AI-102 Implement generative AI solutions Practice Question
You are building a generative AI assistant that must summarize long technical manuals stored in Azure Blob Storage. The manuals are often 300 pages, and the model must produce a concise summary with references to page numbers. Which approach should you use?
⚠ Common exam trap
The trap here is assuming that a large-context model can ingest an entire long manual in one prompt, ignoring token limits and the need for verifiable page 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
✓
Use Azure AI Search to index the manuals with page metadata, then use a retrieval-augmented generation (RAG) pattern with Azure OpenAI to generate summaries and citations.
Long documents exceed model context windows, so retrieval-augmented generation is needed. Azure AI Search indexes content with metadata, allowing Azure OpenAI to generate grounded summaries and cite page numbers. This combination handles length, improves accuracy, and provides traceability, which is essential for technical manuals.
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 Document Intelligence to extract text, then send each page as a separate request to Azure OpenAI and concatenate the summaries.
Why it's wrong here
Summarizing each page independently loses cross-page context and produces disjointed output. Concatenating many page-level summaries does not yield a coherent overall summary, and tracking page references would require additional custom logic. This approach also multiplies API calls and cost without solving the context-window problem.
- ✗
Use Azure OpenAI fine-tuning to train a custom model on the manuals, then ask the model to summarize any manual.
Why it's wrong here
Fine-tuning teaches style and patterns but does not reliably store or retrieve factual content from long documents. The model would not have access to the full manual at inference time, and page-number citations would be hallucinated. Fine-tuning is not a substitute for retrieval when grounding in specific source documents is required.
- ✗
Use Azure OpenAI GPT-4o with a single prompt containing the entire manual text.
Why it's wrong here
Sending an entire 300-page manual in a single prompt will exceed the model's context window and likely result in truncation or failure. Even with large-context models, the token limit is finite, and cost and latency would be prohibitive. This approach also makes it difficult to map generated text back to specific page numbers reliably.
- ✓
Use Azure AI Search to index the manuals with page metadata, then use a retrieval-augmented generation (RAG) pattern with Azure OpenAI to generate summaries and citations.
Why this is correct
Indexing the manuals in Azure AI Search with page-level metadata enables retrieval of relevant chunks and supports citation of page numbers. The RAG pattern lets Azure OpenAI generate a summary grounded in retrieved content, avoiding context-window limits. This is the recommended approach for long documents requiring references.
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
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.