AI-102 Practice Test 47 — 15 Questions

Question 1

Your company has a large set of PDF documents stored in Azure Blob Storage. You need to index these documents in Azure Cognitive Search so that users can search the text content. What is the first step you should take?

Accepted Answer

Create a data source that connects to Azure Blob Storage.. Option A is correct because you need to create a data source that points to the Blob Storage container to fetch the documents. Option B is wrong because you need a data source before creating an indexer. Option C is wrong because the indexer will create the index based on the data source. Option D is wrong because the indexer will handle skillset execution.

Answer

Create an index with a field for each metadata property.

Answer

Create a skillset to extract text from PDFs.

Answer

Create an indexer that runs daily.

Question 2

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?

Accepted Answer

Schedule the indexer to run every 2 hours with a batch size of 20.. Option B uses scheduling to spread the load. Option A increases parallelism, making it worse. Option C increases batch size, causing more requests per batch. Option D uses a different skill but doesn't address rate limit.

Answer

Use a different custom skill that doesn't call the external API.

Answer

Increase the indexer's batch size to 100.

Answer

Increase the indexer's maximum parallelism to 10.

Question 3

You are designing an enterprise search solution using Azure AI Search. The solution must index data from multiple sources: SQL Database, SharePoint Online, and custom REST APIs. The search index must support faceted navigation and filtering by metadata such as department and document type. You also need to ensure that updates to source data are reflected in the index within 5 minutes. Which approach should you use?

Accepted Answer

Configure indexers for SQL and SharePoint, and use the push API for the REST API. Schedule indexers to run every 5 minutes.. Azure AI Search indexers can be scheduled to run periodically (e.g., every 5 minutes) and support various data sources including Azure SQL, SharePoint (via Graph API or custom indexer), and custom APIs via a custom indexer or push API. Using indexers for SQL and SharePoint, and a push API for the REST API, allows near-real-time updates. Option A is wrong because the push API alone for all sources would require custom code to poll sources. Option B is wrong because the push API for all sources is not efficient. Option D is wrong because a single indexer cannot index from multiple heterogeneous sources.

Answer

Use the push API to index all data from a custom application that polls all sources.

Answer

Create a single indexer that reads from all three sources using a data source definition.

Answer

Use only indexers for all sources by creating a custom indexer for the REST API.

Question 4

Your team is using Azure AI Search to index a large collection of technical manuals. Users report that searches for 'disk failure' do not return relevant results because the manuals use terms like 'hard drive crash'. Which feature should you implement to improve recall?

Accepted Answer

Add a synonym map to the index. Option A is correct because a custom synonym map can define equivalent terms like 'disk' and 'hard drive'. Option B is wrong because semantic ranking re-ranks results but does not add synonyms. Option C is wrong because scoring profiles boost by fields, not synonyms. Option D is wrong because filters reduce results but do not expand queries.

Answer

Apply a filter

Answer

Configure a scoring profile

Answer

Enable semantic search

Question 5

You are using Azure AI Language to perform entity recognition on customer feedback. You need to identify the sentiment expressed towards specific entities. Which feature should you use?

Accepted Answer

Sentiment analysis with opinion mining. Option C is correct because sentiment analysis with opinion mining provides sentiment at the aspect level, including entities. Option A is wrong because Named Entity Recognition (NER) only identifies entities, not sentiment. Option B is wrong because key phrase extraction only extracts key phrases. Option D is wrong because entity linking connects entities to knowledge bases, not sentiment analysis.

Answer

Named Entity Recognition (NER)

Answer

Entity linking

Answer

Key phrase extraction

Question 6

You have defined the custom WebApiSkill shown in the exhibit. The skill calls an Azure Function that can process up to 10 documents per second. However, you notice that the skill is failing with 429 errors. What is the most likely cause?

Accepted Answer

The degreeOfParallelism of 3 causes too many concurrent requests, exceeding the function's capacity. Option D is correct because the degreeOfParallelism is set to 3, meaning three batches of 5 documents each (15 docs) are sent concurrently, exceeding the 10 docs/sec capacity. Option A is wrong because the timeout is 30 seconds, which is sufficient. Option B is wrong because context is correct. Option C is wrong because the batch size of 5 is reasonable.

Answer

The timeout of 30 seconds is too short for the function to respond

Answer

The batch size of 5 is too large, causing the function to receive too many documents at once

Answer

The context '/document' is incorrect, causing all documents to be processed as one

Question 7

Which TWO configurations are required to enable incremental enrichment in Azure AI Search?

Accepted Answer

Define a projection in the skillset to store enriched data.. Incremental enrichment requires a projection to store intermediate state and a cache key to identify documents. Option A is not required because blob metadata is not needed. Option D is not required because a custom skill is optional. Option E is not required because incremental enrichment works without custom skills.

Answer

Configure the indexer to run in 'once' mode.

Answer

Enable blob metadata extraction in the indexer.

Answer

Add a custom skill that outputs a hash of the document content.

Question 8

You have an Azure AI Search index defined as shown in the exhibit. Users want to filter search results by author and by a date range, and also see a count of documents per tag. However, the filter on author is not working. What is the most likely reason?

Accepted Answer

The filter expression uses incorrect OData syntax.. For filtering to work, the field must be 'filterable'. In the exhibit, 'author' is set to 'filterable': true. However, if the filter syntax is incorrect (e.g., using 'eq' instead of 'eq' for strings), it would fail. But the most common issue is that the author field is not marked as filterable. Wait, in the exhibit it is 'filterable': true. So another cause: The index might not have been rebuilt after adding filterable. But the exhibit shows the current index definition. Actually, the issue could be that the filter is using an incorrect OData syntax. Option B is wrong because sortable is not required for filtering. Option C is wrong because tags are facetable but not involved. Option D is wrong because the key field is not used for filtering.

