AI-102 Implement knowledge mining and information extraction solutions Practice Test 6 — 15 Questions

Question 1

Refer to the exhibit. You are using Azure AI Search with a skillset that splits documents into pages and then analyzes sentiment per page. You notice that the sentiment analysis is returning unexpected results, such as positive sentiment for negative content. What is the most likely cause?

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

Accepted Answer

The page split mode with overlap may still cut sentences, causing sentiment to be evaluated on incomplete sentences.. The SplitSkill uses 'pages' mode which often splits at page boundaries, potentially cutting sentences in half. This can cause the sentiment analysis to receive incomplete text, leading to incorrect sentiment. Option A is not the primary issue. Option B is about the initial text, not splitting. Option C is about the split context, but the sentiment context is correct.

Answer

The SentimentSkill is receiving the entire document text instead of individual pages.

Answer

The split skill context '/document' should be '/document/content'.

Answer

The defaultLanguageCode is set to 'en' but the documents contain other languages.

Question 2

You are a data scientist at a healthcare research organization. You have been tasked with building a knowledge mining solution to extract key information from thousands of medical journal articles stored as PDFs in an Azure Blob Storage container. The articles are in English and contain tables, figures, and structured text. Your organization uses Microsoft Purview for data governance. You need to design a solution that uses Azure AI Search and Azure AI Services to extract and index the following: article title, authors, publication date, abstract, and key findings (as key phrases). The solution must also detect any mentions of drugs and dosages. The extracted information must be indexed and searchable via a custom web application. Which approach should you take?

Accepted Answer

Use Azure AI Search with a blob indexer and a skillset that includes Document Layout skill, Entity Recognition skill to extract drug names, Key Phrase Extraction skill, and custom skill to extract title/authors/date from the first page. Create an index with fields for each required element.. It combines the Document Layout skill (to extract text from PDFs including tables and figures), Entity Recognition skill (to detect drug names), Key Phrase Extraction skill (to identify key findings), and a custom skill (to parse the first page for title, authors, and publication date). This approach handles the unstructured nature of medical journal articles while meeting all extraction requirements and indexing them into a custom searchable index.

Answer

Use Azure AI Search with a skillset that includes OCR skill, Text Translation skill to translate, Entity Recognition skill for drugs, and Key Phrase Extraction. Index the results.

Answer

Use Azure AI Search with a blob indexer that includes a skillset with Document Layout skill to extract text, Key Phrase Extraction skill to extract key findings, and map built-in metadata for title, authors, date. Use a custom index to store the extracted fields.

Answer

Use Azure AI Search with a skillset that includes OCR skill, Entity Recognition skill, Sentiment skill, and Key Phrase Extraction. Use a knowledge store to project the enriched data.

Question 3

You are a solution architect at a financial services company. You need to implement a knowledge mining solution that extracts information from annual reports (PDF) of publicly traded companies. The reports contain financial tables, executive summaries, and legal disclaimers. The solution must: (1) extract the company name, fiscal year, revenue, net income, and CEO name; (2) redact any personally identifiable information (PII) like email addresses and phone numbers before indexing; (3) index the extracted data in Azure AI Search; (4) allow users to query using natural language (e.g., 'Which company had the highest revenue in 2023?'). The reports are uploaded to an Azure Blob Storage container. You have access to Azure AI Services and Azure OpenAI. Which combination of services and configurations should you use?

Accepted Answer

Use Azure AI Document Intelligence custom extraction model trained on annual reports to extract fields. In the Azure AI Search pipeline, add a PII detection skill to redact PII. Enable semantic search for natural language queries.. Azure AI Document Intelligence can be trained with a custom extraction model to accurately extract specific financial fields like company name, fiscal year, revenue, net income, and CEO name from annual report PDFs. The PII detection skill in the Azure AI Search enrichment pipeline redacts sensitive information such as email addresses and phone numbers before indexing. Enabling semantic search allows users to query using natural language. Option B relies on Azure AI Vision OCR and Azure AI Language entity extraction, which are less precise for structured table extraction and cannot guarantee the specific fields needed. Option C uses generic skills like Document Layout and Entity Recognition, which are not tailored for financial data extraction and may miss critical fields. Option D uses GPT-4, which can be inconsistent for structured data extraction from tables and does not include built-in PII redaction within the search pipeline.

Answer

Use Azure AI Vision OCR to extract text from PDFs, then use Azure AI Language to extract entities and key phrases. Index in Azure AI Search with semantic search.

Answer

Use Azure AI Search with blob indexer, include a skillset with Document Layout skill, Entity Recognition skill (for financial entities), and Key Phrase Extraction. Enable semantic search.

