add docsum example e2e test for GMC. (#347)

* add docsum example e2e test for GMC.

Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* fix curl error for docsum.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* change the manifest e2e yaml.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* change the image format.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* fixing image mapping error.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* change the gmc e2e test.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* accelarate the e2e test.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* change the gmc e2e configuration.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* retrigger.
Signed-off-by: zhlsunshine <huailong.zhang@intel.com>

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: Yingchun Guo <yingchun.guo@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Malini Bhandaru <malini.bhandaru@intel.com>

.github/workflows/gmc-e2e.yaml

@@ -93,12 +93,12 @@ jobs:
         if: always()
         run: |
           if $should_cleanup; then
-            if ! kubectl delete ns $APP_NAMESPACE --timeout=$KUBECTL_TIMEOUT_SECONDS; then
-              kubectl delete pods --namespace $APP_NAMESPACE --force --grace-period=0 --all
-              kubectl delete ns $APP_NAMESPACE --force --grace-period=0 --timeout=$KUBECTL_TIMEOUT_SECONDS
-            fi
             if ! kubectl delete ns $SYSTEM_NAMESPACE --timeout=$KUBECTL_TIMEOUT_SECONDS; then
               kubectl delete pods --namespace $SYSTEM_NAMESPACE --force --grace-period=0 --all
               kubectl delete ns $SYSTEM_NAMESPACE --force --grace-period=0 --timeout=$KUBECTL_TIMEOUT_SECONDS
             fi
+            if ! kubectl delete ns $APP_NAMESPACE --timeout=$KUBECTL_TIMEOUT_SECONDS; then
+              kubectl delete pods --namespace $APP_NAMESPACE --force --grace-period=0 --all
+              kubectl delete ns $APP_NAMESPACE --force --grace-period=0 --timeout=$KUBECTL_TIMEOUT_SECONDS
+            fi
           fi

.github/workflows/manifest-e2e.yml

@@ -58,7 +58,7 @@ jobs:
       - name: Set variables
         run: |
           if [ ${{ matrix.hardware }} == "gaudi" ]; then IMAGE_REPO=${{ vars.IMAGE_REPO_GAUDI }}; else IMAGE_REPO=${{ vars.IMAGE_REPO_XEON }}; fi
-          echo "IMAGE_REPO=${IMAGE_REPO}" >> $GITHUB_ENV
+          echo "IMAGE_REPO=$OPEA_IMAGE_REPO" >> $GITHUB_ENV
           echo "IMAGE_TAG=${{needs.mega-image-build.outputs.image_tag}}" >> $GITHUB_ENV
           lower_example=$(echo "${{ matrix.example }}" | tr '[:upper:]' '[:lower:]')
           echo "NAMESPACE=$lower_example-$(date +%Y%m%d%H%M%S)" >> $GITHUB_ENV

ChatQnA/kubernetes/manifests/docsum_gaudi_llm.yaml

@@ -0,0 +1,74 @@
+# Source: llm-uservice/charts/tgi/templates/service.yaml
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: docsum-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: docsum
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 9000
+      targetPort: 9000
+      protocol: TCP
+      name: llm-uservice
+  selector:
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: docsum
+---
+# Source: llm-uservice/templates/deployment.yaml
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: docsum-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: docsum
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: llm-uservice
+      app.kubernetes.io/instance: docsum
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: llm-uservice
+        app.kubernetes.io/instance: docsum
+    spec:
+      securityContext: {}
+      containers:
+        - name: docsum
+          envFrom:
+            - configMapRef:
+                name: qna-config
+          env:
+            - name: HUGGING_FACE_HUB_TOKEN
+              value: $(HUGGINGFACEHUB_API_TOKEN)
+            - name: HF_TOKEN
+              value: $(HUGGINGFACEHUB_API_TOKEN)
+            - name: LANGCHAIN_TRACING_V2
+              value: "false"
+            - name: LANGCHAIN_PROJECT
+              value: "opea-llm-service"
+          securityContext: {}
+          image: "opea/llm-docsum-tgi:latest"
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: llm-uservice
+              containerPort: 9000
+              protocol: TCP
+          resources: {}

