BigQuery ML is a Google Cloud service which lets you create and execute machine learning models in BigQuery ML by using standard SQL queries. With Vertex AI, you can use pre-trained and custom tooling all within a unified platform. When you register your BigQuery ML models in the Model Registry, you can manage them alongside your other ML models to easily version, evaluate, and deploy for prediction.
With this integration, you can choose which BigQuery ML models to register to the Model Registry. Once registered, you can deploy your BigQuery ML model to an endpoint for online prediction.
From BigQuery ML you can register:
- BigQuery ML built-in models
- BigQuery ML TensorFlow models
While BigQuery ML XGboost and ARIMA_PLUS models can be registered in Vertex AI Model Registry, they can't be deployed.
To learn how to integrate your BigQuery ML models with Vertex AI Model Registry, see BigQuery ML and Vertex AI Model Registry.
Notebook for Vertex AI Model Registry and BigQuery ML
This Notebook, describes how to use Model Registry and BigQuery ML to deploy and make predictions on your models.
This tutorial uses the following Google Cloud services and resources:
- Vertex AI model
- Vertex AI Model Registry resources
- Vertex AI
- Vertex AI Explainable AI
- Vertex AI Prediction
- BigQuery ML
The steps performed include:
- Train a new model using BigQuery ML
- Register the model to Vertex AI Model Registry
- Create a Vertex AI
- Deploy the
modelresource to the
endpointresource and enable XAI
- Make prediction requests to the model