Skip to content

Click in-app to access the full platform documentation for your version of DataRobot.

Monitor external multiclass deployments

Users with multiclass models deployed to external prediction environments can configure the MLOps agent to monitor their deployments. To do so, you must create a deployment in DataRobot with an external model package for the multiclass model.

When creating an external model package, you can indicate the prediction type for the model as multiclass:

Once indicated, via text or via upload of a CSV or TXT file, provide the target classes for your model (one class per line) in the Target classes field:

Once all fields for the model package are defined, click Create package. The package populates in the Model Registry and is available for use.

When you have configured an external model package for your multiclass model, follow the workflow to create a deployment with the external model package and configure it with the MLOps agent.


Updated November 5, 2021
Back to top