MLOps and predictions (V10.1)¶

July 15, 2024

The DataRobot MLOps v10.1 release includes many new features and capabilities, described below. See additional details of Release 10.1 in the data and modeling and code-first release announcements.

New features and enhancements¶

GA¶

Create hosted custom metrics¶

Hosted custom metrics allow you to implement your organization's specialized metrics in a deployment, performing the metric calculation on custom jobs infrastructure. The custom metrics gallery provides a centralized library of pre-made, reusable, and shareable code implementing a variety of hosted custom metrics for predictive and generative models:

For more information, see the documentation.

Batch prediction output support for SAP HANA JDBC connector¶

DataRobot now supports JDBC write-back when you configure a JDBC prediction destination using a SAP HANA data connection through the Job Definitions UI or the Batch Prediction API.

For a complete list of supported output options, see the data sources supported for batch predictions.

Preview¶

Compute Feature Impact in the NextGen Registry¶

Feature Impact is now available for DataRobot and custom models in the NextGen Registry. On the Insights tab for a registered model version, you can compute Feature Impact using SHAP or permutation importance as a calculation method. This feature provides a high-level visualization that identifies which features are most strongly driving model decisions:

Preview documentation.

Feature flag ON by default: Enable SHAP for Custom Models in NextGen

Manage custom execution environments in the NextGen Registry¶

The Environments tab is now available in the NextGen registry, where you can create and manage custom execution environments for your custom models, jobs, applications, and notebooks:

Preview documentation.

Feature flag ON by default: Enable Custom Execution Environments NextGen UI

Predictions on DataRobot serverless environments¶

Create DataRobot serverless prediction environments to make scalable predictions with configurable compute instance settings. To create a DataRobot serverless prediction environment, when you add a prediction environment, select the DataRobot Serverless platform:

When you deploy a model to a DataRobot serverless prediction environment, you can enable real-time predictions and configure the compute instance settings in the Advanced Predictions Configuration:

Preview documentation.

Feature flags ON by default: Enable Real-time (Interactive) Predictions on K8s Prediction Environments, Enable Real-time GenAI Predictions on K8s Prediction Environments

Deprecations and migrations¶

Custom model training data assignment update¶

In DataRobot version 10.1, the assignment of training data to a custom model version—announced in the DataRobot version 9.1 release—replaces the deprecated method of assigning training data at the custom model level. This means that the “per custom model version” method is now the default, and the “per custom model” method is removed. The automatic conversion of any remaining custom models using the “per custom model” method occurs automatically, assigning the training data at the custom model version level. For most users, no action is required; however, if you have any remaining automation relying on unconverted custom models using the “per custom model” assignment method, you should update them to support the “per custom model version” method to avoid any gaps in functionality.

For a summary of the assignment method changes, review the Custom model training data assignment update documentation.

Tableau Analytics Extension and output adapter removal¶

DataRobot previously removed two Tableau Extensions: Insights, and What-If. With this update, the preview Tableau Analytics Extension is removed, along with the Tableau output adapter.

Decisions Flows¶

Support for Decisions Flows, deprecated earlier in the year, has now been removed. Data associated with Decisions Flows (deployments, registered models, model packages, and Decisions Flows themselves) will be deleted via database migration during upgrade to 10.1.

All product and company names are trademarks™ or registered® trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.