[Feature request] Extending MLFlow Runtime to load Model based on Flavour

[hjilke]

Hey Everyone,

could we extend the mlflow runtime to allow using predict_prob(). I know the mlflow pyfunc interface only provides predict(), but there are ways to load the model based on the flavour. Here is an example on how I do it.

That would allow the use of predict_prob().

Let me know, if there is anything I can help with.

Regards Henrik