Hey, I have seen tutorials for bentoml with custom python models and for bentoml+mlflow. is there any tutorials fro bentoml with custom models logged in mlflow? I wanted to know if it is possible to create a service with more functions than just a predict function using custom python models retrieved from mlflow. Thanks.

Please see their examples folder on github, there is an example called "custom api" , so basically you can write fastapi and mount it to bentoml svc object.