Hi, we use

bentoml.sklearn

to save the model with a custom object for preprocessing. We’ve made some changes to the code, and since then, we’ve encountered the following error when attempting to work with the custom object after retrieving the model.

File "/home/azureuser/vsts-agent/_work/1264/s/ml_project/bento/service.py", line 84, in <module>
    preprocess_objs = model.custom_objects[key]
   File "/home/azureuser/vsts-agent/_work/_tool/Python/3.8.13/x64/lib/python3.8/site-packages/bentoml/_internal/models/model.py", line 121, in custom_objects
     self._custom_objects: dict[str, t.Any] | None = cloudpickle.load(
 TypeError: __new__() missing 1 required positional argument: 'etree'

any ideas? thanks alot!