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

Question 1

Your team is implementing a knowledge mining solution using Azure AI Search with custom skills. The custom skill, deployed as an Azure Function, calls a third-party API to enrich documents. You notice that some documents fail enrichment with HTTP 429 (too many requests) errors. You need to ensure all documents are enriched without losing data. What should you do?

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

Accepted Answer

Configure the custom skill to execute in batch mode and set a retry policy on the indexer. Configuring the custom skill to execute in batch mode reduces the number of HTTP requests to the third-party API by processing multiple documents per invocation, while setting a retry policy on the indexer ensures that failed documents due to transient HTTP 429 errors are automatically retried. This combination prevents data loss by not skipping documents and by handling rate-limiting gracefully.

Answer

Increase the number of partitions in the Azure AI Search service

Answer

Enable indexer error handling to skip failed documents

Answer

Scale out the Azure Function to multiple instances

Question 2

You are building a knowledge mining solution that indexes technical manuals in multiple languages. The solution must enable users to search in their native language and retrieve results in the same language. Which approach should you use?

Accepted Answer

Use language-specific analyzers in the Azure AI Search index for each language. Azure AI Search supports language-specific analyzers (e.g., 'de.microsoft' for German, 'fr.microsoft' for French) that apply linguistic rules such as stemming, lemmatization, and stop-word removal tailored to each language. This ensures that queries and documents are processed in the same language, enabling users to search and retrieve results in their native language without translation loss.

Answer

Detect the language of the query using Azure AI Language and then use a generic analyzer

Answer

Translate all queries to English using Azure AI Translator before searching

Answer

Use a single non-language-specific analyzer like 'standard.lucene' for all documents

Question 3

You need to extract product codes (e.g., 'PRD-12345') from scanned invoices using Azure AI Document Intelligence. The product codes always follow a pattern of three uppercase letters, a hyphen, and five digits. Which approach should you use?

Accepted Answer

Build a custom skill in Azure AI Search using a Python regex. The pre-built invoice model in Azure AI Document Intelligence does not support adding custom fields with regex patterns; custom field extraction with regex is only available in custom models. Option B is correct: you can build a custom skill in Azure AI Search using a Python regex to extract the product codes from the text output of Document Intelligence. This approach allows you to apply a regex pattern to the extracted content, providing accurate and flexible extraction without needing to train a model or use a large language model. Option C is less suitable because training a custom NER model requires labeled data and may not guarantee exact pattern matching. Option D is overkill for a simple regex pattern.

Answer

Use the pre-built invoice model in Azure AI Document Intelligence with a regex field extraction

Answer

Train a custom NER model in Azure AI Language

Answer

Use Azure OpenAI GPT-4 with document vision to extract the codes

Question 4

Your Azure AI Search indexer is failing to index a large number of PDFs from Azure Blob Storage. The error log shows 'Document extraction timeout' for many documents. You need to resolve this issue without losing data. What should you do?

Accepted Answer

Increase the indexer execution timeout in the indexer definition. The 'Document extraction timeout' error indicates that the indexer is taking longer than the default 24-hour timeout to process certain PDFs. Increasing the indexer execution timeout in the indexer definition allows the indexer to continue processing these large documents without losing data, as it extends the maximum time the indexer can run for a single execution.

Answer

Change the parsing mode of the indexer to 'text'

Answer

Split large PDFs into smaller files before uploading

Answer

Enable incremental enrichment on the skillset

Question 5

You are building a knowledge mining solution to extract key information from handwritten forms. The forms contain checkboxes, signatures, and handwritten text. Which Azure AI service should you use?

Accepted Answer

Azure AI Document Intelligence layout model. Azure AI Document Intelligence's layout model is designed to extract text, tables, checkboxes, signatures, and structure from documents, including handwritten forms. It combines OCR with deep learning models to understand the spatial relationships between elements, making it the correct choice for this scenario.

Answer

Azure AI Language

Answer

Azure AI Speech

Answer

Azure AI Vision OCR

Question 6

Which TWO actions should you perform to ensure that an Azure AI Search indexer can successfully enrich documents using a custom skill that calls an external API?

Accepted Answer

Configure a retry policy in the skillset definition for the custom skill. A custom skill in an Azure AI Search skillset can fail due to transient errors when calling an external API. Configuring a retry policy in the skillset definition allows the indexer to automatically retry failed skill executions, improving resilience. Option C is correct because using a managed identity for the search service eliminates the need to manage credentials when accessing an Azure Function, providing secure authentication without storing secrets.

