You have a Microsoft Foundry agent that grounds responses from an Azure Search index that contains the following:▪ Searchable text fields for product names and product codes▪ A vector field that stores embeddings for product descriptionsYou need to ensure that users can query the index by using the following:▪ Exact product names or codes▪ Natural language descriptions of the productsWhat should you configure?
Answer(s): B
To meet your requirements, you need to configure a Hybrid Search with Semantic Ranking in Azure AI Search.This setup combines keyword matching for exact identifiers with vector search for natural language queries,delivering the most accurate grounding data to your Microsoft Foundry agent.
https://www.tredence.com/blog/searchsmart-enhancing-rag-with-azure-ai-search-service
You have an Azure AI Search indexer that ingests PDF policy manuals.Client applications must display page-level citations that have bounding polygons for both text and images.You need to add a single built-in multimodal content extraction skill to the Azure AI Search skillset. The solution must meet the following requirements:▪ Provide text and image location metadata.▪ Extract tables that span multiple pages.What should you add?
To meet all requirements for this project, you need the Azure Content Understanding skill (integrated via AzureAI Foundry / Microsoft Foundry Tools).1. Extracting Cross-Page Tables: A critical constraint is the ability to recognize and extract tables that span multiple pages as a single unit. The Azure Content Understanding skill natively supports this capability,whereas the older Document Layout skill outputs layout content as flattened text/markdown boundaries that break across pages, leading to information loss.2. Page-Level Bounding Polygons: It functions as a layout-aware, built-in multimodal content extraction skill that maps out text and image location metadata (location_metadata), satisfying your client application requirement for strict page-level citation boundaries.
https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-content-understanding
You are building an Azure AI Search indexing pipeline named Pipeline1 that ingests invoices stored in AzureBlob Storage. The invoices are stored as scanned images.You need to enable users to search invoice data across the invoice fields.Which built-in skill should you add to the skillset of Pipeline1?
Answer(s): C
You should add the Azure Machine Learning OCR skill (historically known as theMicrosoft.Skills.Vision.OcrSkill) to your skillset pipeline.Text Extraction: Scanned images contain unsearchable pixels rather than text.Data Ingestion: The OCR skill extracts the printed text and layout information from the images.Downstream Processing: It feeds raw text into subsequent skills (like Entity Recognition) or directly into your search index fields.
https://techcommunity.microsoft.com/blog/azurearchitectureblog/from-large-semi-structured-docs-to-actionable-data-reusable-pipelines-with-adi-a/4474054
DRAG DROP (Drag and Drop is not supported)You have a Microsoft Foundry project that uses Azure Content Understanding in Foundry Tools to analyze marketing videos.Video segmentation is enabled.You need to configure an analyzer to output a generated JSON field that describes the color scheme of each video segment.How should you configure the analyzer? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.Note: Each correct selection is worth one point.Select and Place:
Answer(s): A
Box 1: stringThe Type (string): While you want the output schema to contain a description of the color palette or style, AzureContent Understanding schemas map the underlying data types using fundamental types like string, number,or array. The field will output the final result in the JSON response under a key like "valueString"Box 2: generateThe Method (generate): The extract method is only used for pulling literal text exactly as it appears in content(such as speech-to-text transcripts or OCR). Because analyzing visual aesthetics and synthesizing descriptive text about a "color scheme" requires multimodal AI reasoning, you must use the generate method. This instructs the underlying model to analyze the segment and synthesize a completely new descriptive insight.
https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements
You have an invoice-processing application named App1 that uses Azure Constant Understanding in FoundryTools.You are building a new Content Understanding pipeline named Pipeline1 that must meet the following requirements:▪ Compare an invoice to its related purchase order▪ Validate the voice against static vendor contact documents▪ Return a single structured output that includes discrepancy findingsYou need to configure Pipeline1 and expose the pipeline as a single analyzer endpoint. What should you configure?
Multiple-file task: Required over a single-file task. Your pipeline needs to reconcile data across two separate active transactional documents (the invoice and the purchase order) within a single analyzer request.Pro mode is required instead of standard mode. Pro mode is specifically designed for advanced scenarios requiring multi-step reasoning, cross-file analysis, and validation against a knowledge base. Note that Pro mode currently supports classify and generate fields but does not support confidence scores for specific extracted fields.Vendor contract files as reference data: Required. Because the vendor contracts are static compliance documents, they should be uploaded and treated as the analyzer's background knowledge base (reference data) to guide the validation logic.
https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/standard-pro-modes
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.