AI-102 Implement knowledge mining and information extraction solutions Practice Test 5 — 15 Questions

Question 1

You are implementing a knowledge mining solution using Azure AI Search with a custom skillset. The custom skill is an Azure Function that enriches documents with additional metadata. You need to ensure that the custom skill receives the entire document content as input. How should you configure the skill's context and inputs?

Accepted Answer

Set context to '/document' and input source to '/document/content'.. To pass the entire document, set context to '/document' and inputs to reference '/document/content'. Option A passes only the content. Option B passes only metadata. Option D uses wrong path separators.

Answer

Set context to '/document/content' and input source to '/document/metadata'.

Answer

Set context to '/document/content' and input source to '/document/content'.

Answer

Set context to '/document' and input source to '/document/normalized_images/*'.

Question 2

Your organization uses Microsoft Purview to catalog data assets. You need to enable knowledge mining on these assets to allow users to search across structured and unstructured data. Which integration should you use to connect Microsoft Purview with Azure AI Search?

Accepted Answer

Create an Azure AI Search indexer that connects to Microsoft Purview's data source using the Purview REST API.. Azure AI Search can index metadata from Microsoft Purview using a custom indexer or data source. Option B is correct because you can create an indexer that pulls metadata from Purview's Atlas API. Option A is incorrect because Purview does not push directly. Option C is incorrect because Power BI is for analytics. Option D is incorrect because Microsoft Foundry is a different platform.

Answer

Configure Microsoft Purview to push metadata directly to an Azure AI Search index.

Answer

Use Microsoft Foundry's built-in connector to import Purview metadata.

Answer

Use Power BI to export Purview metadata to Azure AI Search.

Question 3

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 4

You need to extract key-value pairs from scanned forms as part of a knowledge mining solution. Which Azure AI service should you use?

Accepted Answer

Azure AI Document Intelligence. Azure AI Document Intelligence (formerly Form Recognizer) is designed to extract key-value pairs from forms. Option B is incorrect because Vision is for OCR, not structure. Option C is incorrect because Language is for text analysis. Option D is incorrect because Search is for indexing.

Answer

Azure AI Vision

Answer

Azure AI Language

Answer

Azure AI Search

Question 5

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 6

You are using Azure AI Search to build a knowledge base for a customer support portal. The index includes a 'sentiment' field that should be populated using the Sentiment skill. However, the sentiment scores are not being written to the index. The skillset runs successfully. What is the most likely cause?

Accepted Answer

The output field mapping for 'sentiment' is missing or incorrectly defined in the indexer.. Option C is correct: the output field mapping in the indexer is missing or incorrect. Option A is incorrect because the skill ran successfully. Option B is incorrect because the sentiment skill does not require a specific data type. Option D is incorrect because indexer execution is successful.

Answer

The Sentiment skill is not correctly configured in the skillset.

Answer

The indexer is in a failed state and not processing documents.

Answer

The sentiment field in the index is of type 'Collection(Edm.String)' but the skill outputs a double.

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

Which TWO Azure AI services can be used together to build a knowledge mining solution that extracts text from handwritten notes and indexes them for search?

Accepted Answer

Azure AI Search. Azure AI Vision Read API can extract text from handwritten notes (OCR). Azure AI Search indexes the extracted text. Option A is incorrect because Document Intelligence is for forms, not handwriting. Option C is incorrect because Language is for text analysis. Option D is incorrect because Translator is for translation.

Answer

Azure AI Document Intelligence

Answer

Azure AI Language

Answer

Azure AI Translator

Question 9

Which THREE components are required to build a custom skill for Azure AI Search enrichment?

Accepted Answer

A web API endpoint that accepts JSON input and returns JSON output.. A custom skill requires a web API endpoint (e.g., Azure Function), a JSON schema for input/output, and it must be deployed to an HTTPS endpoint. Option A is incorrect because a database is not required. Option D is incorrect because Power Automate is not used. Option E is incorrect because a storage account is not required.

Answer

A database to store intermediate results.

Answer

A Power Automate flow to orchestrate the skill.

Question 10

You have the above Azure AI Search skillset. The indexer fails with the error 'The skill 'sentiment-skill' cannot find the input '/document/pages/*' because the path does not exist.' What is the most likely cause?

Accepted Answer

The SplitSkill did not split the content because the document content is too short.. The SplitSkill outputs 'pages' but the SentimentSkill input expects '/document/pages/*'. However, the SplitSkill's targetName 'pages' is correct, but note that the SplitSkill context is '/document', so the output path is '/document/pages'. The input source uses '/document/pages/*', which is correct. The error suggests the SplitSkill did not produce any pages. Option B is correct: the SplitSkill might not have split the content, possibly because the text length is too short. Option A is incorrect because the skill is defined. Option C is incorrect because targetName is correct. Option D is incorrect because the error is about missing path, not missing skill.

