To add a model into the MLOps Model Registry that was built using the DataRobot AutoML or AutoTS platform, the first step is to download the model you want to deploy as a package file from the model Leaderboard. Navigate to your selected model on the Leaderboard, select Predict > Deploy.
Then simply click Generate and download model package.
Figure 3. Leaderboard clicks
Once processing completes, give the package a name and save it to your file system.
Next, navigate to the Model Registry. Under Model Packages select Add New Package and then select Importmodel package file from the dropdown menu. You can either drag and drop the model package file you just saved into the user interface, or you can use the file system browser to locate the file.
Figure 4. Add new package
Since all the information about the model is already known from within DataRobot, such as the target, the source training data, and the label threshold (if a binary classification model), you don’t need to supply any more information. But you may wish to edit the default name and description.
Figure 5. Registry package details
With the package now in the Model Registry, you can now use it to create a deployment.
If you’re a licensed DataRobot customer, search the in-app Platform Documentation for Using the Model Registry.