You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
155 lines
5.4 KiB
155 lines
5.4 KiB
# -- The number of replicas for the NeMo Guardrails microservice deployment.
|
|
replicaCount: 1
|
|
|
|
image:
|
|
# -- The repository location of the NeMo Guardrails container image.
|
|
repository: nvcr.io/nvidia/nemo-microservices/guardrails
|
|
# -- The tag of the NeMo Guardrails container image.
|
|
tag: ""
|
|
# -- The image pull policy for the NeMo Guardrails container image.
|
|
pullPolicy: IfNotPresent
|
|
|
|
# -- Specifies the list of secret names that are needed for the main container and any init containers.
|
|
imagePullSecrets:
|
|
- name: nvcrimagepullsecret
|
|
|
|
# -- Overrides the chart name.
|
|
nameOverride: ""
|
|
|
|
# -- Overrides the full chart name.
|
|
fullnameOverride: ""
|
|
|
|
# -- Environment variables for the container.
|
|
env:
|
|
NIM_ENDPOINT_URL: "https://integrate.api.nvidia.com/v1"
|
|
CONFIG_STORE_PATH: "/app/services/guardrails/config-store"
|
|
DEFAULT_CONFIG_ID: "default"
|
|
DEFAULT_LLM_PROVIDER: "nim"
|
|
NEMO_GUARDRAILS_SERVER_ENABLE_CORS: "False"
|
|
NEMO_GUARDRAILS_SERVER_ALLOWED_ORIGINS: "*"
|
|
GUARDRAILS_HOST: "0.0.0.0"
|
|
GUARDRAILS_PORT: "7331"
|
|
DEMO: "False"
|
|
|
|
# -- Specifies the service type and the port for the deployment.
|
|
service:
|
|
type: ClusterIP
|
|
port: 7331
|
|
|
|
configStore:
|
|
nfs:
|
|
# -- Whether to enable the use of an NFS persistent volume for the configuration store.
|
|
enabled: false
|
|
# -- The path to the root of the Configuration Store folder.
|
|
path: "/path/to/nfs/share"
|
|
# -- The address of the NFS server.
|
|
server: "nfs-server.example.com"
|
|
# -- The path where the NFS volume will be mounted inside the container.
|
|
mountPath: "/config-store"
|
|
# -- The storage class for the PV and PVC.
|
|
storageClass: "standard"
|
|
|
|
readinessProbe:
|
|
# -- The HTTP GET request to use for the readiness probe.
|
|
httpGet:
|
|
path: /v1/health
|
|
port: 7331
|
|
# -- The initial delay seconds for the readiness probe.
|
|
initialDelaySeconds: 5
|
|
# -- The timeout in seconds for the readiness probe.
|
|
timeoutSeconds: 30
|
|
|
|
livenessProbe:
|
|
# -- The HTTP GET request to use for the liveness probe.
|
|
httpGet:
|
|
path: /v1/health
|
|
port: 7331
|
|
# -- The initial delay seconds for the liveness probe.
|
|
initialDelaySeconds: 5
|
|
# -- The timeout in seconds for the liveness probe.
|
|
timeoutSeconds: 30
|
|
|
|
serviceAccount:
|
|
# -- Whether to create a service account for the NeMo Guardrails microservice.
|
|
create: true
|
|
# -- Whether to automatically mount the service account token.
|
|
automount: true
|
|
# -- Annotations to be added to the service account.
|
|
annotations: {}
|
|
# -- The name of the service account to use.
|
|
name: ""
|
|
|
|
# -- Specifies additional annotations to the main deployment pods.
|
|
podAnnotations: {}
|
|
|
|
# -- Specifies additional labels to the main deployment pods.
|
|
podLabels: {}
|
|
|
|
# -- Specifies privilege and access control settings for the pod.
|
|
podSecurityContext: {}
|
|
# -- Specifies the group ID for the pod.
|
|
runAsGroup: ""
|
|
# -- Specifies the file system owner group id.
|
|
fsGroup: ""
|
|
|
|
# -- Specifies security context for the container.
|
|
securityContext: {}
|
|
|
|
ingress:
|
|
# -- Whether to enable the ingress resource.
|
|
enabled: false
|
|
# -- The class name for the ingress resource.
|
|
className: ""
|
|
# -- Additional annotations for the ingress resource.
|
|
annotations:
|
|
{}
|
|
# kubernetes.io/ingress.class: nginx
|
|
# kubernetes.io/tls-acme: "true"
|
|
# -- (list) A list of maps, each containing the keys `host` and `paths` for the ingress resource. You must specify a list for configuring ingress for the microservice.
|
|
# @default -- []
|
|
hosts: {}
|
|
# - host: chart-example.local
|
|
# paths:
|
|
# - path: /
|
|
# pathType: ImplementationSpecific
|
|
# serviceType: openai # can be nemo or openai -- make sure your model serves the appropriate port(s)
|
|
# -- TLS configuration for the ingress resource.
|
|
tls: []
|
|
# - secretName: chart-example-tls
|
|
# hosts:
|
|
# - chart-example.local
|
|
|
|
# -- Specifies resource configurations for the deployment.
|
|
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:'.
|
|
# limits:
|
|
# cpu: 100m
|
|
# memory: 128Mi
|
|
# requests:
|
|
# cpu: 100m
|
|
# memory: 128Mi
|
|
|
|
# -- Specifies autoscaling configurations for the deployment.
|
|
autoscaling:
|
|
# -- Whether to enable horizontal pod autoscaler.
|
|
enabled: false
|
|
# -- The minimum number of replicas for the deployment.
|
|
minReplicas: 1
|
|
# -- The maximum number of replicas for the deployment.
|
|
maxReplicas: 100
|
|
# -- The target CPU utilization percentage.
|
|
targetCPUUtilizationPercentage: 80
|
|
# targetMemoryUtilizationPercentage: 80
|
|
|
|
# -- Specifies labels to ensure that the NeMo Guardrails microservice is deployed only on certain nodes. To learn more, refer to the [Node Selector](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#nodeselector) in the Kubernetes documentation.
|
|
nodeSelector: {}
|
|
|
|
# -- Specifies tolerations for pod assignment. To learn more, refer to the [Taint and Toleration](https://kubernetes.io/docs/concepts/scheduling-eviction/taint-and-toleration/) in the Kubernetes documentation.
|
|
tolerations: []
|
|
|
|
# -- Specifies affinity settings for the deployment. To learn more, refer to the [Affinity and Anti-Affinity](https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#affinity-and-anti-affinity) in the Kubernetes documentation.
|
|
affinity: {}
|
|
|