adapt to AISE 4 ndoes 76->80

.github/CODEOWNERS

@@ -1,23 +1,13 @@
-* 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
-/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
+/AgentQnA/ xuhui.ren@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
+/DocIndexRetriever/ xuhui.ren@intel.com chendi.xue@intel.com
+/FaqGen/ xinyao.wang@intel.com
+/SearchQnA/ sihan.chen@intel.com
+/Translation/ liang1.lv@intel.com
+/VisualQnA/ liang1.lv@intel.com
+/ProductivitySuite/ hoong.tee.yeoh@intel.com
+/*/ liang1.lv@intel.com

.github/ISSUE_TEMPLATE/1_bug_template.yml

@@ -4,7 +4,6 @@
 name: Report Bug
 description: Used to report bug
 title: "[Bug]"
-labels: ["bug"]
 body:
   - type: dropdown
     id: priority
@@ -66,7 +65,6 @@ body:
       options:
         - label: Pull docker images from hub.docker.com
         - label: Build docker images from source
-        - label: Other
     validations:
       required: true
 
@@ -75,11 +73,10 @@ body:
     attributes:
       label: Deploy method
       options:
+        - label: Docker compose
         - label: Docker
-        - label: Docker Compose
-        - label: Kubernetes Helm Charts
-        - label: Kubernetes GMC
-        - label: Other
+        - label: Kubernetes
+        - label: Helm
     validations:
       required: true
 
@@ -90,7 +87,6 @@ body:
       options:
         - Single Node
         - Multiple Nodes
-        - Other
       default: 0
     validations:
       required: true
@@ -130,12 +126,3 @@ 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_feaure_template.yml

@@ -4,7 +4,6 @@
 name: Report Feature
 description: Used to report feature
 title: "[Feature]"
-labels: ["feature"]
 body:
   - type: dropdown
     id: priority
@@ -66,7 +65,6 @@ body:
       options:
         - Single Node
         - Multiple Nodes
-        - Other
       default: 0
     validations:
       required: true

.github/code_spell_ignore.txt

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

.github/license_template.txt

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

.github/workflows/_build_comps_base_image.yml

@@ -1,65 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Build Comps Base Image
-permissions: read-all
-on:
-  workflow_call:
-    inputs:
-      node:
-        required: true
-        type: string
-      build:
-        default: true
-        required: false
-        type: boolean
-      tag:
-        default: "latest"
-        required: false
-        type: string
-      opea_branch:
-        default: "main"
-        required: false
-        type: string
-      inject_commit:
-        default: false
-        required: false
-        type: boolean
-
-jobs:
-  pre-build-image-check:
-    runs-on: ubuntu-latest
-    outputs:
-      should_skip: ${{ steps.check-skip.outputs.should_skip }}
-    steps:
-      - name: Check if job should be skipped
-        id: check-skip
-        run: |
-          should_skip=false
-          if [[ "${{ inputs.node }}" == "gaudi3" || "${{ inputs.node }}" == "rocm" || "${{ inputs.node }}" == "arc" ]]; then
-            should_skip=true
-          fi
-          echo "should_skip=$should_skip"
-          echo "should_skip=$should_skip" >> $GITHUB_OUTPUT
-
-  build-images:
-    needs: [ pre-build-image-check ]
-    if: ${{ needs.pre-build-image-check.outputs.should_skip == 'false' && fromJSON(inputs.build) }}
-    runs-on: "docker-build-${{ inputs.node }}"
-    steps:
-      - name: Clean Up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Clone Required Repo
-        run: |
-          git clone --depth 1 --branch ${{ inputs.opea_branch }} https://github.com/opea-project/GenAIComps.git
-          cd GenAIComps && git rev-parse HEAD && cd ../ && ls -l
-
-      - name: Build Image
-        uses: opea-project/validation/actions/image-build@main
-        with:
-          work_dir: ${{ github.workspace }}/GenAIComps
-          docker_compose_path: ${{ github.workspace }}/GenAIComps/.github/workflows/docker/compose/base-compose.yaml
-          registry: ${OPEA_IMAGE_REPO}opea
-          inject_commit: ${{ inputs.inject_commit }}
-          tag: ${{ inputs.tag }}

.github/workflows/_build_image.yml

@@ -1,103 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Build Images
-permissions: read-all
-on:
-  workflow_call:
-    inputs:
-      node:
-        required: true
-        type: string
-      build:
-        default: true
-        required: false
-        type: boolean
-      example:
-        required: true
-        type: string
-      services:
-        default: ""
-        required: false
-        type: string
-      tag:
-        default: "latest"
-        required: false
-        type: string
-      opea_branch:
-        default: "main"
-        required: false
-        type: string
-      inject_commit:
-        default: false
-        required: false
-        type: boolean
-
-jobs:
-  pre-build-image-check:
-    runs-on: ubuntu-latest
-    outputs:
-      should_skip: ${{ steps.check-skip.outputs.should_skip }}
-    steps:
-      - name: Check if job should be skipped
-        id: check-skip
-        run: |
-          should_skip=false
-          if [[ "${{ inputs.node }}" == "gaudi3" || "${{ inputs.node }}" == "rocm" || "${{ inputs.node }}" == "arc" ]]; then
-            should_skip=true
-          fi
-          echo "should_skip=$should_skip"
-          echo "should_skip=$should_skip" >> $GITHUB_OUTPUT
-
-  build-images:
-    needs: [ pre-build-image-check ]
-    if: ${{ needs.pre-build-image-check.outputs.should_skip == 'false' && fromJSON(inputs.build) }}
-    runs-on: "docker-build-${{ inputs.node }}"
-    steps:
-      - name: Clean Up Working Directory
-        run: sudo rm -rf ${{github.workspace}}/*
-
-      - name: Get Checkout Ref
-        run: |
-          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
-            echo "CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge" >> $GITHUB_ENV
-          else
-            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
-          fi
-
-      - name: Checkout out GenAIExamples
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ env.CHECKOUT_REF }}
-          fetch-depth: 0
-
-      - name: Clone Required Repo
-        run: |
-          cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
-          docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
-          if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
-              git clone https://github.com/vllm-project/vllm.git && cd vllm
-              # Get the latest tag
-              VLLM_VER=$(git describe --tags "$(git rev-list --tags --max-count=1)")
-              echo "Check out vLLM tag ${VLLM_VER}"
-              git checkout ${VLLM_VER} &> /dev/null && cd ../
-          fi
-          if [[ $(grep -c "vllm-gaudi:" ${docker_compose_path}) != 0 ]]; then
-              git clone https://github.com/HabanaAI/vllm-fork.git && cd vllm-fork
-              # Get the latest tag
-              VLLM_VER=$(git describe --tags "$(git rev-list --tags --max-count=1)")
-              echo "Check out vLLM tag ${VLLM_VER}"
-              git checkout ${VLLM_VER} &> /dev/null && cd ../
-          fi
-          git clone --depth 1 --branch ${{ inputs.opea_branch }} https://github.com/opea-project/GenAIComps.git
-          cd GenAIComps && git rev-parse HEAD && cd ../
-
-      - name: Build Image
-        uses: opea-project/validation/actions/image-build@main
-        with:
-          work_dir: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
-          docker_compose_path: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
-          service_list: ${{ inputs.services }}
-          registry: ${OPEA_IMAGE_REPO}opea
-          inject_commit: ${{ inputs.inject_commit }}
-          tag: ${{ inputs.tag }}

.github/workflows/_example-workflow.yml

@@ -12,10 +12,6 @@ on:
       example:
         required: true
         type: string
-      services:
-        default: ""
-        required: false
-        type: string
       tag:
         default: "latest"
         required: false
@@ -28,7 +24,7 @@ on:
         default: false
         required: false
         type: boolean
-      test_helmchart:
+      test_k8s:
         default: false
         required: false
         type: boolean
@@ -40,56 +36,79 @@ on:
         default: "main"
         required: false
         type: string
-      inject_commit:
-        default: false
-        required: false
-        type: boolean
-      use_model_cache:
-        default: false
-        required: false
-        type: boolean
-
 jobs:
 ####################################################################################################
 # Image Build
 ####################################################################################################
   build-images:
-    uses: ./.github/workflows/_build_image.yml
+    runs-on: "docker-build-${{ inputs.node }}"
+    steps:
+      - name: Clean Up Working Directory
+        run: sudo rm -rf ${{github.workspace}}/*
+
+      - name: Get checkout ref
+        run: |
+          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
+            echo "CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge" >> $GITHUB_ENV
+          else
+            echo "CHECKOUT_REF=${{ github.ref }}" >> $GITHUB_ENV
+          fi
+          echo "checkout ref ${{ env.CHECKOUT_REF }}"
+
+      - name: Checkout out Repo
+        uses: actions/checkout@v4
         with:
-      node: ${{ inputs.node }}
-      build: ${{ fromJSON(inputs.build) }}
-      example: ${{ inputs.example }}
-      services: ${{ inputs.services }}
+          ref: ${{ env.CHECKOUT_REF }}
+          fetch-depth: 0
+
+      - name: Clone required Repo
+        run: |
+          cd ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
+          docker_compose_path=${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
+          if [[ $(grep -c "tei-gaudi:" ${docker_compose_path}) != 0 ]]; then
+              git clone https://github.com/huggingface/tei-gaudi.git
+          fi
+          if [[ $(grep -c "vllm:" ${docker_compose_path}) != 0 ]]; then
+              git clone https://github.com/vllm-project/vllm.git
+          fi
+          git clone https://github.com/opea-project/GenAIComps.git
+          cd GenAIComps && git checkout ${{ inputs.opea_branch }} && cd ../
+
+      - name: Build Image
+        if: ${{ fromJSON(inputs.build) }}
+        uses: opea-project/validation/actions/image-build@main
+        with:
+          work_dir: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build
+          docker_compose_path: ${{ github.workspace }}/${{ inputs.example }}/docker_image_build/build.yaml
+          registry: ${OPEA_IMAGE_REPO}opea
           tag: ${{ inputs.tag }}
-      opea_branch: ${{ inputs.opea_branch }}
-      inject_commit: ${{ inputs.inject_commit }}
 
