PMLE Serving and Scaling Models Practice Question
You are using Vertex AI Vector Search with an approximate nearest neighbor index. You need to update the index with new data every hour. The updates must be available for queries immediately. Which update method should you use?
⚠ Common exam trap
A common misconception is that updating an approximate nearest neighbor (ANN) index requires recreating and redeploying it. However, Vertex AI Vector Search provides a streaming API that enables real-time insert, update, and delete operations, making new data immediately available for queries without the overhead of full index rebuilds.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Streaming updates using the streaming API.
Vertex AI Vector Search supports streaming updates via its streaming API, which allows you to insert, update, or delete vectors in real time. This ensures that new data is immediately available for approximate nearest neighbor (ANN) queries without requiring index recreation or redeployment, meeting the requirement for hourly updates with instant query availability.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Recreate the index every hour using a scheduled job.
Why it's wrong here
Rebuilding the index hourly cannot meet the immediate-availability requirement, because a full rebuild takes time and the new index must be deployed and swapped in before queries see it. It is tempting because scheduled rebuilds suit batch refreshes where staleness of hours is acceptable, such as nightly catalogue regeneration.
- ✗
Batch update by creating a new index and deploying it.
Why it's wrong here
Building and deploying a new index rebuilds the whole dataset, so hourly changes are not queryable until that deployment completes, breaking the immediate-availability requirement. Batch rebuilds suit infrequent, large-scale refreshes where a maintenance window is acceptable.
- ✓
Streaming updates using the streaming API.
Why this is correct
Streaming updates via the streaming API mutate the deployed index in place, so newly added or removed datapoints become queryable within seconds. This satisfies the hourly refresh with immediate query visibility, unlike batch rebuilds that require reindexing and redeployment.
- ✗
Use a brute-force index that supports real-time updates.
Why it's wrong here
A brute-force index compares every vector, so query latency and cost scale linearly with dataset size, making it unsuitable for a production workload needing hourly updates at scale. It is tempting because brute-force indexes do support true real-time upserts, which suits small or latency-tolerant datasets.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.