+echo "WORKDIR=${WORKDIR}"
+export ip_address=$(hostname -I | awk '{print $1}')
+export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+
+function stop_crag() {
+    cid=$(docker ps -aq --filter "name=kdd-cup-24-crag-service")
+    echo "Stopping container kdd-cup-24-crag-service with cid $cid"
+    if [[ ! -z "$cid" ]]; then docker rm $cid -f && sleep 1s; fi
+}
+
+function stop_agent_docker() {
+    cd $WORKPATH/docker_compose/amd/gpu/rocm
+    # docker compose -f compose.yaml down
+    container_list=$(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 $cid -f && sleep 1s; fi
+    done
+}
+
+function stop_retrieval_tool() {
+    echo "Stopping Retrieval tool"
+    local RETRIEVAL_TOOL_PATH=$WORKPATH/../DocIndexRetriever
+    cd $RETRIEVAL_TOOL_PATH/docker_compose/intel/cpu/xeon/
+    # docker compose -f compose.yaml down
+    container_list=$(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 "workpath: $WORKPATH"
+echo "=================== Stop containers ===================="
+stop_crag
+stop_agent_docker
+stop_retrieval_tool
+
+cd $WORKPATH/tests
+
+echo "=================== #1 Building docker images===================="
+bash step1_build_images.sh
+echo "=================== #1 Building docker images completed===================="
+
+echo "=================== #2 Start retrieval tool===================="
+bash step2_start_retrieval_tool.sh
+echo "=================== #2 Retrieval tool started===================="
+
+echo "=================== #3 Ingest data and validate retrieval===================="
+bash step3_ingest_data_and_validate_retrieval.sh
+echo "=================== #3 Data ingestion and validation completed===================="
+
+echo "=================== #4 Start agent and API server===================="
+bash step4a_launch_and_validate_agent_tgi_on_rocm.sh
+echo "=================== #4 Agent test passed ===================="
+
+echo "=================== #5 Stop agent and API server===================="
+stop_crag
+stop_agent_docker
+stop_retrieval_tool
+echo "=================== #5 Agent and API server stopped===================="
+
+echo y | docker system prune
+
+echo "ALL DONE!!"

AgentQnA/tools/supervisor_agent_tools.yaml

@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: Apache-2.0
 
 search_knowledge_base:
-  description: Search knowledge base for a given query. Returns text related to the query.
+  description: Search a knowledge base for a given query. Returns text related to the query.
   callable_api: tools.py:search_knowledge_base
   args_schema:
     query:
@@ -10,6 +10,15 @@ search_knowledge_base:
       description: query
   return_output: retrieved_data
 
+search_artist_database:
+  description: Search a SQL database on artists and their music with a natural language query. Returns text related to the query.
+  callable_api: tools.py:search_sql_database
+  args_schema:
+    query:
+      type: str
+      description: natural language query
+  return_output: retrieved_data
+
 get_artist_birth_place:
   description: Get the birth place of an artist.
   callable_api: tools.py:get_artist_birth_place

AgentQnA/tools/tools.py

@@ -8,13 +8,30 @@ from tools.pycragapi import CRAG
 
 
 def search_knowledge_base(query: str) -> str:
-    """Search the knowledge base for a specific query."""
-    # use worker agent (DocGrader) to search the knowledge base
+    """Search a knowledge base about music and singers for a given query.
+
+    Returns text related to the query.
+    """
     url = os.environ.get("WORKER_AGENT_URL")
     print(url)
     proxies = {"http": ""}
     payload = {
-        "query": query,
+        "messages": query,
+    }
+    response = requests.post(url, json=payload, proxies=proxies)
+    return response.json()["text"]
+
+
+def search_sql_database(query: str) -> str:
+    """Search a SQL database on artists and their music with a natural language query.
+
+    Returns text related to the query.
+    """
+    url = os.environ.get("SQL_AGENT_URL")
+    print(url)
+    proxies = {"http": ""}
+    payload = {
+        "messages": query,
     }
     response = requests.post(url, json=payload, proxies=proxies)
     return response.json()["text"]

AgentQnA/tools/worker_agent_tools.py

@@ -12,7 +12,7 @@ def search_knowledge_base(query: str) -> str:
     print(url)
     proxies = {"http": ""}
     payload = {
-        "messages": query,
+        "text": query,
     }
     response = requests.post(url, json=payload, proxies=proxies)
     print(response)

AgentQnA/ui/docker/Dockerfile

@@ -0,0 +1,26 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Use node 20.11.1 as the base image
+FROM node:20.11.1
+
+# Update package manager and install Git
+RUN apt-get update -y && apt-get install -y git
+
+# Copy the front-end code repository
+COPY svelte /home/user/svelte
+
+# Set the working directory
+WORKDIR /home/user/svelte
+
+# Install front-end dependencies
+RUN npm install
+
+# Build the front-end application
+RUN npm run build
+
+# Expose the port of the front-end application
+EXPOSE 5173
+
+# Run the front-end application in preview mode
+CMD ["npm", "run", "preview", "--", "--port", "5173", "--host", "0.0.0.0"]

AgentQnA/ui/svelte/.editorconfig

@@ -0,0 +1,10 @@
+[*]
+indent_style = tab
+
+[package.json]
+indent_style = space
+indent_size = 2
+
+[*.md]
+indent_style = space
+indent_size = 2

AgentQnA/ui/svelte/.env

@@ -0,0 +1 @@
+AGENT_URL = '/v1/chat/completions'

AgentQnA/ui/svelte/.eslintignore

@@ -0,0 +1,13 @@
+.DS_Store
+node_modules
+/build
+/.svelte-kit
+/package
+.env
+.env.*
+!.env.example
+
+# Ignore files for PNPM, NPM and YARN
+pnpm-lock.yaml
+package-lock.json
+yarn.lock

AgentQnA/ui/svelte/.eslintrc.cjs

@@ -0,0 +1,20 @@
+module.exports = {
+	root: true,
+	parser: "@typescript-eslint/parser",
+	extends: ["eslint:recommended", "plugin:@typescript-eslint/recommended", "prettier"],
+	plugins: ["svelte3", "@typescript-eslint", "neverthrow"],
+	ignorePatterns: ["*.cjs"],
+	overrides: [{ files: ["*.svelte"], processor: "svelte3/svelte3" }],
+	settings: {
+		"svelte3/typescript": () => require("typescript"),
+	},
+	parserOptions: {
+		sourceType: "module",
+		ecmaVersion: 2020,
+	},
+	env: {
+		browser: true,
+		es2017: true,
+		node: true,
+	},
+};

AgentQnA/ui/svelte/.prettierignore

@@ -0,0 +1,13 @@
+.DS_Store
+node_modules
+/build
+/.svelte-kit
+/package
+.env
+.env.*
+!.env.example
+
+# Ignore files for PNPM, NPM and YARN
+pnpm-lock.yaml
+package-lock.json
+yarn.lock

AgentQnA/ui/svelte/.prettierrc

@@ -0,0 +1,13 @@
+{
+	"pluginSearchDirs": [
+		"."
+	],
+	"overrides": [
+		{
+			"files": "*.svelte",
+			"options": {
+				"parser": "svelte"
+			}
+		}
+	]
+}

AgentQnA/ui/svelte/README.md

@@ -0,0 +1,60 @@
+# AgentQnA
+
+## 📸 Project Screenshots
+
+![project-screenshot](../../assets/img/agent_ui.png)
+![project-screenshot](../../assets/img/agent_ui_result.png)
+
+## 🧐 Features
+
+Here're some of the project's features:
+
+- Create Agent：Provide more precise answers based on user queries, showcase the high-quality output process of complex queries across different dimensions, and consolidate information to present comprehensive answers.
+
+## 🛠️ Get it Running
+
+1. Clone the repo.
+
+2. cd command to the current folder.
+
+   ```
+   cd AgentQnA/ui
+   ```
+
+3. Modify the required .env variables.
+
+   ```
+   AGENT_URL = ''
+   ```
+
+4. **For Local Development:**
+
+- Install the dependencies:
+
+  ```
+  npm install
+  ```
+
+- Start the development server:
+
+  ```
+  npm run dev
+  ```
+
+- The application will be available at `http://localhost:3000`.
+
+5. **For Docker Setup:**
+
+- Build the Docker image:
+
+  ```
+  docker build -t opea:agent-ui .
+  ```
+
+- Run the Docker container:
+
+  ```
+  docker run -d -p 3000:3000 --name agent-ui opea:agent-ui
+  ```
+
+- The application will be available at `http://localhost:3000`.

