Update mainifest for FaqGen (#582)

* update tgi version

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add k8s for faq

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add benchmark for faq

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* refine k8s for faq

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add tuning for faq

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add prompts with different length for faq

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* add tgi docker for llama3.1

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* remove useless code

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* remove nodeselector

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* remove hg token

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* refine code structure

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix readme

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>

---------

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

FaqGen/docker/gaudi/README.md

@@ -16,7 +16,7 @@ cd GenAIComps
 As TGI Gaudi has been officially published as a Docker image, we simply need to pull it:
 
 ```bash
-docker pull ghcr.io/huggingface/tgi-gaudi:1.2.1
+docker pull ghcr.io/huggingface/tgi-gaudi:2.0.1
 ```
 
 ### 2. Build LLM Image
@@ -56,7 +56,7 @@ docker build -t opea/faqgen-react-ui:latest --build-arg https_proxy=$https_proxy
 
 Then run the command `docker images`, you will have the following Docker Images:
 
-1. `ghcr.io/huggingface/tgi-gaudi:1.2.1`
+1. `ghcr.io/huggingface/tgi-gaudi:2.0.1`
 2. `opea/llm-faqgen-tgi:latest`
 3. `opea/faqgen:latest`
 4. `opea/faqgen-ui:latest`

FaqGen/docker/gaudi/compose.yaml

@@ -17,12 +17,14 @@ services:
       https_proxy: ${https_proxy}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      PREFILL_BATCH_BUCKET_SIZE: 1
+      BATCH_BUCKET_SIZE: 8
     runtime: habana
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096 --max-batch-total-tokens 65536 --max-batch-prefill-tokens 4096
   llm_faqgen:
     image: opea/llm-faqgen-tgi:latest
     container_name: llm-faqgen-server

FaqGen/kubernetes/manifests/README.md

@@ -23,13 +23,24 @@ sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" faqg
 kubectl apply -f faqgen.yaml
 ```
 
+## Deploy UI
+
+```
+cd GenAIExamples/FaqGen/kubernetes/manifests/
+kubectl get svc # get ip address
+ip_address="" # according to your svc address
+sed -i "s/insert_your_ip_here/${ip_address}/g" ui.yaml
+kubectl apply -f ui.yaml
+```
+
 ## Verify Services
 
 Make sure all the pods are running, and restart the faqgen-xxxx pod if necessary.
 
