AI-102 Practice Test 27 — 15 Questions

Question 1

You are a developer at an e-commerce company. The company wants to build a product search feature that allows customers to search for products using natural language phrases like "red running shoes under $100". The product catalog is stored in Azure Cosmos DB and includes product descriptions, prices, and categories. The solution must use Azure AI Search and must extract entities from product descriptions to enable filtering (e.g., color, size, brand). The search must also support fuzzy matching for misspelled queries. You need to design the indexing pipeline. Which actions should you take?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Use Azure AI Language entity extraction as a custom skill, and enable fuzzy search in the index. Using Azure AI Language entity extraction as a custom skill extracts attributes like color, size, and brand from product descriptions, and enabling fuzzy search in the index handles misspellings. Option A is incorrect because key phrase extraction identifies topics, not specific entities like color or brand, and vector search is for similarity matching, not fuzzy matching for typos. Option B is incorrect because Azure AI Document Intelligence is designed to extract text from documents (e.g., PDFs, images), not to extract named entities from text already stored in a database; semantic ranking improves relevance but does not perform entity extraction. Option D is incorrect because Azure AI Vision OCR extracts text from images, not from product descriptions in Cosmos DB, and synonyms expand queries but do not extract entities needed for filtering.

Answer

Use Azure AI Language key phrase extraction, and enable vector search

Answer

Use Azure AI Document Intelligence to extract entities, and enable semantic ranking

Answer

Use Azure AI Vision OCR to extract text, and enable synonyms

Question 2

You are designing a knowledge mining solution that must handle sensitive customer data. The solution must ensure that personally identifiable information (PII) is not returned in search results. What should you do?

Accepted Answer

Use a custom skill in the skillset to detect and redact PII before indexing. Using a custom skill in the enrichment pipeline allows you to detect and redact PII from documents before they are indexed, ensuring that sensitive data is not stored in the index or returned in search results. Option A is incorrect because encryption at rest protects data at the storage level but does not prevent PII from being returned. Option B is incorrect because role-based access control restricts who can search but does not remove PII from results. Option D is incorrect because field mappings control which fields are imported but do not remove PII content from those fields.

Answer

Use Azure AI Search with encryption at rest

Answer

Implement role-based access control on the search index

Answer

Configure field mappings to exclude PII fields

Question 3

You are building a knowledge mining solution for a legal firm that needs to extract key clauses from thousands of scanned contract PDFs. The solution must identify parties, effective dates, and termination conditions. Which Azure AI service should you use as the primary component?

Accepted Answer

Azure AI Document Intelligence. Azure AI Document Intelligence (formerly Form Recognizer) is the appropriate service for extracting structured data like parties, effective dates, and termination conditions from scanned contract PDFs. It offers prebuilt models for contracts and custom extraction capabilities. Azure AI Language is for text analytics and NLP but lacks the OCR and layout understanding needed for scanned documents. Azure AI Vision provides OCR but not structured extraction. Azure AI Search is for indexing and searching, not extraction. Therefore, Option A is correct.

Answer

Azure AI Vision

Answer

Azure AI Language

Answer

Azure AI Search

Question 4

You are building a question answering solution using Azure AI Language. You have a set of frequently asked questions (FAQs) in a Word document. You need to import the FAQs into a project. Which approach should you use?

Accepted Answer

Create a custom question answering project and import the Word document as a source.. Custom question answering in Azure AI Language allows importing FAQ content from Word documents as a source directly. Option A is incorrect because Azure AI Document Intelligence is designed for extracting structured data from documents, not specifically for QnA pair import into a question answering project. Option C is incorrect because the prebuilt question answering API is for out-of-the-box QA, not for custom document import. Option D is incorrect because conversational language understanding (CLU) is used for intent and entity extraction, not for importing FAQs.

Answer

Use Azure AI Document Intelligence to extract QnA pairs.

Answer

Use the prebuilt question answering API to parse the document.

Answer

Use conversational language understanding (CLU) to extract intents and entities.

Question 5

You are designing a knowledge mining solution using Azure AI Search. The solution must process large volumes of PDFs daily. You need to minimize the cost of cognitive skills execution while ensuring the pipeline can handle transient failures. Which approach should you recommend?

Accepted Answer

Enable incremental enrichment on the indexer. Enabling incremental enrichment caches intermediate results and recovers from failures without re-processing unchanged documents, reducing cost. Option B is incorrect because disabling field mappings would break the pipeline. Option C is incorrect because increasing the number of replicas improves query performance, not indexing. Option D is incorrect because using a free tier is not feasible for large volumes.

