# October 2024

> October 2024 - Read about DataRobot's new features, released in October, 2024.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T18:17:10.006323+00:00` (UTC).

## Primary page

- [October 2024](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html): Full documentation for this topic (HTML).

## Sections on this page

- [October 2024](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#october-2024): In-page section heading.
- [October features](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#october-features): In-page section heading.
- [GA](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#ga): In-page section heading.
- [New LLM, Anthropic Claude 3 Opus, now available](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#new-llm-anthropic-claude-3-Opus-now-available): In-page section heading.
- [Multiclass classification now GA in Workbench](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#multiclass-classification-now-GA-in-workbench): In-page section heading.
- [Geospatial modeling now available in Workbench](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#geospatial-modeling-now-available-in-workbench): In-page section heading.
- [Personal data detection now GA in SaaS, Self-Managed](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#personal-data-detection-now-ga-in-saas-self-managed): In-page section heading.
- [XEMP Individual Prediction Explanations now in Workbench](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#xemp-individual-prediction-explanations-now-in-workbench): In-page section heading.
- [Custom tasks now available for Self-Managed users](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#custom-tasks-now-available-for-self-managed-users): In-page section heading.
- [Manage network policies to limit access to public resources](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#manage-network-policies-to-limit-access-to-public-resources): In-page section heading.
- [Monitor EDA resource usage across an organization](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#monitor-eda-resource-usage-across-an-organization): In-page section heading.
- [Understand how individual catalog assets relate to other DataRobot entities](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#understand-how-individual-catalog-assets-relate-to-other-datarobot-entities): In-page section heading.
- [Automatically remove date features before running Autopilot](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#automatically-remove-data-features-before-running-autopilot): In-page section heading.
- [Support for SAP Datasphere connector in DataRobot](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#support-for-sap-datasphere-connector-in-datarobot): In-page section heading.
- [SAP Datasphere integration for batch predictions](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#sap-datasphere-integration-for-batch-predictions): In-page section heading.
- [Additional EDA insights added to Workbench](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#additional-eda-insights-added-to-workbench): In-page section heading.
- [Compliance documentation now available for registered text generation models](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#compliance-documentation-now-available-for-registered-text-generation-models): In-page section heading.
- [Evaluation and moderation for text generation models](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#evaluation-and-moderation-for-text-generation-models): In-page section heading.
- [Filtering and model replacement improvements in the NextGen Console](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#filtering-and-model-replacement-improvements-in-the-nextgen-console): In-page section heading.
- [Manage custom execution environments in the NextGen Registry](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#manage-custom-execution-environments-in-the-nextgen-registry): In-page section heading.
- [Customize feature drift tracking](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#customize-feature-drift-tracking): In-page section heading.
- [Calculate insights during custom model registration](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#calculate-insights-during-custom-model-registration): In-page section heading.
- [Link Registry and Console assets to a Use Case](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#link-registry-and-console-assets-to-a-use-case): In-page section heading.
- [Code-based retraining jobs](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#code-based-retraining-jobs): In-page section heading.
- [Custom model workers runtime parameter](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#custom-model-workers-runtime-parameter): In-page section heading.
- [Notebook and codespace port forwarding now GA](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#notebook-and-codespace-port-forwarding-now-ga): In-page section heading.
- [GPU support for notebooks now GA](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#gpu-support-for-notebooks-now-ga): In-page section heading.
- [Custom application runtime parameters now GA](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#custom-application-runtime-parameters-now-ga): In-page section heading.
- [Build custom applications from the template gallery](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#build-custom-applications-from-the-template-gallery): In-page section heading.
- [Chat generation Q&A application now GA](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#chat-generation-qa-application-now-ga): In-page section heading.
- [Preview](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#preview): In-page section heading.
- [Incremental learning support for dynamic datasets is now available](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#incremental-learning-support-for-dynamic-datasets-is-now-available): In-page section heading.
- [Template gallery for custom jobs](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#template-gallery-for-custom-jobs): In-page section heading.
- [Create and deploy vector databases](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#create-and-deploy-vector-databases): In-page section heading.
- [Geospatial monitoring for deployments](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#geospatial-monitoring-for-deployments): In-page section heading.
- [Prompt monitoring improvements for deployments](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#prompt-monitoring-improvements-for-deployments): In-page section heading.
- [Editable resource settings and runtime parameters for deployments](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#editable-resource-settings-and-runtime-parameters-for-deployments): In-page section heading.
- [Data Registry wrangling for batch predictions](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#data-registry-wrangling-for-batch-predictions): In-page section heading.
- [Code-first](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#code-first): In-page section heading.
- [Use the declarative API to provision DataRobot assets](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/october2024-announce.html#use-the-declarative-API-to-provision-datarobot-assets): In-page section heading.

## Related documentation

- [AI Platform releases](https://docs.datarobot.com/en/docs/release/index.html): Linked from this page.
- [Managed SaaS releases](https://docs.datarobot.com/en/docs/release/cloud-history/index.html): Linked from this page.
- [2024 AI Platform releases](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/index.html): Linked from this page.
- [Self-Managed AI Platform release notes](https://docs.datarobot.com/en/docs/release/archive-release-notes/index.html): Linked from this page.
- [LLM availability](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/llm-availability.html): Linked from this page.
- [March 2024](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/march2024-announce.html#multiclass-modeling-and-confusion-matrix): Linked from this page.
- [Geospatial insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-adv-experiment.html#geospatial-settings): Linked from this page.
- [Accuracy Over Space](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/acc-over-space.html): Linked from this page.
- [Anomaly Over Space](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/anom-over-space.html): Linked from this page.
- [personal data detection](https://docs.datarobot.com/en/docs/classic-ui/data/ai-catalog/catalog.html#personal-data-detection): Linked from this page.
- [Individual Prediction Explanations](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/shap-predex.html): Linked from this page.
- [Custom tasks](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/cml/cml-custom-tasks.html): Linked from this page.
- [limit the public resources users can access](https://docs.datarobot.com/en/docs/platform/admin/network-policy.html): Linked from this page.
- [EDA tab of the Resource Monitor](https://docs.datarobot.com/en/docs/platform/admin/monitoring/resource-monitor.html#eda-resources): Linked from this page.
- [Infotab](https://docs.datarobot.com/en/docs/classic-ui/data/ai-catalog/catalog-asset.html#impact-analysis): Linked from this page.
- [automatically remove date features](https://docs.datarobot.com/en/docs/classic-ui/modeling/build-models/adv-opt/additional.html): Linked from this page.
- [SAP Datasphere connector](https://docs.datarobot.com/en/docs/reference/data-ref/data-sources/wb-sap.html): Linked from this page.
- [batch prediction jobs](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-prediction-jobs.html#schedule-recurring-batch-prediction-jobs): Linked from this page.
- [intake](https://docs.datarobot.com/en/docs/api/reference/batch-prediction-api/intake-options.html#sap-datasphere-scoring): Linked from this page.
- [output](https://docs.datarobot.com/en/docs/api/reference/batch-prediction-api/output-options.html#sap-datasphere-write): Linked from this page.
- [EDA insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/dataprep/explore-data/eda-insights.html): Linked from this page.
- [compliance documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-compliance-doc.html): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-configure-evaluation-moderation.html): Linked from this page.
- [deployment filtering](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-overview/nxt-dashboard.html#filter-deployments): Linked from this page.
- [model replacement experience](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-overview/nxt-deployment-actions.html#replace-deployed-models): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-environment-workshop/nxt-add-custom-env.html): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-deploy-models.html#feature-selection-for-feature-drift): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-register-cus-models.html#custom-model-build-troubleshooting): Linked from this page.
- [registered model](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-view-manage-reg-models.html#link-a-version-to-a-use-case): Linked from this page.
- [application](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/manage-custom-app.html#link-to-a-use-case): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-jobs-workshop/nxt-create-jobs/nxt-create-retraining-job.html): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/custom-model-runtime-parameters.html#datarobot-reserved-runtime-parameters): Linked from this page.
- [port forwarding](https://docs.datarobot.com/en/docs/workbench/wb-notebook/wb-code-nb/wb-env-nb.html#manage-exposed-ports): Linked from this page.
- [templates from which you can build custom applications](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/upload-custom-app.html): Linked from this page.
- [create a chat generation Q&A application](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/create-qa-app.html): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-jobs-workshop/nxt-create-jobs/index.html): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-create-custom-model.html#vector-databases): Linked from this page.
- [Data drift](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-data-drift.html#drift-over-space-chart): Linked from this page.
- [Accuracy](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-accuracy.html#accuracy-over-space-chart): Linked from this page.
- [enable segmented analysis](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-settings/nxt-service-health-settings.html#select-segments-for-analysis): Linked from this page.
- [ingest](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/location-ai/lai-ingest.html): Linked from this page.
- [custom metric templates](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-custom-metrics.html#add-hosted-custom-metrics-from-the-gallery): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-settings/nxt-resource-settings.html): Linked from this page.
- [wrangled](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/dataprep/wrangle-data/index.html): Linked from this page.
- [make predictions with a model before deployment](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/make-predictions.html): Linked from this page.
- [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-make-predictions.html): Linked from this page.