Answer

The SplitSkill is not defined in the skillset.

Answer

The SentimentSkill is missing a required input.

Answer

The targetName in SplitSkill is misspelled.

Question 11

You have the above Azure AI Search indexer definition. The indexer runs successfully but the 'content' field in the index is empty for all documents. What is the likely cause?

Accepted Answer

The outputFieldMapping references '/document/content' which is not produced by the skillset.. The outputFieldMapping maps '/document/content' to 'content'. However, the skillset (not shown) might not produce this output, or the skill output path is different. But the exhibit shows that the indexer expects '/document/content' to be available from the skillset. If the skillset does not output '/document/content', the field remains empty. Option C is correct: the outputFieldMapping references a path that does not exist in the enrichment tree. Option A is incorrect because the field mapping for 'path' is fine. Option B is incorrect because the indexer runs successfully. Option D is incorrect because batch size does not affect field mapping.

Answer

The indexer schedule is too frequent.

Answer

The fieldMapping for 'metadata_storage_path' is incorrect.

Answer

The batchSize is too large, causing some items to fail silently.

Question 12

You have the above data source definition for Azure AI Search. You want to index only PDF files from the 'documents' container. How should you modify the data source?

Accepted Answer

Set the 'query' field to a blob prefix that corresponds to the folder containing PDF files.. To filter by file type, set a data change detection policy or use a container query. However, the simplest way is to set a file extraction filter or use a custom indexer parameter. Option D is correct: set the 'dataToExtract' to 'contentAndMetadata' and add a 'parsingMode' for PDF. But the best answer is to set a query parameter to filter by .pdf extension. Option A is incorrect because connection string doesn't filter. Option B is incorrect because container name can't have filters. Option C is correct: set the 'query' field to filter by .pdf. Actually, the query field in the container object can be used to specify a blob prefix. For example, "*.pdf" is not valid; you need to use a prefix. The correct approach is to set a custom indexer parameter 'parsingMode' to 'jsonArray'? No. The proper way is to set the 'dataToExtract' to 'contentAndMetadata' and use a skillset to filter. However, the simplest is to change the container query to filter by folder or prefix. Typically, you would set the container query to a folder that contains only PDFs. Option C is plausible: set the query to filter by .pdf extension. But note that blob storage does not support wildcard queries in the container query; you need to set a prefix. Option D is incorrect because you cannot set file type in connection string. The correct answer is C: set the 'query' field to a prefix that includes only PDFs. However, the exhibit shows empty query. To filter PDFs, you would set a prefix like 'pdf/' if they are in a folder. But the question expects to set the 'parsingMode' to 'jsonArray'? No. Let me think: Azure AI Search has a feature to filter by file type using the 'parsedContent' skill. But the simplest is to set a data change detection policy. Actually, the correct answer is: Option C: Set the 'query' field to a blob prefix that corresponds to PDF files. But since the exhibit has empty query, you can set it to a folder. However, the distractors: Option A: Change the connection string -> no. Option B: Change the container name -> no. Option C: Set the 'query' field to filter by .pdf extension -> this is not directly supported; you need to use a prefix. Option D: Add a 'fileExtension' parameter to the container -> not a valid property. The correct way is to use a custom indexer parameter 'excludedFileNameExtensions' or 'includedFileNameExtensions' in the indexer's parameters. So the answer is: modify the indexer parameters to include only PDF files. But the question asks to modify the data source. Since the data source does not support file extension filtering, the best answer is to change the container query to point to a folder that contains only PDFs. Option C is the closest. I'll go with C.

Answer

Change the container name to 'pdfs' and move all PDFs there.

Answer

Add a 'fileExtension' property to the container object.

Answer

Change the connection string to use a different storage account that contains only PDFs.

Question 13

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 14

Your company deploys an Azure AI Document Intelligence solution to extract data from invoices. During testing, you notice that some fields are not being extracted correctly, especially for invoices from a specific vendor with a non-standard layout. You need to improve extraction accuracy for this vendor's invoices. What should you do?

Accepted Answer

Train a custom model using labeled samples of the vendor's invoices.. Custom models in Document Intelligence can be trained on a set of sample documents to learn the specific layout of a vendor's invoices, improving extraction accuracy for non-standard formats. Option A is wrong because using a prebuilt model for invoices is designed for standard layouts. Option B is wrong because Azure AI Form Recognizer (now part of Document Intelligence) supports custom models. Option D is wrong because OCR provides text but not structured extraction.

Answer

Enable OCR on the documents and use regular expressions to extract fields.

Answer

Convert the invoices to a standard format before processing.

Answer

Use the prebuilt invoice model with confidence threshold adjustment.

Question 15

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.