 ####################################################################################################
 # Docker Compose Test
 ####################################################################################################
   test-example-compose:
     needs: [build-images]
-    if: ${{ inputs.test_compose }}
+    if: ${{ fromJSON(inputs.test_compose) }}
     uses: ./.github/workflows/_run-docker-compose.yml
     with:
       tag: ${{ inputs.tag }}
       example: ${{ inputs.example }}
       hardware: ${{ inputs.node }}
-      use_model_cache: ${{ inputs.use_model_cache }}
     secrets: inherit
 
 
 ####################################################################################################
-# helmchart Test
+# K8S Test
 ####################################################################################################
-  test-helmchart:
-    if: ${{ fromJSON(inputs.test_helmchart) }}
-    uses: ./.github/workflows/_helm-e2e.yml
+  test-k8s-manifest:
+    needs: [build-images]
+    if: ${{ fromJSON(inputs.test_k8s) }}
+    uses: ./.github/workflows/_manifest-e2e.yml
     with:
       example: ${{ inputs.example }}
       hardware: ${{ inputs.node }}
       tag: ${{ inputs.tag }}
-      mode: "CD"
+      context: "CD"
     secrets: inherit
 
 ####################################################################################################
@@ -97,7 +116,7 @@ jobs:
 ####################################################################################################
   test-gmc-pipeline:
     needs: [build-images]
-    if: false # ${{ fromJSON(inputs.test_gmc) }}
+    if: ${{ fromJSON(inputs.test_gmc) }}
     uses: ./.github/workflows/_gmc-e2e.yml
     with:
       example: ${{ inputs.example }}

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

@@ -14,7 +14,7 @@ on:
       test_mode:
         required: false
         type: string
-        default: 'compose'
+        default: 'docker_compose'
     outputs:
       run_matrix:
         description: "The matrix string"
@@ -42,12 +42,6 @@ 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: ${{ github.workspace }}
-
       - name: Get test matrix
         id: get-test-matrix
         run: |
@@ -60,11 +54,9 @@ jobs:
             base_commit=$(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 "filtered changed_files=$changed_files"
+          echo "changed_files=$changed_files"
           export changed_files=$changed_files
           export test_mode=${{ inputs.test_mode }}
           export WORKSPACE=${{ github.workspace }}

.github/workflows/_gmc-workflow.yml

@@ -67,6 +67,36 @@ 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

@@ -1,234 +0,0 @@
-# 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]
-    if: ${{ needs.get-test-case.outputs.value_files != '[]' }}
-    strategy:
-      matrix:
-        value_file: ${{ fromJSON(needs.get-test-case.outputs.value_files) }}
-      fail-fast: false
-    runs-on: k8s-${{ inputs.hardware }}
-    continue-on-error: true
-    steps:
-      - name: Clean Up Working Directory
-        run: |
-          echo "value_file=${{ matrix.value_file }}"
-          sudo rm -rf ${{github.workspace}}/*
-
-      - name: Get checkout ref
-        id: get-checkout-ref
-        run: |
-          if [ "${{ github.event_name }}" == "pull_request" ] || [ "${{ github.event_name }}" == "pull_request_target" ]; then
-            CHECKOUT_REF=refs/pull/${{ github.event.number }}/merge
-          else
-            CHECKOUT_REF=${{ github.ref }}
-          fi
-          echo "CHECKOUT_REF=${CHECKOUT_REF}" >> $GITHUB_OUTPUT
-          echo "checkout ref ${CHECKOUT_REF}"
-
-      - name: Checkout Repo
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ steps.get-checkout-ref.outputs.CHECKOUT_REF }}
-          fetch-depth: 0
-
-      - name: Set variables
-        env:
-          example: ${{ inputs.example }}
-        run: |
-          CHART_NAME="${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

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

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

@@ -28,10 +28,6 @@ on:
         required: false
         type: string
         default: ""
-      use_model_cache:
-        required: false
-        type: boolean
-        default: false
 jobs:
   get-test-case:
     runs-on: ubuntu-latest
@@ -64,14 +60,9 @@ jobs:
           cd ${{ github.workspace }}/${{ inputs.example }}/tests
           run_test_cases=""
 
-          if [ "${{ inputs.hardware }}" == "gaudi2" ] || [ "${{ inputs.hardware }}" == "gaudi3" ]; then
-            hardware="gaudi"
-          else
-            hardware="${{ inputs.hardware }}"
-          fi
-          default_test_case=$(find . -type f -name "test_compose_on_$hardware.sh" | cut -d/ -f2)
+          default_test_case=$(find . -type f -name "test_compose_on_${{ inputs.hardware }}.sh" | cut -d/ -f2)
           if [ "$default_test_case" ]; then run_test_cases="$default_test_case"; fi
-          other_test_cases=$(find . -type f -name "test_compose_*_on_$hardware.sh" | cut -d/ -f2)
+          other_test_cases=$(find . -type f -name "test_compose_*_on_${{ inputs.hardware }}.sh" | cut -d/ -f2)
           echo "default_test_case=$default_test_case"
           echo "other_test_cases=$other_test_cases"
 
@@ -94,17 +85,12 @@ jobs:
               fi
           done
 
-          if [ -z "$run_test_cases" ] && [[ $(printf '%s\n' "${changed_files[@]}" | grep ${{ inputs.example }} | grep /tests/) ]]; then
-              run_test_cases=$other_test_cases
-          fi
-
           test_cases=$(echo $run_test_cases | tr ' ' '\n' | sort -u | jq -R '.' | jq -sc '.')
           echo "test_cases=$test_cases"
           echo "test_cases=$test_cases" >> $GITHUB_OUTPUT
 
-  compose-test:
+  run-test:
     needs: [get-test-case]
-    if: ${{ needs.get-test-case.outputs.test_cases != '[""]' }}
     strategy:
       matrix:
         test_case: ${{ fromJSON(needs.get-test-case.outputs.test_cases) }}
@@ -125,56 +111,34 @@ 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:
           HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          HF_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           PINECONE_KEY: ${{ secrets.PINECONE_KEY }}
-          PINECONE_KEY_LANGCHAIN_TEST: ${{ secrets.PINECONE_KEY_LANGCHAIN_TEST }}
-          SDK_BASE_URL: ${{ secrets.SDK_BASE_URL }}
-          SERVING_TOKEN: ${{ secrets.SERVING_TOKEN }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           IMAGE_REPO: ${{ inputs.registry }}
           IMAGE_TAG: ${{ inputs.tag }}
           example: ${{ inputs.example }}
           hardware: ${{ inputs.hardware }}
           test_case: ${{ matrix.test_case }}
-          use_model_cache: ${{ inputs.use_model_cache }}
         run: |
           cd ${{ github.workspace }}/$example/tests
           if [[ "$IMAGE_REPO" == "" ]]; then export IMAGE_REPO="${OPEA_IMAGE_REPO}opea"; fi
-          if [[ "$use_model_cache" == "true" ]]; then
-            if [ -d "/data2/hf_model" ]; then
-              export model_cache="/data2/hf_model"
-            else
-              echo "Model cache directory /data2/hf_model does not exist"
-              export model_cache="~/.cache/huggingface/hub"
-            fi
-          fi
-          if [ -f "${test_case}" ]; then timeout 30m bash "${test_case}"; else echo "Test script {${test_case}} not found, skip test!"; 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 after test
+      - name: Clean up container
         shell: bash
         if: cancelled() || failure()
         run: |
-          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"
+          cd ${{ github.workspace }}/${{ inputs.example }}/docker_compose
+          test_case=${{ matrix.test_case }}
+          flag=${test_case%_on_*}
+          flag=${flag#test_}
+          yaml_file=$(find . -type f -wholename "*${{ inputs.hardware }}/${flag}.yaml")
+          echo $yaml_file
+          docker compose -f $yaml_file stop && docker compose -f $yaml_file rm -f || true
           docker system prune -f
           docker rmi $(docker images --filter reference="*:5000/*/*" -q) || true
 

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

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

.github/workflows/daily_check_issue_and_pr.yml

@@ -1,28 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Check stale issue and pr
-
-on:
-  schedule:
-    - cron: "30 22 * * *"
-
-jobs:
-  close-issues:
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-      pull-requests: write
-    steps:
-      - uses: actions/stale@v9
-        with:
-          days-before-issue-stale: 30
-          days-before-pr-stale: 30
-          days-before-issue-close: 7
-          days-before-pr-close: 7
-          stale-issue-message: "This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days."
-          stale-pr-message: "This PR is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 7 days."
-          close-issue-message: "This issue was closed because it has been stalled for 7 days with no activity."
-          close-pr-message: "This PR was closed because it has been stalled for 7 days with no activity."
-          repo-token: ${{ secrets.ACTION_TOKEN }}
-          start-date: "2025-03-01T00:00:00Z"

.github/workflows/dependency-review.yml

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

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

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

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

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

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

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

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

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

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

@@ -1,13 +1,13 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-name: Freeze OPEA images release tag
+name: Freeze OPEA images release tag in readme on manual event
 
 on:
   workflow_dispatch:
     inputs:
       tag:
-        default: "1.1.0"
+        default: "latest"
         description: "Tag to apply to images"
         required: true
         type: string
@@ -23,18 +23,21 @@ 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 "CICD-at-OPEA"
-          git config --global user.email "CICD@opea.dev"
-          git remote set-url origin https://CICD-at-OPEA:"${{ secrets.ACTION_TOKEN }}"@github.com/opea-project/GenAIExamples.git
+          git config --global user.name "NeuralChatBot"
+          git config --global user.email "grp_neural_chat_bot@intel.com"
+          git remote set-url origin https://NeuralChatBot:"${{ secrets.ACTION_TOKEN }}"@github.com/opea-project/GenAIExamples.git
 