AgentQnA/ui/svelte/package.json

@@ -0,0 +1,60 @@
+{
+  "name": "agent-example",
+  "version": "0.0.1",
+  "private": true,
+  "scripts": {
+    "dev": "vite dev --host 0.0.0.0",
+    "build": "vite build",
+    "preview": "vite preview",
+    "check": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json",
+    "check:watch": "svelte-kit sync && svelte-check --tsconfig ./tsconfig.json --watch",
+    "lint": "prettier --check . && eslint .",
+    "format": "prettier --write ."
+  },
+  "devDependencies": {
+    "@fortawesome/free-solid-svg-icons": "6.2.0",
+    "@sveltejs/adapter-auto": "1.0.0-next.75",
+    "@sveltejs/kit": "^1.20.1",
+    "@tailwindcss/typography": "0.5.7",
+    "@types/debug": "4.1.7",
+    "@typescript-eslint/eslint-plugin": "^5.27.0",
+    "@typescript-eslint/parser": "^5.27.0",
+    "autoprefixer": "^10.4.7",
+    "daisyui": "^2.52.0",
+    "debug": "4.3.4",
+    "eslint": "^8.16.0",
+    "eslint-config-prettier": "^8.3.0",
+    "eslint-plugin-neverthrow": "1.1.4",
+    "eslint-plugin-svelte3": "^4.0.0",
+    "neverthrow": "5.0.0",
+    "pocketbase": "0.7.0",
+    "postcss": "^8.4.23",
+    "postcss-load-config": "^4.0.1",
+    "postcss-preset-env": "^8.3.2",
+    "prettier": "^2.8.8",
+    "prettier-plugin-svelte": "^2.7.0",
+    "prettier-plugin-tailwindcss": "^0.3.0",
+    "svelte": "^3.59.1",
+    "svelte-check": "^2.7.1",
+    "svelte-fa": "3.0.3",
+    "svelte-preprocess": "^4.10.7",
+    "tailwindcss": "^3.1.5",
+    "ts-pattern": "4.0.5",
+    "tslib": "^2.3.1",
+    "typescript": "^4.7.4",
+    "vite": "^4.3.9"
+  },
+  "type": "module",
+  "dependencies": {
+    "@heroicons/vue": "^2.1.5",
+    "echarts": "^5.4.2",
+    "flowbite-svelte": "^0.38.5",
+    "flowbite-svelte-icons": "^0.3.6",
+    "fuse.js": "^6.6.2",
+    "marked": "^15.0.0",
+    "ramda": "^0.29.0",
+    "sjcl": "^1.0.8",
+    "sse.js": "^0.6.1",
+    "svelte-notifications": "^0.9.98"
+  }
+}

AgentQnA/ui/svelte/postcss.config.cjs

@@ -0,0 +1,13 @@
+const tailwindcss = require("tailwindcss");
+const autoprefixer = require("autoprefixer");
+
+const config = {
+	plugins: [
+		//Some plugins, like tailwindcss/nesting, need to run before Tailwind,
+		tailwindcss(),
+		//But others, like autoprefixer, need to run after,
+		autoprefixer,
+	],
+};
+
+module.exports = config;

AgentQnA/ui/svelte/src/app.d.ts

@@ -0,0 +1,50 @@
+// Copyright (C) 2025 Intel Corporation
+// SPDX-License-Identifier: Apache-2.0
+
+// See: https://kit.svelte.dev/docs/types#app
+// import { Result} from "neverthrow";
+
+declare namespace App {
+	interface Locals {
+		user?: User;
+	}
+	// interface PageData { }
+	// interface PageError {}
+	// interface Platform {}
+}
+
+interface User {
+	id?: string;
+	email: string;
+	password?: string;
+	token?: string;
+	[key: string]: any;
+}
+
+type AuthResponse = Result<User>;
+
+interface AuthAdapter {
+	login(props: { email: string; password: string }): Promise<AuthResponse>;
+	signup(props: { email: string; password: string; password_confirm: string }): Promise<AuthResponse>;
+	validate_session(props: { token: string }): Promise<AuthResponse>;
+	logout(props: { token: string; email: string }): Promise<Result<void>>;
+	forgotPassword(props: { email: string; password: string }): Promise<Result<void>>;
+}
+
+interface ChatAdapter {
+	modelList(props: {}): Promise<Result<void>>;
+	txt2img(props: {}): Promise<Result<void>>;
+}
+
+interface ChatMessage {
+	role: string;
+	content: string;
+}
+
+interface ChatMessageType {
+	model: string;
+	knowledge: string;
+	temperature: string;
+	max_new_tokens: string;
+	topk: string;
+}

AgentQnA/ui/svelte/src/app.html

@@ -0,0 +1,17 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<!doctype html>
+<html lang="en">
+	<head>
+		<meta charset="utf-8" />
+		<link rel="icon" href="%sveltekit.assets%/favicon.png" />
+		<meta name="viewport" content="width=device-width" />
+		%sveltekit.head%
+	</head>
+	<body>
+		<div>%sveltekit.body%</div>
+	</body>
+</html>

AgentQnA/ui/svelte/src/app.postcss

@@ -0,0 +1,82 @@
+/* Write your global styles here, in PostCSS syntax */
+@tailwind base;
+@tailwind components;
+@tailwind utilities;
+
+.btn {
+	@apply flex-nowrap;
+}
+a.btn {
+	@apply no-underline;
+}
+.input {
+	@apply text-base;
+}
+
+.bg-dark-blue {
+	background-color: #004a86;
+}
+
+.bg-light-blue {
+	background-color: #0068b5;
+}
+
+.bg-turquoise {
+	background-color: #00a3f6;
+}
+
+.bg-header {
+	background-color: #ffffff;
+}
+
+.bg-button {
+	background-color: #0068b5;
+}
+
+.bg-title {
+	background-color: #f7f7f7;
+}
+
+.text-header {
+	color: #0068b5;
+}
+
+.text-button {
+	color: #0071c5;
+}
+
+.text-title-color {
+	color: rgb(38,38,38);
+}
+
+.font-intel {
+	font-family: "intel-clear","tahoma",Helvetica,"helvetica",Arial,sans-serif;
+}
+
+.font-title-intel {
+	font-family: "intel-one","intel-clear",Helvetica,Arial,sans-serif;
+}
+
+.bg-footer {
+	background-color: #e7e7e7;
+}
+
+.bg-light-green {
+	background-color: #d7f3a1;
+}
+
+.bg-purple {
+	background-color: #653171;
+}
+
+.bg-dark-blue {
+	background-color: #224678;
+}
+
+.border-input-color {
+	border-color: #605e5c;
+}
+
+.w-12\/12 {
+	width: 100%
+}

