diff --git a/helm-charts/chatqna/Chart.yaml b/helm-charts/chatqna/Chart.yaml index 229a3c90..b1a0c200 100644 --- a/helm-charts/chatqna/Chart.yaml +++ b/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" diff --git a/helm-charts/chatqna/README.md b/helm-charts/chatqna/README.md index 27768faa..3b0312a7 100644 --- a/helm-charts/chatqna/README.md +++ b/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. | diff --git a/helm-charts/chatqna/nv-values.yaml b/helm-charts/chatqna/nv-values.yaml index fd58e428..6615da78 100644 --- a/helm-charts/chatqna/nv-values.yaml +++ b/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 diff --git a/helm-charts/chatqna/templates/deployment.yaml b/helm-charts/chatqna/templates/deployment.yaml index 48218483..4667666d 100644 --- a/helm-charts/chatqna/templates/deployment.yaml +++ b/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 diff --git a/helm-charts/chatqna/templates/tests/test-pod.yaml b/helm-charts/chatqna/templates/tests/test-pod.yaml index 518542e6..18c4246c 100644 --- a/helm-charts/chatqna/templates/tests/test-pod.yaml +++ b/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 diff --git a/helm-charts/chatqna/values.yaml b/helm-charts/chatqna/values.yaml index 8ad03245..174dcf9a 100644 --- a/helm-charts/chatqna/values.yaml +++ b/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: diff --git a/helm-charts/codegen/Chart.yaml b/helm-charts/codegen/Chart.yaml index 7e88f771..c9bd114e 100644 --- a/helm-charts/codegen/Chart.yaml +++ b/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" diff --git a/helm-charts/codegen/README.md b/helm-charts/codegen/README.md index 5052d3f4..8fef0458 100644 --- a/helm-charts/codegen/README.md +++ b/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. | diff --git a/helm-charts/codegen/templates/deployment.yaml b/helm-charts/codegen/templates/deployment.yaml index 03e4eed3..65a084c5 100644 --- a/helm-charts/codegen/templates/deployment.yaml +++ b/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 diff --git a/helm-charts/codegen/templates/tests/test-pod.yaml b/helm-charts/codegen/templates/tests/test-pod.yaml index 898b1568..95dc26fa 100644 --- a/helm-charts/codegen/templates/tests/test-pod.yaml +++ b/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 diff --git a/helm-charts/codegen/values.yaml b/helm-charts/codegen/values.yaml index 434c4050..0311d6da 100644 --- a/helm-charts/codegen/values.yaml +++ b/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 diff --git a/helm-charts/codetrans/Chart.yaml b/helm-charts/codetrans/Chart.yaml index b6082615..e0e1451b 100644 --- a/helm-charts/codetrans/Chart.yaml +++ b/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" diff --git a/helm-charts/codetrans/README.md b/helm-charts/codetrans/README.md index b55ab0eb..75b7ba6e 100644 --- a/helm-charts/codetrans/README.md +++ b/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 | diff --git a/helm-charts/codetrans/templates/deployment.yaml b/helm-charts/codetrans/templates/deployment.yaml index e7195e98..1eae19ea 100644 --- a/helm-charts/codetrans/templates/deployment.yaml +++ b/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 diff --git a/helm-charts/codetrans/templates/tests/test-pod.yaml b/helm-charts/codetrans/templates/tests/test-pod.yaml index 780d1f11..0338d167 100644 --- a/helm-charts/codetrans/templates/tests/test-pod.yaml +++ b/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 diff --git a/helm-charts/codetrans/values.yaml b/helm-charts/codetrans/values.yaml index 1bbd97bd..700b5962 100644 --- a/helm-charts/codetrans/values.yaml +++ b/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: "" diff --git a/helm-charts/common/asr/Chart.yaml b/helm-charts/common/asr/Chart.yaml index b9312943..b7766288 100644 --- a/helm-charts/common/asr/Chart.yaml +++ b/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 diff --git a/helm-charts/common/asr/README.md b/helm-charts/common/asr/README.md index 6fcf4e8b..adf30333 100644 --- a/helm-charts/common/asr/README.md +++ b/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 | `""` | | diff --git a/helm-charts/common/asr/templates/configmap.yaml b/helm-charts/common/asr/templates/configmap.yaml index 0a80104b..19eb0cf7 100644 --- a/helm-charts/common/asr/templates/configmap.yaml +++ b/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 }} diff --git a/helm-charts/common/asr/templates/deployment.yaml b/helm-charts/common/asr/templates/deployment.yaml index e633f7d6..529c342c 100644 --- a/helm-charts/common/asr/templates/deployment.yaml +++ b/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 diff --git a/helm-charts/common/asr/templates/tests/test-pod.yaml b/helm-charts/common/asr/templates/tests/test-pod.yaml index ab05bc1e..d71fbf9f 100644 --- a/helm-charts/common/asr/templates/tests/test-pod.yaml +++ b/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 diff --git a/helm-charts/common/asr/values.yaml b/helm-charts/common/asr/values.yaml index 285580a9..f8597c91 100644 --- a/helm-charts/common/asr/values.yaml +++ b/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: "" diff --git a/helm-charts/common/ui/.helmignore b/helm-charts/common/chatqna-ui/.helmignore similarity index 100% rename from helm-charts/common/ui/.helmignore rename to helm-charts/common/chatqna-ui/.helmignore diff --git a/helm-charts/common/ui/Chart.yaml b/helm-charts/common/chatqna-ui/Chart.yaml similarity index 90% rename from helm-charts/common/ui/Chart.yaml rename to helm-charts/common/chatqna-ui/Chart.yaml index a6d152d2..fe0cc078 100644 --- a/helm-charts/common/ui/Chart.yaml +++ b/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" diff --git a/helm-charts/common/ui/templates/_helpers.tpl b/helm-charts/common/chatqna-ui/templates/_helpers.tpl similarity index 100% rename from helm-charts/common/ui/templates/_helpers.tpl rename to helm-charts/common/chatqna-ui/templates/_helpers.tpl diff --git a/helm-charts/common/ui/templates/configmap.yaml b/helm-charts/common/chatqna-ui/templates/configmap.yaml similarity index 100% rename from helm-charts/common/ui/templates/configmap.yaml rename to helm-charts/common/chatqna-ui/templates/configmap.yaml diff --git a/helm-charts/common/ui/templates/deployment.yaml b/helm-charts/common/chatqna-ui/templates/deployment.yaml similarity index 94% rename from helm-charts/common/ui/templates/deployment.yaml rename to helm-charts/common/chatqna-ui/templates/deployment.yaml index 4a5fcfbb..f201a58b 100644 --- a/helm-charts/common/ui/templates/deployment.yaml +++ b/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 diff --git a/helm-charts/common/ui/templates/service.yaml b/helm-charts/common/chatqna-ui/templates/service.yaml similarity index 100% rename from helm-charts/common/ui/templates/service.yaml rename to helm-charts/common/chatqna-ui/templates/service.yaml diff --git a/helm-charts/common/ui/templates/tests/test-pod.yaml b/helm-charts/common/chatqna-ui/templates/tests/test-pod.yaml similarity index 100% rename from helm-charts/common/ui/templates/tests/test-pod.yaml rename to helm-charts/common/chatqna-ui/templates/tests/test-pod.yaml diff --git a/helm-charts/common/ui/values.yaml b/helm-charts/common/chatqna-ui/values.yaml similarity index 96% rename from helm-charts/common/ui/values.yaml rename to helm-charts/common/chatqna-ui/values.yaml index fc712a23..bb28851f 100644 --- a/helm-charts/common/ui/values.yaml +++ b/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: "" diff --git a/helm-charts/common/data-prep/Chart.yaml b/helm-charts/common/data-prep/Chart.yaml index ed361292..0c1f2913 100644 --- a/helm-charts/common/data-prep/Chart.yaml +++ b/helm-charts/common/data-prep/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying data prep as microservice type: application version: 0.8.0 # The data prep microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: tei version: 0.8.0 diff --git a/helm-charts/common/data-prep/README.md b/helm-charts/common/data-prep/README.md index c9162554..6c2d3e92 100644 --- a/helm-charts/common/data-prep/README.md +++ b/helm-charts/common/data-prep/README.md @@ -45,9 +45,9 @@ curl http://localhost:6007/v1/dataprep \ ## Values -| Key | Type | Default | Description | -| ---------------------- | ------ | ------------------------------ | ----------- | -| image.repository | string | `"opea/dataprep-redis:latest"` | | -| service.port | string | `"6007"` | | -| REDIS_URL | string | `""` | | -| TEI_EMBEDDING_ENDPOINT | string | `""` | | +| Key | Type | Default | Description | +| ---------------------- | ------ | ----------------------- | ----------- | +| image.repository | string | `"opea/dataprep-redis"` | | +| service.port | string | `"6007"` | | +| REDIS_URL | string | `""` | | +| TEI_EMBEDDING_ENDPOINT | string | `""` | | diff --git a/helm-charts/common/data-prep/templates/configmap.yaml b/helm-charts/common/data-prep/templates/configmap.yaml index aee2aa6d..7d970948 100644 --- a/helm-charts/common/data-prep/templates/configmap.yaml +++ b/helm-charts/common/data-prep/templates/configmap.yaml @@ -24,7 +24,11 @@ data: HF_HOME: "/tmp/.cache/huggingface" http_proxy: {{ .Values.global.http_proxy | quote }} https_proxy: {{ .Values.global.https_proxy | quote }} + {{- if and (not .Values.REDIS_URL) (and (not .Values.TEI_EMBEDDING_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy)) }} + no_proxy: "{{ .Release.Name }}-tei,{{ .Release.Name }}-redis-vector-db,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} LANGCHAIN_TRACING_V2: {{ .Values.global.LANGCHAIN_TRACING_V2 | quote }} LANGCHAIN_API_KEY: {{ .Values.global.LANGCHAIN_API_KEY | quote }} LANGCHAIN_PROJECT: "opea-dataprep-service" diff --git a/helm-charts/common/data-prep/templates/deployment.yaml b/helm-charts/common/data-prep/templates/deployment.yaml index 68603577..bc0103ab 100644 --- a/helm-charts/common/data-prep/templates/deployment.yaml +++ b/helm-charts/common/data-prep/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: data-prep diff --git a/helm-charts/common/data-prep/templates/tests/test-pod.yaml b/helm-charts/common/data-prep/templates/tests/test-pod.yaml index 56233edd..f1217cd2 100644 --- a/helm-charts/common/data-prep/templates/tests/test-pod.yaml +++ b/helm-charts/common/data-prep/templates/tests/test-pod.yaml @@ -13,7 +13,6 @@ metadata: spec: containers: - name: curl - #image: alpine/curl image: python:3.10.14 command: ['bash', '-c'] args: @@ -28,7 +27,8 @@ spec: -X POST \ -H "Content-Type: multipart/form-data" \ -F "files=@/tmp/file1.txt" && break; - sleep 10; + 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 "dataprep test failed."; exit 1; fi + if [ $i -gt $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi restartPolicy: Never diff --git a/helm-charts/common/data-prep/values.yaml b/helm-charts/common/data-prep/values.yaml index af436656..efe9dc4b 100644 --- a/helm-charts/common/data-prep/values.yaml +++ b/helm-charts/common/data-prep/values.yaml @@ -11,10 +11,10 @@ autodependency: replicaCount: 1 image: - repository: opea/dataprep-redis:latest + repository: opea/dataprep-redis pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/embedding-usvc/Chart.yaml b/helm-charts/common/embedding-usvc/Chart.yaml index f844478b..dcd229d8 100644 --- a/helm-charts/common/embedding-usvc/Chart.yaml +++ b/helm-charts/common/embedding-usvc/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying embedding as microservice type: application version: 0.8.0 # The embedding microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: tei version: 0.8.0 diff --git a/helm-charts/common/embedding-usvc/README.md b/helm-charts/common/embedding-usvc/README.md index 2df1d8ca..88926d37 100644 --- a/helm-charts/common/embedding-usvc/README.md +++ b/helm-charts/common/embedding-usvc/README.md @@ -44,8 +44,8 @@ curl http://localhost:6000/v1/embeddings \ ## Values -| Key | Type | Default | Description | -| ---------------------- | ------ | ----------------------------- | ----------- | -| image.repository | string | `"opea/embedding-tei:latest"` | | -| service.port | string | `"6000"` | | -| TEI_EMBEDDING_ENDPOINT | string | `""` | | +| Key | Type | Default | Description | +| ---------------------- | ------ | ---------------------- | ----------- | +| image.repository | string | `"opea/embedding-tei"` | | +| service.port | string | `"6000"` | | +| TEI_EMBEDDING_ENDPOINT | string | `""` | | diff --git a/helm-charts/common/embedding-usvc/templates/configmap.yaml b/helm-charts/common/embedding-usvc/templates/configmap.yaml index 65037894..a7566b7b 100644 --- a/helm-charts/common/embedding-usvc/templates/configmap.yaml +++ b/helm-charts/common/embedding-usvc/templates/configmap.yaml @@ -15,7 +15,11 @@ data: {{- end }} http_proxy: {{ .Values.global.http_proxy | quote }} https_proxy: {{ .Values.global.https_proxy | quote }} + {{- if and (not .Values.TEI_EMBEDDING_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy) }} + no_proxy: "{{ .Release.Name }}-tei,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} LANGCHAIN_TRACING_V2: {{ .Values.global.LANGCHAIN_TRACING_V2 | quote }} LANGCHAIN_API_KEY: {{ .Values.global.LANGCHAIN_API_KEY }} LANGCHAIN_PROJECT: "opea-embedding-service" diff --git a/helm-charts/common/embedding-usvc/templates/deployment.yaml b/helm-charts/common/embedding-usvc/templates/deployment.yaml index dfc35d7a..26f5a76f 100644 --- a/helm-charts/common/embedding-usvc/templates/deployment.yaml +++ b/helm-charts/common/embedding-usvc/templates/deployment.yaml @@ -39,8 +39,8 @@ spec: {{- end }} securityContext: {{- toYaml .Values.securityContext | nindent 12 }} - image: "{{ .Values.image.repository }}" - imagePullPolicy: IfNotPresent + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} ports: - name: embedding-usvc containerPort: 6000 diff --git a/helm-charts/common/embedding-usvc/templates/tests/test-pod.yaml b/helm-charts/common/embedding-usvc/templates/tests/test-pod.yaml index ff0f0e91..7acc267b 100644 --- a/helm-charts/common/embedding-usvc/templates/tests/test-pod.yaml +++ b/helm-charts/common/embedding-usvc/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 http://{{ include "embedding-usvc.fullname" . }}:{{ .Values.service.port }}/v1/embeddings -sS --fail-with-body \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl http://{{ include "embedding-usvc.fullname" . }}:{{ .Values.service.port }}/v1/embeddings -sS --fail-with-body \ -X POST \ -d '{"text":"hello"}' \ - -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 diff --git a/helm-charts/common/embedding-usvc/values.yaml b/helm-charts/common/embedding-usvc/values.yaml index b44fe585..f3b1f9e8 100644 --- a/helm-charts/common/embedding-usvc/values.yaml +++ b/helm-charts/common/embedding-usvc/values.yaml @@ -12,10 +12,10 @@ replicaCount: 1 TEI_EMBEDDING_ENDPOINT: "" image: - repository: opea/embedding-tei:latest + repository: opea/embedding-tei pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - #tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/llm-uservice/Chart.yaml b/helm-charts/common/llm-uservice/Chart.yaml index a69e42e7..b8b76756 100644 --- a/helm-charts/common/llm-uservice/Chart.yaml +++ b/helm-charts/common/llm-uservice/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying llm as microservice type: application version: 0.8.0 # The llm microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: tgi version: 0.8.0 diff --git a/helm-charts/common/llm-uservice/README.md b/helm-charts/common/llm-uservice/README.md index 2c094fd4..191b1efd 100644 --- a/helm-charts/common/llm-uservice/README.md +++ b/helm-charts/common/llm-uservice/README.md @@ -46,10 +46,10 @@ curl http://localhost:9000/v1/chat/completions \ ## Values -| Key | Type | Default | Description | -| ------------------------------- | ------ | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| 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 | -| image.repository | string | `"opea/llm-tgi:latest"` | | -| service.port | string | `"9000"` | | -| TGI_LLM_ENDPOINT | string | `""` | LLM endpoint | +| Key | Type | Default | Description | +| ------------------------------- | ------ | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| 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 | +| image.repository | string | `"opea/llm-tgi"` | | +| service.port | string | `"9000"` | | +| TGI_LLM_ENDPOINT | string | `""` | LLM endpoint | diff --git a/helm-charts/common/llm-uservice/templates/configmap.yaml b/helm-charts/common/llm-uservice/templates/configmap.yaml index ee71c78c..7a823702 100644 --- a/helm-charts/common/llm-uservice/templates/configmap.yaml +++ b/helm-charts/common/llm-uservice/templates/configmap.yaml @@ -17,7 +17,11 @@ data: HF_HOME: "/tmp/.cache/huggingface" http_proxy: {{ .Values.global.http_proxy | quote }} https_proxy: {{ .Values.global.https_proxy | quote }} + {{- if and (not .Values.TGI_LLM_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy) }} + no_proxy: "{{ .Release.Name }}-tgi,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} LANGCHAIN_TRACING_V2: {{ .Values.global.LANGCHAIN_TRACING_V2 | quote }} LANGCHAIN_API_KEY: {{ .Values.global.LANGCHAIN_API_KEY }} LANGCHAIN_PROJECT: "opea-llm-uservice" diff --git a/helm-charts/common/llm-uservice/templates/deployment.yaml b/helm-charts/common/llm-uservice/templates/deployment.yaml index f53adc37..c1dea43e 100644 --- a/helm-charts/common/llm-uservice/templates/deployment.yaml +++ b/helm-charts/common/llm-uservice/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: llm-uservice diff --git a/helm-charts/common/llm-uservice/templates/tests/test-pod.yaml b/helm-charts/common/llm-uservice/templates/tests/test-pod.yaml index 6c859080..61826201 100644 --- a/helm-charts/common/llm-uservice/templates/tests/test-pod.yaml +++ b/helm-charts/common/llm-uservice/templates/tests/test-pod.yaml @@ -13,21 +13,26 @@ 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: - | + max_retry=20; + for ((i=1; i<=max_retry; i++)); do {{- if contains "llm-docsum-tgi" .Values.image.repository }} # Try with docsum endpoint curl http://{{ include "llm-uservice.fullname" . }}:{{ .Values.service.port }}/v1/chat/docsum -sS --fail-with-body \ -X POST \ -d '{"query":"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."}' \ - -H 'Content-Type: application/json' + -H 'Content-Type: application/json' && break; {{- else }} curl http://{{ include "llm-uservice.fullname" . }}:{{ .Values.service.port }}/v1/chat/completions -sS --fail-with-body \ -X POST \ -d '{"query":"What is Deep Learning?","max_new_tokens":17,"top_k":10,"top_p":0.95,"typical_p":0.95,"temperature":0.01,"repetition_penalty":1.03,"streaming":true}' \ - -H 'Content-Type: application/json' + -H 'Content-Type: application/json' && break; {{- end }} + 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 diff --git a/helm-charts/common/llm-uservice/values.yaml b/helm-charts/common/llm-uservice/values.yaml index c57269c8..75972694 100644 --- a/helm-charts/common/llm-uservice/values.yaml +++ b/helm-charts/common/llm-uservice/values.yaml @@ -12,10 +12,10 @@ replicaCount: 1 TGI_LLM_ENDPOINT: "" image: - repository: opea/llm-tgi:latest + repository: opea/llm-tgi pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/reranking-usvc/Chart.yaml b/helm-charts/common/reranking-usvc/Chart.yaml index 5366255f..9d58bf5b 100644 --- a/helm-charts/common/reranking-usvc/Chart.yaml +++ b/helm-charts/common/reranking-usvc/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying reranking as microservice type: application version: 0.8.0 # The reranking microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: teirerank version: 0.8.0 diff --git a/helm-charts/common/reranking-usvc/README.md b/helm-charts/common/reranking-usvc/README.md index 491bc544..7476be9a 100644 --- a/helm-charts/common/reranking-usvc/README.md +++ b/helm-charts/common/reranking-usvc/README.md @@ -44,8 +44,8 @@ curl http://localhost:8000/v1/reranking \ ## Values -| Key | Type | Default | Description | -| ---------------------- | ------ | ----------------------------- | ----------- | -| image.repository | string | `"opea/reranking-tgi:latest"` | | -| TEI_RERANKING_ENDPOINT | string | `""` | | -| service.port | string | `"8000"` | | +| Key | Type | Default | Description | +| ---------------------- | ------ | ---------------------- | ----------- | +| image.repository | string | `"opea/reranking-tgi"` | | +| TEI_RERANKING_ENDPOINT | string | `""` | | +| service.port | string | `"8000"` | | diff --git a/helm-charts/common/reranking-usvc/templates/configmap.yaml b/helm-charts/common/reranking-usvc/templates/configmap.yaml index 74453b36..c805ba09 100644 --- a/helm-charts/common/reranking-usvc/templates/configmap.yaml +++ b/helm-charts/common/reranking-usvc/templates/configmap.yaml @@ -15,7 +15,11 @@ data: {{- end }} http_proxy: {{ .Values.global.http_proxy | quote }} https_proxy: {{ .Values.global.https_proxy | quote }} + {{- if and (not .Values.TEI_RERANKING_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy) }} + no_proxy: "{{ .Release.Name }}-teirerank,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} LANGCHAIN_TRACING_V2: {{ .Values.global.LANGCHAIN_TRACING_V2 | quote }} LANGCHAIN_API_KEY: {{ .Values.global.LANGCHAIN_API_KEY | quote }} LANGCHAIN_PROJECT: "opea-reranking-service" diff --git a/helm-charts/common/reranking-usvc/templates/deployment.yaml b/helm-charts/common/reranking-usvc/templates/deployment.yaml index 5a2089d0..9fc05bc0 100644 --- a/helm-charts/common/reranking-usvc/templates/deployment.yaml +++ b/helm-charts/common/reranking-usvc/templates/deployment.yaml @@ -39,8 +39,8 @@ spec: {{- end }} securityContext: {{- toYaml .Values.securityContext | nindent 12 }} - image: "{{ .Values.image.repository }}" - imagePullPolicy: IfNotPresent + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" + imagePullPolicy: {{ .Values.image.pullPolicy }} ports: - name: reranking-usvc containerPort: 8000 diff --git a/helm-charts/common/reranking-usvc/templates/tests/test-pod.yaml b/helm-charts/common/reranking-usvc/templates/tests/test-pod.yaml index b9f92e0c..4bd7ac74 100644 --- a/helm-charts/common/reranking-usvc/templates/tests/test-pod.yaml +++ b/helm-charts/common/reranking-usvc/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 http://{{ include "reranking-usvc.fullname" . }}:{{ .Values.service.port }}/v1/reranking -sS --fail-with-body \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl http://{{ include "reranking-usvc.fullname" . }}:{{ .Values.service.port }}/v1/reranking -sS --fail-with-body \ -X POST \ -d '{"initial_query":"What is Deep Learning?", "retrieved_docs": [{"text":"Deep Learning is not..."}, {"text":"Deep learning is..."}]}' \ - -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 diff --git a/helm-charts/common/reranking-usvc/values.yaml b/helm-charts/common/reranking-usvc/values.yaml index 7f73fe63..c011cf30 100644 --- a/helm-charts/common/reranking-usvc/values.yaml +++ b/helm-charts/common/reranking-usvc/values.yaml @@ -12,10 +12,10 @@ replicaCount: 1 TEI_RERANKING_ENDPOINT: "" image: - repository: opea/reranking-tei:latest + repository: opea/reranking-tei pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - #tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/retriever-usvc/Chart.yaml b/helm-charts/common/retriever-usvc/Chart.yaml index 8a3cd7d9..f2334b4b 100644 --- a/helm-charts/common/retriever-usvc/Chart.yaml +++ b/helm-charts/common/retriever-usvc/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying retriever as microservice type: application version: 0.8.0 # The retriever microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: tei version: 0.8.0 diff --git a/helm-charts/common/retriever-usvc/README.md b/helm-charts/common/retriever-usvc/README.md index 79672982..e2bcedf5 100644 --- a/helm-charts/common/retriever-usvc/README.md +++ b/helm-charts/common/retriever-usvc/README.md @@ -46,9 +46,9 @@ curl http://localhost:7000/v1/retrieval \ ## Values -| Key | Type | Default | Description | -| ---------------------- | ------ | ----------------------------- | ----------- | -| image.repository | string | `"opea/retriever-tgi:latest"` | | -| service.port | string | `"7000"` | | -| REDIS_URL | string | `""` | | -| TEI_EMBEDDING_ENDPOINT | string | `""` | | +| Key | Type | Default | Description | +| ---------------------- | ------ | ---------------------- | ----------- | +| image.repository | string | `"opea/retriever-tgi"` | | +| service.port | string | `"7000"` | | +| REDIS_URL | string | `""` | | +| TEI_EMBEDDING_ENDPOINT | string | `""` | | diff --git a/helm-charts/common/retriever-usvc/templates/configmap.yaml b/helm-charts/common/retriever-usvc/templates/configmap.yaml index 8ee9c9fc..5412be2a 100644 --- a/helm-charts/common/retriever-usvc/templates/configmap.yaml +++ b/helm-charts/common/retriever-usvc/templates/configmap.yaml @@ -23,7 +23,11 @@ data: EASYOCR_MODULE_PATH: "/tmp/.EasyOCR" http_proxy: {{ .Values.global.http_proxy | quote }} https_proxy: {{ .Values.global.https_proxy | quote }} + {{- if and (not .Values.REDIS_URL) (and (not .Values.TEI_EMBEDDING_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy)) }} + no_proxy: "{{ .Release.Name }}-tei,{{ .Release.Name }}-redis-vector-db,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} LANGCHAIN_TRACING_V2: {{ .Values.global.LANGCHAIN_TRACING_V2 | quote }} LANGCHAIN_API_KEY: {{ .Values.global.LANGCHAIN_API_KEY | quote }} LANGCHAIN_PROJECT: "opea-retriever-service" diff --git a/helm-charts/common/retriever-usvc/templates/deployment.yaml b/helm-charts/common/retriever-usvc/templates/deployment.yaml index 63813dd0..ef31dbf0 100644 --- a/helm-charts/common/retriever-usvc/templates/deployment.yaml +++ b/helm-charts/common/retriever-usvc/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: retriever-usvc diff --git a/helm-charts/common/retriever-usvc/templates/tests/test-pod.yaml b/helm-charts/common/retriever-usvc/templates/tests/test-pod.yaml index 0514b280..3de01889 100644 --- a/helm-charts/common/retriever-usvc/templates/tests/test-pod.yaml +++ b/helm-charts/common/retriever-usvc/templates/tests/test-pod.yaml @@ -13,7 +13,6 @@ metadata: spec: containers: - name: curl - #image: alpine/curl image: python:3.10.14 command: ['bash', '-c'] args: @@ -25,7 +24,8 @@ spec: -X POST \ -d "{\"text\":\"What is the revenue of Nike in 2023?\",\"embedding\":${your_embedding}}" \ -H 'Content-Type: application/json' && break; - sleep 10; + 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 "retriever test failed."; exit 1; fi + if [ $i -gt $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi restartPolicy: Never diff --git a/helm-charts/common/retriever-usvc/values.yaml b/helm-charts/common/retriever-usvc/values.yaml index 36826c9c..8eabeb73 100644 --- a/helm-charts/common/retriever-usvc/values.yaml +++ b/helm-charts/common/retriever-usvc/values.yaml @@ -17,10 +17,10 @@ REDIS_URL: "" INDEX_NAME: "rag-redis" image: - repository: opea/retriever-redis:latest + repository: opea/retriever-redis pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/speecht5/Chart.yaml b/helm-charts/common/speecht5/Chart.yaml index 918c18f3..25172bdf 100644 --- a/helm-charts/common/speecht5/Chart.yaml +++ b/helm-charts/common/speecht5/Chart.yaml @@ -7,4 +7,4 @@ description: The Helm chart for deploying speecht5 as microservice type: application version: 0.8.0 # The speecht5 microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" diff --git a/helm-charts/common/speecht5/README.md b/helm-charts/common/speecht5/README.md index ffc1864c..0a8b7116 100644 --- a/helm-charts/common/speecht5/README.md +++ b/helm-charts/common/speecht5/README.md @@ -25,7 +25,7 @@ curl http://localhost:1234/v1/tts \ ## Values -| Key | Type | Default | Description | -| ---------------- | ------ | ------------------------ | ----------- | -| image.repository | string | `"opea/speecht5:latest"` | | -| service.port | string | `"7055"` | | +| Key | Type | Default | Description | +| ---------------- | ------ | ----------------- | ----------- | +| image.repository | string | `"opea/speecht5"` | | +| service.port | string | `"7055"` | | diff --git a/helm-charts/common/speecht5/gaudi-values.yaml b/helm-charts/common/speecht5/gaudi-values.yaml index d1818f20..a56c8232 100644 --- a/helm-charts/common/speecht5/gaudi-values.yaml +++ b/helm-charts/common/speecht5/gaudi-values.yaml @@ -6,8 +6,8 @@ # Declare variables to be passed into your templates. image: - repository: opea/speecht5-gaudi:latest - # tag: "1.0" + repository: opea/speecht5-gaudi + tag: "" resources: limits: diff --git a/helm-charts/common/speecht5/templates/deployment.yaml b/helm-charts/common/speecht5/templates/deployment.yaml index 29b94e31..f29013ea 100644 --- a/helm-charts/common/speecht5/templates/deployment.yaml +++ b/helm-charts/common/speecht5/templates/deployment.yaml @@ -43,7 +43,7 @@ spec: {{- else }} {{- toYaml .Values.securityContext | nindent 12 }} {{- end }} - image: "{{ .Values.image.repository }}" + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} ports: - name: speecht5 diff --git a/helm-charts/common/speecht5/templates/tests/test-pod.yaml b/helm-charts/common/speecht5/templates/tests/test-pod.yaml index 550f78b9..fd86ea9a 100644 --- a/helm-charts/common/speecht5/templates/tests/test-pod.yaml +++ b/helm-charts/common/speecht5/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 "speecht5.fullname" . }}:{{ .Values.service.port }}/v1/tts \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl -sS --fail-with-body http://{{ include "speecht5.fullname" . }}:{{ .Values.service.port }}/v1/tts \ -X POST \ -d '{"text": "Who are you?"}' \ - -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 diff --git a/helm-charts/common/speecht5/values.yaml b/helm-charts/common/speecht5/values.yaml index f2ca34c5..2d217ddb 100644 --- a/helm-charts/common/speecht5/values.yaml +++ b/helm-charts/common/speecht5/values.yaml @@ -11,10 +11,10 @@ TTS_MODEL_PATH: "microsoft/speecht5_tts" #VOCODE_MODEL: "microsoft/speecht5_hifigan" image: - repository: opea/speecht5:latest + repository: opea/speecht5 pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/tei/Chart.yaml b/helm-charts/common/tei/Chart.yaml index 45b3cb73..f2494dc9 100644 --- a/helm-charts/common/tei/Chart.yaml +++ b/helm-charts/common/tei/Chart.yaml @@ -7,4 +7,4 @@ description: The Helm chart for HuggingFace Text Embedding Inference Server type: application version: 0.8.0 # The HF TEI version -appVersion: "1.2" +appVersion: "cpu-1.5" diff --git a/helm-charts/common/tei/README.md b/helm-charts/common/tei/README.md index a218a9af..14d647f4 100644 --- a/helm-charts/common/tei/README.md +++ b/helm-charts/common/tei/README.md @@ -40,4 +40,4 @@ curl http://localhost:2081/embed -X POST -d '{"inputs":"What is Deep Learning?"} | EMBEDDING_MODEL_ID | string | `"BAAI/bge-base-en-v1.5"` | Models id from https://huggingface.co/, or predownloaded model directory | | global.modelUseHostPath | string | `"/mnt/opea-models"` | Cached models directory, tei will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory. Set this to null/empty will force it to download model. | | image.repository | string | `"ghcr.io/huggingface/text-embeddings-inference"` | | -| image.tag | string | `"cpu-1.2"` | | +| image.tag | string | `"cpu-1.5"` | | diff --git a/helm-charts/common/tei/templates/deployment.yaml b/helm-charts/common/tei/templates/deployment.yaml index f3f72a0a..38122632 100644 --- a/helm-charts/common/tei/templates/deployment.yaml +++ b/helm-charts/common/tei/templates/deployment.yaml @@ -45,6 +45,8 @@ spec: {{- end }} image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/helm-charts/common/tei/templates/tests/test-pod.yaml b/helm-charts/common/tei/templates/tests/test-pod.yaml index 185c2d36..700469be 100644 --- a/helm-charts/common/tei/templates/tests/test-pod.yaml +++ b/helm-charts/common/tei/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 http://{{ include "tei.fullname" . }}/embed -sS --fail-with-body \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl http://{{ include "tei.fullname" . }}/embed -sS --fail-with-body \ -X POST \ -d '{"inputs":"What is Deep Learning?"