       - name: Run script
         run: |
-          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 ${patch}" >> version.txt
+          find . -name "*.md" | xargs sed -i "s|^docker\ compose|TAG=${{ 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'
 
       - name: Commit changes
         run: |

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

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

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

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

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

@@ -1,81 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-name: Nightly build/publish latest docker images
-
-on:
-  schedule:
-    - cron: "30 14 * * *" # UTC time
-  workflow_dispatch:
-
-env:
-  EXAMPLES: ${{ vars.NIGHTLY_RELEASE_EXAMPLES }}
-  TAG: "latest"
-  PUBLISH_TAGS: "latest"
-
-jobs:
-  get-build-matrix:
-    runs-on: ubuntu-latest
-    outputs:
-      examples_json: ${{ steps.get-matrix.outputs.examples_json }}
-      EXAMPLES: ${{ steps.get-matrix.outputs.EXAMPLES }}
-      TAG: ${{ steps.get-matrix.outputs.TAG }}
-      PUBLISH_TAGS: ${{ steps.get-matrix.outputs.PUBLISH_TAGS }}
-    steps:
-      - name: Create Matrix
-        id: get-matrix
-        run: |
-          examples=($(echo ${EXAMPLES} | tr ',' ' '))
-          examples_json=$(printf '%s\n' "${examples[@]}" | sort -u | jq -R '.' | jq -sc '.')
-          echo "examples_json=$examples_json" >> $GITHUB_OUTPUT
-          echo "EXAMPLES=$EXAMPLES" >> $GITHUB_OUTPUT
-          echo "TAG=$TAG" >> $GITHUB_OUTPUT
-          echo "PUBLISH_TAGS=$PUBLISH_TAGS" >> $GITHUB_OUTPUT
-
-  build-comps-base:
-    needs: [get-build-matrix]
-    uses: ./.github/workflows/_build_comps_base_image.yml
-    with:
-      node: gaudi
-
-  build-and-test:
-    needs: get-build-matrix
-    if: ${{ needs.get-build-matrix.outputs.examples_json != '' }}
-    strategy:
-      matrix:
-        example: ${{ fromJSON(needs.get-build-matrix.outputs.examples_json) }}
-      fail-fast: false
-    uses: ./.github/workflows/_example-workflow.yml
-    with:
-      node: gaudi
-      example: ${{ matrix.example }}
-      test_compose: true
-      inject_commit: true
-    secrets: inherit
-
-  get-image-list:
-    needs: get-build-matrix
-    uses: ./.github/workflows/_get-image-list.yml
-    with:
-      examples: ${{ needs.get-build-matrix.outputs.EXAMPLES }}
-
-  publish:
-    needs: [get-build-matrix, get-image-list, build-and-test]
-    if: ${{ needs.get-image-list.outputs.matrix != '' }}
-    strategy:
-      matrix:
-        image: ${{ fromJSON(needs.get-image-list.outputs.matrix) }}
-      fail-fast: false
-    runs-on: "docker-build-gaudi"
-    steps:
-      - uses: docker/login-action@v3.2.0
-        with:
-          username: ${{ secrets.DOCKERHUB_USER }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Image Publish
-        uses: opea-project/validation/actions/image-publish@main
-        with:
-          local_image_ref: ${OPEA_IMAGE_REPO}opea/${{ matrix.image }}:${{ needs.get-build-matrix.outputs.TAG }}
-          image_name: opea/${{ matrix.image }}
-          publish_tags: ${{ needs.get-build-matrix.outputs.PUBLISH_TAGS }}

.github/workflows/pr-bum_list_check.yml

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

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

@@ -1,76 +0,0 @@
-# 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() && ${{ fromJSON(needs.job1.outputs.run_matrix).length != 0 }}
-    uses: ./.github/workflows/_helm-e2e.yml
-    strategy:
-      matrix: ${{ fromJSON(needs.job1.outputs.run_matrix) }}
-    with:
-      example: ${{ matrix.example }}
-      hardware: ${{ matrix.hardware }}
-      mode: "CI"
-    secrets: inherit

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

@@ -1,40 +0,0 @@
-# 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

@@ -34,11 +34,6 @@ 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-docker-compose-e2e.yml

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

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

@@ -1,109 +0,0 @@
-# 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

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

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

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

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

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

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

@@ -1,7 +1,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-name: Check hyperlinks and relative path validity
+name: Check Paths and Hyperlinks
 
 on:
   pull_request:
@@ -9,6 +9,39 @@ 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:
@@ -17,25 +50,17 @@ jobs:
 
       - name: Checkout Repo GenAIExamples
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
       - name: Check the Validity of Hyperlinks
         run: |
           cd ${{github.workspace}}
           fail="FALSE"
-          merged_commit=$(git log -1 --format='%H')
-          changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
-          if  [ -n "$changed_files" ]; then
-            for changed_file in $changed_files; do
-              # echo $changed_file
-              url_lines=$(grep -H -Eo '\]\(http[s]?://[^)]+\)' "$changed_file" | grep -Ev 'GenAIExamples/blob/main') || true
+          url_lines=$(grep -Eo '\]\(http[s]?://[^)]+\)' --include='*.md' -r .)
           if [ -n "$url_lines" ]; then
             for url_line in $url_lines; do
-                  # echo $url_line
               url=$(echo "$url_line"|cut -d '(' -f2 | cut -d ')' -f1|sed 's/\.git$//')
               path=$(echo "$url_line"|cut -d':' -f1 | cut -d'/' -f2-)
-                  response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")|| true
+              response=$(curl -L -s -o /dev/null -w "%{http_code}" "$url")
               if [ "$response" -ne 200 ]; then
                 echo "**********Validation failed, try again**********"
                 response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
@@ -48,10 +73,6 @@ jobs:
               fi
             done
           fi
-            done
-          else
-            echo "No changed .md file."
-          fi
 
           if [[ "$fail" == "TRUE" ]]; then
             exit 1
@@ -68,8 +89,6 @@ jobs:
 
       - name: Checkout Repo GenAIExamples
         uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
 
       - name: Checking Relative Path Validity
         run: |
@@ -83,34 +102,33 @@ jobs:
             branch="https://github.com/opea-project/GenAIExamples/blob/${{ github.event.pull_request.head.ref }}"
           fi
           link_head="https://github.com/opea-project/GenAIExamples/blob/main"
-
-          merged_commit=$(git log -1 --format='%H')
-          changed_files="$(git diff --name-status --diff-filter=ARM ${{ github.event.pull_request.base.sha }} ${merged_commit} | awk '/\.md$/ {print $NF}')"
           png_lines=$(grep -Eo '\]\([^)]+\)' --include='*.md' -r .|grep -Ev 'http')
           if [ -n "$png_lines" ]; then
             for png_line in $png_lines; do
               refer_path=$(echo "$png_line"|cut -d':' -f1 | cut -d'/' -f2-)
               png_path=$(echo "$png_line"|cut -d '(' -f2 | cut -d ')' -f1)
-
               if [[ "${png_path:0:1}" == "/" ]]; then
-                check_path=$png_path
-              elif [[ "$png_path" == *#* ]]; then
-                relative_path=$(echo "$png_path" | cut -d '#' -f1)
-                if [ -n "$relative_path" ]; then
-                  check_path=$(dirname "$refer_path")/$relative_path
-                  png_path=$(echo "$png_path" | awk -F'#' '{print "#" $2}')
+                check_path=${{github.workspace}}$png_path
+              elif [[ "${png_path:0:1}" == "#" ]]; then
+                check_path=${{github.workspace}}/$refer_path$png_path
               else
-                  check_path=$refer_path
+                check_path=${{github.workspace}}/$(dirname "$refer_path")/$png_path
               fi
-              else
-                check_path=$(dirname "$refer_path")/$png_path
-              fi
-
-              if [ -e "$check_path" ]; then
               real_path=$(realpath $check_path)
-                if [[ "$png_line" == *#* ]]; then
-                  if [ -n "changed_files" ] && echo "$changed_files" | grep -q "^${refer_path}$"; then
-                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIExamples||')$png_path
+              if [ $? -ne 0 ]; then
+                echo "Path $png_path in file ${{github.workspace}}/$refer_path does not exist"
+                fail="TRUE"
+              else
+                url=$link_head$(echo "$real_path" | sed 's|.*/GenAIExamples||')
+                response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url")
+                if [ "$response" -ne 200 ]; then
+                  echo "**********Validation failed, try again**********"
+                  response_retry=$(curl -s -o /dev/null -w "%{http_code}" "$url")
+                  if [ "$response_retry" -eq 200 ]; then
+                    echo "*****Retry successfully*****"
+                  else
+                    echo "Retry failed. Check branch ${{ github.event.pull_request.head.ref }}"
+                    url_dev=$branch$(echo "$real_path" | sed 's|.*/GenAIExamples||')
                     response=$(curl -I -L -s -o /dev/null -w "%{http_code}" "$url_dev")
                     if [ "$response" -ne 200 ]; then
                       echo "**********Validation failed, try again**********"
@@ -122,13 +140,10 @@ jobs:
                         fail="TRUE"
                       fi
                     else
-                      echo "Validation succeed $png_line"
+                      echo "Check branch ${{ github.event.pull_request.head.ref }} successfully."
                     fi
                   fi
                 fi
-              else
-                echo "${{github.workspace}}/$refer_path:$png_path does not exist"
-                fail="TRUE"
               fi
             done
           fi