ChatQnA/kubernetes/manifests/docsum_llm.yaml

@@ -0,0 +1,74 @@
+# Source: llm-uservice/charts/tgi/templates/service.yaml
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: docsum-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: docsum
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  type: ClusterIP
+  ports:
+    - port: 9000
+      targetPort: 9000
+      protocol: TCP
+      name: llm-uservice
+  selector:
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: docsum
+---
+# Source: llm-uservice/templates/deployment.yaml
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: docsum-llm-uservice
+  labels:
+    helm.sh/chart: llm-uservice-0.1.0
+    app.kubernetes.io/name: llm-uservice
+    app.kubernetes.io/instance: docsum
+    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/managed-by: Helm
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: llm-uservice
+      app.kubernetes.io/instance: docsum
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: llm-uservice
+        app.kubernetes.io/instance: docsum
+    spec:
+      securityContext: {}
+      containers:
+        - name: docsum
+          envFrom:
+            - configMapRef:
+                name: qna-config
+          env:
+            - name: HUGGING_FACE_HUB_TOKEN
+              value: $(HUGGINGFACEHUB_API_TOKEN)
+            - name: HF_TOKEN
+              value: $(HUGGINGFACEHUB_API_TOKEN)
+            - name: LANGCHAIN_TRACING_V2
+              value: "false"
+            - name: LANGCHAIN_PROJECT
+              value: "opea-llm-service"
+          securityContext: {}
+          image: "opea/llm-docsum-tgi:latest"
+          imagePullPolicy: IfNotPresent
+          ports:
+            - name: llm-uservice
+              containerPort: 9000
+              protocol: TCP
+          resources: {}

ChatQnA/tests/test_gmc_on_gaudi.sh

@@ -22,7 +22,7 @@ function init_chatqna() {
     find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
     # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
     find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: ${IMAGE_REPO}opea\"/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
     # set huggingface token
     find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
     # replace namespace "default" with real namespace

ChatQnA/tests/test_gmc_on_xeon.sh

@@ -22,7 +22,7 @@ function init_chatqna() {
     find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
     # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
     find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: ${IMAGE_REPO}opea\"/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
     # set huggingface token
     find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
     # replace namespace "default" with real namespace

CodeGen/tests/test_gmc_on_gaudi.sh

@@ -22,7 +22,7 @@ function init_codegen() {
     find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
     # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
     find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: ${IMAGE_REPO}opea\"/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
     # set huggingface token
     find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
     # replace namespace "default" with real namespace

CodeGen/tests/test_gmc_on_xeon.sh

@@ -22,7 +22,7 @@ function init_codegen() {
     find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
     # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
     find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: ${IMAGE_REPO}opea\"/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
     # set huggingface token
     find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
     # replace namespace "default" with real namespace

CodeTrans/tests/test_gmc_on_gaudi.sh

@@ -22,7 +22,7 @@ function init_codetrans() {
     find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
     # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
     find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: ${IMAGE_REPO}opea\"/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
     # set huggingface token
     find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
     # replace namespace "default" with real namespace

CodeTrans/tests/test_gmc_on_xeon.sh

@@ -22,7 +22,7 @@ function init_codetrans() {
     find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
     # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
     find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
-    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: ${IMAGE_REPO}opea\"/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
     # set huggingface token
     find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
     # replace namespace "default" with real namespace

DocSum/kubernetes/docsum_gaudi.yaml

@@ -0,0 +1,35 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: gmc.opea.io/v1alpha3
+kind: GMConnector
+metadata:
+  labels:
+    app.kubernetes.io/name: gmconnector
+    app.kubernetes.io/managed-by: kustomize
+    gmc/platform: gaudi
+  name: docsum
+  namespace: docsum
+spec:
+  routerConfig:
+    name: router
+    serviceName: router-service
+  nodes:
+    root:
+      routerType: Sequence
+      steps:
+      - name: DocSumGaudi
+        data: $response
+        internalService:
+          serviceName: docsum-llm-uservice
+          config:
+            endpoint: /v1/chat/docsum
+            PORT: "9009"
+      - name: TgiGaudi
+        internalService:
+          serviceName: tgi-gaudi-svc
+          config:
+            LANGCHAIN_TRACING_V2: "false"
+            LANGCHAIN_PROJECT: "opea-llm-service"
+            endpoint: /generate
+          isDownstreamService: true

