You are developing an ML pipeline using Vertex AI Pipelines for an online inference system. Your task involves uploading a new version of an XGBoost model to the Vertex AI Model Registry and deploying it to Vertex AI Endpoints. Given the need to minimize complexity and use the simplest approach, what should you do?

Exam-Like

Use the Vertex AI REST API within a custom component based on a vertex-ai/prediction/xgboost-cpu image

14.7%

Use the Vertex AI ModelEvaluationOp component to evaluate the model

7.6%

Use the Vertex AI SDK for Python within a custom component based on a python:3.10 image

10.6%

Chain the Vertex AI ModelUploadOp and ModelDeployOp components together

67.1%

Google Professional Machine Learning Engineer