Answer

Enable CORS on the Azure Function app to allow cross-origin requests

Answer

Set the indexer's execution timeout to unlimited

Answer

Add the external API endpoint to the indexer's allowed domains list

Question 7

Which THREE Azure AI services can be used to extract text from images?

Accepted Answer

Azure AI Search. The question asks for three Azure AI services that can extract text from images. Azure AI Document Intelligence layout model (C) and Azure AI Vision OCR (D) are direct text extraction services. Azure AI Search (B) can also extract text from images by using OCR as a built-in cognitive skill in an enrichment pipeline. Option A (Speech) processes audio, not images. Option E (Language custom NER) works only on pre-extracted text. Therefore, the correct options are B, C, and D.

Answer

Azure AI Speech

Answer

Azure AI Language custom NER

Question 8

You deploy the ARM template shown in the exhibit to create an Azure AI Search indexer. The indexer fails to run, and you see an error that the skillset 'demo-skillset' does not exist. What is the most likely cause?

Accepted Answer

The skillset resource was not deployed before the indexer. The ARM template deploys resources in parallel by default, so the indexer can be created before the skillset. Since the indexer references 'demo-skillset' in its configuration, the deployment fails because the skillset resource does not exist at the time the indexer is created. To fix this, you must add a 'dependsOn' property in the indexer resource definition to ensure the skillset is deployed first.

Answer

The field mapping source field 'metadata_storage_path' is incorrect

Answer

The schedule start time is in the past, causing the indexer to be disabled

Answer

The data source 'demo-datasource' does not exist

Question 9

You have defined the custom WebApiSkill shown in the exhibit. The skill calls an Azure Function that can process up to 10 documents per second. However, you notice that the skill is failing with 429 errors. What is the most likely cause?

Accepted Answer

The degreeOfParallelism of 3 causes too many concurrent requests, exceeding the function's capacity. The `degreeOfParallelism` of 3 causes the AI Search enrichment pipeline to invoke the Azure Function with up to 3 concurrent batches, each of size 5, resulting in up to 15 documents per second. Since the function can only handle 10 documents per second, this exceeds its capacity and triggers HTTP 429 (Too Many Requests) errors.

Answer

The timeout of 30 seconds is too short for the function to respond

Answer

The batch size of 5 is too large, causing the function to receive too many documents at once

Answer

The context '/document' is incorrect, causing all documents to be processed as one

Question 10

You are building a knowledge mining solution for legal documents using Azure AI Search. The solution must extract entities like dates, organizations, and persons from PDF files and index them. Which built-in skill should you add to the skillset to perform this extraction?

Accepted Answer

Named Entity Recognition skill. The Named Entity Recognition (NER) skill in Azure AI Search is specifically designed to extract entities such as dates, organizations, and persons from text. When added to a skillset, it processes the content extracted from PDF files and outputs structured entity information that can be indexed and queried. This directly matches the requirement to extract and index named entities from legal documents.

Answer

Language Detection skill

Answer

Optical Character Recognition (OCR) skill

Answer

Key Phrase Extraction skill

Question 11

You are designing a knowledge mining solution to extract information from scanned invoices stored as multi-page TIFF images. Which two Azure AI services should you combine to extract text and structure the data?

Accepted Answer

Azure AI Document Intelligence and Azure AI Vision. Azure AI Document Intelligence (formerly Form Recognizer) can extract structured data like invoice fields, while Azure AI Vision provides OCR to extract text from multi-page TIFF images. Option A is incorrect because Azure AI Language does not process images directly. Option C is incorrect because Azure AI Search indexes data but does not extract text from images. Option D is incorrect because Azure AI Translator translates text but does not extract or structure data.

Answer

Azure AI Language and Azure AI Search

Answer

Azure AI Search and Azure AI Vision

Answer

Azure AI Translator and Azure AI Document Intelligence

Question 12

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 content as input to a custom skill, the skill's context should be set to '/document', which allows the skill to run once per document. The input source should be '/document/content' to reference the entire content field of the document. Options A and B set context to '/document/content', which runs the skill on each content node individually, not the whole document. Option C uses '/document/normalized_images/*' as input, which is for images, not the content. Therefore, option D is correct.

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 13

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 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 14

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 the correct service because it is specifically designed to extract key-value pairs, tables, and structured data from scanned forms and documents using prebuilt and custom models. This aligns directly with the requirement for knowledge mining from scanned forms.

Answer

Azure AI Vision

Answer

Azure AI Language

Answer

Azure AI Search

Question 15

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.