DocSum/kubernetes/docsum_xeon.yaml

@@ -0,0 +1,35 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: gmc.opea.io/v1alpha3
+kind: GMConnector
+metadata:
+  labels:
+    app.kubernetes.io/name: gmconnector
+    app.kubernetes.io/managed-by: kustomize
+    gmc/platform: xeon
+  name: docsum
+  namespace: docsum
+spec:
+  routerConfig:
+    name: router
+    serviceName: router-service
+  nodes:
+    root:
+      routerType: Sequence
+      steps:
+      - name: DocSum
+        data: $response
+        internalService:
+          serviceName: docsum-llm-uservice
+          config:
+            endpoint: /v1/chat/docsum
+            PORT: "9009"
+      - name: Tgi
+        internalService:
+          serviceName: tgi-svc
+          config:
+            LANGCHAIN_TRACING_V2: "false"
+            LANGCHAIN_PROJECT: "opea-llm-service"
+            endpoint: /generate
+          isDownstreamService: true

DocSum/tests/test_gmc_on_gaudi.sh

@@ -0,0 +1,167 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -xe
+USER_ID=$(whoami)
+LOG_PATH=/home/$(whoami)/logs
+MOUNT_DIR=/home/$USER_ID/.cache/huggingface/hub
+IMAGE_REPO=${IMAGE_REPO:-}
+
+function init_docsum() {
+    wget https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/crd/bases/gmc.opea.io_gmconnectors.yaml
+    wget https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/rbac/gmc-manager-rbac.yaml
+    wget https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/manager/gmc-manager.yaml
+    wget -O manifests/gmc-router.yaml https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/gmcrouter/gmc-router.yaml
+
+    # replace namespace for gmc-router and gmc-manager
+    sed -i "s|namespace: system|namespace: $SYSTEM_NAMESPACE|g"  ./gmc-manager.yaml
+    sed -i "s|namespace: system|namespace: $SYSTEM_NAMESPACE|g"  ./gmc-manager-rbac.yaml
+    sed -i "s|name: system|name: $SYSTEM_NAMESPACE|g" ./gmc-manager-rbac.yaml
+    # replace the mount dir "path: /mnt/model" with "path: $CHART_MOUNT"
+    find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
+    # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
+    find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
+    # set huggingface token
+    find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
+    # replace namespace "default" with real namespace
+    find . -name '*.yaml' -type f -exec sed -i "s#default.svc#$APP_NAMESPACE.svc#g" {} \;
+}
+
+function install_docsum() {
+    # Make sure you have to use image tag $VERSION for microservice-connector installation
+    echo "install microservice-connector, using repo $DOCKER_REGISTRY and tag $VERSION"
+    echo "using namespace $SYSTEM_NAMESPACE and $APP_NAMESPACE"
+
+    kubectl apply -f ./gmc.opea.io_gmconnectors.yaml
+    kubectl apply -f ./gmc-manager-rbac.yaml
+    kubectl create configmap gmcyaml -n $SYSTEM_NAMESPACE --from-file $(pwd)/../kubernetes/manifests
+    kubectl apply -f ./gmc-manager.yaml
+
+    # Wait until the gmc controller pod is ready
+    wait_until_pod_ready "gmc-controller" $SYSTEM_NAMESPACE "gmc-controller"
+    kubectl get pods -n $SYSTEM_NAMESPACE
+    rm -f ./gmc.opea.io_gmconnectors.yaml ./gmc-manager-rbac.yaml ./gmc-manager.yaml manifests/gmc-router.yaml
+}
+
+function validate_docsum() {
+    kubectl create ns $APP_NAMESPACE
+    sed -i "s|namespace: docsum|namespace: $APP_NAMESPACE|g"  ./docsum_gaudi.yaml
+    kubectl apply -f ./docsum_gaudi.yaml
+
+    # Wait until the router service is ready
+    echo "Waiting for the docsum router service to be ready..."
+    wait_until_pod_ready "docsum router" $APP_NAMESPACE "router-service"
