Status/Health of RIVA models

Hi is there any whay to check if the ststus or the health of models loaded.
For example, if at some point the inference server stops, is there any way to know that.

Hi @aman.rai1

Thanks for your interest in Riva,
I will check for more inputs from the team,

But for now you can get the status by running the below docker command

docker logs riva-speech

Thanks

Hi @rvinobha

yes, I have been using the same, but I would love to have something which is just as easy as pinging the server and analysing ther response code rather than monitoring the logs 24/7.

Thanks

There’s a health proto? You can ping the /health endpoint. Check out grpccurl on github and you’ll be able to list the available endpoints