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

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

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

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

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

@@ -1,46 +0,0 @@
-# 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

@@ -1,79 +0,0 @@
-# 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

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

.github/workflows/scripts/get_test_matrix.sh

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

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

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

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

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

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v4.6.0
     hooks:
       - id: end-of-file-fixer
         files: (.*\.(py|md|rst|yaml|yml|json|ts|js|html|svelte|sh))$
@@ -18,6 +18,8 @@ repos:
               SearchQnA/ui/svelte/tsconfig.json|
               DocSum/ui/svelte/tsconfig.json
           )$
+      - id: check-yaml
+        args: [--allow-multiple-documents]
       - id: debug-statements
       - id: requirements-txt-fixer
       - id: trailing-whitespace
@@ -79,7 +81,7 @@ repos:
       - id: isort
 
   - repo: https://github.com/PyCQA/docformatter
-    rev: 06907d0
+    rev: v1.7.5
     hooks:
       - id: docformatter
         args: [
@@ -100,18 +102,18 @@ repos:
           - prettier@3.2.5
 
   - repo: https://github.com/psf/black.git
-    rev: 24.10.0
+    rev: 24.4.2
     hooks:
       - id: black
         files: (.*\.py)$
 
   - repo: https://github.com/asottile/blacken-docs
-    rev: 1.19.1
+    rev: 1.18.0
     hooks:
       - id: blacken-docs
         args: [--line-length=120, --skip-errors]
         additional_dependencies:
-          - black==24.10.0
+          - black==24.4.2
 
   - repo: https://github.com/codespell-project/codespell
     rev: v2.3.0
@@ -122,7 +124,7 @@ repos:
           - tomli
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.6
+    rev: v0.5.0
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix, --no-cache]

.set_env.sh

@@ -1,16 +0,0 @@
-# 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

@@ -2,234 +2,105 @@
 
 ## Overview
 
-This example showcases a hierarchical multi-agent system for question-answering applications. The architecture diagram below shows a supervisor agent that interfaces with the user and dispatches tasks to two worker agents to gather information and come up with answers. The worker RAG agent uses the retrieval tool to retrieve relevant documents from a knowledge base - a vector database. The worker SQL agent retrieves relevant data from a SQL database. Although not included in this example by default, other tools such as a web search tool or a knowledge graph query tool can be used by the supervisor agent to gather information from additional sources.
-![Architecture Overview](assets/img/agent_qna_arch.png)
+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)
 
-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.
+### Why Agent for question answering?
 
-```mermaid
----
-config:
-  flowchart:
-    nodeSpacing: 400
-    rankSpacing: 100
-    curve: linear
-  themeVariables:
-    fontSize: 50px
----
-flowchart LR
-    %% Colors %%
-    classDef blue fill:#ADD8E6,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef orange fill:#FBAA60,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef orchid fill:#C26DBC,stroke:#ADD8E6,stroke-width:2px,fill-opacity:0.5
-    classDef invisible fill:transparent,stroke:transparent;
+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.
 
-    %% Subgraphs %%
-    subgraph DocIndexRetriever-MegaService["DocIndexRetriever MegaService "]
-        direction LR
-        EM([Embedding MicroService]):::blue
-        RET([Retrieval MicroService]):::blue
-        RER([Rerank MicroService]):::blue
-    end
-    subgraph UserInput[" User Input "]
-        direction LR
-        a([User Input Query]):::orchid
-        Ingest([Ingest data]):::orchid
-    end
-    AG_REACT([Agent MicroService - react]):::blue
-    AG_RAG([Agent MicroService - rag]):::blue
-    AG_SQL([Agent MicroService - sql]):::blue
-    LLM_gen{{LLM Service <br>}}
-    DP([Data Preparation MicroService]):::blue
-    TEI_RER{{Reranking service<br>}}
-    TEI_EM{{Embedding service <br>}}
-    VDB{{Vector DB<br><br>}}
-    R_RET{{Retriever service <br>}}
+### Roadmap
 
+- v0.9: Worker agent uses open-source websearch tool (duckduckgo), agents use OpenAI GPT-4o-mini as llm backend.
+- v1.0: Worker agent uses OPEA retrieval megaservice as tool.
+- v1.0 or later: agents use open-source llm backend.
+- v1.1 or later: add safeguards
 
+## Getting started
 
-    %% Questions interaction
-    direction LR
-    a[User Input Query] --> AG_REACT
-    AG_REACT --> AG_RAG
-    AG_REACT --> AG_SQL
-    AG_RAG --> DocIndexRetriever-MegaService
-    EM ==> RET
-    RET ==> RER
-    Ingest[Ingest data] --> DP
+1. Build agent docker image </br>
+   First, clone the opea GenAIComps repo
 
-    %% Embedding service flow
-    direction LR
-    AG_RAG <-.-> LLM_gen
-    AG_SQL <-.-> LLM_gen
-    AG_REACT <-.-> LLM_gen
-    EM <-.-> TEI_EM
-    RET <-.-> R_RET
-    RER <-.-> TEI_RER
+   ```
+   export WORKDIR=<your-work-directory>
+   cd $WORKDIR
+   git clone https://github.com/opea-project/GenAIComps.git
+   ```
 
-    direction TB
-    %% Vector DB interaction
-    R_RET <-.-> VDB
-    DP <-.-> VDB
+   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 .
+   ```
+
+2. Launch tool services </br>
+   In this example, we will use some of the mock APIs provided in the Meta CRAG KDD Challenge to demonstrate the benefits of gaining additional context from mock knowledge graphs.
+
+   ```
+   docker run -d -p=8080:8000 docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
+   ```
+
+3. Set up environment for this example </br>
+   First, clone this repo
+
+   ```
+   cd $WORKDIR
+   git clone https://github.com/opea-project/GenAIExamples.git
+   ```
+
+   Second, set up env vars
+
+   ```
+   export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
+   # optional: OPANAI_API_KEY
+   export OPENAI_API_KEY=<your-openai-key>
+   ```
+
+4. Launch agent services</br>
+   The configurations of the supervisor agent and the worker agent are defined in the docker-compose yaml file. We currently use openAI GPT-4o-mini as LLM, and we plan to add support for llama3.1-70B-instruct (served by TGI-Gaudi) in a subsequent release.
+   To use openai llm, run command below.
+
+   ```
+   cd docker_compose/intel/cpu/xeon
+   bash launch_agent_service_openai.sh
+   ```
+
+## Validate services
+
+First look at logs of the agent docker containers:
 
 ```
-
-### Why should AI Agents be used for question-answering?
-
-1. **Improve relevancy of retrieved context.**
-   RAG agents can rephrase user queries, decompose user queries, and iterate to get the most relevant context for answering a user's question. Compared to conventional RAG, RAG agents significantly improve the correctness and relevancy of the answer because of the iterations it goes through.
-2. **Expand scope of skills.**
-   The supervisor agent interacts with multiple worker agents that specialize in different skills (e.g., retrieve documents, write SQL queries, etc.). Thus, it can answer questions with different methods.
-3. **Hierarchical multi-agents improve performance.**
-   Expert worker agents, such as RAG agents and SQL agents, can provide high-quality output for different aspects of a complex query, and the supervisor agent can aggregate the information to provide a comprehensive answer. If only one agent is used and all tools are provided to this single agent, it can lead to large overhead or not use the best tool to provide accurate answers.
-
-## Deploy with docker
-
-### 1. Set up environment </br>
-
-#### First, clone the `GenAIExamples` repo.
-
-```
-export WORKDIR=<your-work-directory>
-cd $WORKDIR
-git clone https://github.com/opea-project/GenAIExamples.git
+docker logs docgrader-agent-endpoint
 ```
 
-#### Second, set up environment variables.
-
-##### For proxy environments only
-
 ```
-export http_proxy="Your_HTTP_Proxy"
-export https_proxy="Your_HTTPs_Proxy"
-# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
-export no_proxy="Your_No_Proxy"
-```
-
-##### For using open-source llms
-
-```
-export HUGGINGFACEHUB_API_TOKEN=<your-HF-token>
-export HF_CACHE_DIR=<directory-where-llms-are-downloaded> #so that no need to redownload every time
-```
-
-##### [Optional] OPANAI_API_KEY to use OpenAI models
-
-```
-export OPENAI_API_KEY=<your-openai-key>
-```
-
-#### Third, set up environment variables for the selected hardware using the corresponding `set_env.sh`
-
-##### Gaudi
-
-```
-source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/set_env.sh
-```
-
-##### Xeon
-
-```
-source $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon/set_env.sh
-```
-
-### 3. Launch the multi-agent system. </br>
-
-Two options are provided for the `llm_engine` of the agents: 1. open-source LLMs on Gaudi, 2. OpenAI models via API calls.
-
-#### Gaudi
-
-On Gaudi, `meta-llama/Meta-Llama-3.1-70B-Instruct` will be served using vllm.
-By default, both the RAG agent and SQL agent will be launched to support the React Agent.  
-The React Agent requires the DocIndexRetriever's [`compose.yaml`](../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml) file, so two `compose.yaml` files need to be run with docker compose to start the multi-agent system.
-
-> **Note**: To enable the web search tool, skip this step and proceed to the "[Optional] Web Search Tool Support" section.
-
-```bash
-cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
-docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml up -d
-```
-
-##### [Optional] Web Search Tool Support
-
-<details>
-<summary> Instructions </summary>
-A web search tool is supported in this example and can be enabled by running docker compose with the `compose.webtool.yaml` file.  
-The Google Search API is used. Follow the [instructions](https://python.langchain.com/docs/integrations/tools/google_search) to create an API key and enable the Custom Search API on a Google account. The environment variables `GOOGLE_CSE_ID` and `GOOGLE_API_KEY` need to be set.
-
-```bash
-cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi/
-export GOOGLE_CSE_ID="YOUR_ID"
-export GOOGLE_API_KEY="YOUR_API_KEY"
-docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml -f compose.webtool.yaml up -d
-```
-
-</details>
-
-#### Xeon
-
-On Xeon, only OpenAI models are supported.
-By default, both the RAG Agent and SQL Agent will be launched to support the React Agent.  
-The React Agent requires the DocIndexRetriever's [`compose.yaml`](../DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml) file, so two `compose yaml` files need to be run with docker compose to start the multi-agent system.
-
-```bash
-export OPENAI_API_KEY=<your-openai-key>
-cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/cpu/xeon
-docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose_openai.yaml up -d
-```
-
-### 4. Ingest Data into the vector database
-
-The `run_ingest_data.sh` script will use an example jsonl file to ingest example documents into a vector database. Other ways to ingest data and other types of documents supported can be found in the OPEA dataprep microservice located in the opea-project/GenAIComps repo.
-
-```bash
-cd  $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool/
-bash run_ingest_data.sh
-```
-
-> **Note**: This is a one-time operation.
-
-## Launch the UI
-
-Open a web browser to http://localhost:5173 to access the UI. Ensure the environment variable `AGENT_URL` is set to http://$ip_address:9090/v1/chat/completions in [ui/svelte/.env](./ui/svelte/.env) or else the UI may not work properly.
-
-The AgentQnA UI can be deployed locally or using Docker. To customize deployment, refer to the [AgentQnA UI Guide](./ui/svelte/README.md).
-
-## [Optional] Deploy using Helm Charts
-
-Refer to the [AgentQnA helm chart](./kubernetes/helm/README.md) for instructions on deploying AgentQnA on Kubernetes.
-
-## Validate Services
-
-1. First look at logs for each of the agent docker containers:
-
-```bash
-# worker RAG agent
-docker logs rag-agent-endpoint
-
-# worker SQL agent
-docker logs sql-agent-endpoint
-
-# supervisor agent
 docker logs react-agent-endpoint
 ```
 
-Look for the message "HTTP server setup successful" to confirm the agent docker container has started successfully.</p>
+You should see something like "HTTP server setup successful" if the docker containers are started successfully.</p>
 
-2. Use python to validate each agent is working properly:
+Second, validate worker agent:
 
-```bash
-# RAG worker agent
-python $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "Tell me about Michael Jackson song Thriller" --agent_role "worker" --ext_port 9095
-
-# SQL agent
-python $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "How many employees in company" --agent_role "worker" --ext_port 9096
-
-# supervisor agent: this will test a two-turn conversation
-python $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --agent_role "supervisor" --ext_port 9090
+```
+curl http://${ip_address}:9095/v1/chat/completions -X POST -H "Content-Type: application/json" -d '{
+     "query": "Most recent album by Taylor Swift"
+    }'
 ```
 
