AI-102 Practice Question: Implement knowledge mining and document intelligence solutions
A company uses Azure AI Search to index a large collection of scanned invoices stored in Azure Blob Storage. They have a skillset that includes an OCR skill to extract text from the invoices. The indexer is configured to run every night. They notice that the indexer takes a long time to complete and sometimes times out. They want to optimize the indexer performance without reducing the quality of the extracted text. What should they do?
⚠ Common exam trap
The trap here is thinking that reducing image resolution or disabling OCR will speed up the indexer, but that sacrifices the required text extraction quality.
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
✓
Enable incremental enrichment and cache the enriched data to avoid reprocessing unchanged documents.
Enabling incremental enrichment and caching is the best approach to optimize indexer performance for recurring runs. It avoids reprocessing documents that have not changed, thus reducing the workload on the OCR skill and other enrichments. This maintains the quality of extracted text because only new or modified documents are processed, while unchanged documents reuse cached enrichments. Other options either reduce quality or do not address the performance bottleneck.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Switch from the OCR skill to the Text Merge skill to combine text from multiple pages.
Why it's wrong here
The Text Merge skill merges text from multiple fields into one; it does not perform OCR. Scanned invoices require OCR to extract text from images. Using Text Merge would not extract any text from the images, leading to missing content. This option does not address the performance issue and would degrade quality.
- ✓
Enable incremental enrichment and cache the enriched data to avoid reprocessing unchanged documents.
Why this is correct
This is correct because incremental enrichment with caching allows the indexer to skip documents that have not changed since the last run, reusing previously enriched data. This reduces the amount of OCR processing required, significantly improving performance for subsequent runs. It maintains text quality because unchanged documents are not reprocessed, and only new or modified documents are enriched.
- ✗
Increase the indexer's batch size and reduce the number of parallel indexers.
Why it's wrong here
Increasing batch size and reducing parallelism would likely worsen performance. A larger batch size means more documents processed per batch, which can increase memory usage and processing time per batch. Reducing parallel indexers decreases throughput. To improve performance, you generally want to optimize parallelism and batch size based on resource limits, not reduce parallelism.
- ✗
Reduce the OCR skill's image resolution by setting the 'imageAction' to 'none' and relying on the document's embedded text.
Why it's wrong here
Setting imageAction to 'none' disables image extraction entirely, so the OCR skill would not run. For scanned invoices, the text is in the images, so this would result in no text extraction and poor search quality. This option sacrifices quality for performance, which is not acceptable per the requirement.
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
This AI-102 question is part of Courseiva's 761-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 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.