Skip to content

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

Model package artifact creation workflow

Availability information

The updated model package creation workflow is off by default. Contact your DataRobot representative or administrator for information on enabling this feature.

Feature flag: Enable .mlpkg Artifact Creation for Model Packages

Now available as a public preview feature, the improved model package artifact creation workflow provides a clearer and more consistent path to model deployment with visible connections between a model and its associated model packages in the Model Registry. Using this new approach, when you deploy a model, you begin by providing model package details and adding the model package to the Model Registry. After you create the model package and allow the build to complete, you can deploy it by adding the deployment information.

Register and deploy a model from the Leaderboard

To register and deploy a model using this new workflow:

  1. From the Leaderboard, select the model to use for generating predictions, and then click Predict > Deploy.

  2. To follow best practices, DataRobot recommends that you first prepare the model for deployment. This process runs Feature Impact, retrains the model on a reduced feature list, and trains on a higher sample size, followed by the entire sample (latest data for date/time partitioned projects).

    • If the model has the Prepared For Deployment badge, proceed to the next step.

    • If the model doesn't have the Prepared For Deployment badge, click Prepare for deployment.

  3. On the Deploy model tab, provide the following model package information, and then click Add to Model Registry:

    Field Description
    Prediction threshold For binary classification models, enter the value a prediction score must exceed to be assigned to the positive class. The default value is 0.5.
    Model package name Enter a descriptive model package name. The default is the model name (followed by the prediction threshold for binary classification model packages).
    Model package description Optional. Enter a description of the model package.


    If you set the prediction threshold before the deployment preparation process, the value does not persist. When deploying the prepared model, if you want it to use a value other than the default, set the value after the model has the Prepared for Deployment badge.

  4. Allow the model to build. The Building status can take a few minutes, depending on the size of the model. A model package must have a Status of Ready before you can deploy it.

  5. In the Model Packages list, locate the model package you want to deploy, and then click Deploy.

  6. Add deployment information and create the deployment.

Deploy a model package from the Model Registry

To deploy a registered model using this new workflow:

  1. Click Model Registry > Model Packages.

  2. Click the Actions menu for the model package you want to deploy, and then click Deploy.

    The Status column shows the build status of the model package.

    If you deploy a model package that doesn't have a Status of Ready, the build process starts:

  3. Add deployment information and create the deployment.

You can also open a model package from the Model Registry and deploy it from Package Info tab:

Updated March 21, 2023
Back to top