mirror of
https://github.com/vectorize-io/hindsight.git
synced 2026-09-14 19:31:49 +08:00
MΞTΔ
a6f99c995c
* feat(helm): add Prometheus operator ServiceMonitor support The api (port 8888) and worker (port 8889) containers expose Prometheus format metrics at /metrics (verified against app source); the chart had no wiring for them — the worker's scrape annotations are gated behind the unrelated podAnnotations value and the api service had nothing. Add a gated metrics.serviceMonitor block that emits per-component ServiceMonitor resources (api always when enabled, worker only when worker.enabled). Selection labels are configurable for the Prometheus operator's serviceMonitorSelector (e.g. release: kube-prometheus-stack). Also scrape the dedicated worker in the dev LGTM compose stack, which previously only scraped the api on :8888. Verified end-to-end on k3d + kube-prometheus-stack: all three targets (api + 2 worker pods via headless endpoints) discovered and up=1. * fix(helm): address ServiceMonitor review
521 lines
13 KiB
YAML
521 lines
13 KiB
YAML
# Default values for hindsight
|
|
|
|
# Global version override - use this to set a consistent image tag across all components
|
|
# If not set, defaults to Chart.appVersion from Chart.yaml
|
|
# version: ""
|
|
|
|
# Use an existing secret instead of creating one from values
|
|
# When set, all keys from this secret are injected as environment variables via envFrom
|
|
# Required keys:
|
|
# - postgres-password: PostgreSQL password (when postgresql.enabled=false)
|
|
# Optional keys (any key becomes an env var):
|
|
# - HINDSIGHT_API_LLM_API_KEY: API key for LLM provider
|
|
# - Any other env vars you want to inject
|
|
# existingSecret: "my-hindsight-secret"
|
|
|
|
# Image settings for api
|
|
api:
|
|
enabled: true
|
|
replicaCount: 1
|
|
image:
|
|
repository: ghcr.io/vectorize-io/hindsight-api
|
|
pullPolicy: IfNotPresent
|
|
# tag defaults to .Values.version if not specified
|
|
|
|
service:
|
|
type: ClusterIP
|
|
port: 8888
|
|
targetPort: 8888
|
|
|
|
# Resource limits and requests
|
|
resources:
|
|
limits:
|
|
cpu: 2000m
|
|
memory: 4Gi
|
|
requests:
|
|
cpu: 500m
|
|
memory: 1Gi
|
|
|
|
# Liveness and readiness probes.
|
|
# Liveness uses /health/live, which performs no database access: a slow or
|
|
# unreachable database must gate traffic (readiness), never restart pods.
|
|
# Needs an image from this chart's appVersion or newer — older ones serve
|
|
# /health only, and would fail this probe with a 404.
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /health/live
|
|
port: 8888
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
|
|
# Readiness checks the database, so a pod that cannot reach it is pulled out
|
|
# of the Service and put back once the database recovers.
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /health
|
|
port: 8888
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 5
|
|
timeoutSeconds: 3
|
|
failureThreshold: 3
|
|
|
|
# Pod disruption budget
|
|
podDisruptionBudget:
|
|
enabled: false
|
|
minAvailable: 1
|
|
# maxUnavailable: 1
|
|
|
|
# Pod affinity/anti-affinity (overrides global affinity for this component)
|
|
# affinity: {}
|
|
|
|
# Persistent volume for local model cache (reranker, embeddings)
|
|
# Models are downloaded to /home/hindsight/.cache on first use.
|
|
# Without persistence, models are re-downloaded on every pod restart.
|
|
#
|
|
# For production, prefer baking models into a custom image instead of
|
|
# enabling this PVC: image layers are pulled once per node and cached
|
|
# for free, while a PVC adds storage cost, pins pods to a node
|
|
# (ReadWriteOnce), and needs lifecycle management on uninstall/upgrade.
|
|
# See docs: developer/installation#bundling-custom-models-in-a-custom-image
|
|
persistence:
|
|
modelCache:
|
|
enabled: false
|
|
size: 5Gi
|
|
storageClass: ""
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
annotations: {}
|
|
|
|
# Extra volume mounts for the api container
|
|
# e.g.
|
|
# extraVolumeMounts:
|
|
# - name: my-volume
|
|
# mountPath: /mnt/my-volume
|
|
extraVolumeMounts: []
|
|
|
|
# Extra volumes for the api pod
|
|
# e.g.
|
|
# extraVolumes:
|
|
# - name: my-volume
|
|
# configMap:
|
|
# name: my-configmap
|
|
extraVolumes: []
|
|
|
|
# Extra sidecar containers for the api pod
|
|
# e.g.
|
|
# extraContainers:
|
|
# - name: cloud-sql-proxy
|
|
# image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.24.1
|
|
# args:
|
|
# - --port=5432
|
|
# - my-project:us-west1:my-instance
|
|
extraContainers: []
|
|
|
|
# Extra init containers for the api pod
|
|
# e.g.
|
|
# extraInitContainers:
|
|
# - name: wait-for-db
|
|
# image: busybox:1.37
|
|
# command: ["sh", "-c", "until nc -z postgresql 5432; do sleep 1; done"]
|
|
extraInitContainers: []
|
|
|
|
# Environment variables
|
|
env:
|
|
#HINDSIGHT_API_LLM_PROVIDER: "groq"
|
|
HINDSIGHT_API_LLM_MODEL: "openai/gpt-oss-120b"
|
|
|
|
# Secret environment variables
|
|
secrets:
|
|
# HINDSIGHT_API_LLM_API_KEY: "your-api-key"
|
|
# HINDSIGHT_API_LLM_BASE_URL: "https://api.groq.com/openai/v1"
|
|
|
|
# Worker settings (distributed task processing)
|
|
# When enabled, dedicated worker pods process tasks and the API's internal worker is disabled
|
|
worker:
|
|
enabled: false
|
|
replicaCount: 2
|
|
image:
|
|
repository: ghcr.io/vectorize-io/hindsight-api
|
|
pullPolicy: IfNotPresent
|
|
# tag: "" # defaults to .Values.version, then Chart.appVersion if not specified
|
|
|
|
service:
|
|
# Service for metrics scraping (headless for StatefulSet)
|
|
port: 8889
|
|
targetPort: 8889
|
|
|
|
# Resource limits and requests
|
|
resources:
|
|
limits:
|
|
cpu: 2000m
|
|
memory: 4Gi
|
|
requests:
|
|
cpu: 500m
|
|
memory: 1Gi
|
|
|
|
# Liveness and readiness probes.
|
|
# Liveness uses /health/live, which performs no database access. Restarting a
|
|
# worker whose database is merely slow requeues its claimed operations with
|
|
# retry_count incremented, so DB checks must stay out of liveness.
|
|
# Needs an image from this chart's appVersion or newer — older ones serve
|
|
# /health only, and would fail this probe with a 404.
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /health/live
|
|
port: 8889
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /health
|
|
port: 8889
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 5
|
|
timeoutSeconds: 3
|
|
failureThreshold: 3
|
|
|
|
# Worker-specific environment variables
|
|
env:
|
|
# Poll interval in milliseconds (how often to check for new tasks)
|
|
HINDSIGHT_API_WORKER_POLL_INTERVAL_MS: "500"
|
|
# Number of tasks to claim per poll cycle
|
|
HINDSIGHT_API_WORKER_BATCH_SIZE: "10"
|
|
# Max retries before marking a task as failed
|
|
HINDSIGHT_API_WORKER_MAX_RETRIES: "3"
|
|
# HTTP port for metrics/health (matches service.targetPort)
|
|
HINDSIGHT_API_WORKER_HTTP_PORT: "8889"
|
|
|
|
# Pod disruption budget
|
|
podDisruptionBudget:
|
|
enabled: false
|
|
minAvailable: 1
|
|
# maxUnavailable: 1
|
|
|
|
# Pod affinity/anti-affinity (overrides global affinity for this component)
|
|
# affinity: {}
|
|
|
|
# Persistent volume for local model cache (reranker, embeddings)
|
|
# Uses volumeClaimTemplates since worker is a StatefulSet — one PVC per
|
|
# replica. For production, prefer baking models into a custom image; see
|
|
# api.persistence.modelCache above and docs:
|
|
# developer/installation#bundling-custom-models-in-a-custom-image
|
|
persistence:
|
|
modelCache:
|
|
enabled: false
|
|
size: 5Gi
|
|
storageClass: ""
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
annotations: {}
|
|
|
|
# Extra volume mounts for the worker container
|
|
# e.g.
|
|
# extraVolumeMounts:
|
|
# - name: my-volume
|
|
# mountPath: /mnt/my-volume
|
|
extraVolumeMounts: []
|
|
|
|
# Extra volumes for the worker pod
|
|
# e.g.
|
|
# extraVolumes:
|
|
# - name: my-volume
|
|
# configMap:
|
|
# name: my-configmap
|
|
extraVolumes: []
|
|
|
|
# Extra sidecar containers for the worker pod
|
|
# e.g.
|
|
# extraContainers:
|
|
# - name: cloud-sql-proxy
|
|
# image: gcr.io/cloud-sql-connectors/cloud-sql-proxy:2.24.1
|
|
# args:
|
|
# - --port=5432
|
|
# - my-project:us-west1:my-instance
|
|
extraContainers: []
|
|
|
|
# Extra init containers for the worker pod
|
|
# e.g.
|
|
# extraInitContainers:
|
|
# - name: wait-for-db
|
|
# image: busybox:1.37
|
|
# command: ["sh", "-c", "until nc -z postgresql 5432; do sleep 1; done"]
|
|
extraInitContainers: []
|
|
|
|
# Secret environment variables (inherited from api.secrets if not specified)
|
|
secrets: {}
|
|
|
|
# Image settings for control plane
|
|
controlPlane:
|
|
enabled: true
|
|
replicaCount: 1
|
|
image:
|
|
repository: ghcr.io/vectorize-io/hindsight-control-plane
|
|
pullPolicy: IfNotPresent
|
|
# tag defaults to .Values.version if not specified
|
|
|
|
service:
|
|
type: ClusterIP
|
|
port: 3000
|
|
targetPort: 3000
|
|
|
|
# Resource limits and requests
|
|
resources:
|
|
limits:
|
|
cpu: 1000m
|
|
memory: 2Gi
|
|
requests:
|
|
cpu: 250m
|
|
memory: 512Mi
|
|
|
|
# Liveness and readiness probes (TCP check)
|
|
livenessProbe:
|
|
tcpSocket:
|
|
port: 3000
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
failureThreshold: 3
|
|
|
|
readinessProbe:
|
|
tcpSocket:
|
|
port: 3000
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 5
|
|
timeoutSeconds: 3
|
|
failureThreshold: 3
|
|
|
|
# Pod disruption budget
|
|
podDisruptionBudget:
|
|
enabled: false
|
|
minAvailable: 1
|
|
# maxUnavailable: 1
|
|
|
|
# Pod affinity/anti-affinity (overrides global affinity for this component)
|
|
# affinity: {}
|
|
|
|
# Extra sidecar containers for the control plane pod
|
|
# e.g.
|
|
# extraContainers:
|
|
# - name: oauth2-proxy
|
|
# image: quay.io/oauth2-proxy/oauth2-proxy:v7.7.1
|
|
# args:
|
|
# - --upstream=http://127.0.0.1:3000
|
|
extraContainers: []
