AI-102 Implement knowledge mining and information extraction solutions Practice Test 4 — 15 Questions

Question 1

Your knowledge mining solution uses Azure AI Search with a custom skill that calls an Azure Function to perform complex data validation. The custom skill returns an error for some documents, but the indexer continues without raising an error. What is the most likely cause?

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

Accepted Answer

The indexer is configured with 'allowSkillsetToExecuteIfError' set to true.. By default, indexers continue on error. To stop on skill errors, set 'allowSkillsetToExecuteIfError' to false. The indexer treats skill errors as warnings by default.

Answer

The indexer is configured with 'allowSkillsetToExecuteIfError' set to false.

Answer

The Azure Function returns HTTP 200 with an error message in the body.

Answer

The custom skill's output field mapping is incorrect.

Question 2

You are designing a knowledge mining solution for customer support emails. The solution must extract the customer's name, issue category, and sentiment from each email. Which two Azure AI services should you combine?

Accepted Answer

Azure AI Language and Azure AI Search. Azure AI Language provides entity extraction and sentiment analysis. Azure AI Search indexes the extracted data for search. The other services are not directly needed for extraction and indexing.

Answer

Azure AI Bot Service and Azure AI Language

Answer

Azure AI Document Intelligence and Azure AI Search

Answer

Azure AI Translator and Azure AI Language

Question 3

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 is designed to extract text from binary files such as PDFs. However, it does not natively extract embedded tables as structured data. For table recognition, you would typically need additional processing, such as using the OCR skill for image-based tables or integrating Azure Document Intelligence. Therefore, among the provided options, Document Extraction is the most relevant for text extraction but does not fully address table recognition without supplementary steps.

Answer

OCR skill

Answer

Custom Web API skill

Answer

Entity Recognition skill

Question 4

Your organization uses Azure AI Search to index customer product reviews. The reviews are in English, Spanish, and French. You need to enable multi-lingual search so that a query in English returns relevant results from all three languages. What should you do?

Accepted Answer

Create separate search fields for each language, each with the corresponding language analyzer (e.g., 'en.microsoft', 'es.microsoft', 'fr.microsoft').. Azure AI Search supports language-specific analyzers (e.g., 'en.microsoft', 'es.microsoft', 'fr.microsoft') that apply linguistic rules like stemming, lemmatization, and stop-word removal tailored to each language. By creating separate search fields with the corresponding analyzer, a query in English can match relevant terms across all three languages because the search engine evaluates the query against each field using its analyzer, allowing cross-language retrieval without translation.

Answer

Use Azure AI Translator to translate all reviews to English before indexing.

Answer

Use a single field with the 'standard' analyzer for all languages.

Answer

Use the 'keyword' analyzer for all fields.

Question 5

You need to enrich documents with key phrases and sentiment before indexing into Azure AI Search. Which type of skill should you use?

Accepted Answer

Cognitive Services skill. The Cognitive Services skill in Azure AI Search is a built-in skill that provides access to a subset of Azure Cognitive Services APIs, including key phrase extraction and sentiment analysis. By using this skill, you can enrich documents with key phrases and sentiment before indexing.

Answer

Entity Recognition skill

Answer

Document Extraction skill

Answer

Custom Web API skill

Question 6

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.. Option B is correct because Azure AI Search's custom skill interface expects the skill to accept a batch of up to 1000 records per call (the indexer sends a JSON payload with a 'values' array), so the skill must be designed to process batched input rather than a single record. Option C is correct because the custom skill is invoked by the Azure AI Search service over the web, so it must expose an HTTPS endpoint that the service can reach (typically an Azure Function or any HTTPS-accessible web API). Option E is correct because the custom skill must return a JSON response containing a 'values' array with one output object per input record, and each output object can include an 'errors' array to report per-record failures/warnings. Option A is not required: statelessness is a good design practice but is not a formal condition enforced by Azure AI Search for custom skills. Option D is not required: a custom skill can be hosted in an Azure Function, but it can also be any HTTPS-accessible endpoint (e.g., a web API or container), so Azure Functions is not mandatory.

