Hi, I have a general question regarding the difference between the python prediction and python function endpoints in the API Service in regards to serving a custom python model. From my understanding, the only advantage that the python prediction endpoint has over the python function endpoint is the ability to automatically include enrichments (which I admit is a pretty important feature). Both can load trained models from managed folders. The python function endpoint however has the following advantages:
Would I be correct to assume that if we didn't need enrichments, then a python function would probably be a simpler better choice, and probably a bit faster, because of the absence of the pre and post processing to convert from and to pandas dataframes? Am I missing any more advantages for the python prediction endpoint?
Have a look this article: https://doc.dataiku.com/dss/latest/apinode/endpoint-python-prediction.html
Our data scientists preferred approach is the use a Managed Folder as outlined here.
Hope this helps
Hey Mark, thanks for the response, given that both the python function endpoint and the python prediction endpoint support using a managed folder, I don't see that as a point of differentiation. Other than enrichments, are there any other advantages for using a python prediction endpoint over a python function endpoint? Are there any points in my post concerning the advantages of the python function endpoint that are invalid?