AgentQnA/ui/svelte/src/lib/assets/Agent/createSub.svelte

@@ -0,0 +1,25 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1731984271860"
+	class="w-8 h-8"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="11418"
+	width="200"
+	height="200"
+	><path
+		d="M0 0m170.666667 0l682.666666 0q170.666667 0 170.666667 170.666667l0 682.666666q0 170.666667-170.666667 170.666667l-682.666666 0q-170.666667 0-170.666667-170.666667l0-682.666666q0-170.666667 170.666667-170.666667Z"
+		fill="#1890FF"
+		fill-opacity=".1"
+		p-id="11419"
+	/><path
+		d="M404.352 552.661333a63.018667 63.018667 0 1 0 0-125.994666 63.018667 63.018667 0 0 0 0 125.994666z m0 213.333334a63.018667 63.018667 0 1 0 0-125.994667 63.018667 63.018667 0 0 0 0 125.994667z m-213.333333-426.666667a63.018667 63.018667 0 1 0 0-125.994667 63.018667 63.018667 0 0 0 0 125.994667z m669.653333-10.88H376.362667a35.669333 35.669333 0 0 1-35.114667-36.096c0-19.882667 15.786667-36.096 35.114667-36.096h484.394666c19.370667 0 35.157333 16.213333 35.157334 36.096a35.669333 35.669333 0 0 1-35.242667 36.096z m16.384 213.034667h-260.821333c-10.410667 0-18.901333-16.213333-18.901334-36.096 0-19.925333 8.490667-36.138667 18.901334-36.138667h260.864c10.410667 0 18.901333 16.213333 18.901333 36.138667-0.042667 19.882667-8.490667 36.096-18.944 36.096z m0 212.992h-260.821333c-10.410667 0-18.901333-16.213333-18.901334-36.096 0-19.925333 8.490667-36.096 18.901334-36.096h260.864c10.410667 0 18.901333 16.213333 18.901333 36.096-0.042667 19.882667-8.490667 36.096-18.944 36.096z"
+		fill="#1890FF"
+		p-id="11420"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/download.svelte

@@ -0,0 +1,9 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg class="w-3.5 h-3.5 me-2.5" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" fill="currentColor" viewBox="0 0 20 20">
+    <path d="M14.707 7.793a1 1 0 0 0-1.414 0L11 10.086V1.5a1 1 0 0 0-2 0v8.586L6.707 7.793a1 1 0 1 0-1.414 1.414l4 4a1 1 0 0 0 1.416 0l4-4a1 1 0 0 0-.002-1.414Z"/>
+    <path d="M18 12h-2.55l-2.975 2.975a3.5 3.5 0 0 1-4.95 0L4.55 12H2a2 2 0 0 0-2 2v4a2 2 0 0 0 2 2h16a2 2 0 0 0 2-2v-4a2 2 0 0 0-2-2Zm-3 5a1 1 0 1 1 0-2 1 1 0 0 1 0 2Z"/>
+  </svg>

AgentQnA/ui/svelte/src/lib/assets/Agent/eye.svelte

@@ -0,0 +1,16 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+						class="me-2 h-3 w-3"
+						aria-hidden="true"
+						xmlns="http://www.w3.org/2000/svg"
+						fill="currentColor"
+						viewBox="0 0 20 14"
+					>
+						<path
+							d="M10 0C4.612 0 0 5.336 0 7c0 1.742 3.546 7 10 7 6.454 0 10-5.258 10-7 0-1.664-4.612-7-10-7Zm0 10a3 3 0 1 1 0-6 3 3 0 0 1 0 6Z"
+						/>
+					</svg>

AgentQnA/ui/svelte/src/lib/assets/Agent/newAI.svelte

@@ -0,0 +1,97 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<!-- <svg class="h-11 w-11 flex-none overflow-visible" fill="none"
+	><defs
+		><filter
+			id="step-icon-2"
+			x="-3"
+			y="-1"
+			width="50"
+			height="50"
+			filterUnits="userSpaceOnUse"
+			color-interpolation-filters="sRGB"
+			><feFlood flood-opacity="0" result="BackgroundImageFix" /><feColorMatrix
+				in="SourceAlpha"
+				values="0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 127 0"
+				result="hardAlpha"
+			/><feOffset dy="2" /><feGaussianBlur stdDeviation="2.5" /><feComposite
+				in2="hardAlpha"
+				operator="out"
+			/><feColorMatrix
+				values="0 0 0 0 0.054902 0 0 0 0 0.647059 0 0 0 0 0.913725 0 0 0 0.12 0"
+			/><feBlend
+				in2="BackgroundImageFix"
+				result="effect1_dropShadow_804_95228"
+			/><feBlend
+				in="SourceGraphic"
+				in2="effect1_dropShadow_804_95228"
+				result="shape"
+			/></filter
+		></defs
+	><g filter="url(#step-icon-2)"
+		><path
+			d="M2.75 10A7.25 7.25 0 0 1 10 2.75h24A7.25 7.25 0 0 1 41.25 10v24A7.25 7.25 0 0 1 34 41.25H10A7.25 7.25 0 0 1 2.75 34V10Z"
+			fill="#EEF2FF"
+		/><path
+			d="M2.75 10A7.25 7.25 0 0 1 10 2.75h24A7.25 7.25 0 0 1 41.25 10v24A7.25 7.25 0 0 1 34 41.25H10A7.25 7.25 0 0 1 2.75 34V10Z"
+			stroke="#6366F1"
+			stroke-width="1.5"
+			stroke-linecap="round"
+			stroke-linejoin="round"
+		/></g
+	><path
+		fill-rule="evenodd"
+		clip-rule="evenodd"
+		d="M23 35.25c.69 0 1.25-.56 1.25-1.25A3.75 3.75 0 0 1 28 30.25a1.25 1.25 0 1 0 0-2.5A3.75 3.75 0 0 1 24.25 24a1.25 1.25 0 1 0-2.5 0A3.75 3.75 0 0 1 18 27.75a1.25 1.25 0 0 0 0 2.5A3.75 3.75 0 0 1 21.75 34c0 .69.56 1.25 1.25 1.25Z"
+		fill="#fff"
+	/><path
+		d="M28 27a.75.75 0 0 0 0 1.5V27Zm-4.5 7a.5.5 0 0 1-.5.5V36a2 2 0 0 0 2-2h-1.5Zm5-5a.5.5 0 0 1-.5.5V31a2 2 0 0 0 2-2h-1.5Zm-.5-.5a.5.5 0 0 1 .5.5H30a2 2 0 0 0-2-2v1.5Zm-5-5a.5.5 0 0 1 .5.5H25a2 2 0 0 0-2-2v1.5Zm-.5.5a.5.5 0 0 1 .5-.5V22a2 2 0 0 0-2 2h1.5Zm-5 5a.5.5 0 0 1 .5-.5V27a2 2 0 0 0-2 2h1.5Zm.5.5a.5.5 0 0 1-.5-.5H16a2 2 0 0 0 2 2v-1.5Zm5 5a.5.5 0 0 1-.5-.5H21a2 2 0 0 0 2 2v-1.5ZM18 31a3 3 0 0 1 3 3h1.5a4.5 4.5 0 0 0-4.5-4.5V31Zm3-7a3 3 0 0 1-3 3v1.5a4.5 4.5 0 0 0 4.5-4.5H21Zm7 3a3 3 0 0 1-3-3h-1.5a4.5 4.5 0 0 0 4.5 4.5V27Zm-3 7a3 3 0 0 1 3-3v-1.5a4.5 4.5 0 0 0-4.5 4.5H25Z"
+		fill="#6366F1"
+	/><path
+		fill-rule="evenodd"
+		clip-rule="evenodd"
+		d="M13 27.25c.69 0 1.25-.56 1.25-1.25 0-.966.784-1.75 1.75-1.75a1.25 1.25 0 1 0 0-2.5A1.75 1.75 0 0 1 14.25 20a1.25 1.25 0 1 0-2.5 0A1.75 1.75 0 0 1 10 21.75a1.25 1.25 0 0 0 0 2.5c.966 0 1.75.784 1.75 1.75 0 .69.56 1.25 1.25 1.25Z"
+		fill="#fff"
+	/><path
+		d="M16 21a.75.75 0 0 0 0 1.5V21Zm-2.5 5a.5.5 0 0 1-.5.5V28a2 2 0 0 0 2-2h-1.5Zm3-3a.5.5 0 0 1-.5.5V25a2 2 0 0 0 2-2h-1.5Zm-.5-.5a.5.5 0 0 1 .5.5H18a2 2 0 0 0-2-2v1.5Zm-3-3a.5.5 0 0 1 .5.5H15a2 2 0 0 0-2-2v1.5Zm-.5.5a.5.5 0 0 1 .5-.5V18a2 2 0 0 0-2 2h1.5Zm-3 3a.5.5 0 0 1 .5-.5V21a2 2 0 0 0-2 2h1.5Zm.5.5a.5.5 0 0 1-.5-.5H8a2 2 0 0 0 2 2v-1.5Zm3 3a.5.5 0 0 1-.5-.5H11a2 2 0 0 0 2 2v-1.5ZM10 25a1 1 0 0 1 1 1h1.5a2.5 2.5 0 0 0-2.5-2.5V25Zm1-5a1 1 0 0 1-1 1v1.5a2.5 2.5 0 0 0 2.5-2.5H11Zm5 1a1 1 0 0 1-1-1h-1.5a2.5 2.5 0 0 0 2.5 2.5V21Zm-1 5a1 1 0 0 1 1-1v-1.5a2.5 2.5 0 0 0-2.5 2.5H15Z"
+		fill="#6366F1"
+	/><path
+		opacity=".4"
+		d="M29.75 35.25h2.5a3 3 0 0 0 3-3v-20.5a3 3 0 0 0-3-3h-20.5a3 3 0 0 0-3 3v5.5M12.75 14.25h18.5"
+		stroke="#6366F1"
+		stroke-width="1.5"
+		stroke-linecap="round"
+		stroke-linejoin="round"
+	/></svg
+> -->
+
+<svg
+	t="1731984480564"
+	class="h-10 w-10"
+	viewBox="0 0 1114 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="29550"
+	width="200"
+	height="200"
+	><path
+		d="M1081.916235 788.781176H909.312v172.634353a24.696471 24.696471 0 0 1-49.332706 0V788.781176H687.314824a24.696471 24.696471 0 0 1 0-49.362823H859.949176V566.814118a24.696471 24.696471 0 0 1 49.332706 0v172.634353h172.664471a24.696471 24.696471 0 0 1 0 49.362823z"
+		fill="#0972E7"
+		p-id="29551"
+	/><path
+		d="M174.772706 143.028706h509.831529c43.550118 0 78.516706 35.689412 78.516706 80.173176v280.576c0 44.453647-34.966588 80.173176-78.516706 80.173177H174.772706c-43.550118 0-78.516706-35.719529-78.516706-80.173177V223.171765c0-43.851294 34.966588-80.173176 78.516706-80.173177z"
+		fill="#CAE4FF"
+		p-id="29552"
+	/><path
+		d="M335.600941 910.637176H104.899765c-24.545882 0-43.550118-20.028235-43.550118-45.086117V107.098353c0-25.057882 19.636706-45.086118 44.182588-45.086118h742.912c23.913412 0 44.182588 20.028235 44.182589 44.453647V282.503529c0 16.896 13.492706 31.322353 30.659764 31.322353a30.72 30.72 0 0 0 30.689883-31.322353V106.465882C953.976471 47.585882 906.721882 0 849.046588 0H104.899765C47.224471 0 0 48.218353 0 107.098353v758.452706c0 58.88 46.622118 107.098353 104.297412 107.098353h230.671059c16.564706 0 30.659765-13.793882 30.659764-31.322353a30.027294 30.027294 0 0 0-30.057411-30.689883z"
+		fill="#0972E7"
+		p-id="29553"
+	/><path
+		d="M709.180235 219.196235c0-16.896-13.492706-31.322353-30.659764-31.322353H171.760941c-16.564706 0-30.659765 13.793882-30.659765 31.322353 0 16.926118 13.492706 31.322353 30.659765 31.322353h506.75953a30.72 30.72 0 0 0 30.659764-31.322353zM171.760941 436.525176c-16.564706 0-30.659765 13.793882-30.659765 31.322353 0 16.896 13.492706 31.322353 30.659765 31.322353h344.786824c16.564706 0 30.689882-13.793882 30.689882-31.322353 0-16.926118-13.522824-31.322353-30.689882-31.322353H171.760941z"
+		fill="#0972E7"
+		p-id="29554"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/resource.svelte

