Question about the get_response() function in the Python API's HTTP/REST Client

[jackylu0124]

Hey all, I have a question regarding the get_response() function in the Python API's HTTP/REST Client, I see that in the client script for the pytorch and add_sub examples, we have a result = response.get_response() call (see https://github.com/triton-inference-server/python_backend/blob/c8b188f26a4e80c7204baaf73e27f11c33f52f57/examples/pytorch/client.py#L58 and https://github.com/triton-inference-server/python_backend/blob/c8b188f26a4e80c7204baaf73e27f11c33f52f57/examples/add_sub/client.py#L58) before we extract the outputs with response.as_numpy("OUTPUT0") for example.

My question is: what is the purpose of the result = response.get_response() call before we extract the outputs with as_numpy(), and whether the result = response.get_response() call is necessary before we extract the outputs with as_numpy(); because I have tried removing the response.get_response() call, and have tried directly extracting the outputs with as_numpy() right after infer(), and I was able to extract the expected outputs.

Thank you very much for your time and help in advance!