K8S manifest: Update ChatQnA/CodeGen/CodeTrans/DocSum

- Update ChatQnA/CodeGen/CodeTrans/DocSum k8s manifest
  to avoid requiring creating directory for cache model.

- Add chatqna-guardrails manifest files.

- Fix bug #752 introduced by PR #669

Signed-off-by: Lianhao Lu <lianhao.lu@intel.com>

Author: lianhao

.github/workflows/_manifest-e2e.yml

@@ -80,6 +80,7 @@ jobs:
               echo "skip_validate=false" >> $GITHUB_ENV
             else
               echo "Timeout waiting for pods in namespace $NAMESPACE to be ready!"
+              .github/workflows/scripts/k8s-utils.sh dump_pods_status $NAMESPACE
               exit 1
             fi
             sleep 60
@@ -91,7 +92,12 @@ jobs:
           if $skip_validate; then
             echo "Skip validate"
           else
-            ${{ github.workspace }}/${{ inputs.example }}/tests/test_manifest_on_${{ inputs.hardware }}.sh validate_${{ inputs.example }} $NAMESPACE
+            if ${{ github.workspace }}/${{ inputs.example }}/tests/test_manifest_on_${{ inputs.hardware }}.sh validate_${{ inputs.example }} $NAMESPACE ; then
+              echo "Validate ${{ inputs.example }} successful!"
+            else
+              echo "Validate ${{ inputs.example }} failure!!!"
+              .github/workflows/scripts/k8s-utils.sh dump_all_pod_logs $NAMESPACE
+            fi
           fi
 
       - name: Kubectl uninstall

.github/workflows/scripts/k8s-utils.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+#set -xe
+
+function dump_pod_log() {
+    pod_name=$1
+    namespace=$2
+    echo "-----------Pod: $pod_name---------"
+    echo "#kubectl describe pod $pod_name -n $namespace"
+    kubectl describe pod $pod_name -n $namespace
+    echo "-----------------------------------"
+    echo "#kubectl logs $pod_name -n $namespace"
+    kubectl logs $pod_name -n $namespace
+    echo "-----------------------------------"
+}
+
+function dump_pods_status() {
+    namespace=$1
+    echo "-----DUMP POD STATUS in NS $namespace------"
+    kubectl get pods -n $namespace -o wide
+    echo "-----------------------------------"
+
+    # Get all pods in the namespace and their statuses
+    pods=$(kubectl get pods -n $namespace --no-headers)
+
+    # Loop through each pod
+    echo "$pods" | while read -r line; do
+        pod_name=$(echo $line | awk '{print $1}')
+        ready=$(echo $line | awk '{print $2}')
+        status=$(echo $line | awk '{print $3}')
+
+        # Extract the READY count
+        ready_count=$(echo $ready | cut -d'/' -f1)
+        required_count=$(echo $ready | cut -d'/' -f2)
+
+        # Check if the pod is not in "Running" status or READY count is less than required
+        if [[ "$status" != "Running" || "$ready_count" -lt "$required_count" ]]; then
+            dump_pod_log $pod_name $namespace
+        fi
+    done
+}
+
+function dump_all_pod_logs() {
+    namespace=$1
+    echo "-----DUMP POD STATUS AND LOG in NS $namespace------"
+
+    pods=$(kubectl get pods -n $namespace -o jsonpath='{.items[*].metadata.name}')
+    for pod_name in $pods
+    do
+        dump_pod_log $pod_name $namespace
+    done
+}
+
+if [ $# -eq 0 ]; then
+    echo "Usage: $0 <function_name>"
+    exit 1
+fi
+
+case "$1" in
+    dump_pods_status)
+        dump_pods_status $2
+        ;;
+    dump_all_pod_logs)
+        dump_all_pod_logs $2
+        ;;
+    *)
+        echo "Unknown function: $1"
+        ;;
+esac