## Documentation content

## October 2024

October 30, 2024

This page provides announcements of newly released features available in DataRobot's SaaS multi-tenant AI Platform, with links to additional resources. From the release center, you can also access:

- Current month's announcements
- Self-Managed AI Platform release notes

## October features

The following table lists each new feature:

**Features grouped by capability**

| Name | GA | Preview |
| --- | --- | --- |
| GenAI |  |  |
| New LLM, Anthropic Claude 3 Opus, now available | ✔ |  |
| Applications |  |  |
| Custom application runtime parameters now GA | ✔ |  |
| Build custom applications from the template gallery | ✔ |  |
| Chat generation Q&A application now GA | ✔ |  |
| Data |  |  |
| Understand how individual catalog assets relate to other DataRobot entities | ✔ |  |
| Support for SAP Datasphere connector in DataRobot | ✔* |  |
| Additional EDA insights added to Workbench | ✔ |  |
| Incremental learning support for dynamic datasets is now available |  | ✔ |
| Modeling |  |  |
| Multiclass classification now GA in Workbench | ✔ |  |
| Geospatial modeling now available in Workbench | ✔ |  |
| Personal data detection now GA in SaaS, Self-Managed | ✔ |  |
| XEMP Individual Prediction Explanations now in Workbench | ✔ |  |
| Custom tasks now available for Self-Managed users | ✔ |  |
| Automatically remove date features before running Autopilot | ✔ |  |
| Predictions and MLOps |  |  |
| Compliance documentation now available for registered text generation models | ✔* |  |
| Evaluation and moderation for text generation models | ✔* |  |
| SAP Datasphere integration for batch predictions | ✔* |  |
| Filtering and model replacement improvements in the NextGen Console | ✔ |  |
| Manage custom execution environments in the NextGen Registry | ✔ |  |
| Customize feature drift tracking | ✔ |  |
| Calculate insights during custom model registration | ✔ |  |
| Link Registry and Console assets to a Use Case | ✔ |  |
| Code-based retraining jobs | ✔ |  |
| Custom model workers runtime parameter | ✔ |  |
| Template gallery for custom jobs |  | ✔ |
| Create and deploy vector databases |  | ✔* |
| Geospatial monitoring for deployments |  | ✔ |
| Prompt monitoring improvements for deployments |  | ✔* |
| Editable resource settings and runtime parameters for deployments |  | ✔ |
| Data Registry wrangling for batch predictions |  | ✔ |
| Notebooks |  |  |
| Notebook and codespace port forwarding now GA | ✔ |  |
| GPU support for notebooks now GA | ✔* |  |
| Admin |  |  |
| Manage network policies to limit access to public resources | ✔ |  |
| Monitor EDA resource usage across an organization | ✔ |  |
| API |  |  |
| Create vector databases with unstructured PDF documents | ✔ |  |
| Use the declarative API to provision DataRobot assets | ✔ |  |

*Premium

### GA

#### New LLM, Anthropic Claude 3 Opus, now available

Now generally available, Anthropic Claude 3 Opus brings support for another Claude-family offering to the DataRobot GenAI product. Each model in the family is targeted at specific needs; Claude 3 Opus, the largest model of the Claude family, excels at heavyweight reasoning and complicated tasks. See the full list of [LLM availability](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/llm-availability.html) in DataRobot, with links to creator documentation for assistance in choosing the appropriate model.

#### Multiclass classification now GA in Workbench

Initially released to Workbench in [March 2024](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/march2024-announce.html#multiclass-modeling-and-confusion-matrix), multiclass modeling and the associated confusion matrix are now generally available. To support an expansive set of multiclass modeling experiments—classification problems in which the answer has more than two outcomes—DataRobot provides support for an unlimited number of classes using aggregation.