-## How to register other tools with the AI agent
+Third, validate supervisor agent:
 
-The [tools](./tools) folder contains YAML and Python files for additional tools for the supervisor and worker agents. Refer to the "Provide your own tools" section in the instructions [here](https://github.com/opea-project/GenAIComps/tree/main/comps/agent/src/README.md) to add tools and customize the AI agents.
+```
+curl http://${ip_address}: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/langchain#5-customize-agent-strategy).

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

@@ -1,101 +0,0 @@
-# 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

@@ -1,97 +0,0 @@
-# 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:
-      - ${HF_CACHE_DIR:-/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

@@ -1,47 +0,0 @@
-# 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

@@ -1,46 +0,0 @@
-#!/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 +0,0 @@
-# Single node on-prem deployment with Docker Compose on Xeon Scalable processors
-
-This example showcases a hierarchical multi-agent system for question-answering applications. To deploy the example on Xeon, OpenAI LLM models via API calls are used. For instructions, refer to the deployment guide [here](../../../../README.md).

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

@@ -2,10 +2,11 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  worker-rag-agent:
-    image: opea/agent:latest
-    container_name: rag-agent-endpoint
+  worker-docgrader-agent:
+    image: opea/agent-langchain:latest
+    container_name: docgrader-agent-endpoint
     volumes:
+      - ${WORKDIR}/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9095:9095"
@@ -13,14 +14,13 @@ services:
     environment:
       ip_address: ${ip_address}
       strategy: rag_agent
-      with_memory: false
       recursion_limit: ${recursion_limit_worker}
       llm_engine: openai
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       model: ${model}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      stream: false
+      streaming: false
       tools: /home/user/tools/worker_agent_tools.yaml
       require_human_feedback: false
       RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
@@ -32,56 +32,26 @@ services:
       LANGCHAIN_PROJECT: "opea-worker-agent-service"
       port: 9095
 
-  worker-sql-agent:
-    image: opea/agent:latest
-    container_name: sql-agent-endpoint
-    volumes:
-      - ${WORKDIR}/GenAIExamples/AgentQnA/tests:/home/user/chinook-db # SQL database
-    ports:
-      - "9096:9096"
-    ipc: host
-    environment:
-      ip_address: ${ip_address}
-      strategy: sql_agent
-      with_memory: false
-      db_name: ${db_name}
-      db_path: ${db_path}
-      use_hints: false
-      recursion_limit: ${recursion_limit_worker}
-      llm_engine: openai
-      OPENAI_API_KEY: ${OPENAI_API_KEY}
-      model: ${model}
-      temperature: 0
-      max_new_tokens: ${max_new_tokens}
-      stream: false
-      require_human_feedback: false
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      port: 9096
 
   supervisor-react-agent:
-    image: opea/agent:latest
+    image: opea/agent-langchain:latest
     container_name: react-agent-endpoint
-    depends_on:
-      - worker-rag-agent
-      - worker-sql-agent
     volumes:
+      - ${WORKDIR}/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9090:9090"
     ipc: host
     environment:
       ip_address: ${ip_address}
-      strategy: react_llama
-      with_memory: true
+      strategy: react_langgraph
       recursion_limit: ${recursion_limit_supervisor}
       llm_engine: openai
       OPENAI_API_KEY: ${OPENAI_API_KEY}
       model: ${model}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      stream: true
+      streaming: false
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}
@@ -92,23 +62,4 @@ services:
       LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
       CRAG_SERVER: $CRAG_SERVER
       WORKER_AGENT_URL: $WORKER_AGENT_URL
-      SQL_AGENT_URL: $SQL_AGENT_URL
       port: 9090
-  mock-api:
-    image: docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
-    container_name: mock-api
-    ports:
-      - "8080:8000"
-    ipc: host
-  agent-ui:
-    image: opea/agent-ui
-    container_name: agent-ui
-    volumes:
-      - ${WORKDIR}/GenAIExamples/AgentQnA/ui/svelte/.env:/home/user/svelte/.env # test db
-    ports:
-      - "5173:5173"
-    ipc: host
-
-networks:
-  default:
-    driver: bridge

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

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

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

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

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

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

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

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

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

@@ -2,26 +2,50 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  worker-rag-agent:
-    image: opea/agent:latest
-    container_name: rag-agent-endpoint
+  tgi-server:
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.4
+    container_name: tgi-server
+    ports:
+      - "8085:80"
     volumes:
+      - ${HF_CACHE_DIR}:/data
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}
+  worker-docgrader-agent:
+    image: opea/agent-langchain:latest
+    container_name: docgrader-agent-endpoint
+    depends_on:
+      - tgi-server
+    volumes:
+      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9095:9095"
     ipc: host
     environment:
       ip_address: ${ip_address}
-      strategy: rag_agent_llama
-      with_memory: false
+      strategy: rag_agent
       recursion_limit: ${recursion_limit_worker}
-      llm_engine: vllm
+      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
+      streaming: false
       tools: /home/user/tools/worker_agent_tools.yaml
       require_human_feedback: false
       RETRIEVAL_TOOL_URL: ${RETRIEVAL_TOOL_URL}
@@ -33,58 +57,30 @@ 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
-      with_memory: false
-      db_name: ${db_name}
-      db_path: ${db_path}
-      use_hints: false
-      recursion_limit: ${recursion_limit_worker}
-      llm_engine: vllm
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      llm_endpoint_url: ${LLM_ENDPOINT_URL}
-      model: ${LLM_MODEL_ID}
-      temperature: ${temperature}
-      max_new_tokens: ${max_new_tokens}
-      stream: false
-      require_human_feedback: false
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      port: 9096
 
   supervisor-react-agent:
-    image: opea/agent:latest
+    image: opea/agent-langchain:latest
     container_name: react-agent-endpoint
     depends_on:
-      - worker-rag-agent
-      - worker-sql-agent
+      - tgi-server
+      - worker-docgrader-agent
     volumes:
+      # - ${WORKDIR}/GenAIExamples/AgentQnA/docker_image_build/GenAIComps/comps/agent/langchain/:/home/user/comps/agent/langchain/
       - ${TOOLSET_PATH}:/home/user/tools/
     ports:
       - "9090:9090"
     ipc: host
     environment:
       ip_address: ${ip_address}
-      strategy: react_llama
-      with_memory: true
+      strategy: react_langgraph
       recursion_limit: ${recursion_limit_supervisor}
-      llm_engine: vllm
+      llm_engine: tgi
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
       llm_endpoint_url: ${LLM_ENDPOINT_URL}
       model: ${LLM_MODEL_ID}
       temperature: ${temperature}
       max_new_tokens: ${max_new_tokens}
-      stream: true
+      streaming: false
       tools: /home/user/tools/supervisor_agent_tools.yaml
       require_human_feedback: false
       no_proxy: ${no_proxy}
@@ -95,49 +91,4 @@ services:
       LANGCHAIN_PROJECT: "opea-supervisor-agent-service"
       CRAG_SERVER: $CRAG_SERVER
       WORKER_AGENT_URL: $WORKER_AGENT_URL
-      SQL_AGENT_URL: $SQL_AGENT_URL
       port: 9090
-  mock-api:
-    image: docker.io/aicrowd/kdd-cup-24-crag-mock-api:v0
-    container_name: mock-api
-    ports:
-      - "8080:8000"
-    ipc: host
-  agent-ui:
-    image: opea/agent-ui
-    container_name: agent-ui
-    volumes:
-      - ${WORKDIR}/GenAIExamples/AgentQnA/ui/svelte/.env:/home/user/svelte/.env
-    environment:
-      host_ip: ${host_ip}
-    ports:
-      - "5173:5173"
-    ipc: host
-  vllm-service:
-    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
-    container_name: vllm-gaudi-server
-    ports:
-      - "8086:8000"
-    volumes:
-      - "./data:/data"
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      LLM_MODEL_ID: ${LLM_MODEL_ID}
-      VLLM_TORCH_PROFILER_DIR: "/mnt"
-      VLLM_SKIP_WARMUP: true
-      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
-    healthcheck:
-      test: ["CMD-SHELL", "curl -f http://$host_ip:8086/health || exit 1"]
-      interval: 10s
-      timeout: 10s
-      retries: 100
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    command: --model $LLM_MODEL_ID --tensor-parallel-size 4 --host 0.0.0.0 --port 8000 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 16384

