Appendix A: Custom Recipes

This appendix describes how to use custom recipes in Driverless AI. You’re welcome to create your own recipes for models, scorers and transformers or select one from a number of open source recipes available in the driverlessai-recipes repository.

In most cases (especially for complex recipes), MOJO for model deployment is not available out of the box. But, it is possible to get the MOJO. Contact support@h2o.ai for more information about creating MOJOs for custom recipes. The Python Scoring Pipeline for deployment has full support for custom recipes.

To enable Shapley calculations in MLI, custom model recipes must use the has_pred_contribs method. Refer to the model recipe template for more info.

Additional Resources