Answer-first summary for fast verification
Answer: Chain the Vertex AI ModelUploadOp and ModelDeployOp components together
The correct answer is D. Using the Vertex AI ModelUploadOp and ModelDeployOp components is the simplest approach because both are pre-built components within Vertex AI Pipelines specifically designed for uploading models and deploying them to endpoints. This method offers a user-friendly interface and reduces code complexity, eliminating the need for writing custom code for model upload and deployment. Option A involves more manual coding and interaction with the REST API, Option B’s ModelEvaluationOp is meant for model evaluation, and Option C, although using the Python SDK, still requires more custom code and setup compared to the pre-built components.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
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?
A
Use the Vertex AI REST API within a custom component based on a vertex-ai/prediction/xgboost-cpu image
B
Use the Vertex AI ModelEvaluationOp component to evaluate the model
C
Use the Vertex AI SDK for Python within a custom component based on a python:3.10 image
D
Chain the Vertex AI ModelUploadOp and ModelDeployOp components together
No comments yet.