Answer

The custom skill must be stateless.

Answer

The custom skill must be hosted in an Azure Function.

Question 7

You have the above indexer configuration. The indexer processes a batch of 10 documents. In that batch, 3 documents fail. What happens?

Accepted Answer

The indexer fails the entire batch but continues with the next batch.. Azure AI Search indexers use a batch-level failure policy: if the number of failed documents in a batch exceeds the configured 'maxFailedItems' threshold (default 0), the entire batch is marked as failed and skipped, but the indexer continues processing subsequent batches. This behavior is controlled by the indexer's 'maxFailedItems' and 'maxFailedItemsPerBatch' properties, which default to 0, meaning any failure in a batch causes the batch to be skipped while the indexer moves on.

Answer

The indexer skips the failed documents and continues with the same batch.

Answer

The indexer stops completely because 3 documents failed.

Answer

The indexer retries the failed documents.

Question 8

Which TWO Azure AI Search features are used to map skill outputs to search index fields? (Select TWO.)

Accepted Answer

outputFieldMappings. Option B, outputFieldMappings, is correct because it is the indexer property that explicitly maps an enriched document node produced by a skillset (for example, /document/sentiment) to a specific field in the target search index, which is exactly the mechanism for routing skill outputs into index fields. Option C, skillset outputs, is correct because each skill in a skillset defines named outputs (such as "text" or "entities") that become enriched-document nodes, and these outputs are the source values that outputFieldMappings then binds to index fields. Option A, indexer parameters, is not correct because indexer parameters configure runtime behavior such as batch size, max failed items, or parsing mode, not the mapping of skill outputs to index fields. Option D, fieldMappings, is not correct because it maps fields from the source data source to index fields before or without enrichment, not skill outputs from the enrichment tree. Option E, index fields, is not correct because index fields are the destination schema definitions in the index, not the feature that performs the mapping from skill outputs.

Answer

indexer parameters

Answer

fieldMappings

Answer

index fields

Question 9

Your knowledge mining solution uses Azure AI Search with a custom skill that calls an Azure Function to perform complex data validation. The custom skill returns an error for some documents, but the indexer continues without raising an error. What is the most likely cause?

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

Accepted Answer

Create a custom skill that calls Azure AI Document Intelligence and returns extracted fields, then use outputFieldMappings to map to index fields.. Azure AI Document Intelligence extracts structured data (like PO number and total amount) from documents, but this data must be explicitly mapped to Azure AI Search index fields using outputFieldMappings in a custom skill. The custom skill invokes Document Intelligence via the Skillset, and outputFieldMappings bridge the extracted fields to the search index schema, making them searchable. This approach ensures the extracted fields are ingested into the index without manual intervention.

Answer

Use Azure AI Document Intelligence's pre-built model to analyze documents and store results in a database, then use a SQL indexer to index the database.

Answer

Use the OCR skill to extract text and then use regular expressions to find PO number and total.

Answer

Manually enter the extracted data into the search index.

Question 10

You are designing a knowledge mining solution for a legal firm. The solution must index contracts and support queries like 'find all contracts where the governing law is New York'. The contracts are stored as PDFs in Azure Blob Storage. Which approach should you use?

Accepted Answer

Use Azure AI Search with a custom skill to extract the governing law field. Azure AI Search custom skills allow you to invoke external processing (e.g., a custom model or logic) to extract specific fields like 'governing law' from PDF content. Since the contracts are stored as PDFs in Blob Storage, you would first use OCR or text extraction (via built-in skills) to get raw text, then a custom skill to parse and extract the structured field. This enables precise queries such as 'find all contracts where the governing law is New York' using a filter on that extracted field.

Answer

Use Azure AI Search with vector search

Answer

Use Azure AI Search with a built-in skillset for OCR

Answer

Use Azure AI Search with full-text search on the extracted text

Question 11

You are using Azure AI Document Intelligence to extract data from purchase orders. The purchase orders have a table of line items. Which prebuilt model should you use?