#### Geospatial modeling now available in Workbench

To help gain insights into geospatial patterns in your data, you can now natively ingest common geospatial formats and build enhanced model blueprints with spatially-explicit modeling tasks when building in Workbench.  During experiment setup, from Additional settings, select a location feature in the [Geospatial insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-adv-experiment.html#geospatial-settings) section and make sure that feature is in the modeling feature list. DataRobot will then create geospatial insights— [Accuracy Over Space](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/acc-over-space.html) for supervised projects and [Anomaly Over Space](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/anom-over-space.html) for unsupervised.

#### Personal data detection now GA in SaaS, Self-Managed

Because the use of personal data as a modeling feature is forbidden in some regulated use cases, DataRobot Classic provides [personal data detection](https://docs.datarobot.com/en/docs/classic-ui/data/ai-catalog/catalog.html#personal-data-detection) capabilities. The feature is now generally available in both SaaS and self-managed environments. Access the check after uploading data to the AI Catalog.

#### XEMP Individual Prediction Explanations now in Workbench

Workbench now offers two methodologies for computing [Individual Prediction Explanations](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/shap-predex.html): SHAP (based on Shapley Values) and XEMP (eXemplar-based Explanations of Model Predictions). This insight, regardless of method, helps explain what drives predictions. The XEMP-based explanations are a proprietary method that support all models—they have long been available in DataRobot Classic. In Workbench, they are only available in experiments that don't support SHAP.

#### Custom tasks now available for Self-Managed users

[Custom tasks](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/cml/cml-custom-tasks.html) allow you to add custom vertices into a DataRobot blueprint, and then train, evaluate, and deploy that blueprint in the same way as you would for any DataRobot-generated blueprint. With v10.2 the functionality is available via DataRobot Classic and the API for on-premise installations as well.

#### Manage network policies to limit access to public resources

By default, some DataRobot capabilities, including Notebooks, have full public internet access from within the cluster DataRobot is deployed on; however, admins can [limit the public resources users can access](https://docs.datarobot.com/en/docs/platform/admin/network-policy.html) within DataRobot by setting network access controls. To do so, open User settings > Policies and enable the network policy control toggle. When enabled, users cannot access public resources from within DataRobot.

#### Monitor EDA resource usage across an organization

Now generally available, administrators can monitor the number of configured workers being used for EDA1 and related tasks on the [EDA tab of the Resource Monitor](https://docs.datarobot.com/en/docs/platform/admin/monitoring/resource-monitor.html#eda-resources). The Resource Monitor provides visibility into DataRobot's active modeling and EDA workers across the installation, providing general information about the current state of the application and specific information about the status of components.

#### Understand how individual catalog assets relate to other DataRobot entities

The AI Catalog serves as a centralized collaboration hub for working with data and related assets in DataRobot. On the [Infotab](https://docs.datarobot.com/en/docs/classic-ui/data/ai-catalog/catalog-asset.html#impact-analysis) for individual assets, you can now see how other entities in the application are related to—or dependent on—the current asset. This is useful for a number of reasons, allowing you to view how popular an item is based on the number of projects in which it is used, understand which other entities might be affected if you were to make changes or deletions, and gain understanding on how the entity is used.

#### Automatically remove date features before running Autopilot

When setting up a non-time aware project in DataRobot Classic, you can now [automatically remove date features](https://docs.datarobot.com/en/docs/classic-ui/modeling/build-models/adv-opt/additional.html) from the feature list you want to use  to run Autopilot. To do so, open Advanced options for the project, select the Additional tab, and then select Remove date features from selected list and create new modeling feature list. Enabling this parameter duplicates the selected feature list, removes raw date features, and uses the new list to run Autopilot. Excluding raw date features from non-time aware projects can prevent issues like overfitting.

#### Support for SAP Datasphere connector in DataRobot

Available as a premium feature, DataRobot now supports the [SAP Datasphere connector](https://docs.datarobot.com/en/docs/reference/data-ref/data-sources/wb-sap.html), available for preview, in both NextGen and DataRobot Classic.

Feature flag OFF by default: Enable SAP Datasphere Connector (Premium feature)

#### SAP Datasphere integration for batch predictions

Available as a premium feature, SAP Datasphere is supported as an intake source and output destination for [batch prediction jobs](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-prediction-jobs.html#schedule-recurring-batch-prediction-jobs).

Feature flags OFF by default: Enable SAP Datasphere Connector (Premium feature), Enable SAP Datasphere Batch Predictions Integration (Premium feature)

For more information, see the prediction [intake](https://docs.datarobot.com/en/docs/api/reference/batch-prediction-api/intake-options.html#sap-datasphere-scoring) and [output](https://docs.datarobot.com/en/docs/api/reference/batch-prediction-api/output-options.html#sap-datasphere-write) options documentation.

