Answer-first summary for fast verification
Answer: Alter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint.
The correct answer is C. You can alter the model by using BigQuery ML and specify Vertex AI as the model registry. This approach allows you to manage and deploy your model directly from BigQuery ML without the need for retraining or exporting the model to Cloud Storage. This method is quick and efficient for deploying the model to a Vertex AI endpoint for online prediction. Options A and B involve unnecessary retraining, and Option D adds extra steps by requiring the export to Cloud Storage and then importing into Vertex AI.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
You recently used BigQuery ML to train an AutoML regression model for a project focused on predicting sales revenue. After thorough evaluation, you shared the results with your team and received positive feedback for the model's performance. Now, you need to deploy your model for online prediction in a production environment as quickly as possible to start making real-time predictions. What should you do?
A
Retrain the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint.
B
Retrain the model by using Vertex AI. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint.
C
Alter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint.
D
Export the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI Model Registry. Deploy the model to a Vertex AI endpoint.