|
|
|
|
# Extra init containers for the control plane pod
|
|
# e.g.
|
|
# extraInitContainers:
|
|
# - name: wait-for-api
|
|
# image: busybox:1.37
|
|
# command: ["sh", "-c", "until nc -z hindsight-api 8888; do sleep 1; done"]
|
|
extraInitContainers: []
|
|
|
|
# Environment variables
|
|
env:
|
|
NODE_ENV: "production"
|
|
HINDSIGHT_CP_HOSTNAME: "0.0.0.0"
|
|
HINDSIGHT_CP_PORT: "3000"
|
|
|
|
# PostgreSQL configuration
|
|
postgresql:
|
|
# Set to true to deploy PostgreSQL as part of this chart
|
|
enabled: true
|
|
|
|
image:
|
|
repository: ankane/pgvector
|
|
tag: latest
|
|
pullPolicy: IfNotPresent
|
|
|
|
auth:
|
|
username: "hindsight"
|
|
password: "hindsight"
|
|
database: "hindsight"
|
|
|
|
service:
|
|
port: 5432
|
|
|
|
persistence:
|
|
enabled: true
|
|
size: 8Gi
|
|
# storageClass: ""
|
|
|
|
resources:
|
|
limits:
|
|
cpu: 1000m
|
|
memory: 1Gi
|
|
requests:
|
|
cpu: 250m
|
|
memory: 256Mi
|
|
|
|
# External PostgreSQL connection details
|
|
# Only used if postgresql.enabled is false
|
|
external:
|
|
host: "postgresql"
|
|
port: 5432
|
|
database: "hindsight"
|
|
username: "hindsight"
|
|
# password: ""
|
|
|
|
# Ingress configuration
|
|
ingress:
|
|
enabled: false
|
|
className: "nginx"
|
|
annotations: {}
|
|
# cert-manager.io/cluster-issuer: "letsencrypt-prod"
|
|
# nginx.ingress.kubernetes.io/ssl-redirect: "true"
|
|
|
|
hosts:
|
|
- host: hindsight.example.com
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
service: controlPlane
|
|
- path: /api
|
|
pathType: Prefix
|
|
service: api
|
|
|
|
tls: []
|
|
# - secretName: hindsight-tls
|
|
# hosts:
|
|
# - hindsight.example.com
|
|
|
|
# Service Account
|
|
serviceAccount:
|
|
create: true
|
|
annotations: {}
|
|
name: ""
|
|
|
|
# Pod annotations
|
|
podAnnotations: {}
|
|
|
|
# Pod security context
|
|
podSecurityContext:
|
|
fsGroup: 1000
|
|
|
|
# Security context
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: false
|
|
allowPrivilegeEscalation: false
|
|
|
|
# Node selector
|
|
nodeSelector: {}
|
|
|
|
# Tolerations
|
|
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
|
|
minReplicas: 1
|
|
maxReplicas: 10
|
|
targetCPUUtilizationPercentage: 80
|
|
targetMemoryUtilizationPercentage: 80
|
|
|
|
# Metrics scraping via Prometheus Operator ServiceMonitors.
|
|
# Requires the prometheus-operator CRDs (monitoring.coreos.com/v1) and a
|
|
# Prometheus instance whose serviceMonitorSelector matches the labels below —
|
|
# e.g. kube-prometheus-stack selects release: <stack-release-name> by default.
|
|
# The api and worker containers serve Prometheus format at /metrics on their
|
|
# service ports; the control plane (Next.js) does not expose metrics.
|
|
metrics:
|
|
serviceMonitor:
|
|
enabled: false
|
|
# Labels added to the ServiceMonitor for Prometheus operator selection,
|
|
# e.g. { release: kube-prometheus-stack }
|
|
labels: {}
|
|
# Endpoints shared by the api and worker monitors
|
|
path: /metrics
|
|
interval: 30s
|
|
scrapeTimeout: 10s
|