AI-103 Exam Dumps - Developing AI Apps and Agents on Azure

The correct answer is C. Split the mixed-language segments into single-language segments and translate each segment separately . Azure Translator has a known limitation for text that contains mixed-language input within the same sentence or segment. Microsoft’s Translator known-issues guidance states that the Text translation API does not support translating sentences that contain mixed-language text and that translations can be incorrect or incomplete when a single sentence includes multiple languages. The documented workaround is to specify the intended source language, remove the mixed-language sentence, or split the text into single-language segments.

In this scenario, specifying English for all segments would fail when Spanish content is present. Automatic language detection can detect a dominant language, but it does not reliably solve a segment that contains both English and Spanish. Document translation is also not the right fix because the issue is mixed-language content inside transcript segments, and Microsoft notes similar incomplete results for mixed-source-language documents. Splitting the transcript into language-homogeneous segments ensures each translation request has a clear source language and lets the entire transcript be translated reliably. Reference topics: Azure Translator in Foundry Tools, text translation, language detection, mixed-language input, and transcript preprocessing.

Pipeline1: Single-file task in standard mode

Pipeline2: Multi-file task in pro mode

Pipeline1 should use a single-file task in standard mode because the workload is high-volume processing of standalone PDF invoices. Azure Content Understanding standard mode is intended for individual files that require straightforward structured extraction, and Microsoft describes it as minimizing cost and latency for broad, data-centric processing scenarios. This makes it the best fit for cost-effective invoice extraction where each PDF can be processed independently.

Pipeline2 should use a multi-file task in pro mode because the requirement includes cross-document validation, multi-step reasoning, and reference data. Microsoft guidance states that pro mode is designed for advanced scenarios requiring multi-step reasoning and cross-file analysis, including processing multiple input files in a single request, validating or enriching data across documents, and using reference data to guide extraction and validation.

Single-file pro mode would add unnecessary capability for Pipeline1 and would not optimize for cost-effective high-volume standalone processing. Multi-file standard mode does not meet the pro-mode requirement for reference-data-based reasoning. Reference topics: Azure Content Understanding standard mode, pro mode, single-file tasks, multi-file tasks, field extraction, and procurement document validation.