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

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

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

@@ -1,69 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-pushd "../../../../../" > /dev/null
-source .set_env.sh
-popd > /dev/null
-WORKPATH=$(dirname "$PWD")/..
-# export WORKDIR=$WORKPATH/../../
-if [[ -z "${WORKDIR}" ]]; then
-	echo "Please set WORKDIR environment variable"
-	exit 0
-fi
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-
-# LLM related environment variables
-export HF_CACHE_DIR=${HF_CACHE_DIR}
-ls $HF_CACHE_DIR
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-export LLM_MODEL_ID="meta-llama/Llama-3.3-70B-Instruct"
-export NUM_SHARDS=4
-export LLM_ENDPOINT_URL="http://${ip_address}:8086"
-export temperature=0
-export max_new_tokens=4096
-
-# agent related environment variables
-export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-echo "TOOLSET_PATH=${TOOLSET_PATH}"
-export recursion_limit_worker=12
-export recursion_limit_supervisor=10
-export WORKER_AGENT_URL="http://${ip_address}:9095/v1/chat/completions"
-export SQL_AGENT_URL="http://${ip_address}:9096/v1/chat/completions"
-export RETRIEVAL_TOOL_URL="http://${ip_address}:8889/v1/retrievaltool"
-export CRAG_SERVER=http://${ip_address}:8080
-
-export db_name=Chinook
-export db_path="sqlite:////home/user/chinook-db/Chinook_Sqlite.sqlite"
-if [ ! -f $WORKDIR/GenAIExamples/AgentQnA/tests/Chinook_Sqlite.sqlite ]; then
-    echo "Download Chinook_Sqlite!"
-    wget  -O $WORKDIR/GenAIExamples/AgentQnA/tests/Chinook_Sqlite.sqlite  https://github.com/lerocha/chinook-database/releases/download/v1.4.5/Chinook_Sqlite.sqlite
-fi
-
-# configure agent ui
-echo "AGENT_URL = 'http://$ip_address:9090/v1/chat/completions'" | tee ${WORKDIR}/GenAIExamples/AgentQnA/ui/svelte/.env
-
-# retriever
-export host_ip=$(hostname -I | awk '{print $1}')
-export no_proxy=${no_proxy}
-export http_proxy=${http_proxy}
-export https_proxy=${https_proxy}
-export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
-export RERANK_MODEL_ID="BAAI/bge-reranker-base"
-export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
-export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
-export REDIS_URL="redis://${host_ip}:6379"
-export INDEX_NAME="rag-redis"
-export RERANK_TYPE="tei"
-export MEGA_SERVICE_HOST_IP=${host_ip}
-export EMBEDDING_SERVICE_HOST_IP=${host_ip}
-export RETRIEVER_SERVICE_HOST_IP=${host_ip}
-export RERANK_SERVICE_HOST_IP=${host_ip}
-export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8889/v1/retrievaltool"
-export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"
-export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get"
-export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete"
-
-
-export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui,vllm-gaudi-server,jaeger,grafana,prometheus,127.0.0.1,localhost,0.0.0.0,$host_ip"

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

@@ -1,30 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-services:
-  tgi-server:
-    image: ghcr.io/huggingface/tgi-gaudi:2.0.6
-    container_name: tgi-server
-    ports:
-      - "8085:80"
-    volumes:
-      - ${HF_CACHE_DIR}:/data
-    environment:
-      no_proxy: ${no_proxy}
-      http_proxy: ${http_proxy}
-      https_proxy: ${https_proxy}
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_HUB_DISABLE_PROGRESS_BARS: 1
-      HF_HUB_ENABLE_HF_TRANSFER: 0
-      HABANA_VISIBLE_DEVICES: all
-      OMPI_MCA_btl_vader_single_copy_mechanism: none
-      PT_HPU_ENABLE_LAZY_COLLECTIVES: true
-      ENABLE_HPU_GRAPH: true
-      LIMIT_HPU_GRAPH: true
-      USE_FLASH_ATTENTION: true
-      FLASH_ATTENTION_RECOMPUTE: true
-    runtime: habana
-    cap_add:
-      - SYS_NICE
-    ipc: host
-    command: --model-id ${LLM_MODEL_ID} --max-input-length 4096 --max-total-tokens 8192 --sharded true --num-shard ${NUM_SHARDS}

AgentQnA/docker_image_build/build.yaml

@@ -2,18 +2,12 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  agent:
+  agent-langchain:
     build:
       context: GenAIComps
-      dockerfile: comps/agent/src/Dockerfile
+      dockerfile: comps/agent/langchain/Dockerfile
       args:
         http_proxy: ${http_proxy}
         https_proxy: ${https_proxy}
         no_proxy: ${no_proxy}
-    image: ${REGISTRY:-opea}/agent:${TAG:-latest}
-  agent-ui:
-    build:
-      context: ../ui
-      dockerfile: ./docker/Dockerfile
-    extends: agent
-    image: ${REGISTRY:-opea}/agent-ui:${TAG:-latest}
+    image: ${REGISTRY:-opea}/agent-langchain:${TAG:-latest}

AgentQnA/kubernetes/helm/README.md

@@ -1,11 +0,0 @@
-# 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

@@ -1,16 +0,0 @@
-# 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/ingest".format(host_ip=host_ip, port=port)
+    url = "http://{host_ip}:{port}/v1/dataprep".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

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

AgentQnA/tests/1_build_images.sh

@@ -11,18 +11,19 @@ export ip_address=$(hostname -I | awk '{print $1}')
 
 function get_genai_comps() {
     if [ ! -d "GenAIComps" ] ; then
-        git clone --depth 1 --branch ${opea_branch:-"main"} https://github.com/opea-project/GenAIComps.git
+        git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
     fi
 }
 
 
 function build_docker_images_for_retrieval_tool(){
     cd $WORKDIR/GenAIExamples/DocIndexRetriever/docker_image_build/
+    # git clone https://github.com/opea-project/GenAIComps.git && cd GenAIComps && git checkout "${opea_branch:-"main"}" && cd ../
     get_genai_comps
     echo "Build all the images with --no-cache..."
-    service_list="doc-index-retriever dataprep embedding retriever reranking"
+    service_list="doc-index-retriever dataprep-redis embedding-tei retriever-redis reranking-tei"
     docker compose -f build.yaml build ${service_list} --no-cache
-    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.6
+    docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
 
     docker images && sleep 1s
 }
@@ -34,26 +35,6 @@ 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 $WORKPATH
-    if [ ! -d "./vllm-fork" ]; then
-        git clone https://github.com/HabanaAI/vllm-fork.git
-    fi
-    cd ./vllm-fork
-    VLLM_VER=$(git describe --tags "$(git rev-list --tags --max-count=1)")
-    git checkout ${VLLM_VER} &> /dev/null
-    docker build --no-cache -f Dockerfile.hpu -t opea/vllm-gaudi:ci --shm-size=128g . --build-arg https_proxy=$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
@@ -62,12 +43,6 @@ 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/2_start_retrieval_tool.sh

@@ -7,9 +7,8 @@ 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=${model_cache:-"$WORKDIR/hf_cache"}
+export HF_CACHE_DIR=$WORKDIR/hf_cache
 if [ ! -d "$HF_CACHE_DIR" ]; then
     echo "Creating HF_CACHE directory"
     mkdir -p "$HF_CACHE_DIR"

AgentQnA/tests/4_launch_and_validate_agent_openai.sh

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

AgentQnA/tests/4_launch_and_validate_agent_tgi.sh

@@ -2,7 +2,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-set -ex
+set -e
 
 WORKPATH=$(dirname "$PWD")
 export WORKDIR=$WORKPATH/../../
@@ -11,7 +11,7 @@ export ip_address=$(hostname -I | awk '{print $1}')
 export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
 export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 
-export HF_CACHE_DIR=${model_cache:-"$WORKDIR/hf_cache"}
+export HF_CACHE_DIR=$WORKDIR/hf_cache
 if [ ! -d "$HF_CACHE_DIR" ]; then
     mkdir -p "$HF_CACHE_DIR"
 fi
@@ -23,8 +23,8 @@ function start_agent_and_api_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
+    cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi
+    bash launch_agent_service_tgi_gaudi.sh
 }
 
 function validate() {
@@ -47,7 +47,7 @@ function validate_agent_service() {
      "query": "Tell me about Michael Jackson song thriller"
     }')
     local EXIT_CODE=$(validate "$CONTENT" "Thriller" "react-agent-endpoint")
-    docker logs rag-agent-endpoint
+    docker logs docgrader-agent-endpoint
     if [ "$EXIT_CODE" == "1" ]; then
         exit 1
     fi

