fleet-memory/helm/hindsight/templates/api-deployment.yaml
Byeonghoon Yoo cefa75545a
feat(helm): add persistent volume for local model cache (#861)
* feat(helm): add persistent volume for local model cache

When using local reranker (e.g., BAAI/bge-reranker-v2-m3) or local
embedding models, the models are downloaded to /home/hindsight/.cache
on every pod restart, causing slow startup and unnecessary bandwidth.

Add optional persistent volume support:
- api: PVC mounted at /home/hindsight/.cache
- worker: volumeClaimTemplate (StatefulSet) at same path

Disabled by default. Enable via:
  api.persistence.modelCache.enabled: true
  worker.persistence.modelCache.enabled: true

Closes #860

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* feat(helm): add extraVolumes and extraVolumeMounts for api and worker

Allow users to mount arbitrary volumes (configMaps, secrets, emptyDir,
etc.) into api and worker pods via values, following common helm chart
library conventions.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-07 09:14:09 +02:00

131 lines
4.9 KiB
YAML

{{- if .Values.api.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "hindsight.fullname" . }}-api
labels:
{{- include "hindsight.api.labels" . | nindent 4 }}
spec:
{{- if not .Values.autoscaling.enabled }}
replicas: {{ .Values.api.replicaCount }}
{{- end }}
selector:
matchLabels:
{{- include "hindsight.api.selectorLabels" . | nindent 6 }}
template:
metadata:
annotations:
{{- if not .Values.existingSecret }}
checksum/secret: {{ include (print $.Template.BasePath "/secret.yaml") . | sha256sum }}
{{- end }}
{{- with .Values.podAnnotations }}
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "hindsight.api.selectorLabels" . | nindent 8 }}
spec:
{{- if .Values.serviceAccount.create }}
serviceAccountName: {{ include "hindsight.serviceAccountName" . }}
{{- end }}
securityContext:
{{- toYaml .Values.podSecurityContext | nindent 8 }}
containers:
- name: api
securityContext:
{{- toYaml .Values.securityContext | nindent 10 }}
image: "{{ .Values.api.image.repository }}:{{ .Values.api.image.tag | default .Values.version | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.api.image.pullPolicy }}
ports:
- name: http
containerPort: {{ .Values.api.service.targetPort }}
protocol: TCP
{{- if .Values.existingSecret }}
envFrom:
- secretRef:
name: {{ .Values.existingSecret }}
{{- end }}
env:
{{- /* POSTGRES_PASSWORD must be defined before DATABASE_URL for $(VAR) interpolation */}}
{{- if not .Values.postgresql.enabled }}
- name: POSTGRES_PASSWORD
valueFrom:
secretKeyRef:
name: {{ include "hindsight.secretName" . }}
key: postgres-password
{{- end }}
- name: HINDSIGHT_API_DATABASE_URL
value: {{ include "hindsight.databaseUrl" . | quote }}
{{- /* Disable internal worker when dedicated workers are enabled */}}
{{- if .Values.worker.enabled }}
- name: HINDSIGHT_API_WORKER_ENABLED
value: "false"
{{- end }}
{{- /* Explicitly set port to override K8s service discovery env var (HINDSIGHT_API_PORT) */}}
- name: HINDSIGHT_API_PORT
value: {{ .Values.api.service.targetPort | quote }}
{{- range $key, $value := .Values.api.env }}
- name: {{ $key }}
value: {{ $value | quote }}
{{- end }}
{{- if .Values.tei.reranker.enabled }}
- name: HINDSIGHT_API_RERANKER_PROVIDER
value: "tei"
- name: HINDSIGHT_API_RERANKER_TEI_URL
value: "http://{{ include "hindsight.fullname" . }}-tei-reranker:{{ .Values.tei.reranker.port }}"
{{- end }}
{{- if .Values.tei.embedding.enabled }}
- name: HINDSIGHT_API_EMBEDDINGS_PROVIDER
value: "tei"
- name: HINDSIGHT_API_EMBEDDINGS_TEI_URL
value: "http://{{ include "hindsight.fullname" . }}-tei-embedding:{{ .Values.tei.embedding.port }}"
{{- end }}
{{- /* Only use api.secrets when not using existingSecret (for chart-managed secrets) */}}
{{- if not .Values.existingSecret }}
{{- range $key, $value := .Values.api.secrets }}
- name: {{ $key }}
valueFrom:
secretKeyRef:
name: {{ include "hindsight.secretName" $ }}
key: {{ $key }}
{{- end }}
{{- end }}
livenessProbe:
{{- toYaml .Values.api.livenessProbe | nindent 10 }}
readinessProbe:
{{- toYaml .Values.api.readinessProbe | nindent 10 }}
resources:
{{- toYaml .Values.api.resources | nindent 10 }}
{{- if or .Values.api.persistence.modelCache.enabled .Values.api.extraVolumeMounts }}
volumeMounts:
{{- if .Values.api.persistence.modelCache.enabled }}
- name: model-cache
mountPath: /home/hindsight/.cache
{{- end }}
{{- with .Values.api.extraVolumeMounts }}
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}
{{- if or .Values.api.persistence.modelCache.enabled .Values.api.extraVolumes }}
volumes:
{{- if .Values.api.persistence.modelCache.enabled }}
- name: model-cache
persistentVolumeClaim:
claimName: {{ include "hindsight.fullname" . }}-api-model-cache
{{- end }}
{{- with .Values.api.extraVolumes }}
{{- toYaml . | nindent 6 }}
{{- end }}
{{- end }}
{{- with .Values.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with (.Values.api.affinity | default .Values.affinity) }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}