TAO Toolkit API - Kubernetes sample setup

[m.digiusto]

HW: RTX A2000 12GB, 32GB RAM, Intel(R) Xeon(R) w5-2445
OS: Ubuntu 22.04, fresh install
TAO Toolkit API: 5.3.0

Hello,

I’m trying to install Tao Toolkit API following the directions available here: Setup - NVIDIA Docs. The API has to run on a single machine.
When starting the TAO pod (last step of installation phase) I get the error:

Readiness probe failed: Get "http://192.168.33.146:8000/api/v1/health/readiness": dial tcp 192.168.33.146:8000: connect: connection refused

Since I have not set the HTTP_PROXY, HTTPS_PROXY, NO_PROXY variables and have not managed the CA certificates, could that be the problem?
Could you provide a complete example where it is explained how to handle these variables and certificates?

Thank you!

[Morganh]

@m.digiusto

When starting the TAO pod (last step of installation phase) I get the error:

Readiness probe failed: Get "http://192.168.33.146:8000/api/v1/health/readiness": dial tcp 192.168.33.146:8000: connect: connection refused

Since I have not set the HTTP_PROXY, HTTPS_PROXY, NO_PROXY variables and have not managed the CA certificates, could that be the problem?

Could you please upload the full log?
Also, it is better to check the pod status.

$ kubectl get pods
$ kubectl describe pod <pod id> 
$ kubectl logs -f <pod id> 
$ kubectl describe pod <pod id>

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks