Implement knowledge mining and information extraction solutions →hardMultiple ChoiceObjective-mapped
AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are designing a knowledge mining solution that ingests content from SharePoint Online. The solution must index documents and also extract custom metadata such as project name and client ID using a custom skill. The custom skill is an Azure Function that calls an external API. The external API has a rate limit of 100 requests per minute. Your indexer processes 1000 documents per hour. How should you configure the indexer to avoid hitting the rate limit?
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
✓
Schedule the indexer to run every 2 hours with a batch size of 20.
Avoids the rate limit by not calling the external API, but it fails to meet the requirement to extract custom metadata using the specified custom skill. Option B schedules the indexer to run every 2 hours with a batch size of 20, which reduces the frequency of runs and limits the number of documents per batch, thereby keeping requests to the external API under 100 per minute. Option C increases the batch size to 100, which could cause each batch to make 100 requests, potentially exceeding the rate limit if multiple batches are processed concurrently. Option D increases maximum parallelism, allowing more batches to run concurrently and increasing the request rate, which could exceed the limit.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use a different custom skill that doesn't call the external API.
Why it's wrong here
Does not address requirement.
- ✓
Schedule the indexer to run every 2 hours with a batch size of 20.
Why this is correct
Spreads requests over time, staying under limit.
- ✗
Increase the indexer's batch size to 100.
Why it's wrong here
Larger batch means more requests per execution.
- ✗
Increase the indexer's maximum parallelism to 10.
Why it's wrong here
More parallelism increases request rate.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 945-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft 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 AI-102 exam.