Have never done something like this before, and I'm unsure about the whole process from successfully serving the model to sending requests to it for inference. Is there any tutorial or example for it?

Did you raise a serving engine?

Is it the IP of the agent?

I just followed the instructions here at https://github.com/allegroai/clearml-serving

In the end it says I can curl at the end point and mentions the serving-engine-ip but I cant find the ip anywhere.

It was working fine for a while but then it just failed.

Basically want to be able to serve a model, and also send requests to it for inference.

I think the serving engine ip depends on how you set it up

I've tried the ip of the ClearML Server and the IP of my local machine on which the agent is also running on and none of the two work.

Yeah I think I did. I followed the tutorial on the repo.

Anyway I restarted the triton serving engine.