Upload production/helm/ml-intern/values.yaml

production/helm/ml-intern/values.yaml

@@ -0,0 +1,161 @@
+replicaCount:
+  api: 2
+  worker: 2
+
+image:
+  repository: ml-intern
+  pullPolicy: IfNotPresent
+  tag: "latest"
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+serviceAccount:
+  create: true
+  annotations: {}
+  name: ""
+
+podAnnotations:
+  prometheus.io/scrape: "true"
+  prometheus.io/port: "8000"
+  prometheus.io/path: "/metrics"
+
+podSecurityContext:
+  fsGroup: 1000
+
+securityContext:
+  runAsNonRoot: true
+  runAsUser: 1000
+  capabilities:
+    drop:
+      - ALL
+  readOnlyRootFilesystem: true
+  allowPrivilegeEscalation: false
+
+service:
+  type: ClusterIP
+  port: 8000
+
+ingress:
+  enabled: false
+  className: "nginx"
+  annotations:
+    nginx.ingress.kubernetes.io/rate-limit: "100"
+    nginx.ingress.kubernetes.io/rate-limit-window: "1m"
+  hosts:
+    - host: ml-intern.local
+      paths:
+        - path: /
+          pathType: Prefix
+  tls: []
+
+resources:
+  api:
+    requests:
+      cpu: 250m
+      memory: 512Mi
+    limits:
+      cpu: 2000m
+      memory: 2Gi
+  worker:
+    requests:
+      cpu: 100m
+      memory: 256Mi
+    limits:
+      cpu: 1000m
+      memory: 1Gi
+
+autoscaling:
+  enabled: true
+  api:
+    minReplicas: 2
+    maxReplicas: 20
+    targetCPUUtilizationPercentage: 70
+    targetMemoryUtilizationPercentage: 80
+    scaleUpStabilizationWindowSeconds: 60
+    scaleDownStabilizationWindowSeconds: 300
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity:
+  api:
+    podAntiAffinity:
+      preferredDuringSchedulingIgnoredDuringExecution:
+        - weight: 100
+          podAffinityTerm:
+            labelSelector:
+              matchExpressions:
+                - key: app.kubernetes.io/name
+                  operator: In
+                  values:
+                    - ml-intern
+            topologyKey: kubernetes.io/hostname
+
+config:
+  port: 8000
+  workers: 4
+  maxConcurrentRequests: 200
+  defaultRpmLimit: 40
+  requestTimeout: 120
+  cacheTtlSeconds: 300
+  budgetUsdPerSession: 10.0
+  circuitBreaker:
+    failureThreshold: 5
+    recoveryTimeout: 60
+  logLevel: INFO
+
+secrets:
+  hfToken: ""
+  anthropicApiKey: ""
+  openaiApiKey: ""
+  groqApiKey: ""
+  nvidiaApiKey: ""
+
+redis:
+  enabled: true
+  architecture: standalone
+  auth:
+    enabled: false
+  master:
+    persistence:
+      enabled: true
+      size: 5Gi
+    resources:
+      requests:
+        memory: 256Mi
+        cpu: 100m
+      limits:
+        memory: 1Gi
+        cpu: 500m
+
+postgresql:
+  enabled: true
+  auth:
+    username: ml_intern
+    password: ml_intern
+    database: ml_intern
+  primary:
+    persistence:
+      enabled: true
+      size: 10Gi
+    resources:
+      requests:
+        memory: 256Mi
+        cpu: 100m
+      limits:
+        memory: 1Gi
+        cpu: 500m
+
+monitoring:
+  enabled: true
+  prometheus:
+    enabled: true
+    retention: "30d"
+  grafana:
+    enabled: true
+    adminPassword: "admin"
+  jaeger:
+    enabled: true