Answer

Disable field mappings

Answer

Increase the number of replicas

Answer

Use the free tier for the indexer

Question 6

Which THREE considerations are important when designing a custom skill for Azure AI Search that calls an external API for specialized data extraction?

Accepted Answer

The API endpoint must be reachable from the search service. Correct options are A, D, and E. Custom skills must have an API endpoint reachable from the search service (public or via private endpoint) [A]. They must handle payloads up to 16 MB due to data size limits [D]. They must complete within 230 seconds (the default timeout) [E]. Option B is incorrect because custom skills can accept multiple inputs and produce multiple outputs. Option C is incorrect because custom skills can be written in any language that supports JSON.

Answer

The skill can only accept one input and produce one output

Answer

The skill must be written in Python

Question 7

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?

Accepted Answer

Configure a retry policy on the custom skill. Azure AI Search indexers can be configured with a retry policy for custom skills. When a custom skill returns HTTP 429 (Too Many Requests), a retry policy will automatically retry the skill execution after a backoff delay, helping to handle rate limiting from the external API. Option A is incorrect: reducing the batch size may reduce the number of requests per batch, but if the API rate limit is per request, it may not resolve the 429 error. Option B is incorrect: increasing the skill timeout does not address rate limiting; it only allows more time for a single request. Option D is incorrect: scheduling the indexer less frequently only reduces the frequency of index runs, not the rate of requests during a run.

Answer

Reduce the batch size in the indexer

Answer

Increase the skill timeout

Answer

Schedule the indexer to run less frequently

Question 8

A healthcare organization needs to mine clinical notes to find mentions of diseases, medications, and treatment procedures. The data is stored in Azure SQL Database. Which Azure AI service should they integrate with Azure AI Search to extract these entities?

Accepted Answer

Azure AI Health Insights. Azure AI Health Insights (formerly Text Analytics for Health) is a specialized service designed to extract healthcare-related entities such as diseases, medications, and treatment procedures from clinical text. Azure AI Language (option D) offers general entity extraction but lacks domain-specific models for healthcare. Azure AI Document Intelligence (option B) is optimized for extracting information from structured documents like forms and invoices, not clinical narratives. Azure AI Search (option C) is the indexing and querying service, not an extraction service. Therefore, Azure AI Health Insights is the appropriate choice to integrate with Azure AI Search for entity extraction from clinical notes.

Answer

Azure AI Document Intelligence

Answer

Azure AI Search

Answer

Azure AI Language

Question 9

Your company is building a knowledge base for customer support using Azure AI Search. You have a large dataset of customer emails stored in Azure Blob Storage. The solution must extract key phrases, detect sentiment, and identify customer intents (e.g., complaint, inquiry, feedback). You plan to use built-in AI skills for key phrase extraction and sentiment detection. For intent identification, you need a custom solution because the intents are specific to your business. You have trained a custom Language Understanding (LUIS) model and published it. How should you integrate the LUIS model into the Azure AI Search enrichment pipeline to extract intents?

Accepted Answer

Create a custom skill in the skillset that calls the LUIS endpoint and returns the top intent.. Azure AI Search allows you to create a custom skill that can call an external API, such as a LUIS endpoint, to extract intents specific to your business. This integrates seamlessly into the enrichment pipeline. Option A is incorrect because Document Intelligence is for document analysis, not intent classification. Option B is incorrect because custom analyzers are for indexing text, not enrichment. Option C is incorrect because the built-in Entity Recognition skill can identify general entities but cannot identify custom business-specific intents. Option D is correct because a custom skill can invoke the LUIS model to return the top intent, and this can be mapped to a field in the index.

Answer

Add a Document Intelligence skill to classify intents.

Answer

Configure the index to use a custom analyzer to parse intents.

Answer

Use the built-in Entity Recognition skill to extract intents.

Question 10

You are designing a knowledge mining solution for a large enterprise that uses Azure AI Search to index millions of documents. The solution must support high-availability and automatic failover. Which TWO actions should you take to meet these requirements?

Accepted Answer

Provision the Azure AI Search service in at least two regions.. To achieve high availability and automatic failover in Azure AI Search, you need to provision the service in at least two regions (Option C) to provide geo-redundancy, and configure at least two replicas within a region (Option D) for high availability and load balancing. Option A is incorrect because index data is stored within the search service, not in Azure Storage, so GRS is not applicable. Option B (semantic search) enhances query capabilities but does not affect availability. Option E (text split skill) is for processing large documents, not for availability.

