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>
This commit is contained in:
Anton Evseev 2026-02-11 19:39:41 +10:00 committed by GitHub
parent f641b30d83
commit 43f9a8bec2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 308 additions and 0 deletions

View file

@ -127,6 +127,38 @@ API URL for control plane
{{- printf "http://%s-api:%d" (include "hindsight.fullname" .) (.Values.api.service.port | int) }}
{{- end }}
{{/*
TEI reranker labels
*/}}
{{- define "hindsight.tei.reranker.labels" -}}
{{ include "hindsight.labels" . }}
app.kubernetes.io/component: tei-reranker
{{- end }}
{{/*
TEI reranker selector labels
*/}}
{{- define "hindsight.tei.reranker.selectorLabels" -}}
{{ include "hindsight.selectorLabels" . }}
app.kubernetes.io/component: tei-reranker
{{- end }}
{{/*
TEI embedding labels
*/}}
{{- define "hindsight.tei.embedding.labels" -}}
{{ include "hindsight.labels" . }}
app.kubernetes.io/component: tei-embedding
{{- end }}
{{/*
TEI embedding selector labels
*/}}
{{- define "hindsight.tei.embedding.selectorLabels" -}}
{{ include "hindsight.selectorLabels" . }}
app.kubernetes.io/component: tei-embedding
{{- end }}
{{/*
Get the name of the secret to use
*/}}

View file

@ -67,6 +67,18 @@ spec:
- 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 }}

View file

@ -0,0 +1,76 @@
{{- if .Values.tei.embedding.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "hindsight.fullname" . }}-tei-embedding
labels:
{{- include "hindsight.tei.embedding.labels" . | nindent 4 }}
spec:
replicas: {{ .Values.tei.embedding.replicaCount }}
selector:
matchLabels:
{{- include "hindsight.tei.embedding.selectorLabels" . | nindent 6 }}
template:
metadata:
{{- with .Values.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "hindsight.tei.embedding.selectorLabels" . | nindent 8 }}
spec:
{{- if .Values.serviceAccount.create }}
serviceAccountName: {{ include "hindsight.serviceAccountName" . }}
{{- end }}
securityContext:
{{- toYaml .Values.podSecurityContext | nindent 8 }}
containers:
- name: tei-embedding
securityContext:
{{- toYaml .Values.securityContext | nindent 10 }}
image: "{{ .Values.tei.embedding.image.repository }}:{{ .Values.tei.embedding.image.tag }}"
imagePullPolicy: {{ .Values.tei.embedding.image.pullPolicy }}
args:
- "--model-id"
- {{ .Values.tei.embedding.model | quote }}
- "--hostname"
- "0.0.0.0"
{{- range .Values.tei.embedding.args }}
- {{ . | quote }}
{{- end }}
ports:
- name: http
containerPort: {{ .Values.tei.embedding.port }}
protocol: TCP
env:
- name: PORT
value: {{ .Values.tei.embedding.port | quote }}
{{- range $key, $value := .Values.tei.embedding.env }}
- name: {{ $key }}
value: {{ $value | quote }}
{{- end }}
livenessProbe:
{{- toYaml .Values.tei.embedding.livenessProbe | nindent 10 }}
readinessProbe:
{{- toYaml .Values.tei.embedding.readinessProbe | nindent 10 }}
resources:
{{- toYaml .Values.tei.embedding.resources | nindent 10 }}
volumeMounts:
- name: model-cache
mountPath: /data
volumes:
- name: model-cache
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 }}
{{- end }}

View file

@ -0,0 +1,17 @@
{{- if .Values.tei.embedding.enabled }}
apiVersion: v1
kind: Service
metadata:
name: {{ include "hindsight.fullname" . }}-tei-embedding
labels:
{{- include "hindsight.tei.embedding.labels" . | nindent 4 }}
spec:
type: ClusterIP
ports:
- port: {{ .Values.tei.embedding.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "hindsight.tei.embedding.selectorLabels" . | nindent 4 }}
{{- end }}

