Introduction to Vertex AI Model Registry

The Vertex AI Model Registry is a central repository where you can manage the lifecycle of your ML models. From the Model Registry, you have an overview of your models so you can better organize, track, and train new versions. When you have a model version you would like to deploy, you can assign it to an endpoint directly from the registry, or using aliases, deploy models to an endpoint.

The Vertex AI Model Registry supports custom models and all AutoML data types - text, tabular, image, and video. The Model Registry can also support BigQuery ML models. If you have models trained in BigQuery ML, you can register them with the Model Registry without needing to export them from BigQuery ML or import them into the Model Registry.

From the model version details page you can evaluate, deploy to an endpoint, set up batch prediction, and view specific model details. The Vertex AI Model Registry provides a straightforward and streamlined interface to manage and deploy your best models to production.

Common workflow

There are many valid workflows for working in the Model Registry. To get started, you might want to follow these guidelines to understand what you can do in the Model Registry and at what stage in your model-training journey.

  • Import models to the Model Registry.
  • Create new models, assign a model version the default alias, ready for production.
  • Add other aliases, or labels to help you manage and organize your models and model versions.
  • Deploy your models to an endpoint for online prediction.
  • Run batch prediction, and start your model evaluation pipeline.
  • View your model details and view performance metrics from the model details page.

To learn more about how to integrate your BigQuery ML models with Vertex AI, see the BigQuery ML documentation.

Search and discover models using Dataplex's Data Catalog service

Dataplex's Data Catalog service is a fully managed, scalable metadata management service that provides a centralized location to search for models across projects and regions.

For details, see Use Data Catalog to search for model and dataset resources.

What's next