Pass the Microsoft Azure AI Engineer Associate AI-102 Questions and answers with CertsForce

Entity linking in Azure AI Language identifies entities in text and links them to entries in a knowledge base such as Wikipedia, providing precisely the additional context and references you need. Custom NER extracts entities but doesn’t link to Wikipedia; Content Safety moderates content; Key phrase extraction surfaces topics without external links.

Microsoft References:

Entity linking overview (links entities to Wikipedia). Microsoft Learn

How to call the Entity Linking API (returns entities with Wikipedia links)

Generate alt text

To automatically suggest descriptive captions for images (usable as alt text), use the Computer Vision Describe Image API. It returns natural-language captions summarizing the image content. Endpoint: /vision/v3.2/describe . Setting maxCandidates=1 gives a single best caption.

Detect inappropriate content

To block adult/racy/gory images with minimal effort, use Computer Vision Analyze Image with the Adult visual feature. This returns flags ( isAdult , isRacy , isGory ) and confidence scores. The provided option includes Adult,Description which still returns the needed adult/racy/gore signals, satisfying the requirement.

These choices minimize development effort by using built-in Computer Vision capabilities without training a custom model or wiring up multiple services.

References

Microsoft Learn – Describe images (Computer Vision): “The Describe Image API returns a list of natural language sentences that describe the image.”

https://learn.microsoft.com/azure/ai-services/computer-vision/overview-image-analysis#describe-images

Microsoft Learn – Analyze images (Adult/Racy/Gore detection): “Use the Adult feature to detect adult, racy, and gory content.”

https://learn.microsoft.com/azure/ai-services/computer-vision/overview-image-analysis#adult-racy-and-gory-content-detection

PaaS databases reduce administrative overhead because Microsoft manages backups, patching, updates, and infrastructure.

Users always get access to the latest features without manual upgrades.

B is incorrect: Backup/restore is automated; you don’t get full manual control.

C is incorrect: In-database ML services are supported in SQL Server (on-prem / IaaS), but not natively in Azure SQL Database.

Your app currently calls the prebuilt Business Card model v2.1. In v2.1, the platform does not provide QR/barcode interpretation. Support for decoding barcodes (including QR codes) was introduced with the v3.x API family as an add-on capability ( ocr.barcode ) that you can enable on analysis requests in API versions 2023-07-31 (GA) and later. Therefore, the first step is to upgrade from v2.1 to v3.0 so your application can use the newer API surface that supports barcode/QR extraction. This meets the “minimize administrative effort” requirement because you keep the same Azure AI Document Intelligence resource, keys, and endpoint—your change is primarily to the API/SDK version and request options.

After upgrading, you have two common implementation patterns:

Continue to use prebuilt Business Card for the contact fields, and in the same flow make an additional call with prebuilt Layout (or General Document) with the ocr.barcode add-on enabled to decode any QR code present on the card. This is the recommended path because the Business Card model itself doesn’t expose add-on features, while the platform’s v3.x analysis APIs do support ocr.barcode on other models. Microsoft Learn

Why the other options are not correct:

A. Deploy a custom model – unnecessary effort; barcode/QR decoding is available out-of-the-box in v3.x via ocr.barcode . Microsoft Learn

B. Implement the read model – Read (OCR) extracts text but does not interpret barcodes/QR codes; you need the barcode add-on introduced in v3.x. Microsoft Learn

D. Implement the contract model – Irrelevant to business cards or QR decoding.

Key Microsoft References

Add-on capabilities (including ocr.barcode with QR support) — available in API 2023-07-31 (GA) and later. Microsoft Learn

Barcode/QR extraction behavior and schema (barcodes collection, kind, value, polygon). Microsoft Learn

Migration guide from v2.1 to v3.x (why upgrade and what changes). Azure Docs

Business Card model documentation and versioning context (v2.1/v3.0/v3.1). Microsoft Learn

SDK/blog announcement of barcode add-on in v3.x (what it returns and when it’s supported). Microsoft for Developers

Code samples showing the barcodes add-on usage. github.com

The agent will reason over the uploaded file.●○

The code will create a run and check the output.○●

The code will create an agent and enable a file search.○●

 The agent will reason over the uploaded file.

Yes : The code includes file = project_client.agents.upload_file_and_poll(file_path= " ./data/file1.zip " , purpose=FilePurpose.AGENTS). The upload_file_and_poll method with FilePurpose.AGENTS suggests that the file (file1.zip) is uploaded for the agent to process, and agents in the Azure AI Foundry Agent Service are typically designed to reason over uploaded data. This indicates the agent will reason over the uploaded file.

 The code will create a run and check the output.

No : The provided code snippet does not include any explicit call to create a run (e.g., a method like create_run or start_run) or check the output (e.g., a method to retrieve or poll run results). The code only uploads a file and creates a vector store, but it does not initiate or monitor a run.

 The code will create an agent and enable a file search.

