You have a Microsoft Foundry project that contains an agent.The agent uses Azure AI Search as the retriever.You plan to ingest PDF into an Azure AI Search index to ensure that the agent can ground responses in texts in both documents and embedded images.Users require citations that link to the source files.You need to ensure that during indexing, the images are extracted into a structure that can be used as input for the built-in optical character recognition (OCR) skill.Which indexing approach should you use?
Answer(s): A
The best configuration step an indexer to extract image data into a normalized_images collection.Cracking Foundation: In Azure AI Search, document cracking automatically separates textual data from visual content. To make embedded images available to image-processing skills like OCR, the indexer must be explicitly configured with an imageAction configuration property (such as generateNormalizedImages or generateNormalizedImagePerPage).Input Structure for OCR: This indexer step extracts embedded images from the PDF and restructures them into an internal normalized_images array (accessed via the path /document/normalized_images/*). The built-inOCR skill strictly requires this normalized image collection format as its input payload.Incorrect:[Not C]Content Field Limitations: The /document/content field generated during document cracking holds only the raw text extracted from the file. It does not contain the binary data or structural properties of embedded images.Targeting Errors: Pointing an OCR skill directly at the raw text content field would fail to analyze the actual images, leaving the agent unable to ground answers in visual elements like diagrams or embedded infographics.
https://docs.azure.cn/en-us/search/tutorial-skillset
You have a Microsoft Foundry project that contains an agent.The knowledge source for the agent is a set of scanned PDF troubleshooting guides stored in Azure BlobStorage. The guide pages contain two-column layouts and tables.You use Azure Content Understanding in Foundry Tools to process the PDFs.You plan to ingest the processed content into an index for Retrieval Augmented Generation (RAG) and store extracted fields for downstream automation.Stakeholders must be able to verify where each extracted field value came from in the original PDF and route low-reliability extractions for manual review.You need to ensure that the Content Understanding document analyzer output includes a per-field confidence score and source grounding to locations within the source document.What should you do?
Answer(s): C
To fulfill all your requirements using Azure Content Understanding in Foundry Tools, you need to configure a custom document analyzer with specific flags, set up an index ingestion pipeline, and build a downstream human-in-the-loop validation rule.*-> 1. Enable Confidence Scores and Source GroundingTo force the analyzer to provide per-field confidence metrics and precise layout/bounding box coordinates for verification, you must opt-in to the estimate FieldSourceAndConfidence parameter within your configuration.Option A (Global): Set estimateFieldSourceAndConfidence = true in the main analyzer config to evaluate all fields.Option B (Field-Level): Set estimateSourceAndConfidence = true under individual field schemas.This ensures the generated JSON response populates the bounding box coordinates, page numbers, and a confidence score 0.0 to 1.0 for every extracted entity.2. Configure Document Extraction for Two-Column & Table Layouts3. Build the Ingestion Pipeline (RAG vs. Automation Dual-Path)4. Implement Threshold Routing and Source Verification
https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/overview
You are building a speech processing solution in Microsoft Foundry for a customer support platform.The platform will transcribe live phone calls, so that supervisors at your company can view call transcripts and detect issues while the calls are in progress. The call audio will arrive as a continuous stream from the telephony system.You need to ensure that the call transcripts appear within only a few seconds of the audio stream.What should you do?
Answer(s): D
You should use Real-Time Speech-to-Text (Streaming STT) for this project.Why Real-Time STT is RequiredLow Latency: It transcribes audio within seconds.Continuous Input: It processes live, ongoing audio streams.Live Monitoring: Supervisors need immediate text to flag issues.
https://learn.microsoft.com/en-us/azure/ai-services/speech-service/get-started-speech-to-text
You are creating an agent workflow in a Microsoft Foundry project to support natural voice interactions.The agent must receive continuous audio input, convert the input into text for reasoning, and then return spoken responses to a user. The workflow must meet the following requirements:▪ Support turn-taking dynamics, where the agent begins to generate the speech output before the user finishes speaking.▪ Operate with low latency to maintain conversational experience.You need to enable both speech to text and text to speech in a real-time agent interaction.What should you do?
Answer(s): B
To achieve low latency and natural turn-taking dynamics in this specific Microsoft Foundry workflow, the best approach is to use real-time speech-to-text for incoming audio and text-to-speech for agent responses.Low Latency: Streaming, real-time Speech-to-Text (STT) and Text-to-Speech (TTS) pipelines process audio chunks concurrently. This allows the system to analyze text and prepare responses while the user is still speaking.Turn-Taking Support: Real-time STT systems utilize voice activity detection (VAD) and continuous streaming.This enables the agent to instantly detect pauses, interruptions, or trailing speech to naturally shift conversational turns.Direct Reasoning Compatibility: Because your workflow requires converting input into text for reasoning (such as prompting a Large Language Model), a highly optimized text-based pipeline fits seamlessly without extra translation layers.
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing
You have an application named App1 that uses Azure Speech in Foundry Tools to transcribe live calls.Transcript segments often contain both English and Spanish. App1 sends each segment to Azure Translator inFoundry Tools to translate to another language.Sometimes, mixed-language segments result in incomplete or incorrect translations.You need to reduce translation errors. The solution must ensure that the entire transcript is translated successfully.What should you do before sending the segments to Translator?
To fix incomplete or incorrect translations from mixed-language transcripts, you must identify and isolate the languages at the sentence or phrase level before sending the text to Azure Translator.Azure Translator performs best when a single request contains only one source language. When it receives a mixed-language segment under a single source language code, it often fails to parse the secondary language correctly.Here is the step-by-step pipeline you should implement inside your application before hitting the Translator API.1. Split Segments into SentencesLive call transcript segments can contain multiple sentences. Do not send the raw, multi-sentence segment directly to the translator if it contains mixed languages.Break the segment into individual sentences.Use regex punctuation rules or a lightweight sentence-splitting library.2. Run Language Detection Per SentenceAzure Translator has a built-in Detect API, but for mixed-language live calls, executing a dedicated detection step per sentence provides better control.
https://medium.com/neural-engineer/azure-ai-speech-to-text-real-time-transcription-58bfd5fd1a28
Post your Comments and Discuss Microsoft AI-103 exam prep with other Community members:
Our website is free, but we have to fight against AI bots and content theft. We're sorry for the inconvenience caused by these security measures. You can access the rest of the AI-103 content, but please register or login to continue.