}' \ - -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 diff --git a/helm-charts/common/tei/values.yaml b/helm-charts/common/tei/values.yaml index 66de346d..54545d80 100644 --- a/helm-charts/common/tei/values.yaml +++ b/helm-charts/common/tei/values.yaml @@ -14,7 +14,7 @@ image: repository: ghcr.io/huggingface/text-embeddings-inference pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - tag: "cpu-1.2" + tag: "cpu-1.5" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/teirerank/Chart.yaml b/helm-charts/common/teirerank/Chart.yaml index 2ce22f50..5a28094f 100644 --- a/helm-charts/common/teirerank/Chart.yaml +++ b/helm-charts/common/teirerank/Chart.yaml @@ -7,4 +7,4 @@ description: The Helm chart for HuggingFace Text Embedding Inference Server type: application version: 0.8.0 # The HF TEI version -appVersion: "1.2" +appVersion: "cpu-1.5" diff --git a/helm-charts/common/teirerank/README.md b/helm-charts/common/teirerank/README.md index 0cf86c75..b3cb2f19 100644 --- a/helm-charts/common/teirerank/README.md +++ b/helm-charts/common/teirerank/README.md @@ -43,4 +43,4 @@ curl http://localhost:2082/rerank \ | RERANK_MODEL_ID | string | `"BAAI/bge-reranker-base"` | Models id from https://huggingface.co/, or predownloaded model directory | | global.modelUseHostPath | string | `"/mnt/opea-models"` | Cached models directory, teirerank will not download if the model is cached here. The host path "modelUseHostPath" will be mounted to container as /data directory. Set this to null/empty will force it to download model. | | image.repository | string | `"ghcr.io/huggingface/text-embeddings-inference"` | | -| image.tag | string | `"cpu-1.2"` | | +| image.tag | string | `"cpu-1.5"` | | diff --git a/helm-charts/common/teirerank/templates/deployment.yaml b/helm-charts/common/teirerank/templates/deployment.yaml index 1bbb87f3..ff2c84a8 100644 --- a/helm-charts/common/teirerank/templates/deployment.yaml +++ b/helm-charts/common/teirerank/templates/deployment.yaml @@ -45,6 +45,8 @@ spec: {{- end }} image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/helm-charts/common/teirerank/templates/tests/test-pod.yaml b/helm-charts/common/teirerank/templates/tests/test-pod.yaml index a160de26..225fe2f5 100644 --- a/helm-charts/common/teirerank/templates/tests/test-pod.yaml +++ b/helm-charts/common/teirerank/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 http://{{ include "teirerank.fullname" . }}/rerank -sS --fail-with-body \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl http://{{ include "teirerank.fullname" . }}/rerank -sS --fail-with-body \ -X POST \ -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' -H 'Content-Type: application/json' \ - -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 $max_retry ]; then echo "test failed with maximum retry"; exit 1; fi restartPolicy: Never diff --git a/helm-charts/common/teirerank/values.yaml b/helm-charts/common/teirerank/values.yaml index 73383973..b0062f1b 100644 --- a/helm-charts/common/teirerank/values.yaml +++ b/helm-charts/common/teirerank/values.yaml @@ -14,7 +14,7 @@ image: repository: ghcr.io/huggingface/text-embeddings-inference pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - tag: "cpu-1.2" + tag: "cpu-1.5" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/tgi/templates/tests/test-pod.yaml b/helm-charts/common/tgi/templates/tests/test-pod.yaml index a4f32782..948f2386 100644 --- a/helm-charts/common/tgi/templates/tests/test-pod.yaml +++ b/helm-charts/common/tgi/templates/tests/test-pod.yaml @@ -13,13 +13,18 @@ metadata: spec: containers: - name: curl - image: alpine/curl - #image: python:3.10.14 - command: ['sh', '-c'] + image: python:3.10.14 + command: ['bash', '-c'] args: - | - curl http://{{ include "tgi.fullname" . }}/generate -sS --fail-with-body \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl http://{{ include "tgi.fullname" . }}/generate -sS --fail-with-body \ -X POST \ -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \ - -H 'Content-Type: application/json' + -H 'Content-Type: application/json' && break; + curlcode=$? + 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 diff --git a/helm-charts/common/tts/Chart.yaml b/helm-charts/common/tts/Chart.yaml index 4a67a6e3..1706459b 100644 --- a/helm-charts/common/tts/Chart.yaml +++ b/helm-charts/common/tts/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying tts as microservice type: application version: 0.8.0 # The tts microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: speecht5 diff --git a/helm-charts/common/tts/README.md b/helm-charts/common/tts/README.md index dd01e2e7..42c0c40f 100644 --- a/helm-charts/common/tts/README.md +++ b/helm-charts/common/tts/README.md @@ -44,8 +44,8 @@ curl http://localhost:9088/v1/audio/speech \ ## Values -| Key | Type | Default | Description | -| ---------------- | ------ | ------------------- | ----------- | -| image.repository | string | `"opea/tts:latest"` | | -| service.port | string | `"9088"` | | -| TTS_ENDPOINT | string | `""` | | +| Key | Type | Default | Description | +| ---------------- | ------ | ------------ | ----------- | +| image.repository | string | `"opea/tts"` | | +| service.port | string | `"9088"` | | +| TTS_ENDPOINT | string | `""` | | diff --git a/helm-charts/common/tts/templates/configmap.yaml b/helm-charts/common/tts/templates/configmap.yaml index da9379c8..5afcee74 100644 --- a/helm-charts/common/tts/templates/configmap.yaml +++ b/helm-charts/common/tts/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.TTS_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy) }} + no_proxy: "{{ .Release.Name }}-speecht5,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} diff --git a/helm-charts/common/tts/templates/deployment.yaml b/helm-charts/common/tts/templates/deployment.yaml index b1799499..ca7f9b36 100644 --- a/helm-charts/common/tts/templates/deployment.yaml +++ b/helm-charts/common/tts/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: tts diff --git a/helm-charts/common/tts/templates/tests/test-pod.yaml b/helm-charts/common/tts/templates/tests/test-pod.yaml index 25161e50..26fcbcca 100644 --- a/helm-charts/common/tts/templates/tests/test-pod.yaml +++ b/helm-charts/common/tts/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 "tts.fullname" . }}:{{ .Values.service.port }}/v1/audio/speech \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl -sS --fail-with-body http://{{ include "tts.fullname" . }}:{{ .Values.service.port }}/v1/audio/speech \ -XPOST \ -d '{"text": "Who are you?"}' \ - -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 diff --git a/helm-charts/common/tts/values.yaml b/helm-charts/common/tts/values.yaml index e78d8d2a..56f5792c 100644 --- a/helm-charts/common/tts/values.yaml +++ b/helm-charts/common/tts/values.yaml @@ -13,10 +13,10 @@ replicaCount: 1 TTS_ENDPOINT: "" image: - repository: opea/tts:latest + repository: opea/tts pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/web-retriever/Chart.yaml b/helm-charts/common/web-retriever/Chart.yaml index 8650a983..f50b7080 100644 --- a/helm-charts/common/web-retriever/Chart.yaml +++ b/helm-charts/common/web-retriever/Chart.yaml @@ -7,7 +7,7 @@ description: The Helm chart for deploying web retriever as microservice type: application version: 0.8.0 # The web retriever microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" dependencies: - name: tei version: 0.8.0 diff --git a/helm-charts/common/web-retriever/README.md b/helm-charts/common/web-retriever/README.md index a8b2b93b..6b4f21b1 100644 --- a/helm-charts/common/web-retriever/README.md +++ b/helm-charts/common/web-retriever/README.md @@ -49,10 +49,10 @@ curl http://localhost:7077/v1/web_retrieval \ ## Values -| Key | Type | Default | Description | -| ---------------------- | ------ | ------------------------------------ | ----------- | -| image.repository | string | `"opea/web-retriever-chroma:latest"` | | -| service.port | string | `"7077"` | | -| TEI_EMBEDDING_ENDPOINT | string | `""` | | -| GOOGLE_API_KEY | string | `""` | | -| GOOGLE_CSE_ID | string | `""` | | +| Key | Type | Default | Description | +| ---------------------- | ------ | ----------------------------- | ----------- | +| image.repository | string | `"opea/web-retriever-chroma"` | | +| service.port | string | `"7077"` | | +| TEI_EMBEDDING_ENDPOINT | string | `""` | | +| GOOGLE_API_KEY | string | `""` | | +| GOOGLE_CSE_ID | string | `""` | | diff --git a/helm-charts/common/web-retriever/templates/configmap.yaml b/helm-charts/common/web-retriever/templates/configmap.yaml index 5a5a98b4..4b2d94d8 100644 --- a/helm-charts/common/web-retriever/templates/configmap.yaml +++ b/helm-charts/common/web-retriever/templates/configmap.yaml @@ -18,5 +18,9 @@ data: EASYOCR_MODULE_PATH: "/tmp/.EasyOCR" http_proxy: {{ .Values.global.http_proxy | quote }} https_proxy: {{ .Values.global.https_proxy | quote }} + {{- if and (not .Values.TEI_EMBEDDING_ENDPOINT) (or .Values.global.http_proxy .Values.global.https_proxy) }} + no_proxy: "{{ .Release.Name }}-tei,{{ .Values.global.no_proxy }}" + {{- else }} no_proxy: {{ .Values.global.no_proxy | quote }} + {{- end }} HF_HOME: "/tmp/.cache/huggingface" diff --git a/helm-charts/common/web-retriever/templates/deployment.yaml b/helm-charts/common/web-retriever/templates/deployment.yaml index 2d23707d..cfb3e696 100644 --- a/helm-charts/common/web-retriever/templates/deployment.yaml +++ b/helm-charts/common/web-retriever/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: web-retriever diff --git a/helm-charts/common/web-retriever/templates/tests/test-pod.yaml b/helm-charts/common/web-retriever/templates/tests/test-pod.yaml index c4e6a5f5..a1c0a3aa 100644 --- a/helm-charts/common/web-retriever/templates/tests/test-pod.yaml +++ b/helm-charts/common/web-retriever/templates/tests/test-pod.yaml @@ -13,14 +13,19 @@ metadata: spec: containers: - name: curl - #image: alpine/curl image: python:3.10.14 - command: ['sh', '-c'] + command: ['bash', '-c'] args: - | your_embedding=$(python -c "import random; embedding = [random.uniform(-1, 1) for _ in range(768)]; print(embedding)"); - curl -sS --fail-with-body http://{{ include "web-retriever.fullname" . }}:{{ .Values.service.port }}/v1/web_retrieval \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl -sS --fail-with-body http://{{ include "web-retriever.fullname" . }}:{{ .Values.service.port }}/v1/web_retrieval \ -X POST \ -d "{\"text\":\"What is OPEA?