docs(k8s): add UI template (#2343)

WIP: add a UI template

docs/source/distributions/k8s/apply.sh

@@ -13,6 +13,8 @@ export POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-llamastack}
 export INFERENCE_MODEL=${INFERENCE_MODEL:-meta-llama/Llama-3.2-3B-Instruct}
 export SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
 
+export NEXT_PUBLIC_LLAMA_STACK_BASE_URL=${NEXT_PUBLIC_LLAMA_STACK_BASE_URL:-}
+
 set -euo pipefail
 set -x
 
@@ -28,3 +30,5 @@ kubectl apply -f stack-configmap.yaml
 
 envsubst < ./stack-k8s.yaml.template | kubectl apply -f -
 envsubst < ./ingress-k8s.yaml.template | kubectl apply -f -
+
+envsubst < ./ui-k8s.yaml.template | kubectl apply -f -

docs/source/distributions/k8s/ingress-k8s.yaml.template

@@ -7,6 +7,11 @@ spec:
   selector:
     app.kubernetes.io/name: llama-stack
   ports:
-    - port: 8321
+    - name: llama-stack-api
+      port: 8321
       targetPort: 8321
       protocol: TCP
+    - name: llama-stack-ui
+      port: 8322
+      targetPort: 8322
+      protocol: TCP

docs/source/distributions/k8s/stack-k8s.yaml.template

@@ -18,10 +18,12 @@ spec:
   selector:
     matchLabels:
       app.kubernetes.io/name: llama-stack
+      app.kubernetes.io/component: server
   template:
     metadata:
       labels:
         app.kubernetes.io/name: llama-stack
+        app.kubernetes.io/component: server
     spec:
       containers:
       - name: llama-stack
@@ -65,16 +67,3 @@ spec:
       - name: llama-config
         configMap:
           name: llama-stack-config
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: llama-stack-service
-spec:
-  selector:
-    app.kubernetes.io/name: llama-stack
-  ports:
-  - protocol: TCP
-    port: 8321
-    targetPort: 8321
-  type: ClusterIP

docs/source/distributions/k8s/ui-k8s.yaml.template

@@ -0,0 +1,62 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llama-stack-ui
+  labels:
+    app.kubernetes.io/name: llama-stack
+    app.kubernetes.io/component: ui
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: llama-stack
+      app.kubernetes.io/component: ui
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: llama-stack
+        app.kubernetes.io/component: ui
+    spec:
+      containers:
+      - name: llama-stack-ui
+        image: node:18-alpine
+        command: ["/bin/sh"]
+        env:
+        - name: NEXT_PUBLIC_LLAMA_STACK_BASE_URL
+          value: ${NEXT_PUBLIC_LLAMA_STACK_BASE_URL}
+        - name: LLAMA_STACK_UI_PORT
+          value: "8322"
+        args:
+          - -c
+          - |
+            # Install git (not included in alpine by default)
+            apk add --no-cache git
+
+            # Clone the repository
+            echo "Cloning repository..."
+            git clone https://github.com/meta-llama/llama-stack.git /app
+
+            # Navigate to the UI directory
+            echo "Navigating to UI directory..."
+            cd /app/llama_stack/ui
+
+            # Check if package.json exists
+            if [ ! -f "package.json" ]; then
+              echo "ERROR: package.json not found in $(pwd)"
+              ls -la
+              exit 1
+            fi
+
+            # Install dependencies with verbose output
+            echo "Installing dependencies..."
+            npm install --verbose
+
+            # Verify next is installed
+            echo "Checking if next is installed..."
+            npx next --version || echo "Next.js not found, checking node_modules..."
+            ls -la node_modules/.bin/ | grep next || echo "No next binary found"
+
+            npm run dev
+        ports:
+        - containerPort: 8322
+        workingDir: /app