Exam AI-102 topic 4 question 25 discussion

Actual exam question from Microsoft's AI-102

Question #: 15
Topic #: 4

HOTSPOT -

You have an Azure subscription that contains an Azure AI Document Intelligence resource named DI1.

You create a PDF document named Test.pdf that contains tabular data.

You need to analyze Test.pdf by using DI1.

How should you complete the command? To answer, select the appropriate options in the answer area.

NOTE: Each correct selection is worth one point.

Show Suggested Answer

Suggested Answer:

by anto69 at July 7, 2024, 2:55 p.m.

Comments

Submit Cancel

JakeCallham

Highly Voted 9 months, 4 weeks ago

Should indeed be layout: https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept-layout?view=doc-intel-4.0.0&tabs=sample-code#tables

upvoted 5 times

...

syupwsh

Most Recent 3 months, 3 weeks ago

prebuilt-layout is CORRECT because this model is designed to analyze documents and extract structural information, such as tables, text, and other layout elements. Since the document contains tabular data, using the prebuilt-layout model will allow you to extract the tables and their contents accurately. Ocp-Apim-Subscription-Key is CORRECT because this is the header used to authenticate API calls to Azure services, including Azure AI Document Intelligence. The value for this key is the subscription key associated with your Azure Document Intelligence resource.

upvoted 2 times

...

famco

9 months, 1 week ago

The "prebuilt-layout" model extracts only the basic elements of the document, such as pages, (which consist of text words/lines and selection marks), tables, and visual text styles along with their bounding regions and spans within the text content of the input documents. The "prebuilt-document" model extracts information about key-value pairs (directed associations between page elements, such as labeled fields) **in addition** to the properties produced by the layout extraction method. In adddition to the layout model? So, what could we select. These questions are just e v i l.

upvoted 1 times

famco

9 months, 1 week ago

Chatgpt answer providing above documentation: You’re right! Based on the documentation you've provided, the "prebuilt-document" model is the more comprehensive option because it includes everything that the "prebuilt-layout" model offers (such as extracting tables and the document layout) plus additional features like extracting key-value pairs and entities. Since you’re looking to analyze a PDF with tabular data and possibly benefit from more advanced document processing, the "prebuilt-document " model would indeed be the better choice in this case. So the correct model for analyzing your PDF (Test.pdf) would be: But I select prebuilt-layout as the answer hoping the Microsoft excellence did not see the "in addition to" in the documentation or did not see the mapping https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept-model-overview?view=doc-intel-4.0.0#model-analysis-features

upvoted 1 times

8d82b67

3 weeks, 4 days ago

In latest version v4, the general document model (prebuilt-document) is deprecated. To extract key-value pairs, selection marks, text, tables, and structure from documents, use the following models: Layout model with the optional query string parameter features=keyValuePairs enabled.

upvoted 1 times

...

Ody

9 months, 3 weeks ago

Looks correct. ... each table cell is extracted with: Its content text. The size and position of its bounding box. If it's part of a header column. Indexes to indicate its row and column position in the table. https://learn.microsoft.com/en-us/training/modules/use-prebuilt-form-recognizer-models/3-use-general-document-read-layout-models

upvoted 3 times

...