No : The code does not contain a method to create an agent (e.g., create_agent) or explicitly enable a file search. The create_vector_store_and_poll method creates a vector store, which is typically used for indexing data for search, but there is no indication of enabling a file search or creating an agent in this snippet.

Upload a glossary file to the container for French files

Define a document translation specification that has a French target

Perform an asynchronous translation by using the document translation specification

You need to translate Word and PowerPoint files (German → French) while preserving formatting and supporting a custom glossary. The correct service is Azure Document Translation, part of the Translator service in Azure Cognitive Services.

Step-by-step reasoning:

Upload a glossary file to the container for French files.

Glossaries (also called custom terminology files) guide translation to ensure consistent word usage.

They are stored in the target container (in this case, the French container).

Define a document translation specification that has a French target.

A translation request is defined by creating a document translation specification JSON.

This specification indicates:

The source container (German files)

The target container (French files)

The glossary file (for custom terminology)

Output target language (French).

Perform an asynchronous translation by using the document translation specification.

Document translation jobs are submitted asynchronously.

This step executes the translation while preserving formatting and applying the glossary rules.

Why not the other options?

Generate a list of files to be translated → not required, the service automatically processes all files in the source container.

Perform asynchronous translation using a list of files → that method does not support document-level translation with glossary and formatting preservation, it’s used for text-based translations.

Correct Answer Order:

Upload a glossary file to the container for French files

Define a document translation specification that has a French target

Perform an asynchronous translation by using the document translation specification

Microsoft References

Document Translation – Translate documents in containers

Use custom glossaries with Document Translation

Submit document translation requests

To identify city names with Azure AI Language, you use the Text Analytics client and its Named Entity Recognition (NER) capability. In the .NET SDK, create a TextAnalyticsClient and call RecognizeEntities(...) . This returns a CategorizedEntityCollection , where each CategorizedEntity has properties such as Text , Category , SubCategory , and ConfidenceScore .

City mentions are recognized under the broader Location category, and the more specific type is surfaced in SubCategory (commonly " City " ). Therefore, iterating the returned entities and filtering with entity.SubCategory.Contains( " City " ) correctly locates city names. Using DocumentAnalysisClient or FormRecognizerClient would be incorrect because those are for document/form extraction scenarios, not general-language NER. QuestionAnsweringClient is for Q & A over knowledge sources. Hence the correct client is TextAnalyticsClient , and the correct discriminator is SubCategory .

Microsoft Azure AI References (titles only)

Azure AI Language – Text Analytics client library: Recognize Entities

Azure AI Language – Named Entity Recognition concepts and categories

Azure AI Language – CategorizedEntity model (Category, SubCategory, ConfidenceScore)

Comprehensive Detailed Explanation

Looking at the exhibit:

The GetWeather dialog is set up with a trigger phrase:

“what is the weather like in {city=Seattle}”

Here, city is an entity (ex: Seattle, New York, London, etc.).

1. User asks “what is the weather like in New York”

Since “New York” matches the city entity, the bot will correctly identify New York as a city entity.

It will not confuse it with a state entity, nor default to Seattle, because entity recognition extracts the correct city name dynamically.

Correct choice: Identify New York as a city entity

2. GetWeather dialog trigger

In Bot Framework Composer, the trigger type determines how the dialog is activated.

Since GetWeather is linked to the intent “GetWeather” from the Language Understanding model (LUIS/CLU), the trigger is Language Understanding Intent recognized.

This means whenever the user utterance maps to the GetWeather intent, the dialog starts.

Correct choice: Language Understanding Intent recognized

Correct Answer:

Identify New York as a city entity

Language Understanding Intent recognized

Microsoft References

Bot Framework Composer – Triggers

Entities in Conversational Language Understanding

The question is about evaluating a Custom Vision classifier after training.

When you train an image classifier in Azure Custom Vision, the service automatically calculates performance metrics to help you evaluate the quality of the model.

Metrics Provided by Custom Vision:

Precision:

The percentage of correct positive predictions out of all positive predictions made.

Formula: Precision = TP / (TP + FP)

Helps determine how reliable positive predictions are.

Recall:

The percentage of actual positives that were correctly predicted.

Formula: Recall = TP / (TP + FN)

Helps determine how many of the true positives were captured.

These two metrics are explicitly shown in the Custom Vision portal and via API.

Option Analysis

A. Recall

Yes, Custom Vision reports recall.

Correct

B. F-score

Not directly reported in the Custom Vision portal.

Although it can be derived from precision and recall, it is not provided as a direct metric.

Incorrect

C. Weighted accuracy

Not reported by Custom Vision.

Incorrect

D. Precision

Yes, Custom Vision reports precision.

Correct

E. Area under the curve (AUC)

Not reported by Custom Vision.

More common in ROC curve analysis, not part of Custom Vision output.

Incorrect

Correct Answer: A. recall, D. precision

Microsoft References

Evaluate the prediction performance of your classifier in Custom Vision

Custom Vision training and evaluation