@@ -0,0 +1,8 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg class="h-5 w-5 flex-shrink-0 text-[#1d4dd5]" viewBox="0 0 20 20" fill="currentColor" aria-hidden="true" data-slot="icon">
+  <path fill-rule="evenodd" d="M15.621 4.379a3 3 0 0 0-4.242 0l-7 7a3 3 0 0 0 4.241 4.243h.001l.497-.5a.75.75 0 0 1 1.064 1.057l-.498.501-.002.002a4.5 4.5 0 0 1-6.364-6.364l7-7a4.5 4.5 0 0 1 6.368 6.36l-3.455 3.553A2.625 2.625 0 1 1 9.52 9.52l3.45-3.451a.75.75 0 1 1 1.061 1.06l-3.45 3.451a1.125 1.125 0 0 0 1.587 1.595l3.454-3.553a3 3 0 0 0 0-4.242Z" clip-rule="evenodd"></path>
+</svg>

AgentQnA/ui/svelte/src/lib/assets/Agent/search.svelte

@@ -0,0 +1,13 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+			class="pointer-events-none absolute left-0 ml-4 hidden h-4 w-4 fill-current text-gray-500 group-hover:text-gray-400 sm:block"
+			xmlns="http://www.w3.org/2000/svg"
+			viewBox="0 0 20 20"
+			><path
+				d="M12.9 14.32a8 8 0 1 1 1.41-1.41l5.35 5.33-1.42 1.42-5.33-5.34zM8 14A6 6 0 1 0 8 2a6 6 0 0 0 0 12z"
+			/></svg
+		>

AgentQnA/ui/svelte/src/lib/assets/Agent/searchDelete.svelte

@@ -0,0 +1,17 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+				fill="none"
+				class="relative h-5 w-5"
+				stroke-linecap="round"
+				stroke-linejoin="round"
+				stroke-width="2"
+				stroke="currentColor"
+				viewBox="0 0 24 24"
+				><path
+					d="M10 14l2-2m0 0l2-2m-2 2l-2-2m2 2l2 2m7-2a9 9 0 11-18 0 9 9 0 0118 0z"
+				/></svg
+			>

AgentQnA/ui/svelte/src/lib/assets/Agent/searchResult.svelte

@@ -0,0 +1,20 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1731987484014"
+	class="w-5 h-5"
+	viewBox="0 0 1267 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="49311"
+	width="200"
+	height="200"
+	><path
+		d="M56.880762 910.214095H1194.666667a57.051429 57.051429 0 0 1 56.880762 56.905143A57.051429 57.051429 0 0 1 1194.666667 1024H56.880762A57.051429 57.051429 0 0 1 0 967.119238a57.051429 57.051429 0 0 1 56.880762-56.905143z m1024-56.880762H170.666667a114.102857 114.102857 0 0 1-113.785905-113.785904V113.785905A114.102857 114.102857 0 0 1 170.666667 0h910.214095A114.102857 114.102857 0 0 1 1194.666667 113.785905l-0.560762 625.761524C1194.105905 802.133333 1143.466667 853.333333 1080.880762 853.333333zM495.006476 227.328a198.948571 198.948571 0 0 0-63.219809 59.977143c-43.227429 63.707429-45.519238 150.747429-3.974096 215.600762 63.146667 99.547429 187.733333 120.027429 277.040762 63.146666l88.185905 88.161524a42.910476 42.910476 0 0 0 60.294095 0 42.910476 42.910476 0 0 0 0-60.294095l-88.746666-88.185905c49.493333-77.360762 40.399238-180.906667-26.745905-248.027428a198.92419 198.92419 0 0 0-242.834286-30.378667z m216.112762 170.910476a113.785905 113.785905 0 1 1-227.571809 0 113.785905 113.785905 0 0 1 227.571809 0z"
+		fill="#0377FF"
+		p-id="49312"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/star.svelte