+    output=$(kubectl get pods -n $APP_NAMESPACE)
+    echo $output
+
+    # deploy client pod for testing
+    kubectl create deployment client-test -n $APP_NAMESPACE --image=python:3.8.13 -- sleep infinity
+
+    # wait for client pod ready
+    wait_until_pod_ready "client-test" $APP_NAMESPACE "client-test"
+    # giving time to populating data
+    sleep 60
+
+    kubectl get pods -n $APP_NAMESPACE
+    # send request to codetrans
+    export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
+    echo "$CLIENT_POD"
+    accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='docsum')].status.accessUrl}")
+    kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl  -X POST  -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'  -H 'Content-Type: application/json' > $LOG_PATH/gmc_docsum.log
+    exit_code=$?
+    if [ $exit_code -ne 0 ]; then
+        echo "docsum failed, please check the logs in ${LOG_PATH}!"
+        exit 1
+    fi
+
+    cat $LOG_PATH/gmc_docsum.log
+    echo "Checking response results, make sure the output is reasonable. "
+    local status=false
+    if [[ -f $LOG_PATH/gmc_docsum.log ]] && \
+    [[ $(grep -c "[DONE]" $LOG_PATH/gmc_docsum.log) != 0 ]]; then
+        status=true
+    fi
+    if [ $status == false ]; then
+        if [[ -f $LOG_PATH/gmc_docsum.log ]]; then
+            cat $LOG_PATH/gmc_docsum.log
+        fi
+        echo "Response check failed, please check the logs in artifacts!"
+        exit 1
+    else
+        echo "Response check succeed!"
+    fi
+}
+
+function wait_until_pod_ready() {
+    echo "Waiting for the $1 to be ready..."
+    max_retries=30
+    retry_count=0
+    while ! is_pod_ready $2 $3; do
+        if [ $retry_count -ge $max_retries ]; then
+            echo "$1 is not ready after waiting for a significant amount of time"
+            get_gmc_controller_logs
+            exit 1
+        fi
+        echo "$1 is not ready yet. Retrying in 10 seconds..."
+        sleep 10
+        output=$(kubectl get pods -n $2)
+        echo $output
+        retry_count=$((retry_count + 1))
+    done
+}
+
+function is_pod_ready() {
+    if [ "$2" == "gmc-controller" ]; then
+      pod_status=$(kubectl get pods -n $1 -o jsonpath='{.items[].status.conditions[?(@.type=="Ready")].status}')
+    else
+      pod_status=$(kubectl get pods -n $1 -l app=$2 -o jsonpath='{.items[].status.conditions[?(@.type=="Ready")].status}')
+    fi
+    if [ "$pod_status" == "True" ]; then
+        return 0
+    else
+        return 1
+    fi
+}
+
+function get_gmc_controller_logs() {
+    # Fetch the name of the pod with the app-name gmc-controller in the specified namespace
+    pod_name=$(kubectl get pods -n $SYSTEM_NAMESPACE -l control-plane=gmc-controller -o jsonpath='{.items[0].metadata.name}')
+
+    # Check if the pod name was found
+    if [ -z "$pod_name" ]; then
+        echo "No pod found with app-name gmc-controller in namespace $SYSTEM_NAMESPACE"
+        return 1
+    fi
+
+    # Get the logs of the found pod
+    echo "Fetching logs for pod $pod_name in namespace $SYSTEM_NAMESPACE..."
+    kubectl logs $pod_name -n $SYSTEM_NAMESPACE
+}
+
+if [ $# -eq 0 ]; then
+    echo "Usage: $0 <function_name>"
+    exit 1
+fi
+
+case "$1" in
+    init_DocSum)
+        pushd ChatQnA/kubernetes
+        init_docsum
+        popd
+        ;;
+    install_DocSum)
+        pushd ChatQnA/kubernetes
+        install_docsum
+        popd
+        ;;
+    validate_DocSum)
+        pushd DocSum/kubernetes
+        validate_docsum
+        popd
+        ;;
+    *)
+        echo "Unknown function: $1"
+        ;;
+esac

