fleet-memory/helm/hindsight/templates/api-deployment.yaml
Anton Evseev 43f9a8bec2
feat(helm): TEI reranker and embedding as separate Deployments (#333)
Refactor TEI from sidecar (PR #333) to standalone Deployment+Service
pairs for independent scaling. Adds embedding support alongside reranker.

- New tei-reranker-deployment.yaml and tei-reranker-service.yaml
- New tei-embedding-deployment.yaml and tei-embedding-service.yaml
- Auto-inject RERANKER/EMBEDDINGS provider and URL env vars on API pod
- Config restructured under tei.reranker.* and tei.embedding.* in values
- Both disabled by default, opt-in via tei.reranker.enabled / tei.embedding.enabled

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 10:39:41 +01:00

110 lines
4.1 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 }}
{{- 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 }}