DataRobot PartnersUnify your AI stack with our open platform, extend your cloud investments, and connect with service providers to help you build, deploy, or migrate to DataRobot.
This post was originally part of the DataRobot Community. Visit now to browse discussions and ask questions about DataRobot, AI Platform, data science, and more.
Creating a deployment begins with uploading a package into the Model Registry. The Model Registry is the central hub for all your model packages, and a package contains a file or set of files with information about your model; this varies depending on the type of model being deployed. Once the package is in the Model Registry you can create a deployment.
Figure 1. Model package
The Model Registry provides you with a consistent deployment, replacement, and management experience for all of your ML models. If the model built is in the DataRobot AutoML platform, the model package is automatically added to the Model Registry package list when the deployment gets created from the Leaderboard; otherwise packages are added to the package list manually by upload.
There are three kinds of model packages in the Model Registry:
models built within DataRobot,
your own model built outside of DataRobot that you upload into MLOps, and
your own external model hosted outside of DataRobot.
Figure 2. Model Registry with different types of models
A key difference is that DataRobot models and custom models have prediction requests received and processed within MLOps through an API call, while external models handle predictions in an outside environment, and after which the predictions are transferred back to MLOps for tracking.
The Model Registry provides the ability to register all of your models in one place to give you a consistent experience, regardless of the origin and location of a deployment. In all three cases, you use MLOps to track the predictions the model makes and assess the model accuracy just the same.