helm: Add audioQnA e2e helm chart (#510)

Signed-off-by: Lianhao Lu <[email protected]>
opea-project · Nov 4, 2024 · 9efacee · 9efacee
1 parent b077d44
commit 9efacee
Show file tree

Hide file tree

Showing 12 changed files with 514 additions and 0 deletions.
diff --git a/helm-charts/audioqna/.helmignore b/helm-charts/audioqna/.helmignore
@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/
diff --git a/helm-charts/audioqna/Chart.yaml b/helm-charts/audioqna/Chart.yaml
@@ -0,0 +1,33 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: v2
+name: audioqna
+description: The Helm chart to deploy AudioQnA
+type: application
+dependencies:
+  - name: asr
+    version: 1.0.0
+    repository: "file://../common/asr"
+  - name: whisper
+    version: 1.0.0
+    repository: "file://../common/whisper"
+  - name: tts
+    version: 1.0.0
+    repository: "file://../common/tts"
+  - name: speecht5
+    version: 1.0.0
+    repository: "file://../common/speecht5"
+  - name: tgi
+    version: 1.0.0
+    repository: "file://../common/tgi"
+  - name: llm-uservice
+    version: 1.0.0
+    repository: "file://../common/llm-uservice"
+# Uncomment the following to enable UI when the UI image is ready on DockerHub
+# - name: ui
+#  version: 1.0.0
+#  repository: "file://../common/ui"
+#  alias: audioqna-ui
+version: 1.1.0
+appVersion: "1.1"
diff --git a/helm-charts/audioqna/README.md b/helm-charts/audioqna/README.md
@@ -0,0 +1,60 @@
+# AudioQnA
+
+Helm chart for deploying AudioQnA service.
+
+AudioQnA depends on the following micro services:
+
+- [asr](../common/asr/README.md)
+- [whisper](../common/whisper/README.md)
+- [llm-uservice](../common/llm-uservice/README.md)
+- [tgi](../common/tgi/README.md)
+- [tts](../common/tts/README.md)
+- [speecht5](../common/speecht5/README.md)
+
+## Installing the Chart
+
+To install the chart, run the following:
+
+```console
+cd GenAIInfra/helm-charts/
+./update_dependency.sh
+helm dependency update audioqna
+export HFTOKEN="insert-your-huggingface-token-here"
+export MODELDIR="/mnt/opea-models"
+export MODELNAME="Intel/neural-chat-7b-v3-3"
+# To run on Xeon
+helm install audioqna audioqna --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} --set global.modelUseHostPath=${MODELDIR} --set tgi.LLM_MODEL_ID=${MODELNAME}
+# To run on Gaudi
+#helm install audioqna audioqna --set global.HUGGINGFACEHUB_API_TOKEN=${HFTOKEN} --set global.modelUseHostPath=${MODELDIR} --set tgi.LLM_MODEL_ID=${MODELNAME} -f audioqna/gaudi-values.yaml
+```
+
+### IMPORTANT NOTE
+
+1. Make sure your `MODELDIR` exists on the node where your workload is schedueled so you can cache the downloaded model for next time use. Otherwise, set `global.modelUseHostPath` to 'null' if you don't want to cache the model.
+
+## Verify
+
+To verify the installation, run the command `kubectl get pod` to make sure all pods are running.
+
+Test the AudioQnA megaservice by recording a .wav file, encoding the file into the base64 format, and then sending the base64 string to the megaservice endpoint. The megaservice will return a spoken response as a base64 string. To listen to the response, decode the base64 string and save it as a .wav file.
+
+### Verify the workload through curl command
+
+Then run the command `kubectl port-forward svc/audioqna 3008:3008` to expose the service for access.
+
+Open another terminal and run the following command to verify the service if working:
+
+```console
+curl http://localhost:3008/v1/audioqna \
+  -X POST \
+  -d '{"audio": "UklGRigAAABXQVZFZm10IBIAAAABAAEARKwAAIhYAQACABAAAABkYXRhAgAAAAEA", "max_tokens":64}' \
+  -H 'Content-Type: application/json' | sed 's/^"//;s/"$//' | base64 -d > output.wav
+```
+
+## Values
+
+| Key              | Type   | Default                     | Description                                                              |
+| ---------------- | ------ | --------------------------- | ------------------------------------------------------------------------ |
+| image.repository | string | `"opea/audioqna"`           |                                                                          |
+| service.port     | string | `"3008"`                    |                                                                          |
