added repo

2026-08-26 03:39:42 +05:30
parent 45c25a95af
commit b8575bb8b9
6889 changed files with 1217125 additions and 0 deletions
@@ -0,0 +1,68 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ .Values.engine.namePrefix }}-config
+  labels:
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+    {{- range $key, $val := .Values.engine.additionalLabels }}
+    {{ $key }}: {{ $val | quote }}
+    {{- end}}
+data:
+  engine.toml: |
+    {{- if .Values.engine.concurrencyLimit.activeRequests }}
+    max_active_requests = {{ .Values.engine.concurrencyLimit.activeRequests }}
+    {{- end }}
+
+    [license]
+      server_url = [
+        {{- if .Values.licenseProxy.enabled }}
+        "https://{{ .Values.licenseProxy.namePrefix }}-internal:{{ .Values.licenseProxy.server.port}}{{ .Values.licenseProxy.server.baseUrl }}"
+        {{- end }}
+        {{- if or (not .Values.licenseProxy.enabled) .Values.licenseProxy.keepUpstreamServerAsBackup }}
+        {{- if .Values.licenseProxy.enabled -}},{{- end -}}"https://license.deepgram.com"
+        {{- end }}
+      ]
+
+    [server]
+      host = "{{ .Values.engine.server.host }}"
+      port = {{ .Values.engine.server.port }}
+
+    [metrics_server]
+      host = "{{ .Values.engine.metricsServer.host }}"
+      port = {{ .Values.engine.metricsServer.port }}
+
+    [model_manager]
+      search_paths = [
+        "/models
+        {{- if .Values.engine.modelManager.volumes.customVolumeClaim.enabled -}}
+          {{- if not (regexMatch `^\/` .Values.engine.modelManager.volumes.customVolumeClaim.modelsDirectory) -}}
+          /
+          {{- end -}}
+        {{- .Values.engine.modelManager.volumes.customVolumeClaim.modelsDirectory -}}
+        {{- end -}}"
+      ]
+
+    [features]
+      multichannel = true
+      language_detection = true
+
+    [chunking.batch]
+      {{- if .Values.engine.chunking.speechToText.batch.minDuration }}
+      min_duration = {{ .Values.engine.chunking.speechToText.batch.minDuration }}
+      {{- end }}
+      {{- if .Values.engine.chunking.speechToText.batch.maxDuration }}
+      max_duration = {{ .Values.engine.chunking.speechToText.batch.maxDuration }}
+      {{- end }}
+
+    [chunking.streaming]
+      {{- if .Values.engine.chunking.speechToText.streaming.minDuration }}
+      min_duration = {{ .Values.engine.chunking.speechToText.streaming.minDuration }}
+      {{- end }}
+      {{- if .Values.engine.chunking.speechToText.streaming.maxDuration }}
+      max_duration = {{ .Values.engine.chunking.speechToText.streaming.maxDuration }}
+      {{- end }}
+      step = {{ .Values.engine.chunking.speechToText.streaming.step }}
+
+    [half_precision]
+      state = "{{ .Values.engine.halfPrecision.state }}"
+
@@ -0,0 +1,144 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ .Values.engine.namePrefix }}
+  labels: &labels
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+    app: deepgram-engine
+    {{- range $key, $val := .Values.engine.additionalLabels }}
+    {{ $key }}: {{ $val | quote }}
+    {{- end}}
+  {{- with .Values.engine.additionalAnnotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  selector:
+    matchLabels:
+      app: deepgram-engine
+      {{ include "deepgram-self-hosted.selectorLabels" . }}
+  {{- if not .Values.engineAutoscaling.enabled }}
+  replicas: {{ .Values.scaling.replicas.engine }}
+  {{- end }}
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: {{ .Values.engine.updateStrategy.rollingUpdate.maxUnavailable }}
+      maxSurge: {{ .Values.engine.updateStrategy.rollingUpdate.maxSurge }}
+  template:
+    metadata:
+      labels: *labels
+      annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/engine/engine.config.yaml") . | sha256sum }}
+    spec:
+      nodeSelector:
+        {{- toYaml .Values.engine.nodeSelector | nindent 8 }}
+      terminationGracePeriodSeconds: {{ .Values.global.outstandingRequestGracePeriod }}
+      {{- if .Values.global.pullSecretRef }}
+      imagePullSecrets:
+      - name: {{ .Values.global.pullSecretRef }}
+      {{- end }}
+      affinity:
+        {{- toYaml .Values.engine.affinity | nindent 8 }}
+      tolerations:
+        {{- toYaml .Values.engine.tolerations | nindent 8 }}
+      securityContext:
+        {{- toYaml .Values.licenseProxy.securityContext | nindent 8 }}