AgentQnA/tests/_test_compose_openai_on_xeon.sh

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

AgentQnA/tests/sql_agent_test/run_data_split.sh

@@ -1,6 +0,0 @@
-# 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

@@ -1,27 +0,0 @@
-# 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/step4_launch_and_validate_agent_gaudi.sh

@@ -1,214 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -e
-
-WORKPATH=$(dirname "$PWD")
-export WORKDIR=$WORKPATH/../../
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-export TOOLSET_PATH=$WORKPATH/tools/
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-model="meta-llama/Llama-3.3-70B-Instruct" #"meta-llama/Meta-Llama-3.1-70B-Instruct"
-
-export HF_CACHE_DIR=${model_cache:-"/data2/huggingface"}
-if [ ! -d "$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
-    source set_env.sh
-    docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml tgi_gaudi.yaml up -d
-
-}
-
-function start_all_services() {
-
-    echo "token is ${HF_TOKEN}"
-
-    echo "start vllm gaudi service"
-    echo "**************model is $model**************"
-    cd $WORKDIR/GenAIExamples/AgentQnA/docker_compose/intel/hpu/gaudi
-    source set_env.sh
-    docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml up -d
-    sleep 5s
-    echo "Waiting vllm gaudi ready"
-    n=0
-    LOG_PATH=$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 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 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: $CONTENT"
-        echo 1
-    fi
-}
-
-function validate_agent_service() {
-    # # test worker rag agent
-    echo "======================Testing worker rag agent======================"
-    export agent_port="9095"
-    export agent_ip="127.0.0.1"
-    prompt="Tell me about Michael Jackson song Thriller"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt" --agent_role "worker" --ip_addr $agent_ip  --ext_port $agent_port)
-    # echo $CONTENT
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "rag-agent-endpoint")
-    echo $EXIT_CODE
-    local EXIT_CODE="${EXIT_CODE:0-1}"
-    if [ "$EXIT_CODE" == "1" ]; then
-        docker logs rag-agent-endpoint
-        exit 1
-    fi
-
-    # # test worker sql agent
-    echo "======================Testing worker sql agent======================"
-    export agent_port="9096"
-    prompt="How many employees are there in the company?"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt" --agent_role "worker" --ip_addr $agent_ip --ext_port $agent_port)
-    local EXIT_CODE=$(validate "$CONTENT" "8" "sql-agent-endpoint")
-    echo $CONTENT
-    # echo $EXIT_CODE
-    local EXIT_CODE="${EXIT_CODE:0-1}"
-    if [ "$EXIT_CODE" == "1" ]; then
-        docker logs sql-agent-endpoint
-        exit 1
-    fi
-
-    # test supervisor react agent
-    echo "======================Testing supervisor react agent======================"
-    export agent_port="9090"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --agent_role "supervisor" --ip_addr $agent_ip  --ext_port $agent_port --stream)
-    local EXIT_CODE=$(validate "$CONTENT" "Iron" "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_chinook_data(){
-    echo "Removing chinook data..."
-    cd $WORKDIR
-    if [ -d "chinook-database" ]; then
-        rm -rf chinook-database
-    fi
-    echo "Chinook data removed!"
-}
-
-export host_ip=$ip_address
-echo "ip_address=${ip_address}"
-
-
-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 ingest_data_and_validate() {
-    echo "Ingesting data"
-    cd $WORKDIR/GenAIExamples/AgentQnA/retrieval_tool/
-    echo $PWD
-    local CONTENT=$(bash run_ingest_data.sh)
-    local EXIT_CODE=$(validate "$CONTENT" "Data preparation succeeded" "dataprep-redis-server")
-    echo "$EXIT_CODE"
-    local EXIT_CODE="${EXIT_CODE:0-1}"
-    echo "return value is $EXIT_CODE"
-    if [ "$EXIT_CODE" == "1" ]; then
-        docker logs dataprep-redis-server
-        return 1
-    fi
-}
-
-function validate_retrieval_tool() {
-    echo "----------------Test retrieval tool ----------------"
-    local CONTENT=$(http_proxy="" curl http://${ip_address}:8889/v1/retrievaltool -X POST -H "Content-Type: application/json" -d '{
-     "text": "Who sang Thriller"
-    }')
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "retrieval-tool")
-
-    if [ "$EXIT_CODE" == "1" ]; then
-        docker logs retrievaltool-xeon-backend-server
-        exit 1
-    fi
-}
-
-function main() {
-    echo "==================== Prepare data ===================="
-    download_chinook_data
-    echo "==================== Data prepare done ===================="
-
-    echo "==================== Start all services ===================="
-    start_all_services
-    echo "==================== all services started ===================="
-
-    echo "==================== Ingest data ===================="
-    ingest_data_and_validate
-    echo "==================== Data ingestion completed ===================="
-
-    echo "==================== Validate retrieval tool ===================="
-    validate_retrieval_tool
-    echo "==================== Retrieval tool validated ===================="
-
-    echo "==================== Validate agent service ===================="
-    validate_agent_service
-    echo "==================== Agent service validated ===================="
-}
-
-
-remove_chinook_data
-
-main
-
-remove_chinook_data

AgentQnA/tests/step4_launch_and_validate_agent_openai.sh

@@ -1,119 +0,0 @@
-#!/bin/bash
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-set -e
-echo "OPENAI_API_KEY=${OPENAI_API_KEY}"
-
-WORKPATH=$(dirname "$PWD")
-export WORKDIR=$WORKPATH/../../
-echo "WORKDIR=${WORKDIR}"
-export ip_address=$(hostname -I | awk '{print $1}')
-export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-
-
-function 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/cpu/xeon/
-    bash launch_agent_service_openai.sh
-    sleep 2m
-}
-
-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: $CONTENT"
-        echo 1
-    fi
-}
-
-function validate_agent_service() {
-    # # test worker rag agent
-    echo "======================Testing worker rag agent======================"
-    export agent_port="9095"
-    prompt="Tell me about Michael Jackson song Thriller"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt" --agent_role "worker" --ext_port $agent_port)
-    # echo $CONTENT
-    local EXIT_CODE=$(validate "$CONTENT" "Thriller" "rag-agent-endpoint")
-    echo $EXIT_CODE
-    local EXIT_CODE="${EXIT_CODE:0-1}"
-    if [ "$EXIT_CODE" == "1" ]; then
-        docker logs rag-agent-endpoint
-        exit 1
-    fi
-
-    # # test worker sql agent
-    echo "======================Testing worker sql agent======================"
-    export agent_port="9096"
-    prompt="How many employees are there in the company?"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --prompt "$prompt" --agent_role "worker" --ext_port $agent_port)
-    local EXIT_CODE=$(validate "$CONTENT" "8" "sql-agent-endpoint")
-    echo $CONTENT
-    # echo $EXIT_CODE
-    local EXIT_CODE="${EXIT_CODE:0-1}"
-    if [ "$EXIT_CODE" == "1" ]; then
-        docker logs sql-agent-endpoint
-        exit 1
-    fi
-
-    # test supervisor react agent
-    echo "======================Testing supervisor react agent======================"
-    export agent_port="9090"
-    local CONTENT=$(python3 $WORKDIR/GenAIExamples/AgentQnA/tests/test.py --agent_role "supervisor" --ext_port $agent_port --stream)
-    local EXIT_CODE=$(validate "$CONTENT" "Iron" "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_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 "==================== Prepare data ===================="
-    download_chinook_data
-    echo "==================== Data prepare done ===================="
-
-    echo "==================== Start agent ===================="
-    start_agent_and_api_server
-    echo "==================== Agent started ===================="
-
-    echo "==================== Validate agent service ===================="
-    validate_agent_service
-    echo "==================== Agent service validated ===================="
-}
-
-
-remove_chinook_data
-
-main
-
-remove_chinook_data

AgentQnA/tests/test.py

@@ -1,77 +0,0 @@
-# Copyright (C) 2025 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-import argparse
-import json
-import uuid
-
-import requests
-
-
-def process_request(url, query, is_stream=False):
-    proxies = {"http": ""}
-    content = json.dumps(query) if query is not None else None
-    try:
-        resp = requests.post(url=url, data=content, proxies=proxies, stream=is_stream)
-        if not is_stream:
-            ret = resp.json()["text"]
-        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}"
-        return None
-
-
-def test_worker_agent(args):
-    url = f"http://{args.ip_addr}:{args.ext_port}/v1/chat/completions"
-    query = {"role": "user", "messages": args.prompt, "stream": "false"}
-    ret = process_request(url, query)
-    print("Response: ", ret)
-
-
-def add_message_and_run(url, user_message, thread_id, stream=False):
-    print("User message: ", user_message)
-    query = {"role": "user", "messages": user_message, "thread_id": thread_id, "stream": stream}
-    ret = process_request(url, query, is_stream=stream)
-    print("Response: ", ret)
-
-
-def test_chat_completion_multi_turn(args):
-    url = f"http://{args.ip_addr}:{args.ext_port}/v1/chat/completions"
-    thread_id = f"{uuid.uuid4()}"
-
-    # first turn
-    print("===============First turn==================")
-    user_message = "Which artist has the most albums in the database?"
-    add_message_and_run(url, user_message, thread_id, stream=args.stream)
-    print("===============End of first turn==================")
-
-    # second turn
-    print("===============Second turn==================")
-    user_message = "Give me a few examples of the artist's albums?"
-    add_message_and_run(url, user_message, thread_id, stream=args.stream)
-    print("===============End of second turn==================")
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--ip_addr", type=str, default="127.0.0.1", help="endpoint ip address")
-    parser.add_argument("--ext_port", type=str, default="9090", help="endpoint port")
-    parser.add_argument("--stream", action="store_true", help="streaming mode")
-    parser.add_argument("--prompt", type=str, help="prompt message")
-    parser.add_argument("--agent_role", type=str, default="supervisor", help="supervisor or worker")
-    args, _ = parser.parse_known_args()
-
-    print(args)
-
-    if args.agent_role == "supervisor":
-        test_chat_completion_multi_turn(args)
-    elif args.agent_role == "worker":
-        test_worker_agent(args)
-    else:
-        raise ValueError("Invalid agent role")

AgentQnA/tests/test_compose_on_gaudi.sh

@@ -1,7 +1,8 @@
 #!/bin/bash
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
-set -xe
+
+set -e
 
 WORKPATH=$(dirname "$PWD")
 export WORKDIR=$WORKPATH/../../
@@ -9,22 +10,6 @@ echo "WORKDIR=${WORKDIR}"
 export ip_address=$(hostname -I | awk '{print $1}')
 export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
 export TOOLSET_PATH=$WORKDIR/GenAIExamples/AgentQnA/tools/
-export no_proxy="$no_proxy,rag-agent-endpoint,sql-agent-endpoint,react-agent-endpoint,agent-ui,vllm-gaudi-server,jaeger,grafana,prometheus,127.0.0.1,localhost,0.0.0.0,$ip_address"
-
-
-function get_genai_comps() {
-    if [ ! -d "GenAIComps" ] ; then
-        git clone --depth 1 --branch ${opea_branch:-"main"} https://github.com/opea-project/GenAIComps.git
-    fi
-}
-
-
-function build_agent_docker_image() {
-    cd $WORKDIR/GenAIExamples/AgentQnA/docker_image_build/
-    get_genai_comps
-    echo "Build agent image with --no-cache..."
-    docker compose -f build.yaml build --no-cache
-}
 
 function stop_crag() {
     cid=$(docker ps -aq --filter "name=kdd-cup-24-crag-service")
@@ -34,32 +19,20 @@ function stop_crag() {
 
 function stop_agent_docker() {
     cd $WORKPATH/docker_compose/intel/hpu/gaudi/
-    docker compose -f $WORKDIR/GenAIExamples/DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml -f compose.yaml down
-}
-
-function stop_llm(){
-    cd $WORKPATH/docker_compose/intel/hpu/gaudi/
-    container_list=$(cat tgi_gaudi.yaml | grep container_name | cut -d':' -f2)
+    # 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 $cid -f && sleep 1s; fi
     done
-
-    cid=$(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() {
     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")
@@ -71,22 +44,30 @@ echo "workpath: $WORKPATH"
 echo "=================== Stop containers ===================="
 stop_crag
 stop_agent_docker
+stop_retrieval_tool
 
 cd $WORKPATH/tests
 
 echo "=================== #1 Building docker images===================="
-build_agent_docker_image
+bash 1_build_images.sh
 echo "=================== #1 Building docker images completed===================="
 
-echo "=================== #4 Start agent, API server, retrieval, and ingest data===================="
-bash $WORKPATH/tests/step4_launch_and_validate_agent_gaudi.sh
-echo "=================== #4 Agent, retrieval test passed ===================="
+echo "=================== #2 Start retrieval tool===================="
+bash 2_start_retrieval_tool.sh
+echo "=================== #2 Retrieval tool started===================="
+
+echo "=================== #3 Ingest data and validate retrieval===================="
+bash 3_ingest_data_and_validate_retrieval.sh
+echo "=================== #3 Data ingestion and validation completed===================="
+
+echo "=================== #4 Start agent and API server===================="
+bash 4_launch_and_validate_agent_tgi.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!!"
+echo "ALL DONE!"

AgentQnA/tests/test_compose_on_rocm.sh

@@ -1,75 +0,0 @@
-#!/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 a knowledge base for a given query. Returns text related to the query.
+  description: Search knowledge base for a given query. Returns text related to the query.
   callable_api: tools.py:search_knowledge_base
   args_schema:
     query:
@@ -10,15 +10,6 @@ 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
@@ -34,7 +25,7 @@ get_billboard_rank_date:
   args_schema:
     rank:
       type: int
-      description: the rank of interest, for example 1 for top 1
+      description: song name
     date:
       type: str
       description: date

AgentQnA/tools/supervisor_agent_webtools.yaml

@@ -1,77 +0,0 @@
-# Copyright (C) 2024 Intel Corporation
-# SPDX-License-Identifier: Apache-2.0
-
-search_web_base:
-  description: Search a web base for a given query. Returns text related to the query.
-  callable_api: tools.py:search_web_base
-  args_schema:
-    query:
-      type: str
-      description: query
-  return_output: retrieved_data
-
-search_knowledge_base:
-  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:
-      type: str
-      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
-  args_schema:
-    artist_name:
-      type: str
-      description: artist name
-  return_output: birth_place
-
-get_billboard_rank_date:
-  description: Get Billboard ranking for a specific rank and date.
-  callable_api: tools.py:get_billboard_rank_date
-  args_schema:
-    rank:
-      type: int
-      description: the rank of interest, for example 1 for top 1
-    date:
-      type: str
-      description: date
-  return_output: billboard_info
-
-get_song_release_date:
-  description: Get the release date of a song.
-  callable_api: tools.py:get_song_release_date
-  args_schema:
-    song_name:
-      type: str
-      description: song name
-  return_output: release_date
-
-get_members:
-  description: Get the member list of a band.
-  callable_api: tools.py:get_members
-  args_schema:
-    band_name:
-      type: str
-      description: band name
-  return_output: members
-
-get_grammy_best_artist_by_year:
-  description: Get the Grammy Best New Artist for a specific year.
-  callable_api: tools.py:get_grammy_best_artist_by_year
-  args_schema:
-    year:
-      type: int
-      description: year
-  return_output: grammy_best_new_artist

AgentQnA/tools/tools.py

@@ -7,49 +7,14 @@ import requests
 from tools.pycragapi import CRAG
 
 
-def search_web_base(query: str) -> str:
-    import os
-
-    from langchain_core.tools import Tool
-    from langchain_google_community import GoogleSearchAPIWrapper
-
-    search = GoogleSearchAPIWrapper()
-
-    tool = Tool(
-        name="google_search",
-        description="Search Google for recent results.",
-        func=search.run,
-    )
-
-    response = tool.run(query)
-    return response
-
-
 def search_knowledge_base(query: str) -> str:
-    """Search a knowledge base about music and singers for a given query.
-
-    Returns text related to the query.
-    """
+    """Search the knowledge base for a specific query."""
+    # use worker agent (DocGrader) to search the knowledge base
     url = os.environ.get("WORKER_AGENT_URL")
     print(url)
     proxies = {"http": ""}
     payload = {
-        "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,
+        "query": query,
     }
     response = requests.post(url, json=payload, proxies=proxies)
     return response.json()["text"]

AgentQnA/tools/worker_agent_tools.py

@@ -16,7 +16,6 @@ def search_knowledge_base(query: str) -> str:
     }
     response = requests.post(url, json=payload, proxies=proxies)
     print(response)
-    if "documents" in response.json():
     docs = response.json()["documents"]
     context = ""
     for i, doc in enumerate(docs):
@@ -24,19 +23,5 @@ def search_knowledge_base(query: str) -> str:
             context = doc
         else:
             context += "\n" + doc
-        # print(context)
+    print(context)
     return context
-    elif "text" in response.json():
-        return response.json()["text"]
-    elif "reranked_docs" in response.json():
-        docs = response.json()["reranked_docs"]
-        context = ""
-        for i, doc in enumerate(docs):
-            if i == 0:
-                context = doc["text"]
-            else:
-                context += "\n" + doc["text"]
-        # print(context)
-        return context
-    else:
-        return "Error parsing response from the knowledge base."

AgentQnA/ui/docker/Dockerfile

@@ -1,26 +0,0 @@
-# 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

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

AgentQnA/ui/svelte/.env

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

AgentQnA/ui/svelte/.eslintignore

@@ -1,13 +0,0 @@
-.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

@@ -1,20 +0,0 @@
-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

@@ -1,13 +0,0 @@
-.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

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

AgentQnA/ui/svelte/README.md

@@ -1,72 +0,0 @@
-# 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/svelte
-   ```
-
-3. Modify the required .env variables. The `AGENT_URL` should be in the form of the following:
-
-   ```
-   AGENT_URL = "http://${ip_address}:${agent_port}/v1/chat/completions"
-   ```
-
-   For example: assume that the ip address of the host machine is 10.10.10.1, and the agent port is 9090,then
-
-   ```
-   AGENT_URL = "http://10.10.10.1:9090/v1/chat/completions"
-   ```
-
-   You can get the ip address of the host machine by running the command below:
-
-   ```bash
-    export ip_address=$(hostname -I | awk '{print $1}')
-   ```
-
-4. **For Local Development:**
-
-- Install the dependencies:
-
-  ```
-  npm install
-  ```
-
-- Start the development server:
-
-  ```
-  npm run dev
-  ```
-
-- The application will be available at `http://localhost:5173`.
-
-5. **For Docker Setup:**
-
-- Build the Docker image:
-
-  ```
-  docker build -t opea:agent-ui .
-  ```
-
-- Run the Docker container:
-
-  ```
-  docker run -d -p 5173:5173 --name agent-ui opea:agent-ui
-  ```
-
-- The application will be available at `http://${ip_address}:5173`. You can access it with a web browser on your laptop. Note the `ip_address` should be the ip address of the host machine where the UI container runs.

AgentQnA/ui/svelte/package.json

@@ -1,60 +0,0 @@
-{
-  "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

@@ -1,13 +0,0 @@
-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

@@ -1,50 +0,0 @@
-// 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

@@ -1,17 +0,0 @@
-<!--
-  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

@@ -1,82 +0,0 @@
-/* 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

@@ -1,25 +0,0 @@
-<!--
-  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
->