+| tgi.LLM_MODEL_ID | string | `Intel/neural-chat-7b-v3-3` | Models id from https://huggingface.co/, or predownloaded model directory |
diff --git a/helm-charts/audioqna/ci-gaudi-values.yaml b/helm-charts/audioqna/ci-gaudi-values.yaml
@@ -0,0 +1 @@
+gaudi-values.yaml
diff --git a/helm-charts/audioqna/ci-values.yaml b/helm-charts/audioqna/ci-values.yaml
@@ -0,0 +1 @@
+values.yaml
diff --git a/helm-charts/audioqna/gaudi-values.yaml b/helm-charts/audioqna/gaudi-values.yaml
@@ -0,0 +1,43 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+tgi:
+  accelDevice: "gaudi"
+  image:
+    repository: ghcr.io/huggingface/tgi-gaudi
+    tag: "2.0.5"
+  resources:
+    limits:
+      habana.ai/gaudi: 1
+  MAX_INPUT_LENGTH: "1024"
+  MAX_TOTAL_TOKENS: "2048"
+  CUDA_GRAPHS: ""
+  livenessProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+  readinessProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+  startupProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120
+
+whisper:
+  image:
+    repository: opea/whisper-gaudi
+    tag: "latest"
+  resources:
+    limits:
+      habana.ai/gaudi: 1
+
+speecht5:
+  image:
+    repository: opea/speecht5-gaudi
+    tag: "latest"
+  resources:
+    limits:
+      habana.ai/gaudi: 1
diff --git a/helm-charts/audioqna/templates/_helpers.tpl b/helm-charts/audioqna/templates/_helpers.tpl
@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "audioqna.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "audioqna.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "audioqna.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "audioqna.labels" -}}
+helm.sh/chart: {{ include "audioqna.chart" . }}
+{{ include "audioqna.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "audioqna.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "audioqna.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "audioqna.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "audioqna.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
diff --git a/helm-charts/audioqna/templates/deployment.yaml b/helm-charts/audioqna/templates/deployment.yaml
@@ -0,0 +1,85 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "audioqna.fullname" . }}
+  labels:
+    {{- include "audioqna.labels" . | nindent 4 }}
+    app: {{ include "audioqna.fullname" . }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "audioqna.selectorLabels" . | nindent 6 }}
+      app: {{ include "audioqna.fullname" . }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "audioqna.selectorLabels" . | nindent 8 }}
+        app: {{ include "audioqna.fullname" . }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Release.Name }}
+          env:
+            - name: LLM_SERVICE_HOST_IP
+              value: {{ include "llm-uservice.fullname" (index .Subcharts "llm-uservice") }}
+            - name: LLM_SERVICE_PORT
+              value: {{ index .Values "llm-uservice" "service" "port" | quote }}
+            - name: ASR_SERVICE_HOST_IP
+              value: {{ include "asr.fullname" (index .Subcharts "asr") }}
+            - name: ASR_SERVICE_PORT
+              value: {{ index .Values "asr" "service" "port" | quote }}
+            - name: TTS_SERVICE_HOST_IP
+              value: {{ include "tts.fullname" (index .Subcharts "tts") }}
+            - name: TTS_SERVICE_PORT
+              value: {{ index .Values "tts" "service" "port" | quote }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          volumeMounts:
+            - mountPath: /tmp
+              name: tmp
+          ports:
+            - name: audioqna
+              containerPort: {{ .Values.port }}
+              protocol: TCP
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      volumes:
+        - name: tmp
+          emptyDir: {}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- if .Values.evenly_distributed }}
+      topologySpreadConstraints:
+        - maxSkew: 1
+          topologyKey: kubernetes.io/hostname
+          whenUnsatisfiable: ScheduleAnyway
+          labelSelector:
+            matchLabels:
+              {{- include "audioqna.selectorLabels" . | nindent 14 }}
+              app: {{ include "audioqna.fullname" . }}
+      {{- end }}