helm: Update helm manifest to address user raised issues (#267)

* helm: Update helm manifest to address user raised issues
Signed-off-by: Lianhao Lu <[email protected]>

helm-charts/chatqna/Chart.yaml

@@ -34,4 +34,4 @@ dependencies:
     version: 0.8.0
     repository: "file://../common/data-prep"
 version: 0.8.0
-appVersion: "1.0.0"
+appVersion: "v0.8"

helm-charts/chatqna/README.md

@@ -52,7 +52,7 @@ curl http://localhost:8888/v1/chatqna \
 
 | Key                             | Type   | Default                       | Description                                                                                                                                                                                                                       |
 | ------------------------------- | ------ | ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| image.repository                | string | `"opea/chatqna:latest"`       |                                                                                                                                                                                                                                   |
+| image.repository                | string | `"opea/chatqna"`              |                                                                                                                                                                                                                                   |
 | service.port                    | string | `"8888"`                      |                                                                                                                                                                                                                                   |
 | global.HUGGINGFACEHUB_API_TOKEN | string | `""`                          | Your own Hugging Face API token                                                                                                                                                                                                   |
 | global.modelUseHostPath         | string | `"/mnt/opea-models"`          | Cached models directory, tgi will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory. Set this to empty/null will force it to download models every time. |

helm-charts/chatqna/nv-values.yaml

@@ -1,52 +1,11 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-# Default values for chatqna.
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-
-replicaCount: 1
-
-image:
-  repository: opea/chatqna:latest
-  pullPolicy: IfNotPresent
-  # Overrides the image tag whose default is the chart appVersion.
-  # tag: "1.0"
-
-port: 8888
-service:
-  type: ClusterIP
-  port: 8888
-
-securityContext:
-  readOnlyRootFilesystem: true
-  allowPrivilegeEscalation: false
-  runAsNonRoot: true
-  runAsUser: 1000
-  capabilities:
-    drop:
-    - ALL
-  seccompProfile:
-    type: RuntimeDefault
-
 # To override values in subchart tgi
 tgi:
-  LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
-  # LLM_MODEL_ID: /data/OpenCodeInterpreter-DS-6.7B
   image:
     repository: ghcr.io/huggingface/text-generation-inference
     tag: "2.0"
   resources:
     limits:
       nvidia.com/gpu: 1
-
-global:
-  http_proxy:
-  https_proxy:
-  no_proxy:
-  HUGGINGFACEHUB_API_TOKEN: "insert-your-huggingface-token-here"
-  LANGCHAIN_TRACING_V2: false
-  LANGCHAIN_API_KEY: "insert-your-langchain-key-here"
-  # set modelUseHostPath to host directory if you want to use hostPath volume for model storage
-  # comment out modeluseHostPath if you want to download the model from huggingface
-  modelUseHostPath: /mnt/opea-models

helm-charts/chatqna/templates/deployment.yaml

@@ -40,7 +40,7 @@ spec:
               value: {{ .Release.Name }}-embedding-usvc
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}"
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
           volumeMounts:
             - mountPath: /tmp

helm-charts/chatqna/templates/tests/test-pod.yaml

@@ -13,12 +13,17 @@ metadata:
 spec:
   containers:
     - name: curl
-      image: alpine/curl
-      #image: python:3.10.14
-      command: ['sh', '-c']
+      image: python:3.10.14
+      command: ['bash', '-c']
       args:
         - |
-          curl http://{{ include "chatqna.fullname" . }}:{{ .Values.service.port }}/v1/chatqna -sS --fail-with-body \
-            -d '{"messages": "What is the revenue of Nike in 2023?"}' \
-            -H 'Content-Type: application/json'
+          max_retry=20;
+          for ((i=1; i<=max_retry; i++)); do
+            curl http://{{ include "chatqna.fullname" . }}:{{ .Values.service.port }}/v1/chatqna -sS --fail-with-body \
+            -d '{"messages": "What is the machine learning?"}' \
+            -H 'Content-Type: application/json' && break;
+            curlcode=$?
+            if [[ $curlcode -eq 7 ]]; then sleep 10; else echo "curl failed with code $curlcode"; exit 1; fi;
+          done;
+          if [ $i -gt $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi
   restartPolicy: Never

helm-charts/chatqna/values.yaml

@@ -8,10 +8,10 @@
 replicaCount: 1
 
 image:
-  repository: opea/chatqna:latest
+  repository: opea/chatqna
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  # tag: "1.0"
+  tag: ""
 
 port: 8888
 service:
@@ -29,10 +29,15 @@ securityContext:
   seccompProfile:
     type: RuntimeDefault
 
