diff --git a/SearchQnA/kubernetes/README.md b/SearchQnA/kubernetes/README.md
new file mode 100644
index 0000000000..6f8848bb42
--- /dev/null
+++ b/SearchQnA/kubernetes/README.md
@@ -0,0 +1,40 @@
+<h1 align="center" id="title">Deploy SearchQnA in a Kubernetes Cluster</h1>
+
+This document outlines the deployment process for a Code Generation (SearchQnA) application that utilizes the [GenAIComps](https://github.com/opea-project/GenAIComps.git) microservice components on Intel Xeon servers and Gaudi machines.
+
+Please install GMC in your Kubernetes cluster, if you have not already done so, by following the steps in Section "Getting Started" at [GMC Install](https://github.com/opea-project/GenAIInfra/tree/main/microservices-connector#readme). We will soon publish images to Docker Hub, at which point no builds will be required, further simplifying install.
+
+If you have only Intel Xeon machines you could use the searchQnA_xeon.yaml file or if you have a Gaudi cluster you could use searchQnA_gaudi.yaml
+In the below example we illustrate on Xeon.
+
+## Deploy the RAG application
+
+1. Create the desired namespace if it does not already exist and deploy the application
+```bash
+export APP_NAMESPACE=CT
+kubectl create ns $APP_NAMESPACE
+sed -i "s|namespace: searchqa|namespace: $APP_NAMESPACE|g"  ./searchQnA_xeon.yaml
+kubectl apply -f ./searchQnA_xeon.yaml
+```
+
+2. Check if the application is up and ready
+```bash
+kubectl get pods -n $APP_NAMESPACE
+```
+
+3. Deploy a client pod for testing
+```bash
+kubectl create deployment client-test -n $APP_NAMESPACE --image=python:3.8.13 -- sleep infinity
+```
+
+4. Check that client pod is ready
+```bash
+    kubectl get pods -n $APP_NAMESPACE
+```
+
+5. Send request to application
+```bash
+export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
+export accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='searchqa')].status.accessUrl}")
+kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl -X POST -d '{"text":"What is the latest news? Give me also the source link."}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_searchqa.log
+```
diff --git a/SearchQnA/kubernetes/searchQnA_gaudi.yaml b/SearchQnA/kubernetes/searchQnA_gaudi.yaml
new file mode 100644
index 0000000000..8f70ea0fe7
--- /dev/null
+++ b/SearchQnA/kubernetes/searchQnA_gaudi.yaml
@@ -0,0 +1,65 @@
+# 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: searchqa
+  namespace: searchqa
+spec:
+  routerConfig:
+    name: router
+    serviceName: router-service
+  nodes:
+    root:
+      routerType: Sequence
+      steps:
+      - name: Embedding
+        internalService:
+          serviceName: embedding-svc
+          config:
+            endpoint: /v1/embeddings
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc
+      - name: TeiEmbeddingGaudi
+        internalService:
+          serviceName: tei-embedding-gaudi-svc
+          isDownstreamService: true
+      - name: WebRetriever
+        data: $response
+        internalService:
+          serviceName: web-retriever-svc
+          config:
+            endpoint: /v1/web_retrieval
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-gaudi-svc
+            GOOGLE_API_KEY: "insert-your-google-api-key-here"
+            GOOGLE_CSE_ID: "insert-your-google-cse-id-here"
+      - name: Reranking
+        data: $response
+        internalService:
+          serviceName: reranking-svc
+          config:
+            endpoint: /v1/reranking
+            TEI_RERANKING_ENDPOINT: tei-reranking-svc
+      - name: TeiReranking
+        internalService:
+          serviceName: tei-reranking-svc
+          config:
+            endpoint: /rerank
+          isDownstreamService: true
+      - name: Llm
+        data: $response
+        internalService:
+          serviceName: llm-svc
+          config:
+            endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-gaudi-svc
+      - name: TgiGaudi
+        internalService:
+          serviceName: tgi-gaudi-svc
+          config:
+            endpoint: /generate
+          isDownstreamService: true
diff --git a/SearchQnA/kubernetes/searchQnA_xeon.yaml b/SearchQnA/kubernetes/searchQnA_xeon.yaml
new file mode 100644
index 0000000000..85d445ce59
--- /dev/null
+++ b/SearchQnA/kubernetes/searchQnA_xeon.yaml
@@ -0,0 +1,65 @@
+# 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: searchqa
+  namespace: searchqa
+spec:
+  routerConfig:
+    name: router
+    serviceName: router-service
+  nodes:
+    root:
+      routerType: Sequence
+      steps:
+      - name: Embedding
+        internalService:
+          serviceName: embedding-svc
+          config:
+            endpoint: /v1/embeddings
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-svc
+      - name: TeiEmbedding
+        internalService:
+          serviceName: tei-embedding-svc
+          isDownstreamService: true
+      - name: WebRetriever
+        data: $response
+        internalService:
+          serviceName: web-retriever-svc
+          config:
+            endpoint: /v1/web_retrieval
+            TEI_EMBEDDING_ENDPOINT: tei-embedding-svc
+            GOOGLE_API_KEY: "insert-your-google-api-key-here"
+            GOOGLE_CSE_ID: "insert-your-google-cse-id-here"
+      - name: Reranking
+        data: $response
+        internalService:
+          serviceName: reranking-svc
+          config:
+            endpoint: /v1/reranking
+            TEI_RERANKING_ENDPOINT: tei-reranking-svc
+      - name: TeiReranking
+        internalService:
+          serviceName: tei-reranking-svc
+          config:
+            endpoint: /rerank
+          isDownstreamService: true
+      - name: Llm
+        data: $response
+        internalService:
+          serviceName: llm-svc
+          config:
+            endpoint: /v1/chat/completions
+            TGI_LLM_ENDPOINT: tgi-service-m
+      - name: Tgi
+        internalService:
+          serviceName: tgi-service-m
+          config:
+            endpoint: /generate
+          isDownstreamService: true
diff --git a/SearchQnA/tests/test_gmc_on_gaudi.sh b/SearchQnA/tests/test_gmc_on_gaudi.sh
new file mode 100755
index 0000000000..86a474d571
--- /dev/null
+++ b/SearchQnA/tests/test_gmc_on_gaudi.sh
@@ -0,0 +1,129 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -xe
+USER_ID=$(whoami)
+LOG_PATH=/home/$(whoami)/logs
+MOUNT_DIR=/home/$USER_ID/.cache/huggingface/hub
+IMAGE_REPO=${IMAGE_REPO:-}
+
+function install_searchqa() {
+    kubectl create ns $APP_NAMESPACE
+    sed -i "s|namespace: searchqa|namespace: $APP_NAMESPACE|g"  ./searchQnA_gaudi.yaml
+    sed -i "s|insert-your-google-api-key-here|$GOOGLE_API_KEY|g"  ./searchQnA_gaudi.yaml
+    sed -i "s|insert-your-google-cse-id-here|$GOOGLE_CSE_ID|g"  ./searchQnA_gaudi.yaml
+    kubectl apply -f ./searchQnA_gaudi.yaml
+
+    # Wait until the router service is ready
+    echo "Waiting for the searchqa router service to be ready..."
+    wait_until_pod_ready "searchqa router" $APP_NAMESPACE "router-service"
+    output=$(kubectl get pods -n $APP_NAMESPACE)
+    echo $output
+}
+
+function validate_searchqa() {
+    # 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 $APP_NAMESPACE
+    # send request to searchqa
+    export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
+    echo "$CLIENT_POD"
+    accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='searchqa')].status.accessUrl}")
+    kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl  -X POST  -d '{"text":"What is the latest news? Give me also the source link."}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_searchqa.log
+    exit_code=$?
+    if [ $exit_code -ne 0 ]; then
+        echo "chatqna failed, please check the logs in ${LOG_PATH}!"
