AI-102 Implement generative AI solutions Practice Question
You need to provide a generative AI solution that can answer questions based on a large set of PDF documents stored in Azure Blob Storage. The solution must support natural language queries and return citations from the documents. Which Azure service combination should you use?
⚠ Common exam trap
Candidates often confuse Azure AI Document Intelligence (which extracts text) with the full search-and-generate pipeline, overlooking that a search index (Cognitive Search) and a generative model (Azure OpenAI) are both required to answer natural language queries with citations.
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
✓
Azure Cognitive Search and Azure OpenAI Service with 'on your data'
Azure Cognitive Search provides the indexing and retrieval capabilities for the PDF content, while Azure OpenAI Service with the 'on your data' feature enables natural language querying and generates answers grounded in the indexed documents, including citations. This combination directly supports the requirement to query a large set of PDFs in Azure Blob Storage and return citations.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Azure Machine Learning and Azure Kubernetes Service
Why it's wrong here
Azure Machine Learning and AKS provide training and container orchestration, not document indexing, semantic retrieval or citation-bearing generation. It is tempting because custom models can be built and served on AKS, which suits bespoke ML pipelines where you own the retrieval and grounding logic entirely.
- ✓
Azure Cognitive Search and Azure OpenAI Service with 'on your data'
Why this is correct
Azure Cognitive Search indexes the Blob-stored PDFs and retrieves relevant passages, while Azure OpenAI Service with 'on your data' grounds responses in those results and returns citations. This pairing satisfies both the natural-language query and citation requirements.
- ✗
Azure AI Bot Service and Azure Functions
Why it's wrong here
Bot Service and Functions provide conversational orchestration and compute but no document indexing or retrieval, so citations cannot be grounded in the PDFs. This pairing suits deploying a pre-built chat interface, not retrieval-augmented generation over stored documents.
- ✗
Azure AI Document Intelligence and Azure AI Translator
Why it's wrong here
Document Intelligence extracts text and layout but performs no retrieval or grounded generation, and Translator only converts languages, so no natural-language answering with citations is produced. It is tempting because Document Intelligence parses PDFs, which suits form extraction or OCR pipelines rather than retrieval-augmented generation over a document corpus.
Quick reference
Azure Blob Storage Tier Comparison
| Tier | Storage Cost | Retrieval Cost | Latency | Use Case |
|---|---|---|---|---|
| Hot | Highest | Lowest | Immediate | Active data, frequent reads |
| Cool | Lower | Higher | Immediate | Data accessed < once / month |
| Cold | Lower still | Higher | Immediate | Data accessed < once / quarter |
| Archive | Lowest | Highest + rehydration delay | Hours | Long-term compliance retention |
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 →
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.