AI-102 Implement knowledge mining and information extraction solutions — 25 Questions

Question 1

You are designing a knowledge mining solution for a medical research organization. The solution must extract relationships between drugs, diseases, and genes from scientific articles. The data will be stored in a knowledge graph for querying. Which Azure AI service should you use for the extraction?

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

Accepted Answer

Azure AI Language healthcare entity recognition and relation extraction. Azure AI Language's healthcare entity recognition and relation extraction is specifically designed to extract medical entities (drugs, diseases, genes) and their relationships from unstructured text, making it ideal for building a knowledge graph. This pre-built model uses deep learning trained on biomedical literature, directly supporting the required extraction without custom training.

Answer

Azure AI Search with semantic ranking

Answer

Azure AI Translator with dictionary lookup

Answer

Azure AI Document Intelligence custom extraction model

Question 2

Which THREE factors should you consider when designing a knowledge mining solution that uses Azure AI Search and custom skills to extract insights from large volumes of documents?

Accepted Answer

The maximum execution time of the custom skill must fit within the indexer timeout. Azure AI Search imposes a timeout on indexer execution, and any custom skill invoked during the enrichment pipeline must complete within that timeout. If the custom skill exceeds the maximum execution time (e.g., 3 minutes for built-in skills or a configurable limit for custom skills), the indexer will fail, causing the entire indexing run to abort. This is a critical design constraint when processing large volumes of documents.

Answer

The number of knowledge store projections affects indexing speed

Answer

Semantic ranking configuration must be included in the skillset

Question 3

Which TWO configurations are required to enable Azure AI Search to index content from an Azure SQL database?

Accepted Answer

Enable change tracking on the Azure SQL table. Azure AI Search requires change tracking to be enabled on the Azure SQL table to support incremental indexing. Without change tracking, the indexer would have to re-read the entire table on each run, which is inefficient for large datasets. Change tracking allows the indexer to detect only new, updated, or deleted rows since the last indexing cycle.

Answer

Create a custom skillset for data enrichment

Answer

Configure semantic ranking on the index

Answer

Enable high availability on the Azure SQL database

Question 4

You have an Azure AI Search solution that indexes customer support tickets. The index includes a 'category' field that should be automatically populated using a custom skill that calls an Azure Machine Learning model. However, the skill fails intermittently with HTTP 429 errors. What is the most likely cause and the best fix?

Accepted Answer

The skill execution batch size is too large, causing high call volume; reduce batch size in the skillset definition.. HTTP 429 errors indicate rate limiting, which occurs when the custom skill sends too many requests to the Azure Machine Learning endpoint in a short period. The skill execution batch size controls how many documents are processed per skill invocation; a large batch size increases call volume and triggers throttling. Reducing the batch size in the skillset definition lowers the request rate, preventing 429 errors.

Answer

The skill has a timeout set too short; increase the timeout.

Answer

The indexer runs too frequently; increase the indexer schedule interval.

Answer

The skill output field mapping is incorrect; fix the mapping.

Question 5

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 use an indexer to connect to Microsoft Purview's Atlas REST API, which allows it to crawl and ingest metadata (e.g., table schemas, file types, classifications) from Purview's data catalog. This integration enables knowledge mining by making both structured and unstructured data assets searchable through a unified Azure AI Search index, without requiring manual metadata push or intermediate tools.

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 6

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.. Training a custom model using labeled samples of the vendor's invoices allows Document Intelligence to learn the non-standard layout, improving extraction accuracy. Option A is incorrect because while OCR and regex can extract text, they are not effective for structured data extraction from variable layouts. Option B is incorrect because converting invoices to a standard format is time-consuming and may lose important data; it's better to train a model on the actual invoices. Option D is incorrect because the prebuilt invoice model is designed for standard invoice layouts; adjusting confidence thresholds won't fix extraction accuracy for non-standard formats.

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 7

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.. A suggester must be defined in the index schema to enable autocomplete. The suggester specifies which fields are used to generate suggestions and the suggestion mode (e.g., 'analyzingInfixMatching' for autocomplete). Without a suggester, the autocomplete API has no source of candidate terms to match against user input.