 ```
 kubectl get pods
-curl http://${host_ip}:8888/v1/faqgen -H "Content-Type: application/json" -d '{
+port=7779 # 7779 for gaudi, 7778 for xeon
+curl http://${host_ip}:7779/v1/faqgen -H "Content-Type: application/json" -d '{
      "messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
      }'
 ```

FaqGen/kubernetes/manifests/gaudi/faqgen.yaml

@@ -1,216 +1,186 @@
 ---
-# Source: codegen/charts/llm-uservice/charts/tgi/templates/service.yaml
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-apiVersion: v1
-kind: Service
-metadata:
-  name: faqgen-tgi
-  labels:
-    helm.sh/chart: tgi-0.1.0
-    app.kubernetes.io/name: tgi
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.4"
-    app.kubernetes.io/managed-by: Helm
-spec:
-  type: ClusterIP
-  ports:
-    - port: 80
-      targetPort: 80
-      protocol: TCP
-      name: tgi
-  selector:
-    app.kubernetes.io/name: tgi
-    app.kubernetes.io/instance: faqgen
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: faqgen-llm-uservice
-  labels:
-    helm.sh/chart: llm-uservice-0.1.0
-    app.kubernetes.io/name: llm-uservice
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
-spec:
-  type: ClusterIP
-  ports:
-    - port: 9000
-      targetPort: 9000
-      protocol: TCP
-      name: llm-uservice
-  selector:
-    app.kubernetes.io/name: llm-uservice
-    app.kubernetes.io/instance: faqgen
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: faqgen
-  labels:
-    helm.sh/chart: faqgen-0.1.0
-    app.kubernetes.io/name: faqgen
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
-spec:
-  type: ClusterIP
-  ports:
-    - port: 8888
-      targetPort: 8888
-      protocol: TCP
-      name: faqgen
-  selector:
-    app.kubernetes.io/name: faqgen
-    app.kubernetes.io/instance: faqgen
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: faqgen-tgi
+  name: faq-tgi-deploy
-  labels:
+  namespace: default
-    helm.sh/chart: tgi-0.1.0
-    app.kubernetes.io/name: tgi
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.4"
-    app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app.kubernetes.io/name: tgi
+      app: faq-tgi-deploy
-      app.kubernetes.io/instance: faqgen
   template:
     metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
       labels:
-        app.kubernetes.io/name: tgi
+        app: faq-tgi-deploy
-        app.kubernetes.io/instance: faqgen
     spec:
-      securityContext: {}
+      hostIPC: true
       containers:
-        - name: tgi
+      - name: faq-tgi-deploy-demo
-          env:
+        env:
-            - name: MODEL_ID
+          - name: HUGGING_FACE_HUB_TOKEN
-              value: Intel/neural-chat-7b-v3-3
+            value: "insert-your-huggingface-token-here"
-            - name: PORT
+          - name: OMPI_MCA_btl_vader_single_copy_mechanism
-              value: "80"
+            value: none
-            - name: http_proxy
+          - name: PT_HPU_ENABLE_LAZY_COLLECTIVES
-              value:
+            value: 'true'
-            - name: https_proxy
+          - name: runtime
-              value:
+            value: habana
-            - name: no_proxy
+          - name: HABANA_VISIBLE_DEVICES
-              value:
+            value: all
-          securityContext: {}
+          - name: PREFILL_BATCH_BUCKET_SIZE
-          image: "ghcr.io/huggingface/text-generation-inference:1.4"
+            value: "1"
-          imagePullPolicy: IfNotPresent
+          - name: BATCH_BUCKET_SIZE
-          volumeMounts:
+            value: "8"
-            - mountPath: /data
+          - name: PORT
-              name: model-volume
+            value: "80"
-          ports:
+        image: ghcr.io/huggingface/tgi-gaudi:2.0.1
-            - name: http
+        imagePullPolicy: IfNotPresent
-              containerPort: 80
+        securityContext:
-              protocol: TCP
+          capabilities:
-          resources: {}
+            add:
+            - SYS_NICE
+        args:
+        - --model-id
+        - 'meta-llama/Meta-Llama-3-8B-Instruct'
+        - --max-input-length
+        - '3096'
+        - --max-total-tokens
+        - '4096'
+        - --max-batch-total-tokens
+        - '65536'
+        - --max-batch-prefill-tokens
+        - '4096'
+        volumeMounts:
+        - mountPath: /data
+          name: model-volume
+        - mountPath: /dev/shm
+          name: shm
+        ports:
+        - containerPort: 80
+        resources:
+          limits:
+            habana.ai/gaudi: 1
