Update K8S manifest for ChatQnA/CodeGen/CodeTrans/DocSum

- Sync with docker-compose changes since v0.8 release

- Add K8S probes

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

CodeGen/kubernetes/manifests/gaudi/codegen.yaml

@@ -11,15 +11,15 @@ metadata:
     helm.sh/chart: llm-uservice-0.8.0
     app.kubernetes.io/name: llm-uservice
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/version: "v0.8"
     app.kubernetes.io/managed-by: Helm
 data:
   TGI_LLM_ENDPOINT: "http://codegen-tgi"
   HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
   HF_HOME: "/tmp/.cache/huggingface"
-  http_proxy:
-  https_proxy:
-  no_proxy:
+  http_proxy: ""
+  https_proxy: ""
+  no_proxy: ""
   LANGCHAIN_TRACING_V2: "false"
   LANGCHAIN_API_KEY: insert-your-langchain-key-here
   LANGCHAIN_PROJECT: "opea-llm-uservice"
@@ -36,22 +36,21 @@ metadata:
     helm.sh/chart: tgi-0.8.0
     app.kubernetes.io/name: tgi
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/version: "2.1.0"
     app.kubernetes.io/managed-by: Helm
 data:
   MODEL_ID: "meta-llama/CodeLlama-7b-hf"
   PORT: "2080"
-  HUGGING_FACE_HUB_TOKEN: "insert-your-huggingface-token-here"
   HF_TOKEN: "insert-your-huggingface-token-here"
-  MAX_INPUT_TOKENS: "1024"
-  MAX_TOTAL_TOKENS: "4096"
-  http_proxy:
-  https_proxy:
-  no_proxy:
+  http_proxy: ""
+  https_proxy: ""
+  no_proxy: ""
   HABANA_LOGS: "/tmp/habana_logs"
   NUMBA_CACHE_DIR: "/tmp"
   TRANSFORMERS_CACHE: "/tmp/transformers_cache"
   HF_HOME: "/tmp/.cache/huggingface"
+  MAX_INPUT_LENGTH: "1024"
+  MAX_TOTAL_TOKENS: "2048"
 ---
 # Source: codegen/charts/llm-uservice/templates/service.yaml
 # Copyright (C) 2024 Intel Corporation
@@ -65,7 +64,7 @@ metadata:
     helm.sh/chart: llm-uservice-0.8.0
     app.kubernetes.io/name: llm-uservice
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/version: "v0.8"
     app.kubernetes.io/managed-by: Helm
 spec:
   type: ClusterIP
@@ -90,7 +89,7 @@ metadata:
     helm.sh/chart: tgi-0.8.0
     app.kubernetes.io/name: tgi
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/version: "2.1.0"
     app.kubernetes.io/managed-by: Helm
 spec:
   type: ClusterIP
@@ -115,7 +114,7 @@ metadata:
     helm.sh/chart: codegen-0.8.0
     app.kubernetes.io/name: codegen
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/version: "v0.8"
     app.kubernetes.io/managed-by: Helm
 spec:
   type: ClusterIP
@@ -140,7 +139,7 @@ metadata:
     helm.sh/chart: llm-uservice-0.8.0
     app.kubernetes.io/name: llm-uservice
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/version: "v0.8"
     app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
@@ -180,14 +179,26 @@ spec:
           volumeMounts:
             - mountPath: /tmp
               name: tmp
-          startupProbe:
-            exec:
-              command:
-              - curl
-              - http://codegen-tgi
+          livenessProbe:
+            failureThreshold: 24
+            httpGet:
+              path: v1/health_check
+              port: llm-uservice
             initialDelaySeconds: 5
             periodSeconds: 5
+          readinessProbe:
+            httpGet:
+              path: v1/health_check
+              port: llm-uservice
+            initialDelaySeconds: 5
+            periodSeconds: 5
+          startupProbe:
             failureThreshold: 120
+            httpGet:
+              path: v1/health_check
+              port: llm-uservice
+            initialDelaySeconds: 5
+            periodSeconds: 5
           resources:
             {}
       volumes:
@@ -206,7 +217,7 @@ metadata:
     helm.sh/chart: tgi-0.8.0
     app.kubernetes.io/name: tgi
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.4"
+    app.kubernetes.io/version: "2.1.0"
     app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
@@ -240,6 +251,23 @@ spec:
             - name: http
               containerPort: 2080
               protocol: TCP
+          livenessProbe:
+            failureThreshold: 24
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            tcpSocket:
+              port: http
+          readinessProbe:
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            tcpSocket:
+              port: http
+          startupProbe:
+            failureThreshold: 120
+            initialDelaySeconds: 5
+            periodSeconds: 5
+            tcpSocket:
+              port: http
           resources:
             limits:
               habana.ai/gaudi: 1
@@ -263,7 +291,7 @@ metadata:
     helm.sh/chart: codegen-0.8.0
     app.kubernetes.io/name: codegen
     app.kubernetes.io/instance: codegen
-    app.kubernetes.io/version: "1.0.0"
+    app.kubernetes.io/version: "v0.8"
     app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1