\",\"embedding\":${your_embedding}}" \ - -H 'Content-Type: application/json' + -H 'Content-Type: application/json' && break; + curlcode=$? + 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 diff --git a/helm-charts/common/web-retriever/values.yaml b/helm-charts/common/web-retriever/values.yaml index e142fdff..156eb0db 100644 --- a/helm-charts/common/web-retriever/values.yaml +++ b/helm-charts/common/web-retriever/values.yaml @@ -15,10 +15,10 @@ GOOGLE_API_KEY: "" GOOGLE_CSE_ID: "" image: - repository: opea/web-retriever-chroma:latest + repository: opea/web-retriever-chroma pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/common/whisper/Chart.yaml b/helm-charts/common/whisper/Chart.yaml index cd5f9cae..b4955f18 100644 --- a/helm-charts/common/whisper/Chart.yaml +++ b/helm-charts/common/whisper/Chart.yaml @@ -7,4 +7,4 @@ description: The Helm chart for deploying whisper as microservice type: application version: 0.8.0 # The whisper microservice server version -appVersion: "1.0.0" +appVersion: "v0.8" diff --git a/helm-charts/common/whisper/README.md b/helm-charts/common/whisper/README.md index e6c85426..6c121551 100644 --- a/helm-charts/common/whisper/README.md +++ b/helm-charts/common/whisper/README.md @@ -26,7 +26,7 @@ curl http://localhost:1234/v1/asr \ ## Values -| Key | Type | Default | Description | -| ---------------- | ------ | ----------------------- | ----------- | -| image.repository | string | `"opea/whisper:latest"` | | -| service.port | string | `"7066"` | | +| Key | Type | Default | Description | +| ---------------- | ------ | ---------------- | ----------- | +| image.repository | string | `"opea/whisper"` | | +| service.port | string | `"7066"` | | diff --git a/helm-charts/common/whisper/gaudi-values.yaml b/helm-charts/common/whisper/gaudi-values.yaml index 4dfc6298..781e99c8 100644 --- a/helm-charts/common/whisper/gaudi-values.yaml +++ b/helm-charts/common/whisper/gaudi-values.yaml @@ -6,8 +6,8 @@ # Declare variables to be passed into your templates. image: - repository: opea/whisper-gaudi:latest - # tag: "1.0" + repository: opea/whisper-gaudi + tag: "" resources: limits: diff --git a/helm-charts/common/whisper/templates/deployment.yaml b/helm-charts/common/whisper/templates/deployment.yaml index c7582408..d766c62d 100644 --- a/helm-charts/common/whisper/templates/deployment.yaml +++ b/helm-charts/common/whisper/templates/deployment.yaml @@ -43,7 +43,7 @@ spec: {{- else }} {{- toYaml .Values.securityContext | nindent 12 }} {{- end }} - image: "{{ .Values.image.repository }}" + image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}" imagePullPolicy: {{ .Values.image.pullPolicy }} ports: - name: whisper diff --git a/helm-charts/common/whisper/templates/tests/test-pod.yaml b/helm-charts/common/whisper/templates/tests/test-pod.yaml index acb45ea3..9d6b1de5 100644 --- a/helm-charts/common/whisper/templates/tests/test-pod.yaml +++ b/helm-charts/common/whisper/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 "whisper.fullname" . }}:{{ .Values.service.port }}/v1/asr \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl -sS --fail-with-body http://{{ include "whisper.fullname" . }}:{{ .Values.service.port }}/v1/asr \ -X POST \ -d '{"audio": "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 diff --git a/helm-charts/common/whisper/values.yaml b/helm-charts/common/whisper/values.yaml index 5fe8b6fd..9a7bb6fb 100644 --- a/helm-charts/common/whisper/values.yaml +++ b/helm-charts/common/whisper/values.yaml @@ -10,10 +10,10 @@ replicaCount: 1 ASR_MODEL_PATH: "openai/whisper-small" image: - repository: opea/whisper:latest + repository: opea/whisper pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" imagePullSecrets: [] nameOverride: "" diff --git a/helm-charts/docsum/Chart.yaml b/helm-charts/docsum/Chart.yaml index eaef0bb9..2350f089 100644 --- a/helm-charts/docsum/Chart.yaml +++ b/helm-charts/docsum/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" diff --git a/helm-charts/docsum/README.md b/helm-charts/docsum/README.md index 109b98f5..9e80f8f9 100644 --- a/helm-charts/docsum/README.md +++ b/helm-charts/docsum/README.md @@ -38,7 +38,7 @@ curl http://localhost:8888/v1/docsum \ | Key | Type | Default | Description | | ------------------------------- | ------ | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| image.repository | string | `"opea/docsum:latest"` | | +| image.repository | string | `"opea/docsum"` | | | 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 | diff --git a/helm-charts/docsum/templates/deployment.yaml b/helm-charts/docsum/templates/deployment.yaml index 1b56ad77..950b67a8 100644 --- a/helm-charts/docsum/templates/deployment.yaml +++ b/helm-charts/docsum/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 diff --git a/helm-charts/docsum/templates/tests/test-pod.yaml b/helm-charts/docsum/templates/tests/test-pod.yaml index 00e8a1bd..b60fc962 100644 --- a/helm-charts/docsum/templates/tests/test-pod.yaml +++ b/helm-charts/docsum/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 "docsum.fullname" . }}:{{ .Values.service.port }}/v1/docsum -sS --fail-with-body \ + max_retry=20; + for ((i=1; i<=max_retry; i++)); do + curl http://{{ include "docsum.fullname" . }}:{{ .Values.service.port }}/v1/docsum -sS --fail-with-body \ -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."}' + -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."}' && 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 diff --git a/helm-charts/docsum/values.yaml b/helm-charts/docsum/values.yaml index a590a2da..99bf2cf5 100644 --- a/helm-charts/docsum/values.yaml +++ b/helm-charts/docsum/values.yaml @@ -9,10 +9,10 @@ replicaCount: 1 LLM_SERVICE_HOST_IP: "" image: - repository: opea/docsum:latest + repository: opea/docsum pullPolicy: IfNotPresent # Overrides the image tag whose default is the chart appVersion. - # tag: "1.0" + tag: "" port: 8888 service: @@ -30,16 +30,15 @@ securityContext: seccompProfile: type: RuntimeDefault -# To override values in subchart llm-uservice -llm-uservice: - image: - repository: opea/llm-docsum-tgi:latest - service: - port: 9000 +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: "" diff --git a/helm-charts/update_manifests.sh b/helm-charts/update_manifests.sh index 0d846b9a..8ff57c38 100755 --- a/helm-charts/update_manifests.sh +++ b/helm-charts/update_manifests.sh @@ -13,11 +13,20 @@ function generate_yaml { chart=$1 outputdir=$2 - helm template $chart ./common/$chart --skip-tests --values ./common/$chart/values.yaml --set global.extraEnvConfig=extra-env-config,noProbe=true > ${outputdir}/$chart.yaml + local extraparams="" + if [[ $(grep -c 'tag: ""' ./common/$chart/values.yaml) != 0 ]]; then + extraparams="--set image.tag=latest" + fi + + helm template $chart ./common/$chart --skip-tests --values ./common/$chart/values.yaml --set global.extraEnvConfig=extra-env-config,noProbe=true $extraparams > ${outputdir}/$chart.yaml for f in `ls ./common/$chart/*-values.yaml 2>/dev/null `; do ext=$(basename $f | cut -d'-' -f1) - helm template $chart ./common/$chart --skip-tests --values ${f} --set global.extraEnvConfig=extra-env-config,noProbe=true > ${outputdir}/${chart}_${ext}.yaml + extraparams="" + if [[ $(grep -c 'tag: ""' $f) != 0 ]]; then + extraparams="--set image.tag=latest" + fi + helm template $chart ./common/$chart --skip-tests --values ${f} --set global.extraEnvConfig=extra-env-config,noProbe=true $extraparams > ${outputdir}/${chart}_${ext}.yaml done } @@ -33,4 +42,4 @@ done # we need special version of docsum-llm-uservice echo "Update manifest for docsum-llm-uservice..." -helm template docsum ./common/llm-uservice --skip-tests --set global.extraEnvConfig=extra-env-config,noProbe=true,image.repository=opea/llm-docsum-tgi:latest > ${OUTPUTDIR}/docsum-llm-uservice.yaml +helm template docsum ./common/llm-uservice --skip-tests --set global.extraEnvConfig=extra-env-config,noProbe=true,image.repository=opea/llm-docsum-tgi,image.tag=latest> ${OUTPUTDIR}/docsum-llm-uservice.yaml diff --git a/microservices-connector/config/manifests/asr.yaml b/microservices-connector/config/manifests/asr.yaml index b2105a8a..5619868b 100644 --- a/microservices-connector/config/manifests/asr.yaml +++ b/microservices-connector/config/manifests/asr.