#### Additional EDA insights added to Workbench

This release introduces the following [EDA insights](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/dataprep/explore-data/eda-insights.html) on the Features tab of the data explore page in Workbench:

- Data quality checks appear as indicators on theFeaturestab of the data explore page as well as insights for individual features.
- TheHistogramchart displays data quality issues with outliers.
- TheFrequent Valueschart reports inliers, disguised missing values, and excess zeros.
- Feature lineage insight for Feature Discovery datasets shows how a feature was generated.

#### Compliance documentation now available for registered text generation models

DataRobot has long provided model development documentation that can be used for regulatory validation of predictive models. Now, the [compliance documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-compliance-doc.html) is expanded to include auto-generated documentation for text generation models on the Models tab in Registry. For DataRobot natively-supported LLMs, the document helps reduce the time spent generating reports, including model overview, informative resources, and most notably, model performance and stability tests. For non-natively supported LLMs, the generated document can serve as a template with all necessary sections. Generating compliance documentation for text generation models requires the Enable Compliance Documentation and Enable Gen AI Experimentation feature flags.

#### Evaluation and moderation for text generation models

Evaluation and moderation guardrails help your organization block prompt injection and hateful, toxic, or inappropriate prompts and responses. It can also prevent hallucinations or low-confidence responses and, more generally, keep the model on topic. In addition, these guardrails can safeguard against the sharing of personally identifiable information (PII). Many evaluation and moderation guardrails connect a deployed text generation model (LLM) to a deployed guard model. These guard models make predictions on LLM prompts and responses and then report these predictions and statistics to the central LLM deployment. To use evaluation and moderation guardrails, first, create and deploy guard models to make predictions on an LLM's prompts or responses; for example, a guard model could identify prompt injection or toxic responses. Then, when you create a custom model with the Text Generation target type, define one or more evaluation and moderation guardrails. The GA Premium release of this feature introduces general configuration settings for moderation timeout and evaluation and moderation logs.

Feature flags OFF by default: Enable Moderation Guardrails (Premium feature), Enable Global Models in the Model Registry (Premium feature), Enable Additional Custom Model Output in Prediction Responses

For more information, see the [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-configure-evaluation-moderation.html).

#### Filtering and model replacement improvements in the NextGen Console

This update to the NextGen Console improves [deployment filtering](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-overview/nxt-dashboard.html#filter-deployments) and updates the [model replacement experience](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-overview/nxt-deployment-actions.html#replace-deployed-models) to provide a more intuitive replacement workflow.

**Deployment filtering:**
On the Console > Deployments tab, you can now filter on Created by me, Tags, and Model type.

[https://docs.datarobot.com/en/docs/images/nxt-deployment-filter-selector.png](https://docs.datarobot.com/en/docs/images/nxt-deployment-filter-selector.png)

**Model replacement:**
On the Console > Deployments tab, or a deployment's Overview, you can access the updated model replacement workflow from the [model actions](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-overview/nxt-deployment-actions.html) menu.

[https://docs.datarobot.com/en/docs/images/nxt-model-replace-selection.png](https://docs.datarobot.com/en/docs/images/nxt-model-replace-selection.png)


#### 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:

For more information, see the [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-environment-workshop/nxt-add-custom-env.html).

#### Customize feature drift tracking

When you enable feature drift tracking for a deployment, you can now customize the features selected for tracking. During or after the deployment process, in the Feature drift section of the deployment settings, choose a feature selection strategy, either allowing DataRobot to automatically select 25 features, or selecting up to 25 features manually.

**During deployment:**
[https://docs.datarobot.com/en/docs/images/nxt-data-drift-deploy-feature-settings.png](https://docs.datarobot.com/en/docs/images/nxt-data-drift-deploy-feature-settings.png)

**After deployment:**
[https://docs.datarobot.com/en/docs/images/nxt-data-drift-feature-drift-settings.png](https://docs.datarobot.com/en/docs/images/nxt-data-drift-feature-drift-settings.png)


For more information, see the [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-deploy-models.html#feature-selection-for-feature-drift).

#### Calculate insights during custom model registration

For custom models with training data assigned, DataRobot now computes model Insights and Prediction Explanation previews during model registration, instead of during model deployment. In addition, new model logs accessible from the model workshop can help you diagnose errors during the Insight computation process.

