AI-102 Implement knowledge mining and information extraction solutions Practice Test 3 — 15 Questions

Question 1

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?

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

Accepted Answer

The indexer and skillset are in different Azure AI Search services.. The error 'No skillset was found with the name 'skillset-name'' indicates that the indexer cannot locate the skillset. The most likely cause is that the indexer and skillset are in different Azure AI Search services because skillsets are scoped to a specific search service and cannot be referenced across services. Option A (the indexer and skillset are in different Azure AI Search services) is correct. Option B is incorrect because while skillset names are case-sensitive, the error would likely be different if it were simply a typo or case mismatch. Option C is incorrect because the error is about the skillset, not the data source. Option D is incorrect because permission issues typically result in an authorization error, not a 'not found' error.

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 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.. Avoids the rate limit by not calling the external API, but it fails to meet the requirement to extract custom metadata using the specified custom skill. Option B schedules the indexer to run every 2 hours with a batch size of 20, which reduces the frequency of runs and limits the number of documents per batch, thereby keeping requests to the external API under 100 per minute. Option C increases the batch size to 100, which could cause each batch to make 100 requests, potentially exceeding the rate limit if multiple batches are processed concurrently. Option D increases maximum parallelism, allowing more batches to run concurrently and increasing the request rate, which could exceed the 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

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 in Azure AI Search relies on a skillset-level cache so that only changed documents are re-enriched, and this requires two things. Option D is correct because defining a projection in the skillset (specifically a knowledge store projection, such as 'projections' with tables/objects/files) persists the enriched data so it can be reused rather than recomputed on every indexer run. Option E is correct because setting the 'cacheKey' property in the skillset to a unique document identifier (e.g., '/document/metadata_storage_path' or a field like '/document/Id') gives each document a stable cache key so the enrichment cache can detect which documents have already been processed and skip them. Option A is wrong because running the indexer in 'once' mode disables scheduled/repeated runs, which is the opposite of incremental enrichment. Option B is wrong because blob metadata extraction is a general indexing feature, not a requirement for incremental enrichment. Option C is wrong because a custom skill outputting a content hash is not the mechanism Azure AI Search uses; the built-in enrichment cache with cacheKey handles change detection.

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 4

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 Search (option A) is correct because it provides the indexing and full-text search engine that stores the extracted content in a searchable index, which is the core of any knowledge mining solution. Azure AI Vision's Read API (option C) is correct because it performs OCR on images and documents, including handwritten text, producing the text that Azure AI Search then indexes. Together, the Read API extracts the handwritten notes and Azure AI Search indexes them so users can query the content. Azure AI Document Intelligence (option B) is not marked correct here because, while it also extracts text, the scenario specifically targets handwritten notes handled by the Read API in this pairing. Azure AI Language (option D) analyzes text for entities, sentiment, and key phrases but does not perform OCR extraction or indexing. Azure AI Translator (option E) only translates text between languages and neither extracts handwriting nor builds a search index.

Answer

Azure AI Document Intelligence

Answer

Azure AI Language

Answer

Azure AI Translator

Question 5

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 error indicates that the input path '/document/pages/*' does not exist. This path is generated by the SplitSkill when it splits the document content into pages. If the SplitSkill does not produce any output, the path will not exist. The most likely cause is that the document content is too short to be split, so no pages are created. Therefore, option A is correct. Option B is incorrect because the SplitSkill is defined. Option C is incorrect because the SentimentSkill's input path is correct, but the source is missing. Option D is incorrect because the error is about a missing path, not a misspelled targetName.

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 6

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 'content' field is populated by an output field mapping that points to a node produced by the skillset or by the document cracking step. If the outputFieldMapping references '/document/content' but no skill in the skillset emits a node at that path, the indexer has nothing to write into the field, so 'content' ends up empty even though the run succeeds.

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 7

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.. Azure AI Search data sources support a 'query' property that accepts a blob prefix or virtual directory path. By setting 'query' to the folder path containing PDFs (e.g., 'documents/pdfs/'), the indexer will only process blobs under that prefix, effectively filtering to PDF files without moving or renaming containers.

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 8

You are building a knowledge mining solution using Azure AI Search and Azure AI Language. The solution must extract key phrases, entities, and sentiment from customer feedback documents. After processing, the enriched content should be stored in the search index for full-text search. You need to configure the enrichment pipeline. Which two Azure AI services should you integrate?

Accepted Answer

Azure AI Language and Azure AI Search. The solution requires key phrase extraction, entity recognition, and sentiment analysis, which are all capabilities of Azure AI Language. Azure AI Search is the other required service because it provides the search index and the enrichment pipeline (skillset) that invokes the AI Language skills to process documents and store the enriched content for full-text search.

Answer

Azure AI Language and a custom skill in Azure Functions

Answer

Azure AI Translator and Azure AI Search

Answer

Azure AI Document Intelligence and Azure AI Search

Question 9

Your organization uses Microsoft Syntex to automatically classify and extract metadata from documents stored in SharePoint. You need to extend this capability to also extract entities such as invoice numbers and dates from PDF invoices that are uploaded to SharePoint. What should you do?