+      {{- if or .Values.engine.serviceAccount.create .Values.engine.serviceAccount.name }}
+      serviceAccountName: {{ default (printf "%s-sa" .Values.engine.namePrefix) .Values.engine.serviceAccount.name }}
+      {{- end }}
+      containers:
+      - name: {{ .Values.engine.namePrefix }}
+        image: {{ .Values.engine.image.path }}:{{ .Values.engine.image.tag }}
+        imagePullPolicy: {{ .Values.engine.image.pullPolicy }}
+        envFrom:
+        - secretRef:
+            name: {{ required "Missing Deepgram self-hosted API key - see `global.deepgramSecretRef`" .Values.global.deepgramSecretRef }}
+        {{- if le (int .Values.engine.resources.requests.gpu) 0 }}
+        env:
+        - name: NVIDIA_VISIBLE_DEVICES
+          value: "void"
+        {{- end }}
+        command: [ "impeller" ]
+        args: ["-v", "serve", "/etc/config/engine.toml"]
+        resources:
+          requests:
+            memory: "{{ .Values.engine.resources.requests.memory }}"
+            cpu: "{{ .Values.engine.resources.requests.cpu }}"
+            {{- if gt (int .Values.engine.resources.requests.gpu) 0 }}
+            nvidia.com/gpu: {{ .Values.engine.resources.requests.gpu }}
+            {{- end }}
+          limits:
+            memory: "{{ .Values.engine.resources.limits.memory }}"
+            cpu: "{{ .Values.engine.resources.limits.cpu }}"
+            {{- if gt (int .Values.engine.resources.limits.gpu) 0 }}
+            nvidia.com/gpu: {{ .Values.engine.resources.limits.gpu }}
+            {{- end }}
+        volumeMounts:
+        - name: engine-config-volume
+          mountPath: /etc/config
+        - name: models-volume
+          mountPath: /models
+        ports:
+        - name: primary
+          containerPort: {{ .Values.engine.server.port }}
+        - name: metrics
+          containerPort: {{ .Values.engine.metricsServer.port }}
+        startupProbe:
+          tcpSocket:
+            port: {{ .Values.engine.server.port }}
+          periodSeconds: {{ .Values.engine.startupProbe.periodSeconds }}
+          failureThreshold: {{ .Values.engine.startupProbe.failureThreshold }}
+        livenessProbe:
+          tcpSocket:
+            port: {{ .Values.engine.server.port }}
+          initialDelaySeconds: {{ .Values.engine.livenessProbe.initialDelaySeconds }}
+          periodSeconds: {{ .Values.engine.livenessProbe.periodSeconds }}
+          failureThreshold: {{ .Values.engine.livenessProbe.failureThreshold }}
+        readinessProbe:
+          tcpSocket:
+            port: {{ .Values.engine.server.port }}
+          initialDelaySeconds: {{ .Values.engine.readinessProbe.initialDelaySeconds }}
+          periodSeconds: {{ .Values.engine.readinessProbe.periodSeconds }}
+          failureThreshold: {{ .Values.engine.readinessProbe.failureThreshold }}
+        {{- if .Values.engine.lifecycle }}
+        lifecycle:
+          {{- toYaml .Values.engine.lifecycle | nindent 10 }}
+        {{- end }}
+      volumes:
+      - name: engine-config-volume
+        configMap:
+          name: {{ .Values.engine.namePrefix }}-config
+      - name: models-volume
+        persistentVolumeClaim:
+          {{- $customClaimEnabled := .Values.engine.modelManager.volumes.customVolumeClaim.enabled }}
+          {{- $customClaimName := .Values.engine.modelManager.volumes.customVolumeClaim.name }}
+          {{- $awsEfsEnabled := .Values.engine.modelManager.volumes.aws.efs.enabled }}
+          {{- $gcpGpdEnabled := .Values.engine.modelManager.volumes.gcp.gpd.enabled }}
+          {{- $nova3Enabled  := .Values.engine.modelManager.volumes.nova3.enabled }}
+          {{- $nova3MultilingualEnabled  := .Values.engine.modelManager.volumes.nova3.multilingual.enabled }}
+
+          {{- $enabledCount := (int $customClaimEnabled) | add (int $awsEfsEnabled) | add (int $gcpGpdEnabled) }}
+ 
+          {{- if eq $enabledCount 0 }}
+          {{- fail "Error: At least one of customVolumeClaim.enabled, aws.efs.enabled, or gcp.gpd.enabled must be set to true." }}
+          {{- else if gt $enabledCount 1 }}
+          {{- fail "Error: Only one of customVolumeClaim.enabled, aws.efs.enabled, or gcp.gpd.enabled can be set to true." }}
+          {{- end }}
+ 
+          {{- if $customClaimEnabled }}
+            {{- if not $customClaimName }}
+            {{- fail "Error: customVolumeClaim.name must be set when customVolumeClaim.enabled is true." }}
+            {{- else }}
+          claimName: {{ $customClaimName }}
+            {{- end }}
+          {{- else if $awsEfsEnabled }}
+          claimName: {{ .Values.engine.modelManager.volumes.aws.efs.namePrefix }}-aws-efs-pvc
+          {{- else if and $gcpGpdEnabled $nova3Enabled }}
+          claimName: {{ .Values.engine.modelManager.volumes.gcp.gpd.namePrefix }}-gcp-gpd-pvc-nova3
+          {{- else if and $gcpGpdEnabled $nova3MultilingualEnabled }}
+          claimName: {{ .Values.engine.modelManager.volumes.gcp.gpd.namePrefix }}-gcp-gpd-pvc-nova3-multilingual
+          {{- else }}
+          claimName: {{ .Values.engine.modelManager.volumes.gcp.gpd.namePrefix }}-gcp-gpd-pvc-v1
+          {{- end }}
+
@@ -0,0 +1,73 @@
+{{- if .Values.scaling.auto.enabled -}}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ .Values.engine.namePrefix }}-hpa
+  labels: &labels
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+    {{- range $key, $val := .Values.engine.additionalLabels }}
+    {{ $key }}: {{ $val | quote }}
+    {{- end}}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ .Values.engine.namePrefix }}
+  minReplicas: {{ .Values.scaling.auto.engine.minReplicas }}
+  maxReplicas: {{ .Values.scaling.auto.engine.maxReplicas }}
+  metrics:
+    {{- $sttBatchScaling        := .Values.scaling.auto.engine.metrics.speechToText.batch.requestsPerPod }}
+    {{- $sttStreamingScaling    := .Values.scaling.auto.engine.metrics.speechToText.streaming.requestsPerPod }}
+    {{- $ttsBatchScaling        := .Values.scaling.auto.engine.metrics.textToSpeech.batch.requestsPerPod }}
+    {{- $requestCapacityScaling := .Values.scaling.auto.engine.metrics.requestCapacityRatio }}
+    {{- $customScaling          := .Values.scaling.auto.engine.metrics.custom }}
+
+    {{- if and (not $sttBatchScaling) (not $sttStreamingScaling) (not $ttsBatchScaling) (not $requestCapacityScaling) (not $customScaling) }}
+    {{- fail "Error: When autoscaling is enabled, at least one scaling metric in scaling.auto.engine.metrics must be defined." }}
+    {{- end }}
+
+    {{- if .Values.scaling.auto.engine.metrics.speechToText.batch.requestsPerPod }}
+    - type: External
+      external:
+        metric:
+          name: engine_active_requests_stt_batch
+        target:
+          type: Value
+          value: {{ .Values.scaling.auto.engine.metrics.speechToText.batch.requestsPerPod }}
+    {{- end }}
+    {{- if .Values.scaling.auto.engine.metrics.speechToText.streaming.requestsPerPod }}
+    - type: External
+      external:
+        metric:
+          name: engine_active_requests_stt_streaming
+        target:
+          type: Value
+          value: {{ .Values.scaling.auto.engine.metrics.speechToText.streaming.requestsPerPod }}
+    {{- end }}
+    {{- if .Values.scaling.auto.engine.metrics.textToSpeech.batch.requestsPerPod }}
+    - type: External
+      external:
+        metric:
+          name: engine_active_requests_tts_batch
+        target:
+          type: Value
+          value: {{ .Values.scaling.auto.engine.metrics.textToSpeech.batch.requestsPerPod }}
+    {{- end }}
+    {{- if .Values.scaling.auto.engine.metrics.requestCapacityRatio }}
+    {{- if not .Values.engine.concurrencyLimit.activeRequests }}
+    {{- fail "Error: engine.concurrencyLimit.activeRequests must be set to autoscale using requestCapacityRatio." }}
+    {{- end }}
+    - type: External
+      external:
+        metric:
+          name: engine_requests_active_to_max_ratio
+        target:
+          type: Value
+          value: {{ .Values.scaling.auto.engine.metrics.requestCapacityRatio }}
+    {{- end }}
+    {{- if .Values.scaling.auto.engine.metrics.custom }}
+    {{- toYaml .Values.scaling.auto.engine.metrics.custom | nindent 4 }}
+    {{- end }}
+  behavior:
+    {{- toYaml .Values.scaling.auto.engine.behavior | nindent 4 }}
+{{- end -}}
@@ -0,0 +1,49 @@
+{{- if .Values.engine.serviceAccount.create }}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ default (printf "%s-sa" .Values.engine.namePrefix) .Values.engine.serviceAccount.name }}
+  labels:
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: {{ .Values.engine.namePrefix }}-role
+  labels:
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+rules:
+  - apiGroups: [""]
+    resources: ["configmaps"]