For more information, see the [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-register-cus-models.html#custom-model-build-troubleshooting).

#### Link Registry and Console assets to a Use Case

Associate registered model versions, model deployments, and custom applications to a Use Case with the new Use Case linking functionality. Link these assets to an existing Use Case, create a new Use Case, or manage the list of linked Use Cases.

**Select Use Case:**
[https://docs.datarobot.com/en/docs/images/wb-select-use-case.png](https://docs.datarobot.com/en/docs/images/wb-select-use-case.png)

**Create Use Case:**
[https://docs.datarobot.com/en/docs/images/wb-create-use-case.png](https://docs.datarobot.com/en/docs/images/wb-create-use-case.png)

**Managed linked Use Cases(#):**
[https://docs.datarobot.com/en/docs/images/wb-manage-use-case.png](https://docs.datarobot.com/en/docs/images/wb-manage-use-case.png)


For more information, see the [registered model](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-view-manage-reg-models.html#link-a-version-to-a-use-case), [deployment](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-overview/nxt-deployment-actions.html#link-to-a-use-case), and [application](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/manage-custom-app.html#link-to-a-use-case) linking documentation.

#### Code-based retraining jobs

Add a job, manually or from a template, implementing a code-based retraining policy. To view and add retraining jobs, navigate to the Jobs > Retraining tab, and then:

- To add a new retraining job manually, click+ Add new retraining job(or the minimized add buttonwhen the job panel is open).
- To create a retraining job from a template, next to the add button, click, and then, underRetraining, clickCreate new from template.

For more information, see the [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-jobs-workshop/nxt-create-jobs/nxt-create-retraining-job.html).

#### Custom model workers runtime parameter

A new DataRobot-reserved runtime parameter, `CUSTOM_MODEL_WORKERS`, is available for custom model configuration. This numeric runtime parameter allows each replica to handle the set number of concurrent processes. This option is intended for process safe custom models, primarily in generative AI use cases.

> [!WARNING] Custom model process safety
> When enabling and configuring `CUSTOM_MODEL_WORKERS`, ensure that your model is process safe. This configuration option is only intended for process safe custom models, it is not intended for general use with custom models to make them more resource efficient. Only process safe custom models with I/O-bound tasks (like proxy models) benefit from utilizing CPU resources this way.

For more information, see the [documentation](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/custom-model-runtime-parameters.html#datarobot-reserved-runtime-parameters).

#### Notebook and codespace port forwarding now GA

Now generally available, you can enable [port forwarding](https://docs.datarobot.com/en/docs/workbench/wb-notebook/wb-code-nb/wb-env-nb.html#manage-exposed-ports) for notebooks and codespaces to access web applications launched by tools and libraries like MLflow and Streamlit. When developing locally, the web application is accessible at `http://localhost:PORT`; however, when developing in a hosted DataRobot environment, the port that the web application is running on (in the session container) must be forwarded to access the application. You can expose up to five ports in one notebook or codespace.

#### GPU support for notebooks now GA

GPU support for Notebook and Codespace sessions is now available as a GA Premium feature for managed AI Platform users. When configuring the environment for your DataRobot Notebook or Codespace session, you can select a GPU machine from the list of resource types. DataRobot also provides GPU-optimized built-in environments that you can select from to use for your session. These environment images contain the necessary GPU drivers as well as GPU-accelerated packages like TensorFlow, PyTorch, and RAPIDS.

#### Custom application runtime parameters now GA

Now generally available, you can [configure the resources and runtime parameters for application sources](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/manage-custom-app.html#runtime-parameters) in the NextGen Registry. The resources bundle determines the maximum amount of memory and CPU that an application can consume to minimize potential environment errors in production. You can create and define runtime parameters used by the custom application by including them in the `metadata.yaml` file built from the application source.

#### Build custom applications from the template gallery

DataRobot provides [templates from which you can build custom applications](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/upload-custom-app.html). These templates allow you to leverage pre-built application front-ends, out of the box, and offer extensive customization options. You can leverage a model that has already been deployed to quickly start and access a Streamlit, Flask, or Slack application. Use a custom application template as a simple method for building and running custom code within DataRobot.

#### Chat generation Q&A application now GA

Now generally available, you can leveraging generative AI to [create a chat generation Q&A application](https://docs.datarobot.com/en/docs/wb-apps/custom-apps/create-qa-app.html). Explore Q&A use cases, make business decisions, and showcase business value. The Q&A app offers an intuitive and responsive way to prototype, explore, and share the results of LLM models you've built, including with non-DataRobot users, to expand its usability.