Accepted Answer

Prebuilt invoice model. The prebuilt invoice model is optimized for extracting line-item tables from financial documents such as purchase orders. The prebuilt document model extracts general key-value pairs and tables but lacks semantic understanding of line items. The custom model is not a prebuilt model. The layout model extracts only structural elements like tables and text, not semantic data.

Answer

Prebuilt document model

Answer

Layout model

Answer

Custom model

Question 12

Your knowledge mining solution uses Azure AI Search with a custom skill that calls an Azure Function to perform complex data validation. The custom skill returns an error for some documents, but the indexer continues without raising an error. What is the most likely cause?

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

Accepted Answer

Enable debug mode on the skillset. When a skillset execution fails during enrichment, the first diagnostic step is to enable debug mode on the skillset. Debug mode allows you to step through each skill execution, inspect inputs and outputs, and identify exactly where the failure occurs. This targeted approach is more efficient than reviewing logs or re-running the indexer, because it provides granular, per-document debugging without waiting for a full indexer run.

Answer

Review the indexer execution history in the portal

Answer

Re-run the indexer with a fresh document

Answer

Check the indexer logs in Azure Monitor

Question 13

You need to build a chatbot that answers questions based on your company's internal knowledge base. The knowledge base consists of Word documents and PDFs. Which service should you use to create a conversational interface that retrieves answers from these documents?

Accepted Answer

Azure AI Search with Azure AI Bot Service. Azure AI Search indexes the content from Word documents and PDFs, enabling full-text and vector search over the knowledge base. Azure AI Bot Service provides the conversational interface that queries the search index and returns answers to users. Together, they form a retrieval-augmented generation (RAG) pipeline that answers questions from unstructured documents.

Answer

Azure AI Language Service - Custom Question Answering

Answer

Azure AI Computer Vision

Answer

Azure AI Document Intelligence

Question 14

Which TWO services can be used to enrich an Azure AI Search index with knowledge mining skills? (Choose two.)

Accepted Answer

Azure AI Computer Vision. Azure AI Computer Vision (option A) is correct because it provides built-in cognitive skills such as OCR, image analysis, and optical character recognition that can be attached to an Azure AI Search skillset to extract text and visual features from images during indexing. Azure AI Language Service (option C) is also correct because it offers skills like entity recognition, key phrase extraction, language detection, and sentiment analysis that enrich indexed documents with linguistic metadata. Azure AI Video Indexer (option B) is not a directly supported enrichment skill in Azure AI Search skillsets; it is a standalone video analytics service. Azure AI Speech Service (option D) is not a built-in cognitive skill for index enrichment, though speech-to-text could be used externally before indexing. Azure AI Translator (option E) is not a native Azure AI Search enrichment skill, even though translation can be performed separately in a custom skill.

Answer

Azure AI Video Indexer

Answer

Azure AI Speech Service

Answer

Azure AI Translator

Question 15

Which THREE actions should you take when designing a custom skill for an Azure AI Search enrichment pipeline? (Choose three.)

Accepted Answer

Define input and output parameters in the skillset definition. Option A is correct because a custom skill in an Azure AI Search skillset must declare its interface in the skillset JSON via the "inputs" and "outputs" arrays, mapping each input to a source (for example /document/content) and each output to a name that downstream skills or the index can consume. Option B is correct because the custom skill's web API must return proper HTTP status codes (for example 200 on success, 4xx/5xx on failure) and include error/warning messages in the response so the enrichment pipeline can record them in the skillset execution history and apply the defined error handling behavior. Option E is correct because a custom skill is implemented as an external web API—typically an Azure Function or any HTTPS endpoint—that Azure AI Search calls during enrichment, and the skillset references it through the "uri" property of the custom skill definition. Option C is not required: the documented timeout for a custom skill call is 30 seconds (with retries), not 2 minutes, so designing for a 2-minute execution is neither necessary nor supported. Option D is not a design action: the skill runs as an external HTTP service, so Azure AI Search does not constrain the implementation language; any language capable of exposing the required JSON interface works.

Answer

Ensure the skill executes within 2 minutes

Answer

Write the skill in a language supported by Azure AI Search