AI-102 Practice Question: Implement knowledge mining and information extraction solutions
You are implementing a knowledge mining solution with Azure AI Search that ingests data from Azure Blob Storage. The pipeline includes a custom skill that calls an external API for specialized entity extraction. The custom skill sometimes returns HTTP 429 (Too Many Requests). How should you handle this to ensure reliable indexing?
⚠ Common exam trap
AI-102 often tests the misconception that increasing timeout or reducing batch size solves rate limiting, when the correct approach is to implement a retry policy that respects the API's rate limits.
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
✓
Configure a retry policy on the custom skill
Configuring a retry policy on the custom skill is the correct way to handle HTTP 429 errors, as it allows the skill to retry the request after a delay, respecting the Retry-After header if provided. This ensures reliable indexing without overwhelming the external API.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Reduce the batch size in the indexer
Why it's wrong here
Shrinking batch size reduces parallel skill invocations per run, yet 429s stem from the external API's rate limit, which smaller batches only partially relieve without retry handling. Batch tuning suits throughput optimisation, not rate-limit recovery, which needs Retry-After-based retries.
- ✗
Increase the skill timeout
Why it's wrong here
Raising the timeout does not reduce request volume, so the external API keeps returning 429 and indexing still fails; throttling requires retry logic with exponential backoff and a batch size limit. Timeouts suit slow-but-successful calls, such as a skill whose API responds in 45 seconds.
- ✓
Configure a retry policy on the custom skill
Why this is correct
A retry policy on the custom skill handles transient HTTP 429 responses by reissuing the request after a delay, honouring Retry-After where supplied. This keeps indexing reliable without discarding enriched documents, directly addressing the throttling constraint described in the stem.
- ✗
Schedule the indexer to run less frequently
Why it's wrong here
Reducing indexer frequency does not address 429s, which occur when the custom skill exceeds the external API's rate limit during a run; the indexer still bursts requests. Throttling suits load management, but the fix here is retry logic honouring Retry-After.
Quick reference
Azure Blob Storage Tier Comparison
| Tier | Storage Cost | Retrieval Cost | Latency | Use Case |
|---|---|---|---|---|
| Hot | Highest | Lowest | Immediate | Active data, frequent reads |
| Cool | Lower | Higher | Immediate | Data accessed < once / month |
| Cold | Lower still | Higher | Immediate | Data accessed < once / quarter |
| Archive | Lowest | Highest + rehydration delay | Hours | Long-term compliance retention |
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.