diff --git a/docs/source/distributions/k8s/apply.sh b/docs/source/distributions/k8s/apply.sh
index 308ca6ee9..8e834680b 100755
--- a/docs/source/distributions/k8s/apply.sh
+++ b/docs/source/distributions/k8s/apply.sh
@@ -27,3 +27,4 @@ kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \
 kubectl apply -f stack-configmap.yaml
 
 envsubst < ./stack-k8s.yaml.template | kubectl apply -f -
+envsubst < ./ingress-k8s.yaml.template | kubectl apply -f -
diff --git a/docs/source/distributions/k8s/ingress-k8s.yaml.template b/docs/source/distributions/k8s/ingress-k8s.yaml.template
new file mode 100644
index 000000000..1cd95b5e5
--- /dev/null
+++ b/docs/source/distributions/k8s/ingress-k8s.yaml.template
@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: llama-stack-service
+spec:
+  type: LoadBalancer
+  selector:
+    app.kubernetes.io/name: llama-stack
+  ports:
+    - port: 8321
+      targetPort: 8321
+      protocol: TCP