@@ -0,0 +1,22 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1730766012593"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="11065"
+	class="w-4 h-4"
+	><path
+		d="M996.693333 494.933333l-341.333333-126.293333-126.293333-341.333333c-3.413333-13.653333-27.306667-13.653333-30.72 0l-126.293334 341.333333-341.333333 126.293333c-6.826667 3.413333-10.24 10.24-10.24 17.066667s3.413333 13.653333 10.24 17.066667l341.333333 126.293333 126.293334 341.333333c3.413333 6.826667 10.24 10.24 17.066666 10.24s13.653333-3.413333 17.066667-10.24l126.293333-341.333333 341.333334-126.293333c6.826667-3.413333 10.24-10.24 10.24-17.066667s-6.826667-13.653333-13.653334-17.066667z m-314.026666 34.133334h-153.6V682.666667c0 10.24-6.826667 17.066667-17.066667 17.066666s-17.066667-6.826667-17.066667-17.066666v-153.6H341.333333c-10.24 0-17.066667-6.826667-17.066666-17.066667s6.826667-17.066667 17.066666-17.066667h153.6V341.333333c0-10.24 6.826667-17.066667 17.066667-17.066666s17.066667 6.826667 17.066667 17.066666v153.6H682.666667c10.24 0 17.066667 6.826667 17.066666 17.066667s-6.826667 17.066667-17.066666 17.066667z"
+		fill="#ffffff"
+		p-id="11066"
+	/><path
+		d="M293.546667 703.146667l-136.533334 136.533333c-6.826667 6.826667-6.826667 17.066667 0 23.893333 3.413333 3.413333 6.826667 3.413333 13.653334 3.413334s10.24 0 13.653333-3.413334l136.533333-136.533333c6.826667-6.826667 6.826667-17.066667 0-23.893333s-20.48-6.826667-27.306666 0zM716.8 324.266667c3.413333 0 10.24 0 13.653333-3.413334l136.533334-136.533333c6.826667-6.826667 6.826667-17.066667 0-23.893333s-17.066667-6.826667-23.893334 0l-136.533333 136.533333c-6.826667 6.826667-6.826667 17.066667 0 23.893333 0 0 6.826667 3.413333 10.24 3.413334zM293.546667 317.44c3.413333 3.413333 10.24 6.826667 13.653333 6.826667s10.24 0 13.653333-3.413334c6.826667-6.826667 6.826667-17.066667 0-23.893333l-136.533333-136.533333c-6.826667-6.826667-17.066667-6.826667-23.893333 0s-6.826667 17.066667 0 23.893333l133.12 133.12zM730.453333 703.146667c-6.826667-6.826667-17.066667-6.826667-23.893333 0s-6.826667 17.066667 0 23.893333l136.533333 136.533333c3.413333 3.413333 6.826667 3.413333 13.653334 3.413334s10.24 0 13.653333-3.413334c6.826667-6.826667 6.826667-17.066667 0-23.893333l-139.946667-136.533333z"
+		fill="#ffffff"
+		p-id="11067"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/summary.svelte

@@ -0,0 +1,44 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1731984744752"
+	class="w-12 h-12"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="31753"
+	width="200"
+	height="200"
+	><path
+		d="M244.224 370.78016h526.336c48.64 0 87.552 39.424 87.552 87.552v292.352c0 48.64-39.424 87.552-87.552 87.552H244.224c-48.64 0-87.552-39.424-87.552-87.552v-292.352c-0.512-48.128 38.912-87.552 87.552-87.552z"
+		fill="#CAE4FF"
+		p-id="31754"
+	/><path
+		d="M760.832 983.30624H245.76c-114.176 0-206.848-92.672-206.848-206.848v-357.888c0-114.176 92.672-206.336 206.848-206.848h515.072c114.176 0 206.336 92.672 206.848 206.848v357.888c0 114.176-92.672 206.848-206.848 206.848zM245.76 270.09024c-81.92 0-148.48 66.56-148.48 148.48v357.888c0 81.92 66.56 148.48 148.48 148.48h515.072c81.92 0 148.48-66.56 148.48-148.48v-357.888c0-81.92-66.56-148.48-148.48-148.48H245.76z"
+		fill="#0972E7"
+		p-id="31755"
+	/><path
+		d="M303.616 748.29824c0.512 14.848-11.264 27.648-26.112 28.16-14.848 0.512-27.648-11.264-28.16-26.112v-291.328c0.512-14.848 13.312-26.624 28.16-26.112 14.336 0.512 25.6 11.776 26.112 26.112v289.28z"
+		fill="#0972E7"
+		p-id="31756"
+	/><path
+		d="M742.912 758.53824c0 13.824-11.264 25.088-25.088 25.088H274.432c-13.824 0.512-25.6-9.728-26.112-23.552-0.512-13.824 9.728-25.6 23.552-26.112h446.464c13.312 0 24.576 11.264 24.576 24.576z m-261.12-224.768c-9.728-10.24-26.112-10.24-36.352-0.512l-78.848 79.36c-10.24 10.24-10.24 26.624 0 36.864 9.728 10.24 26.112 10.24 36.352 0.512l79.36-78.848c9.728-10.752 9.728-27.136-0.512-37.376z"
+		fill="#0972E7"
+		p-id="31757"
+	/><path
+		d="M564.736 648.97024c10.24-9.728 10.24-26.112 0-36.352l-79.36-78.848c-10.24-10.24-26.624-10.24-36.864 0-10.24 9.728-10.24 26.112 0 36.352l78.848 78.848c10.752 10.24 27.136 10.24 37.376 0z"
+		fill="#0972E7"
+		p-id="31758"
+	/><path
+		d="M649.216 533.77024c-9.728-10.24-26.112-10.24-36.352-0.512l-79.36 78.848c-10.24 10.24-10.24 26.624 0 36.864 9.728 10.24 26.112 10.24 36.352 0.512l79.36-78.848c9.728-10.24 9.728-26.624 0-36.864z"
+		fill="#0972E7"
+		p-id="31759"
+	/><path
+		d="M714.24 468.74624c-9.728-10.24-26.112-10.24-36.352-0.512l-79.36 78.848c-10.24 10.24-10.24 26.624 0 36.864 9.728 10.24 26.112 10.24 36.352 0.512l79.36-78.848c10.24-10.24 10.24-27.136 0-36.864zM97.792 404.74624H39.936c0-51.2-0.512-120.832-0.512-120.832 0-112.128 91.136-203.264 203.264-203.264h136.704c123.392 0 194.56 66.56 194.56 182.784h-57.856c0-83.968-44.544-124.928-136.192-124.928H242.688c-80.384 0-145.408 65.024-145.408 145.408 0 0 0.512 69.632 0.512 120.832z"
+		fill="#0972E7"
+		p-id="31760"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/taskIcon.svelte

@@ -0,0 +1,24 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1731987065328"
+	class="w-5 h-5"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="35111"
+	width="200"
+	height="200"
+	><path
+		d="M740.565333 112c63.146667 0 114.304 51.2 114.304 114.304v457.130667H169.130667V226.304c0-63.146667 51.2-114.304 114.304-114.304h457.130666z m-219.434666 326.826667H331.434667c-32 0-48 16.042667-48 48.042666l0.213333 6.186667c2.005333 27.861333 17.92 41.813333 47.786667 41.813333h189.696c32 0 48-16 48-48l-0.213334-6.186666c-1.962667-27.904-17.92-41.813333-47.786666-41.813334z m171.434666-212.522667H331.434667c-32 0-48 16-48 48l0.213333 6.186667c2.005333 27.861333 17.92 41.813333 47.786667 41.813333h361.130666c32 0 48-16 48-48l-0.213333-6.186667c-2.005333-27.904-17.92-41.813333-47.786667-41.813333z"
+		fill="#93C0FB"
+		p-id="35112"
+	/><path
+		d="M154.752 422.101333l343.68 196.096a28.586667 28.586667 0 0 0 28.330667 0l342.485333-196.010666a28.586667 28.586667 0 0 1 42.752 24.789333v350.72c0 63.146667-51.2 114.304-114.304 114.304H226.261333c-63.104 0-114.261333-51.2-114.261333-114.304v-350.805333a28.586667 28.586667 0 0 1 42.752-24.789334z"
+		fill="#4B96F9"
+		p-id="35113"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/taskResult.svelte