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 8

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

Accepted Answer

outputFieldMappings. In Azure AI Search, the two features used to map skill outputs to search index fields are outputFieldMappings and skillset outputs. outputFieldMappings explicitly define how outputs from cognitive skills are mapped to fields in the search index. Skillset outputs are the definitions within the skillset that specify which outputs each skill produces; these outputs are then referenced by outputFieldMappings. Field mappings (fieldMappings) are used to map source data fields, not skill outputs. Indexer parameters control indexer behavior but do not map skill outputs. Index fields are the destination fields in the index, not a mapping feature.

Answer

indexer parameters

Answer

fieldMappings

Answer

index fields

Question 9

You are designing a knowledge mining solution for a medical research organization. The solution must extract relationships between drugs, diseases, and genes from scientific articles. The data will be stored in a knowledge graph for querying. Which Azure AI service should you use for the extraction?

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

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 10

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 11

You are designing an Azure Cognitive Search solution for a legal document repository. The solution must support search across multiple languages, including English and Spanish. You need to ensure that searches return documents regardless of the language of the query. Which approach should you use?

Accepted Answer

Create separate fields for each language and set the analyzer per field.. The recommended approach in Azure AI Search for multilingual search is to create separate fields for each language and configure each field with the appropriate language analyzer (e.g., Microsoft English analyzer for English text, Microsoft Spanish analyzer for Spanish text). When querying, the client application can determine the query language and target the corresponding field, or use a `searchFields` parameter to search across multiple language-specific fields. This ensures that language-specific linguistic processing (stemming, stop words, etc.) is applied correctly. Option C is incorrect because Azure AI Search does not allow assigning multiple analyzers to a single field; a field can have only one analyzer. Options A and B are also incorrect: a custom splitter does not provide language-specific analysis, and assuming translation is unreliable.

Answer

Create a custom analyzer that splits text by language.

Answer

Use a single language analyzer set to English, and assume Spanish documents are translated.

Answer

Use the Microsoft analyzer for English and Spanish in a multi-language field.

Question 12

You are implementing a knowledge mining solution using Azure Cognitive Search with built-in AI enrichment. The pipeline must extract named entities and key phrases from documents. The enrichment pipeline should be triggered only for documents that are larger than 1 MB. Which approach should you use?

Accepted Answer

Implement a custom skill that checks the document size and only calls the built-in skills if size > 1 MB.. Azure Cognitive Search does not natively support document-size-based conditional skill execution. By implementing a custom skill that checks the document size and only invokes the built-in entity recognition and key phrase extraction skills for documents larger than 1 MB, you achieve the required conditional enrichment logic. This approach leverages the custom skill's ability to inspect document metadata and control downstream skill execution.

Answer

Configure the skillset to run entity recognition and key phrase extraction on all documents.

Answer

Use indexer parameters to specify a document size filter.

Answer

Create two indexers: one for large documents with skills, one for small documents without.

Question 13

Which TWO Azure AI Search features should you enable to improve the relevance of search results for a knowledge mining solution that supports natural language queries?

Accepted Answer

Semantic ranking. Options B and D are correct. Semantic ranking (B) uses deep learning models to re-rank search results based on query intent, improving relevance for natural language queries. Scoring profiles (D) allow customization of relevance through field weights, boosting, and freshness. Option A is incorrect because synonyms expand queries but do not re-rank results. Option C is incorrect because search mode 'all' returns documents containing all terms, which does not improve relevance ranking. Option E is incorrect because filters narrow results but do not affect ranking.

Answer

Synonyms

Answer

Search mode 'all'

Answer

Filters

Question 14

You are building a knowledge mining solution for a legal firm to extract clauses from contracts. The contracts are stored as PDFs in Azure Blob Storage. You need to design the solution to minimize cost while ensuring high accuracy for clause extraction. Which approach should you use?

Accepted Answer

Use Azure AI Document Intelligence with a custom extraction model trained on contract clauses.. Azure AI Document Intelligence (formerly Form Recognizer) provides custom extraction models that can be trained on specific contract clauses, delivering high accuracy and cost efficiency for document understanding. It is optimized for extracting structured data from PDFs. Option A (Custom Vision) is for image analysis, not text extraction. Option B (GPT-4) can be used but is often more expensive and less deterministic for structured extraction without fine-tuning. Option C (Azure AI Search blob indexer) is for indexing and search, not dedicated clause extraction.

Answer

Use Azure AI Custom Vision to detect clause regions in scanned documents.

Answer

Use Azure OpenAI GPT-4 to process each PDF and extract clauses using prompts.

Answer

Use Azure AI Search with a blob indexer to extract clauses during indexing.

