diff --git a/tensorflow-serving/README.md b/tensorflow-serving/README.md
index afa09a9..31a5e5d 100644
--- a/tensorflow-serving/README.md
+++ b/tensorflow-serving/README.md
@@ -51,6 +51,7 @@ Docker Hub.
     git clone https://github.com/tensorflow/serving
     TESTDATA="$(pwd)/serving/tensorflow_serving/servables/tensorflow/testdata"
     ```
+    
 3. Start a container using the examples below:
 
     ```
@@ -59,13 +60,46 @@ Docker Hub.
     -e MODEL_NAME=half_plus_two \
     clearlinux/tensorflow-serving &
     ```
+    
 4. Query the model using the predict API and the return => { "predictions": [2.5, 3.0, 4.5] }
 
     ```
     curl -d '{"instances": [1.0, 2.0, 5.0]}' \
     -X POST http://localhost:8501/v1/models/half_plus_two:predict
     ```
+
+### Deploy with Kubernetes
+
+This image can also be deployed on a Kubernetes cluster, such as [minikube](https://kubernetes.io/docs/setup/learning-environment/minikube/).The following example YAML files are provided in the repository as reference for Kubernetes deployment:
+
+- [`tensorflow-serving-deployment.yaml`](https://github.com/clearlinux/dockerfiles/blob/master/tensorflow-serving/tensorflow-serving-deployment.yaml): example to create a basic tensorflow-serving service.
+
+
+
+Steps to deploy tensorflow-serving on a Kubernetes cluster:
+
+1. Download a tensorflow-serving repo.
+
+   ```
+   cd /var/tmp
+   git clone https://github.com/tensorflow/serving
+   ```
+
+2. Deploy `tensorflow-serving-deployment.yaml` .
+
+   ```
+   kubectl create -f tensorflow-serving-deployment.yaml
+   ```
+
+3. Query the model using the predict API and the return => { "predictions": [2.5, 3.0, 4.5] }, where 30001 is the port number defined in your service.
+
+   ```
+   curl -d '{"instances": [1.0, 2.0, 5.0]}' \
+   -X POST http://<nodeIP>:30001/v1/models/half_plus_two:predict
+   ```
+
 <!-- Required -->
+
 ## Build and modify:
 
 The Dockerfiles for all Clear Linux* OS based container images are available at
diff --git a/tensorflow-serving/tensorflow-serving-deployment.yaml b/tensorflow-serving/tensorflow-serving-deployment.yaml
new file mode 100644
index 0000000..175d6b9
--- /dev/null
+++ b/tensorflow-serving/tensorflow-serving-deployment.yaml
@@ -0,0 +1,54 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: tf-serving-config
+data:
+  MODEL_NAME: half_plus_two
+
+---
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: tf-serving
+spec:
+  replicas: 1
+  template:
+    metadata:
+      labels:
+        app: tf-serving
+    spec:
+      containers:
+      - name: tf-serving
+        image: docker.io/clearlinux/tensorflow-serving
+        ports:
+        - containerPort: 8501
+        env:
+          - name: MODEL_NAME
+            valueFrom:
+              configMapKeyRef:
+                name: tf-serving-config
+                key: MODEL_NAME
+        volumeMounts:
+          - name: tf-serving-volume
+            mountPath: /models/half_plus_two
+
+      volumes:
+        - name: tf-serving-volume
+          hostPath:
+            # /var/tmp is the root directory where you saved your models
+            path: /var/tmp/serving/tensorflow_serving/servables/tensorflow/testdata/saved_model_half_plus_two_cpu
+            type: Directory
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: tf-serving
+spec:
+  type: NodePort
+  ports:
+  - port: 8501
+    targetPort: 8501
+    nodePort: 30001
+  selector:
+    app: tf-serving