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: asr-0.8.0 app.kubernetes.io/name: asr app.kubernetes.io/instance: asr - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: ASR_ENDPOINT: "http://asr-whisper:7066" @@ -31,7 +31,7 @@ metadata: helm.sh/chart: asr-0.8.0 app.kubernetes.io/name: asr app.kubernetes.io/instance: asr - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -56,7 +56,7 @@ metadata: helm.sh/chart: asr-0.8.0 app.kubernetes.io/name: asr app.kubernetes.io/instance: asr - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/manifests/common/ui.yaml b/microservices-connector/config/manifests/chatqna-ui.yaml similarity index 79% rename from manifests/common/ui.yaml rename to microservices-connector/config/manifests/chatqna-ui.yaml index e482a026..01a5c854 100644 --- a/manifests/common/ui.yaml +++ b/microservices-connector/config/manifests/chatqna-ui.yaml @@ -6,12 +6,12 @@ apiVersion: v1 kind: ConfigMap metadata: - name: ui-config + name: chatqna-ui-config labels: helm.sh/chart: ui-0.8.0 app.kubernetes.io/name: ui - app.kubernetes.io/instance: ui - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/instance: chatqna-ui + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: http_proxy: "" @@ -32,12 +32,12 @@ data: apiVersion: v1 kind: Service metadata: - name: ui + name: chatqna-ui labels: helm.sh/chart: ui-0.8.0 app.kubernetes.io/name: ui - app.kubernetes.io/instance: ui - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/instance: chatqna-ui + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -48,7 +48,7 @@ spec: name: ui selector: app.kubernetes.io/name: ui - app.kubernetes.io/instance: ui + app.kubernetes.io/instance: chatqna-ui --- # Source: ui/templates/deployment.yaml # Copyright (C) 2024 Intel Corporation @@ -57,26 +57,26 @@ spec: apiVersion: apps/v1 kind: Deployment metadata: - name: ui + name: chatqna-ui labels: helm.sh/chart: ui-0.8.0 app.kubernetes.io/name: ui - app.kubernetes.io/instance: ui - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/instance: chatqna-ui + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 selector: matchLabels: app.kubernetes.io/name: ui - app.kubernetes.io/instance: ui + app.kubernetes.io/instance: chatqna-ui template: metadata: labels: helm.sh/chart: ui-0.8.0 app.kubernetes.io/name: ui - app.kubernetes.io/instance: ui - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/instance: chatqna-ui + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: securityContext: @@ -85,7 +85,7 @@ spec: - name: ui envFrom: - configMapRef: - name: ui-config + name: chatqna-ui-config - configMapRef: name: extra-env-config optional: true diff --git a/microservices-connector/config/manifests/data-prep.yaml b/microservices-connector/config/manifests/data-prep.yaml index bf5a2d39..7212b675 100644 --- a/microservices-connector/config/manifests/data-prep.yaml +++ b/microservices-connector/config/manifests/data-prep.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: data-prep-0.8.0 app.kubernetes.io/name: data-prep app.kubernetes.io/instance: data-prep - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TEI_ENDPOINT: "http://data-prep-tei" @@ -39,7 +39,7 @@ metadata: helm.sh/chart: data-prep-0.8.0 app.kubernetes.io/name: data-prep app.kubernetes.io/instance: data-prep - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -72,7 +72,7 @@ metadata: helm.sh/chart: data-prep-0.8.0 app.kubernetes.io/name: data-prep app.kubernetes.io/instance: data-prep - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/docsum-llm-uservice.yaml b/microservices-connector/config/manifests/docsum-llm-uservice.yaml index bf9ee68f..61b5acc8 100644 --- a/microservices-connector/config/manifests/docsum-llm-uservice.yaml +++ b/microservices-connector/config/manifests/docsum-llm-uservice.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: llm-uservice-0.8.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: docsum - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TGI_LLM_ENDPOINT: "http://docsum-tgi" @@ -36,7 +36,7 @@ metadata: helm.sh/chart: llm-uservice-0.8.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: docsum - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -61,7 +61,7 @@ metadata: helm.sh/chart: llm-uservice-0.8.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: docsum - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/embedding-usvc.yaml b/microservices-connector/config/manifests/embedding-usvc.yaml index ec7110a4..da8036a1 100644 --- a/microservices-connector/config/manifests/embedding-usvc.yaml +++ b/microservices-connector/config/manifests/embedding-usvc.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: embedding-usvc-0.8.0 app.kubernetes.io/name: embedding-usvc app.kubernetes.io/instance: embedding-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TEI_EMBEDDING_ENDPOINT: "http://embedding-usvc-tei" @@ -34,7 +34,7 @@ metadata: helm.sh/chart: embedding-usvc-0.8.0 app.kubernetes.io/name: embedding-usvc app.kubernetes.io/instance: embedding-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -59,7 +59,7 @@ metadata: helm.sh/chart: embedding-usvc-0.8.0 app.kubernetes.io/name: embedding-usvc app.kubernetes.io/instance: embedding-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/llm-uservice.yaml b/microservices-connector/config/manifests/llm-uservice.yaml index e53033fe..7f35b7fe 100644 --- a/microservices-connector/config/manifests/llm-uservice.yaml +++ b/microservices-connector/config/manifests/llm-uservice.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: llm-uservice-0.8.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: llm-uservice - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TGI_LLM_ENDPOINT: "http://llm-uservice-tgi" @@ -36,7 +36,7 @@ metadata: helm.sh/chart: llm-uservice-0.8.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: llm-uservice - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -61,7 +61,7 @@ metadata: helm.sh/chart: llm-uservice-0.8.0 app.kubernetes.io/name: llm-uservice app.kubernetes.io/instance: llm-uservice - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/reranking-usvc.yaml b/microservices-connector/config/manifests/reranking-usvc.yaml index 6b473369..6f386bf7 100644 --- a/microservices-connector/config/manifests/reranking-usvc.yaml +++ b/microservices-connector/config/manifests/reranking-usvc.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: reranking-usvc-0.8.0 app.kubernetes.io/name: reranking-usvc app.kubernetes.io/instance: reranking-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TEI_RERANKING_ENDPOINT: "http://reranking-usvc-teirerank" @@ -34,7 +34,7 @@ metadata: helm.sh/chart: reranking-usvc-0.8.0 app.kubernetes.io/name: reranking-usvc app.kubernetes.io/instance: reranking-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -59,7 +59,7 @@ metadata: helm.sh/chart: reranking-usvc-0.8.0 app.kubernetes.io/name: reranking-usvc app.kubernetes.io/instance: reranking-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/retriever-usvc.yaml b/microservices-connector/config/manifests/retriever-usvc.yaml index a977bd60..f9d8ce16 100644 --- a/microservices-connector/config/manifests/retriever-usvc.yaml +++ b/microservices-connector/config/manifests/retriever-usvc.