+        exit 1
+    fi
+
+    echo "Checking response results, make sure the output is reasonable. "
+    local status=false
+    if [[ -f $LOG_PATH/gmc_searchqa.log ]] && \
+    [[ $(grep -c "[DONE]" $LOG_PATH/gmc_searchqa.log) != 0 ]]; then
+        status=true
+    fi
+    if [ $status == false ]; then
+        if [[ -f $LOG_PATH/gmc_searchqa.log ]]; then
+            cat $LOG_PATH/gmc_searchqa.log
+        fi
+        echo "Response check failed, please check the logs in artifacts!"
+        cat $LOG_PATH/gmc_searchqa.log
+        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
+    install_SearchQnA)
+        pushd SearchQnA/kubernetes
+        install_searchqa
+        popd
+        ;;
+    validate_SearchQnA)
+        pushd SearchQnA/kubernetes
+        validate_searchqa
+        popd
+        ;;
+    *)
+        echo "Unknown function: $1"
+        ;;
+esac
diff --git a/SearchQnA/tests/test_gmc_on_xeon.sh b/SearchQnA/tests/test_gmc_on_xeon.sh
new file mode 100755
index 0000000000..8e577a2d91
--- /dev/null
+++ b/SearchQnA/tests/test_gmc_on_xeon.sh
@@ -0,0 +1,129 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -xe
+USER_ID=$(whoami)
+LOG_PATH=/home/$(whoami)/logs
+MOUNT_DIR=/home/$USER_ID/.cache/huggingface/hub
+IMAGE_REPO=${IMAGE_REPO:-}
+
+function install_searchqa() {
+    kubectl create ns $APP_NAMESPACE
+    sed -i "s|namespace: searchqa|namespace: $APP_NAMESPACE|g"  ./searchQnA_xeon.yaml
+    sed -i "s|insert-your-google-api-key-here|$GOOGLE_API_KEY|g"  ./searchQnA_xeon.yaml
+    sed -i "s|insert-your-google-cse-id-here|$GOOGLE_CSE_ID|g"  ./searchQnA_xeon.yaml
+    kubectl apply -f ./searchQnA_xeon.yaml
+
+    # Wait until the router service is ready
+    echo "Waiting for the searchqa router service to be ready..."
+    wait_until_pod_ready "searchqa router" $APP_NAMESPACE "router-service"
+    output=$(kubectl get pods -n $APP_NAMESPACE)
+    echo $output
+}
+
+function validate_searchqa() {
+    # 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 $APP_NAMESPACE
+    # send request to searchqa
+    export CLIENT_POD=$(kubectl get pod -n $APP_NAMESPACE -l app=client-test -o jsonpath={.items..metadata.name})
+    echo "$CLIENT_POD"
+    accessUrl=$(kubectl get gmc -n $APP_NAMESPACE -o jsonpath="{.items[?(@.metadata.name=='searchqa')].status.accessUrl}")
+    kubectl exec "$CLIENT_POD" -n $APP_NAMESPACE -- curl $accessUrl  -X POST  -d '{"text":"What is the latest news? Give me also the source link."}' -H 'Content-Type: application/json' > $LOG_PATH/gmc_searchqa.log
+    exit_code=$?
+    if [ $exit_code -ne 0 ]; then
+        echo "chatqna failed, please check the logs in ${LOG_PATH}!"
+        exit 1
+    fi
+
+    echo "Checking response results, make sure the output is reasonable. "
+    local status=false
+    if [[ -f $LOG_PATH/gmc_searchqa.log ]] && \
+    [[ $(grep -c "[DONE]" $LOG_PATH/gmc_searchqa.log) != 0 ]]; then
+        status=true
+    fi
+    if [ $status == false ]; then
+        if [[ -f $LOG_PATH/gmc_searchqa.log ]]; then
+            cat $LOG_PATH/gmc_searchqa.log
+        fi
+        echo "Response check failed, please check the logs in artifacts!"
+        cat $LOG_PATH/gmc_searchqa.log
+        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
+    install_SearchQnA)
+        pushd SearchQnA/kubernetes
+        install_searchqa
+        popd
+        ;;
+    validate_SearchQnA)
+        pushd SearchQnA/kubernetes
+        validate_searchqa
+        popd
+        ;;
+    *)
+        echo "Unknown function: $1"
+        ;;
+esac