@@ -0,0 +1,60 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1731987759041"
+	class="w-7 h-7"
+	viewBox="0 0 1230 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="50480"
+	width="200"
+	height="200"
+	><path
+		d="M455.756297 168.055915a69.477515 69.477515 0 0 1-1.687986 16.069629c-2.768298 18.837927-9.385204 26.062508-9.385204 31.058948s5.536595 6.076751 10.465515 6.07675c30.991428 0 98.51088-32.679414 196.414084-32.679414 28.695767 0 112.554925 3.848609 112.554926 32.139259C764.117632 276.154556 533.403666 351.101147 533.403666 351.101147a0.540156 0.540156 0 0 0 0.540156 0.540156h15.461954c40.511671-2.228142 140.643017-39.36384 321.662667-39.36384 118.024001 0 291.819069 21.606224 291.819069 62.590531 0 23.901886-56.783859 73.731241-116.94369 121.535013-51.7199 40.849268-122.885402 77.51233-122.885402 118.024001 0 27.007781 30.856389 31.599103 59.012001 31.599103 55.703547 0 139.02255-19.378083 193.645786-19.378083 23.766847 0 54.623236 3.848609 54.623236 27.007781 0 37.743373-262.042991 370.344191-652.710536 370.344191-44.090202 0-102.021891-6.751945-102.021891-49.896875s55.163392-108.031122 103.169721-145.301859c38.080971-29.303442 67.519451-38.216009 67.519452-43.752605 0-3.308453-11.07319-3.916128-14.921799-3.916128-32.00422 0-110.866939 16.137149-183.720427 60.767507-55.703547 34.367401-71.165502 48.208888-121.535013 73.73124-31.396545 15.529474-63.94092 37.135698-110.326783 37.135699-62.320454 0-93.784518-37.743373-93.784518-93.716999 0-63.738362 60.767506-81.495978 60.767506-143.006198C183.180272 657.571937 47.263616 698.556244 47.263616 629.821443c0-29.911117 27.007781-65.966504 33.759726-74.811552 114.242912-152.458921 226.190162-143.613873 253.805618-157.995517 31.464064-16.069629-2.768298-25.522353-25.387314-25.522352-20.998549 0-45.778188 8.304893-67.519452 17.21746-9.385204 3.848609-22.078861 16.069629-40.51167 16.069629-14.921799 0-19.378083-14.989318-19.378083-29.978636C180.95213 282.231307 374.057761 143.681393 434.757748 143.681393c15.461954 0 20.998549 8.845048 20.998549 24.374522z"
+		fill="#E1EBFF"
+		p-id="50481"
+	/><path
+		d="M898.751418 191.350125H341.513385A24.712119 24.712119 0 0 0 316.666227 216.062244v671.886061a24.712119 24.712119 0 0 0 24.847158 24.374522h557.238033a25.049716 25.049716 0 0 0 24.847158-24.374522V216.062244a24.712119 24.712119 0 0 0-24.847158-24.374521"
+		fill="#335DFF"
+		p-id="50482"
+	/><path
+		d="M847.436635 853.783463h-458.457075a25.049716 25.049716 0 0 1-24.847159-24.374522V279.463009a24.6446 24.6446 0 0 1 24.847159-24.374522h458.457075a25.049716 25.049716 0 0 1 24.847158 24.374522v549.945932a24.712119 24.712119 0 0 1-24.847158 24.374522z"
+		fill="#FFFFFF"
+		p-id="50483"
+	/><path
+		d="M58.471845 792.273243H41.389424v-17.21746a8.507451 8.507451 0 0 0-8.304893-8.304893 8.439931 8.439931 0 0 0-8.237373 8.304893v17.21746H8.304893a8.304893 8.304893 0 1 0 0 16.609785h17.082421v17.21746A8.507451 8.507451 0 0 0 33.759726 834.40538a8.57497 8.57497 0 0 0 8.237373-8.304892v-17.21746h17.082421a8.304893 8.304893 0 1 0-0.607675-16.609785z"
+		fill="#D2DFFF"
+		p-id="50484"
+	/><path
+		d="M809.355664 225.717526h-371.356983a16.204668 16.204668 0 0 1-16.542265-16.069629v-39.903996a16.204668 16.204668 0 0 1 16.542265-16.137149h371.356983a16.204668 16.204668 0 0 1 16.609785 16.069629v40.511671a16.137149 16.137149 0 0 1-16.609785 15.529474z"
+		fill="#8FAFFF"
+		p-id="50485"
+	/><path
+		d="M677.490175 181.357246H570.471845A16.542266 16.542266 0 0 1 553.659502 165.287617v-55.973625a16.137149 16.137149 0 0 1 16.542265-16.06963h107.018331a16.542266 16.542266 0 0 1 16.609785 16.06963v56.513781a16.474746 16.474746 0 0 1-16.339708 15.529473z"
+		fill="#8FAFFF"
+		p-id="50486"
+	/><path
+		d="M459.13227 688.02321h280.205723a16.272188 16.272188 0 0 1 16.542265 16.609785v8.912567a16.272188 16.272188 0 0 1-16.542265 16.609785H459.13227a16.272188 16.272188 0 0 1-16.542266-16.002109v-9.520243A17.014902 17.014902 0 0 1 459.13227 688.02321z m0-111.947251h224.569695a16.272188 16.272188 0 0 1 16.542266 16.609785v8.845049a16.272188 16.272188 0 0 1-16.542266 16.677304H459.13227a16.272188 16.272188 0 0 1-16.542266-16.069629 1.890545 1.890545 0 0 1 0-0.607675v-8.845049A16.609785 16.609785 0 0 1 459.13227 576.075959z m0-112.014769h224.569695a16.272188 16.272188 0 0 1 16.542266 16.609785v8.912567a16.272188 16.272188 0 0 1-16.677305 16.812344H459.13227a16.204668 16.204668 0 0 1-16.542266-16.00211 1.890545 1.890545 0 0 1 0-0.607676v-9.115125A16.677304 16.677304 0 0 1 459.13227 464.06119z m0-111.947251h280.205723a16.272188 16.272188 0 0 1 16.879863 16.609785v8.912568a16.272188 16.272188 0 0 1-16.542266 16.609785H459.13227A16.339707 16.339707 0 0 1 442.454965 378.108928v-9.452723A16.609785 16.609785 0 0 1 459.13227 352.113939zM247.526309 0.810233l-10.465515 18.905447a39.093762 39.093762 0 0 1-14.921799 14.921799l-18.230252 10.533034a2.160622 2.160622 0 0 0 0 3.375973l18.230252 10.465515A39.296321 39.296321 0 0 1 237.060794 74.271397l10.465515 18.837926a2.025584 2.025584 0 0 0 3.308453 0L261.300277 74.271397a38.823685 38.823685 0 0 1 14.921799-14.989319l18.230252-10.465515a2.160622 2.160622 0 0 0 0-3.375972l-18.230252-10.533035a38.621126 38.621126 0 0 1-14.921799-15.191876L250.834762 0.810233c-0.540156-0.810233-2.228142-0.810233-3.308453 0zM1057.624687 183.585388a22.754055 22.754055 0 1 1-22.011341 22.686536 21.606224 21.606224 0 0 1 22.011341-22.686536z m0-11.07319a33.759726 33.759726 0 0 0-33.084531 33.759726 33.152051 33.152051 0 1 0 66.236581 0 33.354609 33.354609 0 0 0-33.15205-33.759726z"
+		fill="#D2DFFF"
+		p-id="50487"
+	/><path
+		d="M642.785177 138.144798a22.821575 22.821575 0 0 1-22.686535 22.686535 22.281419 22.281419 0 0 1-22.551497-22.213899 1.147831 1.147831 0 0 1 0-0.472636 22.821575 22.821575 0 0 1 22.619016-22.754056 22.416458 22.416458 0 0 1 22.686536 22.2139z m68.059607 445.628379A178.791507 178.791507 0 1 0 762.969801 456.971647a179.66926 179.66926 0 0 0-52.125017 126.869049z"
+		fill="#FFFFFF"
+		p-id="50488"
+	/><path
+		d="M889.298694 436.91837a145.706976 145.706976 0 0 0-145.504417 145.909535v1.012791a145.571937 145.571937 0 1 0 291.076355 0.742714v-0.742714a146.787287 146.787287 0 0 0-145.571938-146.989845z"
+		fill="#2ED073"
+		p-id="50489"
+	/><path
+		d="M856.230925 638.373959m5.681472-5.681472l95.534667-95.534667q5.681472-5.681472 11.362944 0l0 0q5.681472 5.681472 0 11.362943l-95.534667 95.534668q-5.681472 5.681472-11.362944 0l0 0q-5.681472-5.681472 0-11.362944Z"
+		fill="#FFFFFF"
+		p-id="50490"
+	/><path
+		d="M804.217647 586.365756m5.681472-5.681472l0 0q5.681472-5.681472 11.362944 0l51.944886 51.944887q5.681472 5.681472 0 11.362944l0 0q-5.681472 5.681472-11.362944 0l-51.944886-51.944887q-5.681472-5.681472 0-11.362944Z"
+		fill="#FFFFFF"
+		p-id="50491"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/Agent/time.svelte