+      serviceAccountName: default
       volumes:
-        - name: model-volume
+      - name: model-volume
-          hostPath:
+        hostPath:
-            path: /mnt
+          path: /home/sdp/cesg
-            type: Directory
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: faq-tgi-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: faq-tgi-deploy
+  ports:
+  - name: service
+    port: 8010
+    targetPort: 80
 ---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: faqgen-llm-uservice
+  name: faq-micro-deploy
-  labels:
+  namespace: default
-    helm.sh/chart: llm-uservice-0.1.0
-    app.kubernetes.io/name: llm-uservice
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app.kubernetes.io/name: llm-uservice
+      app: faq-micro-deploy
-      app.kubernetes.io/instance: faqgen
   template:
     metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
       labels:
-        app.kubernetes.io/name: llm-uservice
+        app: faq-micro-deploy
-        app.kubernetes.io/instance: faqgen
     spec:
-      securityContext: {}
+      hostIPC: true
       containers:
-        - name: faqgen
+        - name: faq-micro-deploy
           env:
             - name: TGI_LLM_ENDPOINT
-              value: "http://faqgen-tgi:80"
+              value: "http://faq-tgi-svc.default.svc.cluster.local:8010"
             - name: HUGGINGFACEHUB_API_TOKEN
               value: "insert-your-huggingface-token-here"
-            - name: http_proxy
+          image: opea/llm-faqgen-tgi:latest
-              value:
-            - name: https_proxy
-              value:
-            - name: no_proxy
-              value:
-          securityContext: {}
-          image: "opea/llm-faqgen-tgi:latest"
           imagePullPolicy: IfNotPresent
+          args: null
           ports:
-            - name: llm-uservice
+          - containerPort: 9000
-              containerPort: 9000
+      serviceAccountName: default
-              protocol: TCP
+---
-          startupProbe:
+kind: Service
-            exec:
+apiVersion: v1
-              command:
+metadata:
-                - curl
+  name: faq-micro-svc
-                - http://faqgen-tgi:80
+spec:
-            initialDelaySeconds: 5
+  type: ClusterIP
-            periodSeconds: 5
+  selector:
-            failureThreshold: 120
+    app: faq-micro-deploy
-          resources: {}
+  ports:
+  - name: service
+    port: 9003
+    targetPort: 9000
 ---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: faqgen
+  name: faq-mega-server-deploy
-  labels:
+  namespace: default
-    helm.sh/chart: faqgen-0.1.0
-    app.kubernetes.io/name: faqgen
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app.kubernetes.io/name: faqgen
+      app: faq-mega-server-deploy
-      app.kubernetes.io/instance: faqgen
   template:
     metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
       labels:
-        app.kubernetes.io/name: faqgen
+        app: faq-mega-server-deploy
-        app.kubernetes.io/instance: faqgen
     spec:
-      securityContext: null
+      hostIPC: true
       containers:
-        - name: faqgen
+        - name: faq-mega-server-deploy
           env:
             - name: LLM_SERVICE_HOST_IP
-              value: faqgen-llm-uservice
+              value: faq-micro-svc
-            - name: http_proxy
+            - name: LLM_SERVICE_PORT
-              value:
+              value: "9003"
-            - name: https_proxy
+            - name: MEGA_SERVICE_HOST_IP
-              value:
+              value: faq-mega-server-svc
-            - name: no_proxy
+            - name: MEGA_SERVICE_PORT
-              value:
+              value: "7777"
-          securityContext: null
+          image: opea/faqgen:latest
-          image: "opea/faqgen:latest"
           imagePullPolicy: IfNotPresent
+          args: null
           ports:
-            - name: faqgen
+          - containerPort: 7777
-              containerPort: 8888
+      serviceAccountName: default
-              protocol: TCP
+---
-          resources: null
+kind: Service
+apiVersion: v1
+metadata:
+  name: faq-mega-server-svc
+spec:
+  type: NodePort
+  selector:
+    app: faq-mega-server-deploy
+  ports:
+  - name: service
+    port: 7779
+    targetPort: 7777
+    nodePort: 30779

FaqGen/kubernetes/manifests/ui.yaml

@@ -0,0 +1,46 @@
+---
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: faq-mega-ui-deploy
+  namespace: default
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: faq-mega-ui-deploy
+  template:
+    metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
+      labels:
+        app: faq-mega-ui-deploy
+    spec:
+      hostIPC: true
+      containers:
+        - name: faq-mega-ui-deploy
+          env:
+            - name: DOC_BASE_URL
+              value: http://{insert_your_ip_here}:7779/v1/faqgen
+          image: opea/faqgen-ui:latest
+          imagePullPolicy: IfNotPresent
+          args: null
+          ports:
+          - containerPort: 5173
+      serviceAccountName: default
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: faq-mega-ui-svc
+spec:
+  type: NodePort
+  selector:
+    app: faq-mega-ui-deploy
+  ports:
+  - name: service
+    port: 5175
+    targetPort: 5173
+    nodePort: 30175

FaqGen/kubernetes/manifests/xeon/faqgen.yaml

@@ -1,216 +1,165 @@
 ---
-# Source: codegen/charts/llm-uservice/charts/tgi/templates/service.yaml
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-apiVersion: v1
-kind: Service
-metadata:
-  name: faqgen-tgi
-  labels:
-    helm.sh/chart: tgi-0.1.0
-    app.kubernetes.io/name: tgi
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.4"
-    app.kubernetes.io/managed-by: Helm
-spec:
-  type: ClusterIP
-  ports:
-    - port: 80
-      targetPort: 80
-      protocol: TCP
-      name: tgi
-  selector:
-    app.kubernetes.io/name: tgi
-    app.kubernetes.io/instance: faqgen
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: faqgen-llm-uservice
-  labels:
-    helm.sh/chart: llm-uservice-0.1.0
-    app.kubernetes.io/name: llm-uservice
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
-spec:
-  type: ClusterIP
-  ports:
-    - port: 9000
-      targetPort: 9000
-      protocol: TCP
-      name: llm-uservice
-  selector:
-    app.kubernetes.io/name: llm-uservice
-    app.kubernetes.io/instance: faqgen
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: faqgen
-  labels:
-    helm.sh/chart: faqgen-0.1.0
-    app.kubernetes.io/name: faqgen
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
-spec:
-  type: ClusterIP
-  ports:
-    - port: 8888
-      targetPort: 8888
-      protocol: TCP
-      name: faqgen
-  selector:
-    app.kubernetes.io/name: faqgen
-    app.kubernetes.io/instance: faqgen
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: faqgen-tgi
+  name: faq-tgi-cpu-deploy
-  labels:
+  namespace: default
-    helm.sh/chart: tgi-0.1.0
-    app.kubernetes.io/name: tgi
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.4"
-    app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app.kubernetes.io/name: tgi
+      app: faq-tgi-cpu-deploy
-      app.kubernetes.io/instance: faqgen
   template:
     metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
       labels:
-        app.kubernetes.io/name: tgi
+        app: faq-tgi-cpu-deploy
-        app.kubernetes.io/instance: faqgen
     spec:
+      hostIPC: true
       securityContext: {}
       containers:
-        - name: tgi
+      - name: faq-tgi-cpu-deploy-demo
-          env:
+        env:
-            - name: MODEL_ID
+          - name: HUGGING_FACE_HUB_TOKEN
-              value: Intel/neural-chat-7b-v3-3
+            value: "insert-your-huggingface-token-here"
-            - name: PORT
+          - name: PORT
-              value: "80"
+            value: "80"
-            - name: http_proxy
+        image: ghcr.io/huggingface/text-generation-inference:1.4
-              value:
+        imagePullPolicy: IfNotPresent
-            - name: https_proxy
+        securityContext: {}
-              value:
+        args:
-            - name: no_proxy
+        - --model-id
-              value:
+        - 'meta-llama/Meta-Llama-3-8B-Instruct'
-          securityContext: {}
+        - --max-input-length
-          image: "ghcr.io/huggingface/text-generation-inference:1.4"
+        - '3096'
-          imagePullPolicy: IfNotPresent
+        - --max-total-tokens
-          volumeMounts:
+        - '4096'
-            - mountPath: /data
+        volumeMounts:
-              name: model-volume
+        - mountPath: /data
-          ports:
+          name: model-volume
-            - name: http
+        - mountPath: /dev/shm
-              containerPort: 80
+          name: shm
-              protocol: TCP
+        ports:
-          resources: {}
+        - containerPort: 80
+      serviceAccountName: default
       volumes:
-        - name: model-volume
+      - name: model-volume
-          hostPath:
