Files
2026-08-26 03:39:42 +05:30

137 lines
4.3 KiB
YAML

# See the Chart [README](https://github.com/deepgram/self-hosted-resources/blob/main/charts/deepgram-self-hosted#values)
# for documentation on all available options.
global:
# pullSecretRef should refer to a K8s secret that
# must be created prior to installing this Chart.
# Consult the [official Kubernetes documentation](https://kubernetes.io/docs/concepts/configuration/secret/) for best practices on configuring Secrets for use in your cluster.
#
# You can create a secret for your image pull credentials
# with the following commands:
# ```bash
# docker login quay.io
# kubectl create secret generic dg-regcred \
# --from-file=.dockerconfigjson=$HOME/.docker/config.json \
# --type=kubernetes.io/dockerconfigjson
# ```
pullSecretRef: "dg-regcred"
# deepgramSecretRef should refer to a K8s secret that
# must be created prior to installing this Chart.
# Consult the [official Kubernetes documentation](https://kubernetes.io/docs/concepts/configuration/secret/) for best practices on configuring Secrets for use in your cluster.
#
# You can create a secret for your Deepgram self-hosted API key
# with the following command:
# ```bash
# kubectl create secret generic dg-self-hosted-api-key --from-literal=DEEPGRAM_API_KEY='<id>'
# ```
deepgramSecretRef: "dg-self-hosted-api-key"
scaling:
replicas:
api: 1
engine: 1
auto:
# Can toggle to true to enable autoscaling. Make sure to set a value for one of the available metrics
enabled: false
engine:
metrics:
speechToText:
batch:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
streaming:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
textToSpeech:
batch:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
# Discuss a reasoanble value with your Deepgram Account Representative
# Must also set engine.concurrencyLimit.activeRequests if using request ratio for autoscaling
requestCapacityRatio:
api:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: k8s.deepgram.com/node-type
operator: In
values:
- api
resources:
requests:
memory: "4Gi"
cpu: "2000m"
limits:
memory: "8Gi"
cpu: "4000m"
engine:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: k8s.deepgram.com/node-type
operator: In
values:
- engine
resources:
requests:
memory: "28Gi"
cpu: "6000m"
gpu: 1
limits:
memory: "40Gi"
cpu: "8000m"
gpu: 1
# Discuss a reasonable value with your Deepgram Account Representative
# If not using autoscaling, can be left empty, but must be set if using
# autoscaling with scaling.auto.engine.metrics.requestCapacityRatio
concurrencyLimit:
activeRequests:
modelManager:
volumes:
aws:
efs:
enabled: true
fileSystemId: fs-xxxxxxxxxxxxxxxx # Replace with your EFS ID
models:
links:
- https://link-to-model-1.dg # Replace these links with those provided to you
- https://link-to-model-2.dg # by your Deepgram Account Representative.
- https://link-to-model-3.dg
- ...
licenseProxy:
enabled: true
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: k8s.deepgram.com/node-type
operator: In
values:
- license-proxy
resources:
requests:
memory: "6Gi"
cpu: "1500m"
limits:
memory: "8Gi"
cpu: "2000m"
cluster-autoscaler:
enabled: true
rbac:
serviceAccount:
name: "cluster-autoscaler-sa"
annotations:
# Replace with the AWS Role ARN configured for the Cluster Autoscaler
eks.amazonaws.com/role-arn: "arn:aws:iam::000000000000:role/MyRoleName"
autoDiscovery:
clusterName: "deepgram-self-hosted-cluster"
awsRegion: "us-west-2"