asyncio example

[msaroufim]

📚 Documentation

When doing batch inferencing the default way a lot of python programmers will go about it is making a call with requests. Unfortunately the library is synchronous so users will get confused by results that are always batch_size=1 so instead would like to add an asyncio example in our getting started guide

[mdaj06]

@msaroufim could i have a look at this?

[msaroufim]

Yup go for it!

[LuigiCerone]

Hello, is anyone working on this?

@msaroufim can you please further clarify the purpose of the guide?

[msaroufim]

@LuigiCerone We have an example here https://github.com/pytorch/serve/blob/master/examples/cloud_storage_stream_inference/stream_inference.py#L25

If you don't think it's enough lmk and we can expand it more