+        hostPath:
-            path: /mnt
+          path: /home/sdp/cesg
-            type: Directory
+          type: Directory
+      - name: shm
+        emptyDir:
+          medium: Memory
+          sizeLimit: 1Gi
+---
+kind: Service
+apiVersion: v1
+metadata:
+  name: faq-tgi-cpu-svc
+spec:
+  type: ClusterIP
+  selector:
+    app: faq-tgi-cpu-deploy
+  ports:
+  - name: service
+    port: 8011
+    targetPort: 80
 ---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: faqgen-llm-uservice
+  name: faq-micro-cpu-deploy
-  labels:
+  namespace: default
-    helm.sh/chart: llm-uservice-0.1.0
-    app.kubernetes.io/name: llm-uservice
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app.kubernetes.io/name: llm-uservice
+      app: faq-micro-cpu-deploy
-      app.kubernetes.io/instance: faqgen
   template:
     metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
       labels:
-        app.kubernetes.io/name: llm-uservice
+        app: faq-micro-cpu-deploy
-        app.kubernetes.io/instance: faqgen
     spec:
-      securityContext: {}
+      hostIPC: true
       containers:
-        - name: faqgen
+        - name: faq-micro-cpu-deploy
           env:
             - name: TGI_LLM_ENDPOINT
-              value: "http://faqgen-tgi:80"
+              value: "http://faq-tgi-cpu-svc.default.svc.cluster.local:8011"
             - name: HUGGINGFACEHUB_API_TOKEN
               value: "insert-your-huggingface-token-here"
-            - name: http_proxy
+          image: opea/llm-faqgen-tgi:latest
-              value:
-            - name: https_proxy
-              value:
-            - name: no_proxy
-              value:
-          securityContext: {}
-          image: "opea/llm-faqgen-tgi:latest"
           imagePullPolicy: IfNotPresent
+          args: null
           ports:
-            - name: llm-uservice
+          - containerPort: 9000
-              containerPort: 9000
+      serviceAccountName: default
-              protocol: TCP
+---
-          startupProbe:
+kind: Service
-            exec:
+apiVersion: v1
-              command:
+metadata:
-                - curl
+  name: faq-micro-cpu-svc
-                - http://faqgen-tgi:80
+spec:
-            initialDelaySeconds: 5
+  type: ClusterIP
-            periodSeconds: 5
+  selector:
-            failureThreshold: 120
+    app: faq-micro-cpu-deploy
-          resources: {}
+  ports:
+  - name: service
+    port: 9004
+    targetPort: 9000
 ---
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: faqgen
+  name: faq-mega-server-cpu-deploy
-  labels:
+  namespace: default
-    helm.sh/chart: faqgen-0.1.0
-    app.kubernetes.io/name: faqgen
-    app.kubernetes.io/instance: faqgen
-    app.kubernetes.io/version: "1.0.0"
-    app.kubernetes.io/managed-by: Helm
 spec:
   replicas: 1
   selector:
     matchLabels:
-      app.kubernetes.io/name: faqgen
+      app: faq-mega-server-cpu-deploy
-      app.kubernetes.io/instance: faqgen
   template:
     metadata:
+      annotations:
+        sidecar.istio.io/rewriteAppHTTPProbers: 'true'
       labels:
-        app.kubernetes.io/name: faqgen
+        app: faq-mega-server-cpu-deploy
-        app.kubernetes.io/instance: faqgen
     spec:
-      securityContext: null
+      hostIPC: true
       containers:
-        - name: faqgen
+        - name: faq-mega-server-cpu-deploy
           env:
             - name: LLM_SERVICE_HOST_IP
-              value: faqgen-llm-uservice
+              value: faq-micro-cpu-svc
-            - name: http_proxy
+            - name: LLM_SERVICE_PORT
-              value:
+              value: "9004"
-            - name: https_proxy
+            - name: MEGA_SERVICE_HOST_IP
-              value:
+              value: faq-mega-server-cpu-svc
-            - name: no_proxy
+            - name: MEGA_SERVICE_PORT
-              value:
+              value: "7777"
-          securityContext: null
+          image: opea/faqgen:latest
-          image: "opea/faqgen:latest"
           imagePullPolicy: IfNotPresent
+          args: null
           ports:
-            - name: faqgen
+          - containerPort: 7777
-              containerPort: 8888
+      serviceAccountName: default
-              protocol: TCP
+---
-          resources: null
+kind: Service
+apiVersion: v1
+metadata:
+  name: faq-mega-server-cpu-svc
+spec:
+  type: NodePort
+  selector:
+    app: faq-mega-server-cpu-deploy
+  ports:
+  - name: service
+    port: 7778
+    targetPort: 7777
+    nodePort: 30778