- A
Use Azure AI Vision OCR to extract text, split by page, and use Azure AI Search keyword search
Why wrong: Splitting by page loses context and does not support vector search.
- B
Use Azure AI Document Intelligence prebuilt-read model, chunk by character count, and use Azure AI Search with semantic ranking
Why wrong: Character-based chunking may break tables and footnotes; semantic ranking is not vector search.
- C
Use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search
Preserves structure and enables RAG with vector search.
- D
Use Azure AI Language to extract key phrases, create a non-vector index, and use simple search
Why wrong: Does not support semantic retrieval or RAG effectively.
Quick Answer
The correct approach is to use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search. This method preserves the semantic structure of legal documents, ensuring complex tables and footnotes remain intact within meaningful chunks rather than being broken across arbitrary page boundaries. On the Microsoft Azure AI Engineer Associate AI-102 exam, this scenario tests your understanding of designing a RAG ingestion pipeline with Document Intelligence, specifically how to handle dense, structured PDFs for grounded answers and follow-up questions. A common trap is assuming page-level splitting is sufficient, but that destroys context for tables and footnotes, while keyword-only search lacks the semantic understanding needed for legal queries. Remember the mnemonic “Extract, Chunk, Embed, Index” to recall the correct pipeline order: Document Intelligence for extraction, heading/paragraph chunking, Azure OpenAI for embeddings, and Azure AI Search with vector search for retrieval.
AI-102 Practice Question: Implement knowledge mining and information extraction solutions
This AI-102 practice question tests your understanding of implement knowledge mining and information extraction solutions. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
You are a solution architect at a legal firm. The firm wants to build a copilot using Microsoft Foundry that answers questions about case law documents stored in Azure Blob Storage. The copilot should use the Retrieval Augmented Generation (RAG) pattern with Azure AI Search as the vector store. The documents are in PDF format and include complex tables and footnotes. The solution must ensure that the answers are grounded in the documents and that the copilot can handle follow-up questions. You need to design the ingestion pipeline. Which approach should you take?
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
Use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search
Option A is correct. Using Azure AI Document Intelligence to chunk documents into meaningful sections preserves context, and generating embeddings with Azure OpenAI allows vector search for RAG. Option B is incorrect because splitting by page may break tables and footnotes. Option C is incorrect because keyword search alone does not support semantic understanding. Option D is incorrect because Azure AI Language does not handle PDF extraction or vector generation.
Key principle: NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use Azure AI Vision OCR to extract text, split by page, and use Azure AI Search keyword search
Why it's wrong here
Splitting by page loses context and does not support vector search.
- ✗
Use Azure AI Document Intelligence prebuilt-read model, chunk by character count, and use Azure AI Search with semantic ranking
Why it's wrong here
Character-based chunking may break tables and footnotes; semantic ranking is not vector search.
- ✓
Use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search
Why this is correct
Preserves structure and enables RAG with vector search.
Related concept
Static NAT maps one inside address to one outside address.
- ✗
Use Azure AI Language to extract key phrases, create a non-vector index, and use simple search
Why it's wrong here
Does not support semantic retrieval or RAG effectively.
Common exam traps
Common exam trap: NAT rules depend on direction and matching traffic
NAT is not only about the public address. The inside/outside interface roles and the ACL or rule that matches traffic are just as important.
Detailed technical explanation
How to think about this question
NAT questions usually test address translation, overload/PAT behaviour, static mappings and whether the right traffic is being translated. Read the interface direction and address terms carefully.
KKey Concepts to Remember
- Static NAT maps one inside address to one outside address.
- PAT allows many inside hosts to share one public address using ports.
- Inside local and inside global describe the private and translated addresses.
- NAT ACLs identify traffic for translation, not always security filtering.
TExam Day Tips
- Identify inside and outside interfaces first.
- Check whether the scenario needs static NAT, dynamic NAT or PAT.
- Do not confuse NAT matching ACLs with normal packet-filtering intent.
Key takeaway
NAT direction and interface roles matter as much as the IP address mapping. Inside/outside designation controls which traffic is translated.
Real-world example
How this comes up in practice
A media company stores terabytes of video archives that are accessed once a year for audit purposes. Moving these objects to a cold storage tier (Azure Archive, S3 Glacier, or Google Nearline) costs a fraction of hot storage. Questions like this test whether you understand storage tiers, access frequency tradeoffs, and retrieval latency requirements.
What to study next
Got this wrong? Here's your next step.
Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related AI-102 NAT questions on configuration and troubleshooting.
- →
Implement knowledge mining and information extraction solutions — study guide chapter
Learn the concepts, then practise the questions
- →
Implement knowledge mining and information extraction solutions practice questions
Targeted practice on this topic area only
- →
All AI-102 questions
988 questions across all exam domains
- →
Microsoft Azure AI Engineer Associate AI-102 study guide
Full concept coverage aligned to exam objectives
- →
AI-102 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI-102 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Implement an agentic solution practice questions
Practise AI-102 questions linked to Implement an agentic solution.
Implement computer vision solutions practice questions
Practise AI-102 questions linked to Implement computer vision solutions.
Implement knowledge mining and information extraction solutions practice questions
Practise AI-102 questions linked to Implement knowledge mining and information extraction solutions.
Implement image and video processing solutions practice questions
Practise AI-102 questions linked to Implement image and video processing solutions.
Implement natural language processing solutions practice questions
Practise AI-102 questions linked to Implement natural language processing solutions.
Implement generative AI solutions practice questions
Practise AI-102 questions linked to Implement generative AI solutions.
Implement agentic AI solutions practice questions
Practise AI-102 questions linked to Implement agentic AI solutions.
Implement knowledge mining and document intelligence solutions practice questions
Practise AI-102 questions linked to Implement knowledge mining and document intelligence solutions.
Plan and manage an Azure AI solution practice questions
Practise AI-102 questions linked to Plan and manage an Azure AI solution.
Implement content moderation solutions practice questions
Practise AI-102 questions linked to Implement content moderation solutions.
AI-102 fundamentals practice questions
Practise AI-102 questions linked to AI-102 fundamentals.
AI-102 scenario practice questions
Practise AI-102 questions linked to AI-102 scenario.
Practice this exam
Start a free AI-102 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AI-102 question test?
Implement knowledge mining and information extraction solutions — This question tests Implement knowledge mining and information extraction solutions — Static NAT maps one inside address to one outside address..
What is the correct answer to this question?
The correct answer is: Use Azure AI Document Intelligence to extract content, then chunk by headings and paragraphs, generate embeddings using Azure OpenAI, and index in Azure AI Search with vector search — Option A is correct. Using Azure AI Document Intelligence to chunk documents into meaningful sections preserves context, and generating embeddings with Azure OpenAI allows vector search for RAG. Option B is incorrect because splitting by page may break tables and footnotes. Option C is incorrect because keyword search alone does not support semantic understanding. Option D is incorrect because Azure AI Language does not handle PDF extraction or vector generation.
What should I do if I get this AI-102 question wrong?
Review the four NAT address types (inside local, inside global, outside local, outside global), PAT port overload, and static vs dynamic NAT use cases. Then practise related AI-102 NAT questions on configuration and troubleshooting.
What is the key concept behind this question?
Static NAT maps one inside address to one outside address.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 20, 2026
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.