Answer

Use Azure OpenAI GPT-4 to process each report via a custom extraction prompt, then send extracted JSON to Azure AI Search. Enable semantic search.

Question 4

You are a developer at a legal firm. The firm has a repository of court case documents stored as PDFs in Azure Blob Storage. You need to build a knowledge mining solution that enables lawyers to search for cases by parties involved, judge name, case number, date, and key legal topics. The documents are in English and contain both typed and handwritten text. The solution must extract the aforementioned metadata and also identify citations to other cases (e.g., 'Smith v. Jones'). You plan to use Azure AI Search with cognitive skills. Which combination of skills should you include in your skillset?

Accepted Answer

Document Layout skill, Entity Recognition skill (for person names and organizations), Custom Entity Lookup skill (for case citation patterns), and Key Phrase Extraction skill for legal topics.. The combination of Document Layout skill, Entity Recognition skill, Custom Entity Lookup skill, and Key Phrase Extraction skill addresses all requirements: Document Layout extracts text and structure from PDFs, Entity Recognition identifies parties and judges, Custom Entity Lookup finds case citations using patterns, and Key Phrase Extraction identifies legal topics.

Answer

OCR skill (to handle handwriting), Key Phrase Extraction skill, Sentiment skill, and Language Detection skill.

Answer

OCR skill, Document Layout skill, Entity Recognition skill, and Text Translation skill.

Answer

Document Layout skill, Text Translation skill, Sentiment skill, and Key Phrase Extraction skill.

Question 5

You are a machine learning engineer at a retail company. The company wants to build a product knowledge base by extracting information from product manuals, specifications sheets, and customer reviews. The data sources include PDFs, Word documents, and plain text files stored in Azure Blob Storage. The solution must: (1) extract product name, model number, price, and key features; (2) analyze customer reviews to extract sentiment and common issues; (3) enable natural language queries like 'Which products have the best reviews under $100?'; (4) handle documents in English and Spanish. You need to design a solution using Azure AI Search and Azure AI Services. Which approach meets all requirements with the least development effort?

Accepted Answer

Use a single Azure AI Search pipeline with a skillset that includes Document Layout skill, Text Translation skill (to English), Sentiment skill, and Key Phrase Extraction skill. Enable semantic search.. It uses a single Azure AI Search pipeline with a skillset that includes Document Layout skill (to handle various document formats like PDFs, Word docs, and text files), Text Translation skill (to convert Spanish documents to English, unifying the language), Sentiment skill (to analyze customer reviews for sentiment), and Key Phrase Extraction skill (to extract key features and common issues). Enabling semantic search allows natural language queries such as 'Which products have the best reviews under $100?'. This approach meets all requirements with the least development effort, as it avoids the need for multiple pipelines or custom model training required by other options.

Answer

Use Azure AI Document Intelligence custom model to extract product info from manuals/specs. Use a separate Azure AI Search pipeline for customer reviews with sentiment analysis. Enable semantic search.

Answer

Use Azure AI Search with a blob indexer and a skillset that includes OCR skill (for scanned PDFs), Text Translation skill, Sentiment skill, and Entity Recognition skill. Enable semantic search.

Answer

Use Azure AI Document Intelligence to extract product info from all documents, then feed into Azure AI Search. Enable semantic search.

Question 6

A company is building a knowledge mining solution using Azure AI Search. They need to extract entities from a large set of PDF documents stored in Azure Blob Storage. The solution must use a built-in AI skill to identify people, organizations, and locations. Which TWO actions should be taken? (Choose two.)

Accepted Answer

Enable OCR (Optical Character Recognition) in the indexer configuration.. Option E is correct because the Entity Recognition skill is the built-in Azure AI Search cognitive skill that invokes the Text Analytics entity recognition model to identify people, organizations, and locations (its 'categories' include Person, Organization, and Location) from text content. Option D is correct because the source documents are PDFs; enabling OCR in the indexer configuration (via the 'imageAction'/'ocr' settings on the document extraction) is required so that text embedded in scanned or image-based PDFs is extracted and made available to the enrichment pipeline before the Entity Recognition skill can run. Option A is incorrect because a custom analyzer affects how text is tokenized and indexed for search, not how entities are extracted. Option B is incorrect because the Key Phrase Extraction skill returns key phrases, not people, organizations, and locations. Option C is incorrect because the requirement is to use a built-in AI skill, and a custom Azure Functions skill would be a custom skill rather than a built-in one.

Answer

Configure the index to use a custom analyzer.

Answer

Add the Key Phrase Extraction skill to the skillset.

Answer

Deploy a custom skill using Azure Functions to extract entities.