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
 # To override values in subchart tgi
 tgi:
   LLM_MODEL_ID: Intel/neural-chat-7b-v3-3
-  # LLM_MODEL_ID: /data/OpenCodeInterpreter-DS-6.7B
 
 global:
   http_proxy:

helm-charts/codegen/Chart.yaml

@@ -13,4 +13,4 @@ dependencies:
     version: 0.8.0
     repository: "file://../common/llm-uservice"
 version: 0.8.0
-appVersion: "1.0.0"
+appVersion: "v0.8"

helm-charts/codegen/README.md

@@ -45,7 +45,7 @@ curl http://localhost:7778/v1/codegen \
 
 | Key                             | Type   | Default                        | Description                                                                                                                                                                                                                       |
 | ------------------------------- | ------ | ------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| image.repository                | string | `"opea/codegen:latest"`        |                                                                                                                                                                                                                                   |
+| image.repository                | string | `"opea/codegen"`               |                                                                                                                                                                                                                                   |
 | service.port                    | string | `"7778"`                       |                                                                                                                                                                                                                                   |
 | global.HUGGINGFACEHUB_API_TOKEN | string | `""`                           | Your own Hugging Face API token                                                                                                                                                                                                   |
 | global.modelUseHostPath         | string | `"/mnt/opea-models"`           | Cached models directory, tgi will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory. Set this to empty/null will force it to download models every time. |

helm-charts/codegen/templates/deployment.yaml

@@ -36,7 +36,7 @@ spec:
             #  value: {{ .Values.port }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}"
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
           volumeMounts:
             - mountPath: /tmp

helm-charts/codegen/templates/tests/test-pod.yaml

@@ -13,12 +13,17 @@ metadata:
 spec:
   containers:
     - name: curl
-      image: alpine/curl
-      #image: python:3.10.14
-      command: ['sh', '-c']
+      image: python:3.10.14
+      command: ['bash', '-c']
       args:
         - |
-          curl http://{{ include "codegen.fullname" . }}:{{ .Values.service.port }}/v1/codegen -sS --fail-with-body \
+          max_retry=20;
+          for ((i=1; i<=max_retry; i++)); do
+            curl http://{{ include "codegen.fullname" . }}:{{ .Values.service.port }}/v1/codegen -sS --fail-with-body \
             -d '{"messages": "def print_hello_world():"}' \
-            -H 'Content-Type: application/json'
+            -H 'Content-Type: application/json' && break;
+            curlcode=$?
+            if [[ $curlcode -eq 7 ]]; then sleep 10; else echo "curl failed with code $curlcode"; exit 1; fi;
+          done;
+          if [ $i -gt $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi
   restartPolicy: Never

helm-charts/codegen/values.yaml

@@ -8,10 +8,10 @@
 replicaCount: 1
 
 image:
-  repository: opea/codegen:latest
+  repository: opea/codegen
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  # tag: "1.0"
+  tag: ""
 
 port: 7778
 service:
@@ -29,12 +29,12 @@ securityContext:
   seccompProfile:
     type: RuntimeDefault
 
-# To override values in subchart llm-uservice
-llm-uservice:
-  image:
-    repository: opea/llm-tgi:latest
-  service:
-    port: 9000
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
 # To override values in subchart tgi
 tgi:
   LLM_MODEL_ID: meta-llama/CodeLlama-7b-hf

helm-charts/codetrans/Chart.yaml

@@ -13,4 +13,4 @@ dependencies:
     version: 0.8.0
     repository: "file://../common/llm-uservice"
 version: 0.8.0
-appVersion: "1.0.0"
+appVersion: "v0.8"

helm-charts/codetrans/README.md

@@ -38,7 +38,7 @@ curl http://localhost:7777/v1/codetrans \
 
 | Key                             | Type   | Default                           | Description                                                                                                                                                  |
 | ------------------------------- | ------ | --------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| image.repository                | string | `"opea/codetrans:latest"`         |                                                                                                                                                              |
+| image.repository                | string | `"opea/codetrans"`                |                                                                                                                                                              |
 | service.port                    | string | `"7777"`                          |                                                                                                                                                              |
 | global.HUGGINGFACEHUB_API_TOKEN | string | `""`                              | Your own Hugging Face API token                                                                                                                              |
 | global.modelUseHostPath         | string | `"/mnt/opea-models"`              | Cached models directory, tgi will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory |

helm-charts/codetrans/templates/deployment.yaml

@@ -40,7 +40,7 @@ spec:
             #  value: {{ .Values.port }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}"
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
           volumeMounts:
             - mountPath: /tmp

helm-charts/codetrans/templates/tests/test-pod.yaml

@@ -13,12 +13,17 @@ metadata:
 spec:
   containers:
     - name: curl
-      image: alpine/curl
-      #image: python:3.10.14
-      command: ['sh', '-c']
+      image: python:3.10.14
+      command: ['bash', '-c']
       args:
         - |
-          curl http://{{ include "codetrans.fullname" . }}:{{ .Values.service.port }}/v1/codetrans -sS --fail-with-body \
+          max_retry=20;
+          for ((i=1; i<=max_retry; i++)); do
+            curl http://{{ include "codetrans.fullname" . }}:{{ .Values.service.port }}/v1/codetrans -sS --fail-with-body \
             -H 'Content-Type: application/json' \
-            -d '{"language_from": "Golang","language_to": "Python","source_code": "package main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n}"}'
+            -d '{"language_from": "Golang","language_to": "Python","source_code": "package main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n}"}' && break;
+            curlcode=$?
+            if [[ $curlcode -eq 7 ]]; then sleep 10; else echo "curl failed with code $curlcode"; exit 1; fi;
+          done;
+          if [ $i -gt $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi
   restartPolicy: Never

helm-charts/codetrans/values.yaml

@@ -9,10 +9,10 @@ replicaCount: 1
 LLM_SERVICE_HOST_IP: ""
 
 image:
-  repository: opea/codetrans:latest
+  repository: opea/codetrans
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  # tag: "1.0"
+  tag: ""
 
 port: 7777
 service:
@@ -30,16 +30,15 @@ securityContext:
   seccompProfile:
     type: RuntimeDefault
 