You can also use a code-first workflow to manage the chat generation Q&A application. To access the flow, navigate to [DataRobot's GitHub repo](https://github.com/datarobot-oss/qa-app-streamlit). The repo contains a modifiable template for application components.

### Preview

#### Incremental learning support for dynamic datasets is now available

Support for modeling on dynamic datasets larger than 10GB, for example, data in a Snowflake, BigQuery, or Databricks data source, is now available. When configuring the experiment, set an ordering feature to create a deterministic sample from the dataset and then begin incremental modeling as usual. After model building starts, View experiment info now reports the selected ordering feature.

Feature flags ON by default: Enable incremental learning, Enable dynamic datasets in Workbench, Enable data chunking service

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-adv-experiment.html#configure-incremental-learning).

#### Template gallery for custom jobs

The custom jobs template gallery is now available for the generic, notification, and retraining job types—in addition to custom metric jobs. To access the new template gallery, from the Registry > Jobs tab, create a job from a template for any job type.

Feature flag ON by default: Enable Custom Jobs Template Gallery

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-jobs-workshop/nxt-create-jobs/index.html).

#### Create and deploy vector databases

With the vector database target type in the model workshop, you can [register](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-register-cus-models.html) and [deploy](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-deploy-models.html) vector databases, as you would any other custom model.

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-create-custom-model.html#vector-databases).

#### Geospatial monitoring for deployments

For a deployed binary classification, regression, or multiclass model built with location data in the training dataset, you can now leverage DataRobot Location AI to perform geospatial monitoring on the deployment's [Data drift](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-data-drift.html#drift-over-space-chart) and [Accuracy](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-accuracy.html#accuracy-over-space-chart) tabs. To enable geospatial analysis for a deployment, [enable segmented analysis](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-settings/nxt-service-health-settings.html#select-segments-for-analysis) and define a segment for the location feature `geometry`, generated during location data [ingest](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/location-ai/lai-ingest.html). The `geometry` segment contains the identifier used to segment the world into a grid of [H3 cells](https://h3geo.org/).

**Drift over space:**
[https://docs.datarobot.com/en/docs/images/nxt-drift-over-space-chart.png](https://docs.datarobot.com/en/docs/images/nxt-drift-over-space-chart.png)

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-data-drift.html#drift-over-space-chart)

**Accuracy over space:**
[https://docs.datarobot.com/en/docs/images/nxt-accuracy-over-space-chart.png](https://docs.datarobot.com/en/docs/images/nxt-accuracy-over-space-chart.png)

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-accuracy.html#accuracy-over-space-chart).


Feature flags ON by default: Enable Geospatial Features Monitoring, Enable Geospatial Features in Workbench

#### Prompt monitoring improvements for deployments

For deployed text generation models, the Monitoring > Data exploration tab includes additional sort and filter options on the Tracing table, providing new ways to interact with a Generative AI deployment's stored prompt and response data and gain insight into a model's performance through the configured custom metrics. In addition, this release introduces [custom metric templates](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-custom-metrics.html#add-hosted-custom-metrics-from-the-gallery) for Cosine Similarity and Euclidean Distance.

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-monitoring/nxt-custom-metrics.html#explore-metric-data).

Feature flags OFF by default: Enable Data Quality Table for Text Generation Target Types (Premium feature), Enable Actuals Storage for Generative Models (Premium feature)

Feature flags ON by default: Enable Custom Jobs Template Gallery

#### Editable resource settings and runtime parameters for deployments

For deployed custom models, the custom model CPU (or GPU) resource bundle and runtime parameters defined during [custom model assembly](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-workshop/nxt-create-custom-model.html#configure-custom-model-resource-settings) are now editable after assembly.

**Resource bundles:**
If the custom model is deployed on a DataRobot Serverless prediction environment and the deployment is inactive, you can modify the Resource bundle settings from the Resources tab.