Question 15

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.. It combines Document Layout skill (extracts text and layout from typed and handwritten text), Entity Recognition skill (identifies person names like parties and judge, as well as dates and case numbers), Custom Entity Lookup skill (recognizes case citation patterns like 'Smith v. Jones'), and Key Phrase Extraction skill (extracts legal topics). Option A is incorrect because it uses OCR skill instead of Document Layout (OCR may not capture layout well) and includes unnecessary Sentiment and Language Detection skills. Option B is missing Key Phrase Extraction for topics and Custom Entity Lookup for citations. Option D includes unnecessary Text Translation and Sentiment skills.

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 16

You are building a knowledge mining solution to extract insights from a large set of PDF contracts. The solution must identify parties, dates, and monetary amounts. Which Azure AI service should you use as the primary extraction engine?

Accepted Answer

Azure AI Document Intelligence. Azure AI Document Intelligence (formerly Form Recognizer) is the correct choice because it is specifically designed for document analysis and extraction of structured data such as parties, dates, and monetary amounts from PDFs and images. Its prebuilt models (e.g., the 'prebuilt-invoice' or 'prebuilt-contract' model) use optical character recognition (OCR) and deep learning to extract key-value pairs and entities from contracts without requiring custom training.

Answer

Azure AI Language (custom NER)

Answer

Azure AI Search with integrated vectorization

Answer

Azure OpenAI Service with GPT-4o

Question 17

Your team has built a knowledge mining pipeline using Azure AI Search and Document Intelligence. After ingestion, you notice that some documents are not appearing in search results. What is the most likely cause?

Accepted Answer

The indexer encountered errors and marked the documents as failed. If the indexer encounters errors while processing specific documents (e.g., unsupported formats, parsing failures, or skill errors), those documents are marked as failed and not indexed. This explains why only some documents are missing from search results. Option B is incorrect because semantic configuration affects ranking and relevance features, not whether documents are indexed. Option C is incorrect because insufficient replicas affect query performance and availability, not document ingestion. Option D is incorrect because throttling during high query volume would impact all search queries, not the indexing of specific documents.

Answer

The index does not have a semantic configuration

Answer

The search service has insufficient replicas

Answer

The search service is throttled due to high query volume

Question 18

You are designing a knowledge mining solution that must extract entities from scanned handwritten forms. The forms contain signatures and checkboxes. Which combination of Azure AI services should you recommend?

Accepted Answer

Azure AI Document Intelligence with a custom neural model and Azure AI Language for entity linking. The scenario requires extracting entities from scanned handwritten forms, which demands a custom neural model in Azure AI Document Intelligence to handle the variability of handwriting, signatures, and checkboxes. Azure AI Language's entity linking then enriches the extracted entities by disambiguating and linking them to a knowledge base, providing structured, meaningful output. The premade models in Document Intelligence are designed for printed text and common layouts, not handwritten content, making a custom neural model essential.

Answer

Azure AI Document Intelligence with a premade model and Azure AI Computer Vision

Answer

Azure AI Computer Vision (OCR) and Azure AI Search with integrated vectorization

Answer

Azure Cognitive Search and Azure AI Document Intelligence with a premade model

Question 19

Your knowledge mining solution uses Azure AI Search. Users complain that search results are not relevant. You have enabled semantic search but results still lack context. What should you do to improve relevance?

Accepted Answer

Ensure the index includes a semantic configuration with title and content fields. Semantic search in Azure AI Search requires a semantic configuration that explicitly maps the title and content fields to be used for semantic ranking. Without this configuration, the search engine cannot apply the deep neural network models that understand context and intent, so results remain based on keyword matching even when the semantic search feature is enabled.

Answer

Increase the number of partitions to handle more data

Answer

Configure a scoring profile with boosting based on metadata

Answer

Increase the number of replicas to improve query performance

Question 20

You need to extract key-value pairs from a large set of invoices. The invoices have a consistent layout but vary in format (PDF, TIFF). Which Document Intelligence model should you use?

Accepted Answer

Premade invoice model. The premade invoice model (D) is specifically designed to extract key-value pairs from invoices, including fields like invoice date, total amount, and vendor details, even when the invoices vary in format (PDF, TIFF). It leverages pre-trained deep learning models optimized for invoice layouts, making it the most efficient choice for this task without requiring custom training.

Answer

Custom extraction model

Answer

Layout model

Answer

Read model