Accepted Answer

Create a document understanding model in Syntex that extracts entities from invoices.. Microsoft Syntex document understanding models can classify documents and extract entities such as invoice numbers and dates. Option A is incorrect because Syntex does not use AI Builder's out-of-the-box entity extraction; it uses its own model training. Option B is incorrect because Azure AI Search is a search service, not an entity extraction service integrated with Syntex. Option C is incorrect because Power Automate with AI Builder is a separate workflow automation approach, not part of Syntex. Therefore, option D is correct: create a document understanding model in Syntex that extracts entities from invoices.

Answer

Create a custom entity extraction model in Syntex using AI Builder.

Answer

Integrate Azure AI Search with SharePoint to extract entities.

Answer

Use Power Automate with AI Builder to extract entities from invoices.

Question 10

You are building a chatbot using Microsoft Copilot Studio that needs to answer questions based on content from a set of technical manuals stored as PDFs. The content must be indexed and made available to the chatbot. You need to configure the knowledge source for the chatbot. What should you do?

Accepted Answer

Create an Azure AI Search index from the PDFs and connect it to Copilot Studio as a knowledge source.. Azure AI Search provides a dedicated indexing service that can extract and store text from PDFs, enabling Copilot Studio to perform semantic search and retrieval-augmented generation (RAG). This allows the chatbot to answer questions based on the specific content of the technical manuals, rather than relying on external or unstructured data sources.

Answer

Upload the PDFs to a SharePoint library and use SharePoint as the knowledge source.

Answer

Add a web search connector to the chatbot to search for information online.

Answer

Store the content in Azure SQL Database and use it as a knowledge source.

Question 11

You are designing an Azure AI Search solution that indexes customer support tickets from a SQL database and also from a custom CRM system via a custom API. The index must support scoring profiles that boost tickets from VIP customers. The VIP status is stored in the CRM system. You need to ensure that the boost factor is applied correctly. What should you do?

Accepted Answer

Include the VIP status field in the index by pushing it from the CRM system via the push API, then use a scoring profile with a field boost.. The VIP status must be present in the index for a scoring profile to use it. By pushing the VIP status field from the CRM system via the Push API, you include it in the index. Then, a scoring profile with a field boost can apply a higher score to documents where the VIP field matches a specific value, ensuring the boost is applied at query time without external dependencies.

Answer

Use a scoring profile with a tag boost that references a field in the SQL database.

Answer

Use a scoring profile with a function that queries the CRM system at query time.

Answer

Configure a custom analyzer that boosts VIP terms.

Question 12

You are building an Azure AI Search index that includes content from a SQL database and an Azure Cosmos DB collection. The index must support autocomplete suggestions as users type. Which TWO configurations are required to enable autocomplete?

Accepted Answer

Define a suggester in the index definition.. Option B is correct because autocomplete in Azure AI Search requires a suggester defined in the index; the suggester specifies which fields (and optional source fields) are used to generate suggestions, and without it the autocomplete API returns an error. Option E is correct because the application must actually call the Autocomplete API endpoint (for example, POST /indexes/{index}/docs/autocomplete with the suggester name and search text) to retrieve suggestions as the user types. Option A is not required: CORS only enables browser-based cross-origin calls and is unrelated to autocomplete functionality. Option C is not required: custom analyzers affect tokenization for search and can influence suggester behavior, but they are not a prerequisite for enabling autocomplete. Option D is not required: scoring profiles affect relevance ranking of search results, not the generation of autocomplete suggestions.

Answer

Enable CORS on the search service.

Answer

Configure a custom analyzer for the fields used in autocomplete.

Answer

Create a scoring profile to boost relevant suggestions.

Question 13

You have an Azure AI Search skillset defined as shown in the exhibit. When you run the indexer, the enrichment pipeline produces outputs but no entities are extracted. The source documents are in English and contain clear organization and person names. What is the most likely cause?

Accepted Answer

The '/document/content' field is an array, but the skill expects a string.. The most likely cause is that the '/document/content' field is an array, but the Entity Recognition skill expects a string input. In Azure AI Search, if the source field is an array, the skill cannot process it directly, resulting in no entities being extracted even though the documents contain clear organization and person names.

Answer

The skill output is not mapped to the index.

Answer

The skills are in the wrong order.

Answer

The documents are not in English.

Question 14

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.. The most likely reason the filter on author is not working is that the filter expression uses incorrect OData syntax. Azure AI Search filters require proper OData syntax, such as `author eq 'John'`. If the syntax is wrong, the filter will fail.

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 15

You have configured an Azure AI Search indexer with a Cosmos DB data source as shown in the exhibit. The indexer runs successfully, but you notice that the index is missing some documents that were recently added to Cosmos DB. What is the most likely cause?

Accepted Answer

The high water mark is not being updated correctly, causing some documents to be skipped.. The most likely cause is that the high water mark (the _ts value) is not being updated correctly, causing the indexer to skip documents that were recently added. Azure AI Search uses a high water mark strategy to track changes from Cosmos DB, and if the _ts value is not properly recorded or the indexer's change tracking logic fails, new documents may be missed even though the indexer runs successfully.

Answer

The indexer is not configured to track changes using _ts.

Answer

The container name is misspelled.

Answer

The query does not select all fields required by the index.