This error comes from trying to pickle the Pool object. don’t know why that’s happening. Here’s the line of code with the Pool object. source: https://github.com/dagster-io/dagster/issues/10412 Here’s the line of code in question:

catb_runner.predict_proba.run(Pool(X[feature_columns], cat_features=feature_columns))

If anyone else runs in to this: I solved it by building a custom runner: https://docs.bentoml.org/en/latest/concepts/runner.html#custom-model-runner passing in the Dataframe to the runner and using Pool inside the runner