Vertex AI endpoint predict timeout feature for model prediction when using raw_predict

[anuragbisht-turing]

Thanks for stopping by to let us know something could be better!

PLEASE READ: If you have a support contract with Google, please create an issue in the support console instead of filing on GitHub. This will ensure a timely response.

Is your feature request related to a problem? Please describe.
Currently we wanted to use raw predictions in our pipelines but having a timeout value due to some business constraints.
Describe the solution you'd like
vertex ai endpoint has option to give raw_prediction as response, but the timeout doesn't work, setting the timeout should be respected in when real_predict is true.
Describe alternatives you've considered
We have set timeout explicitly.
Additional context
this is related to endpoint functionality of vertex ai python package

[ntakouris]

Did you check:

from google.api_core.future.polling import DEFAULT_POLLING

### Set the default timeoutto 3600 seconds
DEFAULT_POLLING._timeout = 3600

?