DocSum/tests/test_gmc_on_xeon.sh

@@ -0,0 +1,168 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -xe
+USER_ID=$(whoami)
+LOG_PATH=/home/$(whoami)/logs
+MOUNT_DIR=/home/$USER_ID/.cache/huggingface/hub
+IMAGE_REPO=${IMAGE_REPO:-}
+
+function init_docsum() {
+    wget https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/crd/bases/gmc.opea.io_gmconnectors.yaml
+    wget https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/rbac/gmc-manager-rbac.yaml
+    wget https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/manager/gmc-manager.yaml
+    wget -O manifests/gmc-router.yaml https://raw.githubusercontent.com/opea-project/GenAIInfra/main/microservices-connector/config/gmcrouter/gmc-router.yaml
+
+    # replace namespace for gmc-router and gmc-manager
+    sed -i "s|namespace: system|namespace: $SYSTEM_NAMESPACE|g"  ./gmc-manager.yaml
+    sed -i "s|namespace: system|namespace: $SYSTEM_NAMESPACE|g"  ./gmc-manager-rbac.yaml
+    sed -i "s|name: system|name: $SYSTEM_NAMESPACE|g" ./gmc-manager-rbac.yaml
+    # replace the mount dir "path: /mnt/model" with "path: $CHART_MOUNT"
+    find . -name '*.yaml' -type f -exec sed -i "s#path: /mnt/models#path: $MOUNT_DIR#g" {} \;
+    # replace the repository "image: opea/*" with "image: ${IMAGE_REPO}opea/"
+    find . -name '*.yaml' -type f -exec sed -i "s#image: opea/*#image: ${IMAGE_REPO}opea/#g" {} \;
+    find . -name '*.yaml' -type f -exec sed -i "s#image: \"opea/*#image: \"${IMAGE_REPO}opea/#g" {} \;
+    # set huggingface token
+    find . -name '*.yaml' -type f -exec sed -i "s#\${HUGGINGFACEHUB_API_TOKEN}#$(cat /home/$USER_ID/.cache/huggingface/token)#g" {} \;
+    # replace namespace "default" with real namespace
+    find . -name '*.yaml' -type f -exec sed -i "s#default.svc#$APP_NAMESPACE.svc#g" {} \;
+}
+
+function install_docsum() {
+    # Make sure you have to use image tag $VERSION for microservice-connector installation
+    echo "install microservice-connector, using repo $DOCKER_REGISTRY and tag $VERSION"
+    echo "using namespace $SYSTEM_NAMESPACE and $APP_NAMESPACE"
+
+    kubectl apply -f ./gmc.opea.io_gmconnectors.yaml
+    kubectl apply -f ./gmc-manager-rbac.yaml
+    kubectl create configmap gmcyaml -n $SYSTEM_NAMESPACE --from-file $(pwd)/../kubernetes/manifests
+    kubectl apply -f ./gmc-manager.yaml
+
+    # Wait until the gmc controller pod is ready
+    wait_until_pod_ready "gmc-controller" $SYSTEM_NAMESPACE "gmc-controller"
+    kubectl get pods -n $SYSTEM_NAMESPACE
+    rm -f ./gmc.opea.io_gmconnectors.yaml ./gmc-manager-rbac.yaml ./gmc-manager.yaml manifests/gmc-router.yaml
+}
+
+function validate_docsum() {
+    kubectl create ns $APP_NAMESPACE
+    sed -i "s|namespace: docsum|namespace: $APP_NAMESPACE|g"  ./docsum_xeon.yaml
+    kubectl apply -f ./docsum_xeon.yaml
+
+    # Wait until the router service is ready
+    echo "Waiting for the docsum router service to be ready..."
+    wait_until_pod_ready "docsum router" $APP_NAMESPACE "router-service"
+    output=$(kubectl get pods -n $APP_NAMESPACE)
+    echo $output
+
+
+    # deploy client pod for testing
+    kubectl create deployment client-test -n $APP_NAMESPACE --image=python:3.8.13 -- sleep infinity
+
+    # wait for client pod ready
+    wait_until_pod_ready "client-test" $APP_NAMESPACE "client-test"