@@ -0,0 +1,8 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg class="w-2.5 h-2.5 text-blue-800 dark:text-blue-300" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" fill="currentColor" viewBox="0 0 20 20">
+    <path d="M20 4a2 2 0 0 0-2-2h-2V1a1 1 0 0 0-2 0v1h-3V1a1 1 0 0 0-2 0v1H6V1a1 1 0 0 0-2 0v1H2a2 2 0 0 0-2 2v2h20V4ZM0 18a2 2 0 0 0 2 2h16a2 2 0 0 0 2-2V8H0v10Zm5-8h10a1 1 0 0 1 0 2H5a1 1 0 0 1 0-2Z"/>
+</svg>

AgentQnA/ui/svelte/src/lib/assets/Agent/toolIcon.svelte

@@ -0,0 +1,36 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1731987374334"
+	class="w-4 h-4"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="47097"
+	width="200"
+	height="200"
+	><path
+		d="M210.488889 246.670222m35.043555 0l349.923556 0q35.043556 0 35.043556 35.043556l0 0.056889q0 35.043556-35.043556 35.043555l-349.923556 0q-35.043556 0-35.043555-35.043555l0-0.056889q0-35.043556 35.043555-35.043556Z"
+		fill="#89BAF7"
+		p-id="47098"
+	/><path
+		d="M210.488889 471.210667m35.043555 0l349.923556 0q35.043556 0 35.043556 35.043555l0 0.056889q0 35.043556-35.043556 35.043556l-349.923556 0q-35.043556 0-35.043555-35.043556l0-0.056889q0-35.043556 35.043555-35.043555Z"
+		fill="#89BAF7"
+		p-id="47099"
+	/><path
+		d="M210.488889 695.296m35.043555 0l140.344889 0q35.043556 0 35.043556 35.043556l0 0.056888q0 35.043556-35.043556 35.043556l-140.344889 0q-35.043556 0-35.043555-35.043556l0-0.056888q0-35.043556 35.043555-35.043556Z"
+		fill="#89BAF7"
+		p-id="47100"
+	/><path
+		d="M436.565333 982.186667h-261.176889a175.559111 175.559111 0 0 1-175.331555-175.388445v-631.466666a175.559111 175.559111 0 0 1 175.331555-175.388445h490.951112a175.559111 175.559111 0 0 1 175.331555 175.388445v278.016a35.100444 35.100444 0 1 1-70.144 0v-278.016a105.358222 105.358222 0 0 0-105.187555-105.244445h-490.951112a105.358222 105.358222 0 0 0-105.187555 105.244445v631.466666a105.358222 105.358222 0 0 0 105.187555 105.244445h261.176889a35.100444 35.100444 0 0 1 0 70.144z"
+		fill="#0A71EF"
+		p-id="47101"
+	/><path
+		d="M1008.184889 628.167111l-5.688889-11.889778-2.104889-2.616889a19.683556 19.683556 0 0 0-24.519111-2.616888h-0.910222l-97.28 97.336888-49.265778-49.265777 101.489778-101.717334-1.080889-1.422222a18.090667 18.090667 0 0 0-4.039111-18.944 16.668444 16.668444 0 0 0-5.688889-3.868444l-10.695111-4.721778a192.056889 192.056889 0 0 0-258.958222 235.292444l-105.927112 105.927111a87.608889 87.608889 0 0 0 0 123.619556 87.608889 87.608889 0 0 0 123.448889 0l105.927111-106.097778a188.757333 188.757333 0 0 0 59.278223 9.500445 192.056889 192.056889 0 0 0 176.355555-268.288z m-176.355556 215.836445a137.728 137.728 0 0 1-55.409777-11.377778l-16.327112-6.997334-130.446222 130.446223a35.669333 35.669333 0 0 1-49.265778 0 34.702222 34.702222 0 0 1 0-49.265778l130.446223-130.446222-6.997334-16.497778a136.192 136.192 0 0 1-11.377777-55.239111 139.719111 139.719111 0 0 1 139.548444-139.548445 111.502222 111.502222 0 0 1 15.303111 0.853334l-79.985778 79.985777a20.650667 20.650667 0 0 0-3.356444 21.219556l-0.512 1.251556 101.489778 101.546666a19.569778 19.569778 0 0 0 24.746666 0.341334l81.009778-81.009778a151.210667 151.210667 0 0 1 0.853333 15.416889 139.719111 139.719111 0 0 1-139.605333 139.320889z"
+		fill="#FD7733"
+		p-id="47102"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/icons/ActiveDislikeButtonIcon.svelte

@@ -0,0 +1,28 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1699532005309"
+	class="icon"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="31791"
+	width="1rem"
+	height="1rem"
+	><path
+		d="M505.088 513.1264m-450.816 0a450.816 450.816 0 1 0 901.632 0 450.816 450.816 0 1 0-901.632 0Z"
+		fill="#e02424"
+		p-id="31792"
+		data-spm-anchor-id="a313x.search_index.0.i28.33343a81AAN1qI"
+		class="selected"
+	/><path
+		d="M356.6592 575.0784c0-54.5792 0.3584-109.1584-0.2048-163.6864-0.1536-15.872 5.5296-24.2176 20.992-29.5424 58.88-20.2752 93.7472-63.1296 110.848-121.9072 5.9392-20.4288 11.4176-41.216 19.7632-60.672 13.4656-31.5904 38.2464-42.7008 72.6528-35.328 26.5216 5.6832 43.3152 28.3648 43.5712 60.16 0.3584 40.4992 0.0512 80.9984 0.1536 121.4976 0.0512 22.2208 3.9424 26.7264 26.5728 26.9824 45.568 0.512 91.1872 1.536 136.704-0.256 40.5504-1.5872 69.9392 24.832 59.7504 69.9904-12.2368 54.0672-27.648 107.4688-42.7008 160.8704-9.2672 32.9216-20.1728 65.4336-30.8736 97.9456-14.1312 43.008-40.448 62.0544-84.8896 62.0544H390.2976c-32.1024 0-33.6384-1.536-33.6384-32.8704v-155.2384zM307.8656 573.9008c0 52.8896 0.1024 105.7792-0.0512 158.6688-0.1024 26.0096-4.9152 30.6176-30.3616 30.6688-7.3216 0-14.6432 0.0512-21.9648 0-29.8496-0.1536-44.032-14.08-44.2368-44.6976-0.3072-55.1424-0.1024-110.2848-0.1024-165.4272 0-40.4992-0.1536-81.0496 0.0512-121.5488 0.2048-32.2048 15.7696-47.616 47.5136-47.7184 49.1008-0.2048 49.152-0.2048 49.152 48.2304 0.0512 47.2576 0.0512 94.5152 0 141.824z"
+		fill="#ffffff"
+		p-id="31793"
+		data-spm-anchor-id="a313x.search_index.0.i26.33343a81AAN1qI"
+		class=""
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/icons/ActiveLikeButtonIcon.svelte