Question 7

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.. Option A is correct because the Text Analytics for Health skill is the built-in Azure AI Search cognitive skill that invokes the healthcare NLP model to extract entities such as medical conditions, medications, and treatment procedures from unstructured medical record text during skillset enrichment. Option B is correct because an Azure AI Search index is required to store the enriched documents and their extracted entities so the knowledge mining solution can be queried and surfaced. Option C is correct because the Text Analytics for Health model in Microsoft Foundry is the pre-built model that performs the entity extraction for medical conditions, medications, and procedures, and it is the Foundry-hosted capability the scenario requires. Option D is not correct because Azure AI Document Intelligence custom models are trained for form and document layout extraction, not for identifying clinical entities like conditions and medications. Option E is not correct because LUIS is a conversational language understanding service for intents and utterances, not a pre-built medical entity extraction model.

Answer

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

Answer

Language Understanding (LUIS) model.

Question 8

You are developing a knowledge mining solution for a legal firm that needs to process thousands of legal contracts stored as PDFs in Azure Blob Storage. The solution must extract clauses, parties, and dates using a custom model. You are using Microsoft Foundry with Azure AI Search and Azure AI Document Intelligence. The custom model must be trained on labeled contract data. After training, you deploy the model and integrate it into the AI Search enrichment pipeline. The pipeline must also perform OCR for scanned contracts. You have configured the following:

- A custom classification model in Document Intelligence for document types.
- A custom extraction model in Document Intelligence for clauses, parties, and dates.
- An Azure AI Search index with fields: clause, party, date.
- A skillset with a Document Intelligence skill pointing to the custom extraction model.

During testing, the pipeline runs successfully for digital PDFs but fails for scanned PDFs. The error indicates that OCR is not being applied. What should you do to fix the issue?

Accepted Answer

Modify the Document Intelligence skill configuration to enable OCR processing.. Scanned PDFs contain images of text, so OCR must be performed to extract text before the custom extraction model can process it. Azure AI Document Intelligence's custom extraction model can perform OCR internally if the skill configuration has OCR enabled. By default, the Document Intelligence skill in the skillset does not automatically enable OCR for scanned documents; you must set the `enableOcr` property to `true` in the skill configuration. Option A is incorrect because retraining the model with scanned images would not enable OCR; the model still needs text input. Option B is incorrect because recreating the index does not address the missing OCR step. Option D is incorrect because adding a separate OCR skill is not necessary; Document Intelligence can handle OCR internally when configured correctly.

Answer

Retrain the custom extraction model with scanned document images.

Answer

Delete and recreate the index with a different field mapping.

Answer

Add an OCR skill to the skillset before the Document Intelligence skill.

Question 9

You are building a knowledge mining solution for a financial services company that needs to extract key financial terms (e.g., revenue, EBITDA, net income) from annual reports in PDF format. The solution must use a custom skill that runs a Python script to perform the extraction. The Python script is deployed as an Azure Function. You have added the custom skill to the skillset and tested it with a small set of documents. However, when processing the full dataset, the custom skill fails with time-out errors. The Azure Function has a default timeout of 230 seconds. What should you do to resolve the issue without changing the extraction logic?

Accepted Answer

Change the Azure Function to a Premium plan and increase the function timeout.. The custom skill is implemented as an Azure Function, and the timeout error is caused by the function's execution time exceeding the default 230-second limit for the Consumption plan. Azure Functions on the Consumption plan have a maximum timeout of 10 minutes (600 seconds) but the default is 230 seconds; on the Premium plan, the maximum timeout is unbounded (or up to 60 minutes on App Service plan). By moving to a Premium plan, you can increase the timeout setting to a value greater than 230 seconds, allowing the Python script to complete without altering the extraction logic. This directly addresses the root cause: the function needs more time to process larger documents.

Answer

Configure the indexer to process documents in smaller batches.

Answer

Replace the custom skill with a Document Intelligence custom extraction model.

Answer

Split the skillset into multiple skillsets and run them sequentially.

Question 10

Your company is developing a knowledge mining solution for a legal firm that needs to extract information from scanned legal documents. The documents contain handwritten notes in addition to printed text. You need to extract both printed and handwritten text. You are using Azure AI Document Intelligence with the Read OCR model. The solution must be integrated into Azure AI Search. During testing, the printed text is extracted correctly, but handwritten text is often missing or incorrect. What should you do to improve the extraction of handwritten text?

Accepted Answer

Ensure the Document Intelligence skill is configured with the Read OCR model and handwriting recognition enabled.. The Document Intelligence Read OCR model supports handwriting recognition, but it must be explicitly enabled in the skill configuration. By ensuring handwriting recognition is enabled, the solution will extract handwritten text. Option C is incorrect because training a custom model is unnecessary; the Read OCR model already handles handwriting when enabled. Option A is incorrect because increasing resolution may improve overall quality but does not specifically enable handwriting recognition. Option B is incorrect because the built-in OCR skill in Azure AI Search does not support handwriting.

Answer

Preprocess the documents to increase image resolution before sending to Document Intelligence.

Answer

Add an OCR skill from Azure AI Search's built-in skills to the skillset.

Answer

Train a custom Document Intelligence model on handwritten samples.

Question 11

You are creating an Azure AI Search index that will store extracted entities from contracts. You need to define a field that will contain multiple values of the same type, such as a list of party names. Which index field attribute should you set to true?

Accepted Answer

collection. To store multiple values of the same type in an Azure AI Search index field, you must define the field as a collection type, such as Collection(Edm.String). This is specified in the field definition, not through attributes like searchable, filterable, or facetable. The collection type enables the field to hold an array of values.

Answer

filterable

Answer

facetable

Answer

searchable

Question 12

You are building an Azure AI Search solution that indexes documents from Azure Blob Storage. The documents are in various formats, including PDF, Microsoft Word, and plain text. You need to extract text content and metadata such as author and creation date. You also need to preserve the original file path in the index. Which indexer configuration should you use?

Accepted Answer

Use the Azure Blob indexer with the 'content' and 'metadata' properties, and map the 'metadata_storage_path' to an index field.. The Azure Blob indexer is designed to extract content and metadata from documents in Blob Storage, including PDF, Word, and text files. It automatically provides metadata such as author and creation date, and the 'metadata_storage_path' field can be mapped to preserve the file path. This built-in capability meets all requirements without custom code.

Answer

Use the Azure Blob indexer with a custom skill that calls Azure AI Document Intelligence to extract text and metadata.

Answer

Use the Azure Cosmos DB indexer and store documents in Cosmos DB with metadata fields.

Answer

Use the Azure Table indexer and store document metadata in Azure Table Storage.

Question 13

You are creating an Azure AI Search solution that indexes customer support tickets stored in Azure Cosmos DB. Each ticket has a 'description' field containing free-form text. You need to enrich the tickets by extracting named entities such as product names, organizations, and locations from the description. You also need to ensure that the enrichment pipeline can handle up to 100,000 characters per document. Which built-in skill should you use?

Accepted Answer

Entity Recognition skill. The Entity Recognition skill is the correct choice because it extracts named entities such as organizations, locations, and product names from text. It is designed for this purpose and can handle large documents within the limits of the enrichment pipeline. The other skills either extract different information (key phrases, sentiment) or perform translation, none of which meet the requirement of extracting named entities.

Answer

Text Translation skill

Answer

Key Phrase Extraction skill

Answer

Sentiment Analysis skill

Question 14

You are building an Azure AI Search enrichment pipeline that includes a custom skill implemented as an Azure Function. The custom skill must process a batch of documents and return enriched data. You need to configure the custom skill to handle errors gracefully and ensure that the pipeline continues processing other documents if one fails. Which two actions should you perform? (Choose two.)

Accepted Answer

Set the ignoreErrors property to true in the custom skill definition.. To handle errors gracefully in a custom skill, you should set ignoreErrors to true so the pipeline continues despite failures. Additionally, including an 'errors' array in the response body allows for detailed error reporting per document. These two actions together ensure that a single document failure does not halt the entire enrichment process and that errors are properly logged for troubleshooting.

Answer

Set the batchSize property to a value greater than 1.

Answer

Set the timeout property to a high value to prevent timeouts.

Answer

Configure the Azure Function to return a 200 OK response with an error message in the response body for failed documents.

Question 15

You are building an Azure AI Search enrichment pipeline that includes a custom skill implemented as an Azure Function. The custom skill calls an external API that has a rate limit of 100 requests per second. You need to ensure that the indexer does not exceed this rate limit while processing a large number of documents. What should you configure?

Accepted Answer

Set the 'degreeOfParallelism' property in the indexer definition to a lower value.. Reducing the 'degreeOfParallelism' in the indexer definition limits the number of concurrent document processing operations, which in turn reduces the rate at which the custom skill is invoked. This is the appropriate way to throttle requests to an external API with a rate limit. The other options either do not exist or do not control the request rate.

Answer

Set the 'maxBatchSize' property in the indexer definition to 100.

Answer

Set the 'maxTransientRetries' property in the custom skill definition to 3.

Answer

Set the 'batchSize' property in the custom skill definition to 100.