AI-102 Implement generative AI solutions Practice Question
You are building a generative AI assistant with Azure OpenAI Service that must answer questions using a large corpus of internal product manuals. The manuals are updated weekly, and the assistant must reflect changes without retraining the model. You need to implement a retrieval-augmented generation (RAG) pattern. What should you use to index and retrieve relevant manual content?
⚠ Common exam trap
The trap here is assuming that fine-tuning or passing all documents in the prompt can substitute for a proper retrieval index.
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
✓
Create an Azure AI Search index with vector embeddings of the manual chunks and use it as a data source in the Azure OpenAI 'on your data' configuration.
The correct approach is to use Azure AI Search with vector embeddings as a data source for Azure OpenAI 'on your data'. This enables retrieval-augmented generation, where relevant manual chunks are retrieved and supplied to the model, ensuring responses reflect weekly updates without retraining. It is the supported, scalable method for grounding generative AI in dynamic internal documents.
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 Cosmos DB with the built-in vector search and connect it directly to the model via a function calling tool.
Why it's wrong here
While Cosmos DB supports vector search, it is not a native data source for Azure OpenAI 'on your data'. Implementing retrieval via function calling would require custom orchestration and lacks built-in integration. It adds complexity and does not meet the straightforward RAG requirement as effectively as Azure AI Search.
- ✓
Create an Azure AI Search index with vector embeddings of the manual chunks and use it as a data source in the Azure OpenAI 'on your data' configuration.
Why this is correct
This correctly implements RAG by using vector search to retrieve semantically relevant manual chunks, which are then passed to the model. Azure AI Search supports vector indexes and integrates with Azure OpenAI 'on your data', enabling weekly updates without retraining. It is the standard, supported approach for grounding generative responses in dynamic internal content.
- ✗
Store the manuals as plain text in Azure Blob Storage and pass the entire corpus in each prompt.
Why it's wrong here
Passing the entire corpus in each prompt exceeds token limits and is impractical for large manuals. It also increases cost and latency and may truncate content. This approach does not scale and fails to retrieve only relevant sections. It is not a viable RAG implementation for a large, dynamic corpus.
- ✗
Fine-tune the base model on the manuals each week using Azure OpenAI fine-tuning.
Why it's wrong here
Fine-tuning embeds knowledge into model weights and does not provide dynamic retrieval of updated manuals. Weekly retraining is costly, slow, and not designed for frequent content changes. It also risks overfitting and cannot cite sources. This approach fails the requirement to reflect weekly updates without retraining and is not a RAG pattern.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. 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.