HELM: Error: INSTALLATION FAILED: template: riva-api/templates/modeldeploykey.yaml:1:12:

Please provide the following information when requesting support.

Hardware - GPU Titan RTX
Hardware - CPU i9
Operating System Ubuntu 20.04
Riva Version
TLT Version (if relevant)
How to reproduce the issue ? (This is for errors. Please share the command and the detailed log here)

Have a local Kubernetes cluster running through minikube (1 node) I am trying to install Riva via Helm Chart ( new to Helm Charts). I am getting the following error:

v@mila:~/Projects/test2-riva-rasa$ helm install riva-api riva-api
Error: INSTALLATION FAILED: template: riva-api/templates/modeldeploykey.yaml:1:12: executing "riva-api/templates/modeldeploykey.yaml" at <len .Values.modelRepoGenerator.modelDeployKey>: error calling len: len of nil pointer

I am using the default values.yaml file and have not modified.
Any help would be appreciated.

Hi @vanessa.crosby ,

Per the Overview from the NGC Helm Chart page for the Riva Speech Skills helm chart here: Riva Speech Skills | NVIDIA NGC

The values.yaml does not have everything set by default. You’ll need to either edit the values.yaml or set them when deploying with the --set flag in the helm CLI:

helm install riva-api --set ngcCredentials.password=`echo -n $NGC_API_KEY | base64 -w0` --set ngcCredentials.email=your_email@your_domain.com --set modelRepoGenerator.modelDeployKey=`echo -n model_key_string | base64 -w0`

Ok - I see. So I just want to confirm that even in beta stage Riva ASR, NLP and TTS are able to be deployed to a cluster and accessed by the public via API. (before I go down the road too far and find out otherwise.) :) Thanks…

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.