A data scientist has developed a BigQuery ML model gcp video

Full Certification Question

A data scientist has developed a BigQuery ML model and requests the creation of an ML pipeline for serving predictions. Your REST API application must fulfill the requirement of serving predictions for individual user IDs within a latency of under 100 milliseconds. The prediction query is as follows: SELECT predicted_label, user_id FROM ML.PREDICT (MODEL 'dataset.model', table user_features). How should you design the ML pipeline?