Extracting Key-Value Pairs from Invoices with Azure AI Document Intelligence
You need to extract key-value pairs from a large set of invoices. The invoices have a consistent layout but vary in format (PDF, TIFF). Which Document Intelligence model should you use?
Quick Answer
The answer is the premade invoice model. This is the correct choice because Azure AI Document Intelligence’s premade invoice model is specifically trained to extract key-value pairs—such as invoice number, date, and total amount—from common invoice layouts, handling both PDF and TIFF formats without requiring any custom training. On the Microsoft Azure AI Engineer Associate AI-102 exam, this question tests your ability to distinguish between Document Intelligence models: the layout model extracts text and tables but not key-value pairs, the read model only extracts raw text, and custom extraction requires labeled training data, making the premade invoice model the most efficient for consistent but varied invoice formats. A common trap is confusing the layout model’s table extraction with key-value pair extraction, so remember that key-value pairs are specific to prebuilt models like invoice or receipt. Memory tip: “Invoice for pairs, layout for squares”—the premade invoice model handles the paired data, while layout handles the rectangular tables.
⚠ Common exam trap
Test-takers frequently confuse the Layout model's ability to extract tables and structure with the specific key-value pair extraction needed for invoices, overlooking that the premade invoice model is purpose-built for this exact use case.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Premade invoice model
The premade invoice model (D) is specifically designed to extract key-value pairs from invoices, including fields like invoice date, total amount, and vendor details, even when the invoices vary in format (PDF, TIFF). It leverages pre-trained deep learning models optimized for invoice layouts, making it the most efficient choice for this task without requiring custom training.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Custom extraction model
Why it's wrong here
A custom extraction model needs labelled training samples per field and layout; the scenario specifies consistent layout with no labelling effort, so training is unnecessary overhead. It is tempting because custom models handle unusual documents. The prebuilt invoice model already extracts standard invoice key-value pairs across PDF and TIFF inputs.
- ✗
Layout model
Why it's wrong here
The layout model returns text, tables and selection marks with their positions; it does not output labelled key-value pairs such as invoice number or total. It is tempting because it handles varied PDF and TIFF layouts without training. Invoice field extraction requires a prebuilt invoice model or a custom extraction model.
- ✗
Read model
Why it's wrong here
The Read model returns only text lines and words with no field or value structure, so it cannot produce key-value pairs from invoices. It is tempting because it handles PDF and TIFF input, but that OCR capability is the correct choice only when you need raw text extraction, not structured invoice fields.
- ✓
Premade invoice model
Why this is correct
The premade invoice model is trained on invoice layout and extracts key-value pairs such as vendor, dates and totals, while accepting PDF and TIFF inputs. Consistent invoice layout matches its domain, avoiding custom model training.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on AI-102
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. You need to extract key-value pairs from scanned forms as part of a knowledge mining solution. Which Azure AI service should you use?
easy- A.Azure AI Vision
- B.Azure AI Language
- C.Azure AI Search
- ✓ D.Azure AI Document Intelligence
Why D: Azure AI Document Intelligence (formerly Form Recognizer) is the correct service because it is specifically designed to extract key-value pairs, tables, and structured data from scanned forms and documents using prebuilt and custom models. This aligns directly with the requirement for knowledge mining from scanned forms.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.