-# To override values in subchart llm-uservice
-llm-uservice:
-  image:
-    repository: opea/llm-tgi:latest
-  service:
-    port: 9000
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
 # To override values in subchart tgi
 tgi:
   LLM_MODEL_ID: HuggingFaceH4/mistral-7b-grok
-  # LLM_MODEL_ID: /data/OpenCodeInterpreter-DS-6.7B
 
 global:
   http_proxy: ""

helm-charts/common/asr/Chart.yaml

@@ -7,7 +7,7 @@ description: The Helm chart for deploying asr as microservice
 type: application
 version: 0.8.0
 # The asr microservice server version
-appVersion: "1.0.0"
+appVersion: "v0.8"
 dependencies:
   - name: whisper
     version: 0.8.0

helm-charts/common/asr/README.md

@@ -44,8 +44,8 @@ curl http://localhost:9099/v1/audio/transcriptions \
 
 ## Values
 
-| Key              | Type   | Default             | Description |
-| ---------------- | ------ | ------------------- | ----------- |
-| image.repository | string | `"opea/asr:latest"` |             |
-| service.port     | string | `"9099"`            |             |
-| ASR_ENDPOINT     | string | `""`                |             |
+| Key              | Type   | Default      | Description |
+| ---------------- | ------ | ------------ | ----------- |
+| image.repository | string | `"opea/asr"` |             |
+| service.port     | string | `"9099"`     |             |
+| ASR_ENDPOINT     | string | `""`         |             |

helm-charts/common/asr/templates/configmap.yaml

@@ -15,4 +15,8 @@ data:
   {{- end }}
   http_proxy: {{ .Values.global.http_proxy | quote }}
   https_proxy: {{ .Values.global.https_proxy | quote }}
+  {{- if and (not .Values.ASR_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy) }}
+  no_proxy: "{{ .Release.Name }}-whisper,{{ .Values.global.no_proxy }}"
+  {{- else }}
   no_proxy: {{ .Values.global.no_proxy | quote }}
+  {{- end }}

helm-charts/common/asr/templates/deployment.yaml

@@ -39,7 +39,7 @@ spec:
             {{- end }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}"
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
           ports:
             - name: asr

helm-charts/common/asr/templates/tests/test-pod.yaml

@@ -13,13 +13,18 @@ metadata:
 spec:
   containers:
     - name: curl
-      image: alpine/curl
-      #image: python:3.10.14
-      command: ['sh', '-c']
+      image: python:3.10.14
+      command: ['bash', '-c']
       args:
         - |
-          curl -sS --fail-with-body http://{{ include "asr.fullname" . }}:{{ .Values.service.port }}/v1/audio/transcriptions \
+          max_retry=20;
+          for ((i=1; i<=max_retry; i++)); do
+            curl -sS --fail-with-body http://{{ include "asr.fullname" . }}:{{ .Values.service.port }}/v1/audio/transcriptions \
             -XPOST \
             -d '{"byte_str": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA"}' \
-            -H 'Content-Type: application/json'
+            -H 'Content-Type: application/json' && break;
+            curlcode=$?
+            if [[ $curlcode -eq 7 ]]; then sleep 10; else echo "curl failed with code $curlcode"; exit 1; fi;
+          done;
+          if [ $i -gt $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi
   restartPolicy: Never

helm-charts/common/asr/values.yaml

@@ -13,10 +13,10 @@ replicaCount: 1
 ASR_ENDPOINT: ""
 
 image:
-  repository: opea/asr:latest
+  repository: opea/asr
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  # tag: "1.0"
+  tag: ""
 
 imagePullSecrets: []
 nameOverride: ""

helm-charts/common/ui/Chart.yaml → helm-charts/common/chatqna-ui/Chart.yaml

@@ -6,4 +6,4 @@ name: ui
 description: A Helm chart to the UI for chatQnA workload
 type: application
 version: 0.8.0
-appVersion: "1.0.0"
+appVersion: "v0.8"

helm-charts/common/ui/templates/deployment.yaml → helm-charts/common/chatqna-ui/templates/deployment.yaml

@@ -39,7 +39,7 @@ spec:
             {{- end }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}"
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
           ports:
             - name: ui

helm-charts/common/ui/values.yaml → helm-charts/common/chatqna-ui/values.yaml

@@ -8,10 +8,10 @@
 replicaCount: 1
 
 image:
-  repository: opea/chatqna-conversation-ui:latest
+  repository: opea/chatqna-conversation-ui
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  # tag: ""
+  tag: ""
 
 imagePullSecrets: []
 nameOverride: ""