+    # giving time to populating data
+    sleep 60
+
+    kubectl get pods -n $APP_NAMESPACE
+    # send request to docsum
+    export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
+    echo "$CLIENT_POD"
+    accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='docsum')].status.accessUrl}")
+    kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl  -X POST  -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}'  -H 'Content-Type: application/json' > $LOG_PATH/gmc_docsum.log
+    exit_code=$?
+    if [ $exit_code -ne 0 ]; then
+        echo "docsum failed, please check the logs in ${LOG_PATH}!"
+        exit 1
+    fi
+
+    cat $LOG_PATH/gmc_docsum.log
+    echo "Checking response results, make sure the output is reasonable. "
+    local status=false
+    if [[ -f $LOG_PATH/gmc_docsum.log ]] && \
+    [[ $(grep -c "[DONE]" $LOG_PATH/gmc_docsum.log) != 0 ]]; then
+        status=true
+    fi
+    if [ $status == false ]; then
+        if [[ -f $LOG_PATH/gmc_docsum.log ]]; then
+            cat $LOG_PATH/gmc_docsum.log
+        fi
+        echo "Response check failed, please check the logs in artifacts!"
+        exit 1
+    else
+        echo "Response check succeed!"
+    fi
+}
+
+function wait_until_pod_ready() {
+    echo "Waiting for the $1 to be ready..."
+    max_retries=30
+    retry_count=0
+    while ! is_pod_ready $2 $3; do
+        if [ $retry_count -ge $max_retries ]; then
+            echo "$1 is not ready after waiting for a significant amount of time"
+            get_gmc_controller_logs
+            exit 1
+        fi
+        echo "$1 is not ready yet. Retrying in 10 seconds..."
+        sleep 10
+        output=$(kubectl get pods -n $2)
+        echo $output
+        retry_count=$((retry_count + 1))
+    done
+}
+
+function is_pod_ready() {
+    if [ "$2" == "gmc-controller" ]; then
+      pod_status=$(kubectl get pods -n $1 -o jsonpath='{.items[].status.conditions[?(@.type=="Ready")].status}')
+    else
+      pod_status=$(kubectl get pods -n $1 -l app=$2 -o jsonpath='{.items[].status.conditions[?(@.type=="Ready")].status}')
+    fi
+    if [ "$pod_status" == "True" ]; then
+        return 0
+    else
+        return 1
+    fi
+}
+
+function get_gmc_controller_logs() {
+    # Fetch the name of the pod with the app-name gmc-controller in the specified namespace
+    pod_name=$(kubectl get pods -n $SYSTEM_NAMESPACE -l control-plane=gmc-controller -o jsonpath='{.items[0].metadata.name}')
+
+    # Check if the pod name was found
+    if [ -z "$pod_name" ]; then
+        echo "No pod found with app-name gmc-controller in namespace $SYSTEM_NAMESPACE"
+        return 1
+    fi
+
+    # Get the logs of the found pod
+    echo "Fetching logs for pod $pod_name in namespace $SYSTEM_NAMESPACE..."
+    kubectl logs $pod_name -n $SYSTEM_NAMESPACE
+}
+
+if [ $# -eq 0 ]; then
+    echo "Usage: $0 <function_name>"
+    exit 1
+fi
+
+case "$1" in
+    init_DocSum)
+        pushd ChatQnA/kubernetes
+        init_docsum
+        popd
+        ;;
+    install_DocSum)
+        pushd ChatQnA/kubernetes
+        install_docsum
+        popd
+        ;;
+    validate_DocSum)
+        pushd DocSum/kubernetes
+        validate_docsum
+        popd
+        ;;
+    *)
+        echo "Unknown function: $1"
+        ;;
+esac