[https://docs.datarobot.com/en/docs/images/nxt-deploy-resource-settings-bundle.png](https://docs.datarobot.com/en/docs/images/nxt-deploy-resource-settings-bundle.png)

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-settings/nxt-resource-settings.html)

**Runtime parameters:**
You can modify a custom model's runtime parameters during or after the deployment process.

[https://docs.datarobot.com/en/docs/images/nxt-deploy-settings-runtime-params.png](https://docs.datarobot.com/en/docs/images/nxt-deploy-settings-runtime-params.png)

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-deploy-models.html#runtime-parameters)


Feature flag ON by default: Enable Editing Custom Model Runtime-Parameters on Deployments

Feature flags OFF by default: Enable Resource Bundles, Enable Custom Model GPU Inference (Premium feature)

#### Data Registry wrangling for batch predictions

Use a deployment's Predictions > Make predictions tab to make batch predictions on a recipe [wrangled](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/dataprep/wrangle-data/index.html) from the Data Registry. Batch predictions are a method of making predictions with large datasets, in which you pass input data and get predictions for each row. In the Prediction dataset box, click Choose file > Wrangler recipe, then pick a recipe from the Data Registry:

> [!TIP] Predictions in Workbench
> Batch predictions on recipes wrangled from the Data Registry are also available in Workbench. To [make predictions with a model before deployment](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/make-predictions.html), select the model from the Models list in an experiment and then click Model actions > Make predictions.

You can also schedule [batch prediction jobs](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-prediction-jobs.html) by specifying the prediction data source and destination and determining when DataRobot runs the predictions.

Preview [documentation](https://docs.datarobot.com/en/docs/workbench/nxt-console/nxt-predictions/nxt-make-predictions.html).

Feature flag OFF by default: Enable Wrangling Pushdown for Data Registry Datasets

### Code-first

#### Use the declarative API to provision DataRobot assets

You can use the DataRobot declarative API as a code-first method for provisioning resources end-to-end in a way that is both repeatable and scalable. Supporting both [Terraform](https://registry.terraform.io/providers/datarobot-community/datarobot/latest) and [Pulumi](https://www.pulumi.com/registry/packages/datarobot/), you can use the declarative API to programmatically provision DataRobot entities such as models, deployments, applications, and more. The declarative API allows you to:

- Specify the desired end state of infrastructure, simplifying management and enhancing adaptability across cloud providers.
- Automate the provisioning of DataRobot assets to ensure consistency across environments and alleviate concerns about execution order. Terraform and Pulumi allow you to provision in two phases: planning and application. You can view a plan that outlines what resources are created before committing to provisioning actions, and then resolve any infrastructure dependencies on your behalf when a change is made. Then, you can execute the provisioning separately. This makes provisioning easier to manage within a complex infrastructure. You can preview the impacts that changes will have to DataRobot assets downstream in the workflow.
- Simplify version control.
- Use application templates to reduce workflow duplication and ensure consistency.
- Integrate with DevOps and CI/CD to ensure predictable, consistent infrastructure and reduce deployment risks.

Review an example below of how you can use the declarative API to provision DataRobot resources using the Pulumi CLI:

```
import pulumi_datarobot as datarobot
import pulumi
import os

for var in [
    "OPENAI_API_KEY",
    "OPENAI_API_BASE",
    "OPENAI_API_DEPLOYMENT_ID",
    "OPENAI_API_VERSION",
]:
    assert var in os.environ

pe = datarobot.PredictionEnvironment(
    "pulumi_serverless_env", platform="datarobotServerless"
)

credential = datarobot.ApiTokenCredential(
    "pulumi_credential", api_token=os.environ["OPENAI_API_KEY"]
)

cm = datarobot.CustomModel(
    "pulumi_custom_model",
    base_environment_id="65f9b27eab986d30d4c64268",  # GenAI 3.11 w/ moderations
    folder_path="model/",
    runtime_parameter_values=[
        {"key": "OPENAI_API_KEY", "type": "credential", "value": credential.id},
        {
            "key": "OPENAI_API_BASE",
            "type": "string",
            "value": os.environ["OPENAI_API_BASE"],
        },
        {
            "key": "OPENAI_API_DEPLOYMENT_ID",
            "type": "string",
            "value": os.environ["OPENAI_API_DEPLOYMENT_ID"],
        },
        {
            "key": "OPENAI_API_VERSION",
            "type": "string",
            "value": os.environ["OPENAI_API_VERSION"],
        },
    ],
    target_name="resultText",
    target_type="TextGeneration",
)

rm = datarobot.RegisteredModel(
    resource_name="pulumi_registered_model",
    name=None,
    custom_model_version_id=cm.version_id,
)

d = datarobot.Deployment(
    "pulumi_deployment",
    label="pulumi_deployment",
    prediction_environment_id=pe.id,
    registered_model_version_id=rm.version_id,
)

pulumi.export("deployment_id", d.id)
```