+    resourceNames: ["{{ .Values.engine.namePrefix }}-config"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["secrets"]
+    resourceNames: ["{{ .Values.global.pullSecretRef }}", "{{ .Values.global.deepgramSecretRef }}"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["services"]
+    resourceNames: [{{- if .Values.licenseProxy.enabled -}}"{{ .Values.licenseProxy.namePrefix }}-internal"{{- end -}}]
+    verbs: ["get"]
+  - apiGroups: [""]
+    resources: ["persistentvolumeclaims"]
+    resourceNames: ["{{ .Values.engine.modelManager.volumes.customVolumeClaim.name }}", "{{ .Values.engine.modelManager.volumes.aws.efs.namePrefix }}-aws-efs-pvc", "{{ .Values.engine.modelManager.volumes.gcp.gpd.namePrefix }}-gcp-gpd-pvc" ]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["nvidia.com"]
+    resources: ["*"]
+    verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: {{ .Values.engine.namePrefix }}-rolebinding
+  labels:
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+subjects:
+  - kind: ServiceAccount
+    name: {{ default (printf "%s-sa" .Values.engine.namePrefix) .Values.engine.serviceAccount.name }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: {{ .Values.engine.namePrefix }}-role
+{{- end }}
@@ -0,0 +1,55 @@
+{{- if .Values.engineAutoscaling.enabled }}
+apiVersion: keda.sh/v1alpha1
+kind: ScaledObject
+metadata:
+  labels: &labels
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+  namespace: {{ .Values.engineAutoscaling.namespace }}
+  name: deepgram-engine-hpa
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ .Values.engineAutoscaling.targetName }}
+  pollingInterval:  {{ .Values.engineAutoscaling.pollingInterval }}
+  {{- if ( default false (.Values.disasterRecovery).enabled ) }}
+  minReplicaCount: 1
+  {{- else }}
+  minReplicaCount:  {{ .Values.engineAutoscaling.minReplicas }}
+  {{- end }}
+  maxReplicaCount:  {{ .Values.engineAutoscaling.maxReplicas }}
+  advanced:
+    horizontalPodAutoscalerConfig:
+      behavior:
+        scaleDown:
+          stabilizationWindowSeconds: {{ .Values.engineAutoscaling.scaledown.stabilizationWindowSeconds }}
+          policies:
+          {{- range .Values.engineAutoscaling.scaledown.policies }}
+          - type: {{ .type }}
+            value: {{ .value }}
+            periodSeconds: {{ .periodseconds }}
+          {{- end }}
+          selectPolicy: {{ .Values.engineAutoscaling.scaledown.selectpolicy }}
+        scaleUp: 
+          stabilizationWindowSeconds: {{ .Values.engineAutoscaling.scaleup.stabilizationWindowSeconds }}
+          policies:
+          {{- range .Values.engineAutoscaling.scaleup.policies }}
+          - type: {{ .type }}
+            value: {{ .value }}
+            periodSeconds: {{ .periodseconds }}
+          {{- end }}
+          selectPolicy: {{ .Values.engineAutoscaling.scaleup.selectpolicy }}
+  triggers:
+  {{- if ( default false (.Values.disasterRecovery).enabled ) }}
+  {{- range $.Values.engineAutoscaling.triggers }}
+    {{- if or  (eq .type "cpu") (eq .type "memory") }}
+    - metadata:
+      {{- toYaml .metadata | nindent 8 }} 
+      type: {{ .type }}
+      metricType: "Utilization"
+    {{- end }}
+  {{- end }}
+  {{- else }}
+  {{- toYaml .Values.engineAutoscaling.triggers | nindent 2 }}
+  {{ end }}
+{{- end }}
@@ -0,0 +1,38 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ .Values.engine.namePrefix }}-metrics
+  labels:
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+    {{- range $key, $val := .Values.engine.additionalLabels }}
+    {{ $key }}: {{ $val | quote }}
+    {{- end}}
+spec:
+  selector:
+    app: deepgram-engine
+    {{ include "deepgram-self-hosted.selectorLabels" . }}
+  ports:
+    - name: "metrics"
+      port: {{ .Values.engine.metricsServer.port }}
+      targetPort: {{ .Values.engine.metricsServer.port }}
+
+---
+
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ .Values.engine.namePrefix }}-internal
+  labels:
+{{ include "deepgram-self-hosted.labels" . | indent 4}}
+    {{- range $key, $val := .Values.engine.additionalLabels }}
+    {{ $key }}: {{ $val | quote }}
+    {{- end}}
+spec:
+  selector:
+    app: deepgram-engine
+    {{ include "deepgram-self-hosted.selectorLabels" . }}
+  ports:
+    - name: "primary"
+      port: {{ .Values.engine.server.port }}
+      targetPort: {{ .Values.engine.server.port }}
+