Answer

Use geo-redundant storage (GRS) for the index data.

Answer

Enable semantic search on the index.

Answer

Enable indexing of large documents using the text split skill.

Question 11

You are troubleshooting an Azure AI Search indexer that fails to index a PDF file stored in Azure Blob Storage. The error message indicates that the document is encrypted. What is the most likely cause and solution?

Accepted Answer

The PDF is encrypted; remove encryption before indexing. Azure AI Search cannot index encrypted documents; the solution is to remove encryption before indexing. Option A is incorrect: the indexer does not require a specific PDF parser; it can index PDFs by default with the appropriate skillset. Option B is incorrect: unsupported file formats would generate a different error, and encryption is not a format issue. Option C is incorrect: file size limits exist (up to 16 MB for PDFs), but the error specifically mentions encryption, not size.

Answer

The indexer is not configured with the PDF parser; set the parsing mode

Answer

The file format is unsupported; convert to PDF/A

Answer

The file is too large; split it into smaller parts

Question 12

A healthcare organization is implementing a knowledge mining solution to extract information from medical records. They need to ensure that the solution can identify medical conditions, medications, and treatment procedures using a pre-built model. The solution must be deployed in Microsoft Foundry. Which THREE components should be included? (Choose three.)

Accepted Answer

Text Analytics for Health skill in an Azure AI Search skillset.. The Text Analytics for Health skill in an Azure AI Search skillset applies the pre-built healthcare model to extract medical conditions, medications, and treatment procedures during indexing. Option B is correct because the Azure AI Search index stores the extracted healthcare entities and supports search and retrieval. Option C is correct because the Text Analytics for Health model is a pre-built model available in Microsoft Foundry (Azure AI Foundry) for direct use in knowledge mining solutions. Option D is incorrect because Azure AI Document Intelligence custom model is designed for extracting structured data from forms and requires training, not for pre-built healthcare entity extraction. Option E is incorrect because Language Understanding (LUIS) is used for conversational intent and entity recognition, not for extracting medical concepts from documents.

Answer

Azure AI Document Intelligence (formerly Form Recognizer) custom model.

Answer

Language Understanding (LUIS) model.

Question 13

You are designing an Azure Cognitive Search solution that indexes customer support tickets. The index must include a field for 'sentiment' that is populated from an AI enrichment pipeline. Which TWO actions are required to achieve this?

Accepted Answer

Add a built-in Sentiment skill to the skillset.. Options A and E are correct. The enrichment pipeline must include a built-in Sentiment skill (A) to analyze sentiment from the support ticket text, and an output field mapping must be configured in the indexer (E) to map the skill's output to the 'sentiment' field in the index. Option B is wrong because a custom skill is not needed as the sentiment skill is built-in. Option C is wrong because the built-in sentiment skill uses Azure AI Language, so a custom skill is unnecessary. Option D is wrong because Collection(Edm.String) is not the correct type for sentiment; a simple string or numeric type would be appropriate.

Answer

Implement a custom skill to normalize sentiment values.

Answer

Create a custom sentiment analysis skill using Azure AI Language.

Answer

Define a 'sentiment' field in the index with type Collection(Edm.String).

Question 14

You are building an application that analyzes images of handwritten notes. The application must extract the handwritten text and preserve the original layout, including line breaks and indentation. Which Azure AI service should you use?

Accepted Answer

Azure AI Document Intelligence Read model. The Azure AI Document Intelligence Read model is specifically designed to extract printed and handwritten text from documents while preserving the original layout, including line breaks and indentation. It uses advanced OCR capabilities optimized for document-like content, making it the correct choice for this scenario.

Answer

Azure AI Vision OCR

Answer

Azure AI Document Intelligence Layout model

Answer

Azure AI Translator

Question 15

A company needs to extract personally identifiable information (PII) from customer support transcripts stored in Azure Blob Storage. Which Azure AI service should they use?

Accepted Answer

Azure AI Language Service. Azure AI Language Service (formerly Text Analytics) includes a pre-built PII detection feature that can identify, categorize, and redact personally identifiable information from unstructured text. This service is specifically designed for text-based extraction tasks, making it the correct choice for processing customer support transcripts stored in Azure Blob Storage.

Answer

Azure AI Speech

Answer

Azure AI Translator

Answer

Azure AI Vision