@@ -0,0 +1,24 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1699531880178"
+	class="icon"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="26552"
+	width="1rem"
+	height="1rem"
+	><path
+		d="M505.088 513.1264m-450.816 0a450.816 450.816 0 1 0 901.632 0 450.816 450.816 0 1 0-901.632 0Z"
+		fill="#FFBC42"
+		p-id="26553"
+	/><path
+		d="M356.6592 575.0784c0-54.5792 0.3584-109.1584-0.2048-163.6864-0.1536-15.872 5.5296-24.2176 20.992-29.5424 58.88-20.2752 93.7472-63.1296 110.848-121.9072 5.9392-20.4288 11.4176-41.216 19.7632-60.672 13.4656-31.5904 38.2464-42.7008 72.6528-35.328 26.5216 5.6832 43.3152 28.3648 43.5712 60.16 0.3584 40.4992 0.0512 80.9984 0.1536 121.4976 0.0512 22.2208 3.9424 26.7264 26.5728 26.9824 45.568 0.512 91.1872 1.536 136.704-0.256 40.5504-1.5872 69.9392 24.832 59.7504 69.9904-12.2368 54.0672-27.648 107.4688-42.7008 160.8704-9.2672 32.9216-20.1728 65.4336-30.8736 97.9456-14.1312 43.008-40.448 62.0544-84.8896 62.0544H390.2976c-32.1024 0-33.6384-1.536-33.6384-32.8704v-155.2384zM307.8656 573.9008c0 52.8896 0.1024 105.7792-0.0512 158.6688-0.1024 26.0096-4.9152 30.6176-30.3616 30.6688-7.3216 0-14.6432 0.0512-21.9648 0-29.8496-0.1536-44.032-14.08-44.2368-44.6976-0.3072-55.1424-0.1024-110.2848-0.1024-165.4272 0-40.4992-0.1536-81.0496 0.0512-121.5488 0.2048-32.2048 15.7696-47.616 47.5136-47.7184 49.1008-0.2048 49.152-0.2048 49.152 48.2304 0.0512 47.2576 0.0512 94.5152 0 141.824z"
+		fill="#FFFFFF"
+		p-id="26554"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/icons/Folder.svelte

@@ -0,0 +1,28 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	t="1697617760586"
+	class="h-10 w-10"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	p-id="5216"
+	width="200"
+	height="200"
+	><path
+		d="M826.9 461.6h-723v391.5c0 21.7 17.7 39.4 39.4 39.4h677c4.1-6.4 6.6-14.1 6.6-22.3V461.6zM826.9 422.3v-64.7c0-22.9-18.6-41.6-41.6-41.6H340l-32.7-61.2c-7.2-13.5-21.3-22-36.7-22H134.9c-12.4 0-23.4 5.5-31 14.2v175.2l723 0.1z"
+		fill="#FFD524"
+		p-id="5217"
+	/><path
+		d="M687 252.6h11.4c10.8 0 19.6-8.8 19.6-19.6s-8.8-19.6-19.6-19.6H687c-10.8 0-19.6 8.8-19.6 19.6s8.8 19.6 19.6 19.6zM753.3 252.6h18c10.8 0 19.6-8.8 19.6-19.6s-8.8-19.6-19.6-19.6h-18c-10.8 0-19.6 8.8-19.6 19.6s8.7 19.6 19.6 19.6z"
+		fill="#6B400D"
+		p-id="5218"
+	/><path
+		d="M881.6 213.3h-44.9c-10.8 0-19.6 8.8-19.6 19.6s8.8 19.6 19.6 19.6h44.9c21.7 0 39.4 17.7 39.4 39.4v130.3H103.8V173.9c0-21.7 17.7-39.4 39.4-39.4h193c14.6 0 27.9 8 34.7 20.8l46.5 86.9c3.4 6.4 10.1 10.4 17.3 10.4h84.5c10.8 0 19.6-8.8 19.6-19.6s-8.8-19.6-19.6-19.6h-72.7l-40.9-76.5c-13.7-25.7-40.3-41.6-69.4-41.6H143.3c-43.4 0-78.7 35.3-78.7 78.7v679.3c0 43.4 35.3 78.7 78.7 78.7h738.3c43.4 0 78.7-35.3 78.7-78.7V292c0-43.4-35.3-78.7-78.7-78.7z m39.5 639.8c0 21.7-17.7 39.4-39.4 39.4H143.4c-21.7 0-39.4-17.7-39.4-39.4V461.6h817.2v391.5z"
+		fill="#6B400D"
+		p-id="5219"
+	/></svg
+>

AgentQnA/ui/svelte/src/lib/assets/icons/Knowledge.svelte

@@ -0,0 +1,38 @@
+<!--
+  Copyright (C) 2025 Intel Corporation
+  SPDX-License-Identifier: Apache-2.0
+-->
+
+<svg
+	class="h-10 w-10"
+	viewBox="0 0 1024 1024"
+	version="1.1"
+	xmlns="http://www.w3.org/2000/svg"
+	width="200"
+	height="200"
+	><path
+		d="M192.028 0.008c-47.06 0-85.34 38.282-85.34 85.342V853.34c0 11.782 9.53 21.312 21.342 21.312h106.654V0.008H192.028z"
+		fill="#656D78"
+	/><path
+		d="M192.028 789.34c-35.374 0-63.998 28.656-63.998 64s28.624 63.996 63.998 63.996H896V789.34H192.028z"
+		fill="#E6E9ED"
+	/><path
+		d="M917.312 21.352c0-11.782-9.562-21.344-21.312-21.344H234.684v810.644H896c11.75 0 21.312-9.532 21.312-21.312V21.352z"
+		fill="#5D9CEC"
+	/><path
+		d="M384.026 874.652H213.34c-11.75 0-21.312-9.532-21.312-21.312s9.562-21.344 21.312-21.344h170.686c11.782 0 21.312 9.562 21.312 21.344s-9.532 21.312-21.312 21.312zM725.316 831.996c-11.75 0-21.312 9.562-21.312 21.344s9.562 21.312 21.312 21.312H896v-42.656h-170.684z"
+		fill="#CCD1D9"
+	/><path d="M320.026 149.35h490.662v255.996H320.026z" fill="#E6E9ED" /><path
+		d="M128.03 170.678c11.782 0 21.312-9.546 21.312-21.328s-9.532-21.344-21.312-21.344H106.686v42.672h21.344zM128.03 298.676c11.782 0 21.312-9.546 21.312-21.328 0-11.78-9.532-21.342-21.312-21.342H106.686v42.67h21.344zM128.03 426.672c11.782 0 21.312-9.546 21.312-21.328 0-11.78-9.532-21.342-21.312-21.342H106.686v42.67h21.344zM128.03 554.656c11.782 0 21.312-9.532 21.312-21.312S139.81 512 128.03 512H106.686v42.656h21.344zM128.03 682.656c11.782 0 21.312-9.532 21.312-21.312S139.81 640 128.03 640H106.686v42.656h21.344zM725.316 298.676h-319.98c-11.75 0-21.312-9.546-21.312-21.328 0-11.78 9.562-21.342 21.312-21.342h319.98c11.812 0 21.376 9.562 21.376 21.342s-9.564 21.328-21.376 21.328z"
+		fill="#434A54"
+	/><path
+		d="M917.312 917.336c0-11.782-9.562-21.344-21.312-21.344H234.684v42.656H896c11.75 0 21.312-9.53 21.312-21.312z"
+		fill="#5D9CEC"
+	/><path
+		d="M234.684 895.992H192.028c-23.53 0-42.686-19.152-42.686-42.652 0-23.532 19.156-42.688 42.686-42.688h42.656v-42.656H192.028c-47.06 0-85.34 38.282-85.34 85.344 0 47.028 38.28 85.308 85.34 85.308h42.656v-42.656z"
+		fill="#656D78"
+	/><path
+		d="M362.682 853.34H213.34v149.308c0 6.876 3.312 13.312 8.876 17.312s12.718 5.094 19.218 2.938l57.25-19.094 57.25 19.094c2.218 0.718 4.468 1.094 6.75 1.094 4.406 0 8.782-1.376 12.468-4.032 5.562-4 8.876-10.438 8.876-17.312V853.34h-21.346z"
+		fill="#ED5564"
+	/></svg
+>