Microsoft Updated AI-102 Exam Questions and Answers by montgomery

Detect the incoming language:

Service: Speech to Text

Reasoning: The Speech to Text service can transcribe spoken language into text and includes language identification capabilities, allowing the system to detect whether the caller is speaking French or English.

Respond in the callers ' own language:

Service: Text to Speech

Reasoning: The Text to Speech service can convert text responses into spoken language in the detected language (French or English), enabling the system to respond to callers in their own language.

Ordered Mapping:

Detect the incoming language: Speech to Text

Respond in the callers ' own language: Text to Speech

Box 1: Text Analytics

The Language Detection feature of the Azure Text Analytics REST API evaluates text input for each document and returns language identifiers with a score that indicates the strength of the analysis.

Box 2: Translator

Translator is a cloud-based neural machine translation service that is part of the Azure Cognitive Services family of REST APIs. Translator can be used with any operating system and powers many Microsoft products and services used by thousands of businesses worldwide to perform language translation and other language-related operations.

You have press releases stored as PDF files. The task involves two parts:

Extract text

The correct service for OCR and text extraction from images and PDFs is Azure Computer Vision (specifically, the OCR and Read API).

While Form Recognizer can also extract text, it is primarily used for structured documents like invoices, receipts, or forms. Since the documents here are press releases (unstructured text), the best service is Computer Vision.

Perform sentiment analysis

Sentiment analysis falls under natural language processing (NLP).

The correct service is Azure AI Language (Text Analytics API).

It provides sentiment analysis, opinion mining, key phrase extraction, entity recognition, and more.

Why not other options?

Azure Cognitive Search is used for search indexing, not OCR or sentiment.

Form Recognizer specializes in structured document extraction, not sentiment analysis.

Computer Vision cannot perform sentiment analysis (only visual/text extraction).

Correct Answer:

Extract text → Computer Vision

Perform sentiment analysis → Language

Microsoft References

Computer Vision Read OCR

Language service – Sentiment Analysis

Azure AI Content Understanding supports common document and image formats including .pdf, .docx, .jpg, and .png. .webp isn’t listed among supported types. Therefore, you can analyze File1.pdf, File2.jpg, File3.docx, and File5.png, but not File4.webp. Microsoft Learn

Microsoft References:

Content Understanding: service limits and supported file types. Microsoft Learn

=========================

To prevent an Azure OpenAI model (such as GPT-4 or GPT-3.5) from returning outputs that include hate speech, you must configure Azure AI Content Safety content filters on the model deployment. Content filters evaluate prompts and/or completions for categories like Hate/Unfairness, Harassment/Violence, Sexual, and Self-harm and can block or redact responses when they exceed your selected threshold. Applying a content filter to Model1 ensures that App1 will not return hate speech, satisfying the requirement.

Why the other options are incorrect:

A. Frequency penalty – discourages token/repetition in output; it does not moderate harmful content.

B. Abuse monitoring – provides telemetry/policy monitoring for potential misuse; it is not a response-time content filter and does not block specific hate content.

D. Temperature – adjusts randomness/creativity; it does not enforce safety.

Microsoft Azure AI References

Azure OpenAI Service – Safety system & content filtering (configure per deployment; categories include Hate).

Azure AI Content Safety – Overview and moderation categories.

Azure OpenAI Studio – Attach Content Safety filters to deployments (prompt/completion filtering).