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: retriever-usvc-0.8.0 app.kubernetes.io/name: retriever-usvc app.kubernetes.io/instance: retriever-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TEI_EMBEDDING_ENDPOINT: "http://retriever-usvc-tei" @@ -39,7 +39,7 @@ metadata: helm.sh/chart: retriever-usvc-0.8.0 app.kubernetes.io/name: retriever-usvc app.kubernetes.io/instance: retriever-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -64,7 +64,7 @@ metadata: helm.sh/chart: retriever-usvc-0.8.0 app.kubernetes.io/name: retriever-usvc app.kubernetes.io/instance: retriever-usvc - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/speecht5.yaml b/microservices-connector/config/manifests/speecht5.yaml index a40b1e7b..2ae7af9d 100644 --- a/microservices-connector/config/manifests/speecht5.yaml +++ b/microservices-connector/config/manifests/speecht5.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: speecht5-0.8.0 app.kubernetes.io/name: speecht5 app.kubernetes.io/instance: speecht5 - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: EASYOCR_MODULE_PATH: "/tmp/.EasyOCR" @@ -34,7 +34,7 @@ metadata: helm.sh/chart: speecht5-0.8.0 app.kubernetes.io/name: speecht5 app.kubernetes.io/instance: speecht5 - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -59,7 +59,7 @@ metadata: helm.sh/chart: speecht5-0.8.0 app.kubernetes.io/name: speecht5 app.kubernetes.io/instance: speecht5 - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/speecht5_gaudi.yaml b/microservices-connector/config/manifests/speecht5_gaudi.yaml index 0e25c779..f01604cb 100644 --- a/microservices-connector/config/manifests/speecht5_gaudi.yaml +++ b/microservices-connector/config/manifests/speecht5_gaudi.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: speecht5-0.8.0 app.kubernetes.io/name: speecht5 app.kubernetes.io/instance: speecht5 - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: EASYOCR_MODULE_PATH: "/tmp/.EasyOCR" @@ -34,7 +34,7 @@ metadata: helm.sh/chart: speecht5-0.8.0 app.kubernetes.io/name: speecht5 app.kubernetes.io/instance: speecht5 - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -59,7 +59,7 @@ metadata: helm.sh/chart: speecht5-0.8.0 app.kubernetes.io/name: speecht5 app.kubernetes.io/instance: speecht5 - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/tei.yaml b/microservices-connector/config/manifests/tei.yaml index fcb52f2e..9a76b5ff 100644 --- a/microservices-connector/config/manifests/tei.yaml +++ b/microservices-connector/config/manifests/tei.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "BAAI/bge-base-en-v1.5" @@ -36,7 +36,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -61,7 +61,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: replicas: 1 @@ -87,8 +87,10 @@ spec: optional: true securityContext: {} - image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.2" + image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.5" imagePullPolicy: IfNotPresent + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/microservices-connector/config/manifests/tei_gaudi.yaml b/microservices-connector/config/manifests/tei_gaudi.yaml index 4ac593ce..75626b79 100644 --- a/microservices-connector/config/manifests/tei_gaudi.yaml +++ b/microservices-connector/config/manifests/tei_gaudi.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "BAAI/bge-base-en-v1.5" @@ -36,7 +36,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -61,7 +61,7 @@ metadata: helm.sh/chart: tei-0.8.0 app.kubernetes.io/name: tei app.kubernetes.io/instance: tei - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: replicas: 1 @@ -89,6 +89,8 @@ spec: {} image: "ghcr.io/huggingface/tei-gaudi:synapse_1.16" imagePullPolicy: IfNotPresent + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/microservices-connector/config/manifests/teirerank.yaml b/microservices-connector/config/manifests/teirerank.yaml index 46836586..4991e6e0 100644 --- a/microservices-connector/config/manifests/teirerank.yaml +++ b/microservices-connector/config/manifests/teirerank.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: teirerank-0.8.0 app.kubernetes.io/name: teirerank app.kubernetes.io/instance: teirerank - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm data: MODEL_ID: "BAAI/bge-reranker-base" @@ -35,7 +35,7 @@ metadata: helm.sh/chart: teirerank-0.8.0 app.kubernetes.io/name: teirerank app.kubernetes.io/instance: teirerank - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -60,7 +60,7 @@ metadata: helm.sh/chart: teirerank-0.8.0 app.kubernetes.io/name: teirerank app.kubernetes.io/instance: teirerank - app.kubernetes.io/version: "1.2" + app.kubernetes.io/version: "cpu-1.5" app.kubernetes.io/managed-by: Helm spec: replicas: 1 @@ -86,8 +86,10 @@ spec: optional: true securityContext: {} - image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.2" + image: "ghcr.io/huggingface/text-embeddings-inference:cpu-1.5" imagePullPolicy: IfNotPresent + args: + - "--auto-truncate" volumeMounts: - mountPath: /data name: model-volume diff --git a/microservices-connector/config/manifests/tts.yaml b/microservices-connector/config/manifests/tts.yaml index 55c12a9b..d25eb74c 100644 --- a/microservices-connector/config/manifests/tts.yaml +++ b/microservices-connector/config/manifests/tts.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: tts-0.8.0 app.kubernetes.io/name: tts app.kubernetes.io/instance: tts - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TTS_ENDPOINT: "http://tts-speecht5:7055" @@ -31,7 +31,7 @@ metadata: helm.sh/chart: tts-0.8.0 app.kubernetes.io/name: tts app.kubernetes.io/instance: tts - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -56,7 +56,7 @@ metadata: helm.sh/chart: tts-0.8.0 app.kubernetes.io/name: tts app.kubernetes.io/instance: tts - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/web-retriever.yaml b/microservices-connector/config/manifests/web-retriever.yaml index 1ef96d94..975182f5 100644 --- a/microservices-connector/config/manifests/web-retriever.yaml +++ b/microservices-connector/config/manifests/web-retriever.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: web-retriever-0.8.0 app.kubernetes.io/name: web-retriever app.kubernetes.io/instance: web-retriever - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: TEI_EMBEDDING_ENDPOINT: "http://web-retriever-tei" @@ -35,7 +35,7 @@ metadata: helm.sh/chart: web-retriever-0.8.0 app.kubernetes.io/name: web-retriever app.kubernetes.io/instance: web-retriever - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -60,7 +60,7 @@ metadata: helm.sh/chart: web-retriever-0.8.0 app.kubernetes.io/name: web-retriever app.kubernetes.io/instance: web-retriever - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/whisper.yaml b/microservices-connector/config/manifests/whisper.yaml index 7d89d843..85335e93 100644 --- a/microservices-connector/config/manifests/whisper.yaml +++ b/microservices-connector/config/manifests/whisper.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: whisper-0.8.0 app.kubernetes.io/name: whisper app.kubernetes.io/instance: whisper - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: EASYOCR_MODULE_PATH: "/tmp/.EasyOCR" @@ -34,7 +34,7 @@ metadata: helm.sh/chart: whisper-0.8.0 app.kubernetes.io/name: whisper app.kubernetes.io/instance: whisper - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -59,7 +59,7 @@ metadata: helm.sh/chart: whisper-0.8.0 app.kubernetes.io/name: whisper app.kubernetes.io/instance: whisper - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1 diff --git a/microservices-connector/config/manifests/whisper_gaudi.yaml b/microservices-connector/config/manifests/whisper_gaudi.yaml index 1fcdd1b2..7741d2b3 100644 --- a/microservices-connector/config/manifests/whisper_gaudi.yaml +++ b/microservices-connector/config/manifests/whisper_gaudi.yaml @@ -11,7 +11,7 @@ metadata: helm.sh/chart: whisper-0.8.0 app.kubernetes.io/name: whisper app.kubernetes.io/instance: whisper - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm data: EASYOCR_MODULE_PATH: "/tmp/.EasyOCR" @@ -34,7 +34,7 @@ metadata: helm.sh/chart: whisper-0.8.0 app.kubernetes.io/name: whisper app.kubernetes.io/instance: whisper - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: type: ClusterIP @@ -59,7 +59,7 @@ metadata: helm.sh/chart: whisper-0.8.0 app.kubernetes.io/name: whisper app.kubernetes.io/instance: whisper - app.kubernetes.io/version: "1.0.0" + app.kubernetes.io/version: "v0.8" app.kubernetes.io/managed-by: Helm spec: replicas: 1