Answer

The 'id' field is not used as the key.

Answer

The 'author' field is not set as filterable in the index definition.

Answer

The query uses a $orderby parameter that conflicts with the filter.

Question 9

You plan to use Azure AI Search to index a large number of text documents stored in Azure Blob Storage. The documents are in English. You want to automatically extract key phrases from the content during indexing. What should you add to the skillset?

Accepted Answer

Key Phrase Extraction skill. The Key Phrase Extraction skill is a built-in cognitive skill that extracts key phrases from text. It is part of the Azure AI Language cognitive services.

Answer

Sentiment skill

Answer

Language Detection skill

Answer

Entity Recognition skill

Question 10

Which TWO actions should you perform to ensure that an Azure AI Search indexer can successfully enrich documents using a custom skill that calls an external API?

Accepted Answer

Configure a retry policy in the skillset definition for the custom skill. Options A and D are correct. A: Providing managed identity allows the indexer to authenticate to the Azure Function hosting the custom skill. D: Configuring a retry policy ensures transient failures are retried. Option B is wrong because CORS is not needed for indexer-to-function calls (they are server-to-server). Option C is wrong because the indexer does not call the API directly; it calls the custom skill endpoint. Option E is wrong because the indexer already has its own timeout settings.

Answer

Enable CORS on the Azure Function app to allow cross-origin requests

Answer

Set the indexer's execution timeout to unlimited

Answer

Add the external API endpoint to the indexer's allowed domains list

Question 11

You are troubleshooting an Azure AI Search indexer that is failing with the error 'No skillset was found with the name 'skillset-name'.' The skillset exists in the same resource group. What is the most likely cause?

Accepted Answer

The indexer and skillset are in different Azure AI Search services.. The indexer and skillset might be in different Azure AI Search services. Option B is correct. Option A is incorrect because skillset names are case-sensitive, but the error says 'not found', not 'invalid name'. Option C is incorrect because the indexer is separate from the skillset location. Option D is incorrect because permissions don't cause 'not found' if it exists.

Answer

The skillset name has a typo or is case-sensitive.

Answer

The indexer's data source is misconfigured.

Answer

The indexer does not have permission to access the skillset.

Question 12

Your organization is using Azure AI Search to index a large collection of PDF documents stored in Azure Blob Storage. The index currently returns search results, but users complain that the results are not relevant when they search using natural language phrases. You need to improve the relevance of search results without rewriting the application. What should you do?

Accepted Answer

Enable semantic search on the index and configure a semantic configuration.. Semantic search in Azure AI Search uses deep learning models to understand the intent behind queries and improve relevance of results. Enabling semantic search on the index addresses the natural language relevance issue without requiring application changes. Option A is wrong because creating a new index with blob indexers does not change relevance. Option B is wrong because adding a custom analyzer helps with tokenization, not semantic understanding. Option D is wrong because increasing the number of replicas improves throughput, not relevance.

Answer

Increase the number of replicas for the search service to improve query performance.

Answer

Create a new index with a blob indexer that uses the 'content' field only.

Answer

Configure a custom analyzer on the index to handle stop words and synonyms.

Question 13

Your knowledge mining pipeline uses Azure AI Search to index PDF files. You need to extract text from the PDFs and also recognize embedded tables. Which built-in skill should you use?

Accepted Answer

Document Extraction skill. The Document Extraction skill extracts text from PDFs and other file types. For tables, you would use Document Intelligence. The other skills are for different purposes.

Answer

OCR skill

Answer

Custom Web API skill

Answer

Entity Recognition skill

Question 14

Which THREE conditions must be met for Azure AI Search to use a custom skill? (Select THREE.)

Accepted Answer

The custom skill must handle batch requests of up to 1000 records per call.. A custom skill must be a web API that returns JSON, handles errors, and is reachable from the search service. The skill can be stateless or stateful, state is not required. There is no requirement to be hosted in Azure; it can be on-premises if accessible.

Answer

The custom skill must be stateless.

Answer

The custom skill must be hosted in an Azure Function.

Question 15

You are a solution architect at a legal firm. The firm wants to build a copilot using Microsoft Foundry that answers questions about case law documents stored in Azure Blob Storage. The copilot should use the Retrieval Augmented Generation (RAG) pattern with Azure AI Search as the vector store. The documents are in PDF format and include complex tables and footnotes. The solution must ensure that the answers are grounded in the documents and that the copilot can handle follow-up questions. You need to design the ingestion pipeline. Which approach should you take?

Accepted Answer

Use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search. Option A is correct. Using Azure AI Document Intelligence to chunk documents into meaningful sections preserves context, and generating embeddings with Azure OpenAI allows vector search for RAG. Option B is incorrect because splitting by page may break tables and footnotes. Option C is incorrect because keyword search alone does not support semantic understanding. Option D is incorrect because Azure AI Language does not handle PDF extraction or vector generation.

Answer

Use Azure AI Vision OCR to extract text, split by page, and use Azure AI Search keyword search

Answer

Use Azure AI Document Intelligence prebuilt-read model, chunk by character count, and use Azure AI Search with semantic ranking

Answer

Use Azure AI Language to extract key phrases, create a non-vector index, and use simple search