dev_omi_vad_values.yaml

# Default values for vad.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

# This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
replicaCount: 1

# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
  repository: gcr.io/based-hardware-dev/models
  # This sets the pull policy for images.
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: ""

# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets: []
# This is to override the chart name.
nameOverride: ""
fullnameOverride: ""

# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
serviceAccount:
  # Specifies whether a service account should be created
  create: true
  # Automatically mount a ServiceAccount's API credentials?
  automount: true
  # Annotations to add to the service account
  annotations: {}
  # The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""

# This is for setting Kubernetes Annotations to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
podAnnotations: {}
# This is for setting Kubernetes Labels to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
podLabels: {}

podSecurityContext: {}
  # fsGroup: 2000

securityContext: {}
  # capabilities:
  #   drop:
  #   - ALL
  # readOnlyRootFilesystem: true
  # runAsNonRoot: true
  # runAsUser: 1000

# This is for setting up a service more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/
service:
  # This sets the service type more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
  type: ClusterIP
  # This sets the ports more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports
  port: 8080

# This block is for setting up the ingress for more information can be found here: https://kubernetes.io/docs/concepts/services-networking/ingress/
ingress:
  enabled: true
  className: ""
  annotations:
    kubernetes.io/ingress.class: "gce-internal"
    kubernetes.io/ingress.regional-static-ip-name: "dev-vad-ilb-ip-address"
    kubernetes.io/ingress.allow-http: "true"
  hosts:
    - host: vad.omiapi.com
      paths:
        - path: /v1/vad
          pathType: Prefix
  tls: []
  #  - secretName: chart-example-tls
  #    hosts:
  #      - chart-example.local

env:
  - name: HUGGINGFACE_TOKEN
    valueFrom:
      secretKeyRef:
        name: dev-omi-backend-secrets
        key: HUGGINGFACE_TOKEN
  - name: ENCRYPTION_SECRET
    valueFrom:
      secretKeyRef:
        name: dev-omi-backend-secrets
        key: ENCRYPTION_SECRET

resources:
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  requests:
    cpu: 1
    memory: 4Gi
    nvidia.com/gpu: 1
  limits:
    cpu: 2
    memory: 6Gi
    nvidia.com/gpu: 1

# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
livenessProbe:
  tcpSocket:
    port: 8080
  failureThreshold: 30
  periodSeconds: 10

readinessProbe:
  tcpSocket:
    port: 8080
  failureThreshold: 30
  periodSeconds: 10

startupProbe:
  tcpSocket:
    port: 8080
  failureThreshold: 30
  periodSeconds: 10

# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
autoscaling:
  enabled: true
  minReplicas: 1
  maxReplicas: 3
  behavior:
    scaleDown:
      stabilizationWindowSeconds: 600
      policies:
      - type: Percent
        value: 20
        periodSeconds: 300
      - type: Pods
        value: 1
        periodSeconds: 120
      selectPolicy: Min
    scaleUp:
      stabilizationWindowSeconds: 300
      policies:
      - type: Percent
        value: 20
        periodSeconds: 15
      - type: Pods
        value: 1
        periodSeconds: 15
      selectPolicy: Max
  # targetCPUUtilizationPercentage: 70
  # targetMemoryUtilizationPercentage: 70
  requestLatencyP99: 2000 # milliseconds

# Additional volumes on the output Deployment definition.
volumes: []
# - name: foo
#   secret:
#     secretName: mysecret
#     optional: false

# Additional volumeMounts on the output Deployment definition.
volumeMounts: []
# - name: foo
#   mountPath: "/etc/foo"
#   readOnly: true

nodeSelector: {}

tolerations: []

affinity:
  nodeAffinity:
    requiredDuringSchedulingIgnoredDuringExecution:
      nodeSelectorTerms:
        - matchExpressions:
            - key: service
              operator: In
              values:
                - vad
            - key: env
              operator: In
              values:
                - dev


strategy:
  type: RollingUpdate
  rollingUpdate:
    maxUnavailable: 1
    maxSurge: 0