View file

@ -0,0 +1,76 @@
{{- if .Values.tei.reranker.enabled }}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "hindsight.fullname" . }}-tei-reranker
labels:
{{- include "hindsight.tei.reranker.labels" . | nindent 4 }}
spec:
replicas: {{ .Values.tei.reranker.replicaCount }}
selector:
matchLabels:
{{- include "hindsight.tei.reranker.selectorLabels" . | nindent 6 }}
template:
metadata:
{{- with .Values.podAnnotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
labels:
{{- include "hindsight.tei.reranker.selectorLabels" . | nindent 8 }}
spec:
{{- if .Values.serviceAccount.create }}
serviceAccountName: {{ include "hindsight.serviceAccountName" . }}
{{- end }}
securityContext:
{{- toYaml .Values.podSecurityContext | nindent 8 }}
containers:
- name: tei-reranker
securityContext:
{{- toYaml .Values.securityContext | nindent 10 }}
image: "{{ .Values.tei.reranker.image.repository }}:{{ .Values.tei.reranker.image.tag }}"
imagePullPolicy: {{ .Values.tei.reranker.image.pullPolicy }}
args:
- "--model-id"
- {{ .Values.tei.reranker.model | quote }}
- "--hostname"
- "0.0.0.0"
{{- range .Values.tei.reranker.args }}
- {{ . | quote }}
{{- end }}
ports:
- name: http
containerPort: {{ .Values.tei.reranker.port }}
protocol: TCP
env:
- name: PORT
value: {{ .Values.tei.reranker.port | quote }}
{{- range $key, $value := .Values.tei.reranker.env }}
- name: {{ $key }}
value: {{ $value | quote }}
{{- end }}
livenessProbe:
{{- toYaml .Values.tei.reranker.livenessProbe | nindent 10 }}
readinessProbe:
{{- toYaml .Values.tei.reranker.readinessProbe | nindent 10 }}
resources:
{{- toYaml .Values.tei.reranker.resources | nindent 10 }}
volumeMounts:
- name: model-cache
mountPath: /data
volumes:
- name: model-cache
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 }}
{{- end }}

View file

@ -0,0 +1,17 @@
{{- if .Values.tei.reranker.enabled }}
apiVersion: v1
kind: Service
metadata:
name: {{ include "hindsight.fullname" . }}-tei-reranker
labels:
{{- include "hindsight.tei.reranker.labels" . | nindent 4 }}
spec:
type: ClusterIP
ports:
- port: {{ .Values.tei.reranker.port }}
targetPort: http
protocol: TCP
name: http
selector:
{{- include "hindsight.tei.reranker.selectorLabels" . | nindent 4 }}
{{- end }}

View file

@ -293,6 +293,84 @@ tolerations: []
# Affinity (applied to all components unless overridden per-component)
affinity: {}
# TEI (Text Embeddings Inference) - optional standalone deployments
# for reranking and/or embedding models
tei:
reranker:
enabled: false
replicaCount: 1
image:
repository: ghcr.io/huggingface/text-embeddings-inference
tag: cpu-1.8.3
pullPolicy: IfNotPresent
model: "cross-encoder/ms-marco-MiniLM-L-6-v2"
port: 8090
args:
- "--auto-truncate"
env:
PAYLOAD_LIMIT: "10000000"
MAX_CLIENT_BATCH_SIZE: "256"
resources:
limits:
cpu: 2000m
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
livenessProbe:
httpGet:
path: /health
port: 8090
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 6
readinessProbe:
httpGet:
path: /health
port: 8090
initialDelaySeconds: 15
periodSeconds: 5
timeoutSeconds: 3
failureThreshold: 3
embedding:
enabled: false
replicaCount: 1
image:
repository: ghcr.io/huggingface/text-embeddings-inference
tag: cpu-1.8.3
pullPolicy: IfNotPresent
model: "sentence-transformers/all-MiniLM-L6-v2"
port: 8091
args: []
env:
PAYLOAD_LIMIT: "10000000"
MAX_CLIENT_BATCH_SIZE: "256"
resources:
limits:
cpu: 2000m
memory: 2Gi
requests:
cpu: 500m
memory: 1Gi
livenessProbe:
httpGet:
path: /health
port: 8091
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 5
failureThreshold: 6
readinessProbe:
httpGet:
path: /health
port: 8091
initialDelaySeconds: 15
periodSeconds: 5
timeoutSeconds: 3
failureThreshold: 3
# Autoscaling
autoscaling:
enabled: false