BentoML

If you want vanilla API then you should be add it with Flask or FastAPI: <https://docs.bentoml.org/en/latest/guides/server.html#bundle-asgi-app-e-g-fastapi>

<@U044H7LK47K> just wondering, what’s the use case for API without input?

<@UKB4CLKP1> when I need a API for parameter of my models.

Is this for providing parameters for the training process?

<@UKB4CLKP1> it is the dict values ​​of the columns when training the ml model. When predicting , the data must be in it.

For example when predicting house prices with an address column. When you make a prediction, you have to enter the address that is in the trained data. That is also the weakness of the machine learning model such as Decision trees