AI-102 Implement generative AI solutions Practice Question
You are implementing a generative AI chat solution on Azure OpenAI Service. The solution must ground its answers in a large internal knowledge base and return inline citations that link back to the exact source chunks. You want to minimize custom code and use a managed retrieval pipeline. Which Azure OpenAI feature should you configure?
⚠ Common exam trap
The trap here is assuming that a prompt or fine-tuned model can reliably cite internal documents without a 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
✓
Use the On Your Data feature with an Azure AI Search index and set the citation output to include document references.
Grounding answers in private data with verifiable citations requires a retrieval pipeline. Azure OpenAI On Your Data with an Azure AI Search index provides managed ingestion, chunking, retrieval, and citation output, so answers link to the actual source chunks. Prompt instructions or model tuning alone cannot retrieve documents or guarantee accurate references.
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 the On Your Data feature with an Azure AI Search index and set the citation output to include document references.
Why this is correct
On Your Data with Azure AI Search is the managed retrieval-augmented generation feature of Azure OpenAI. It chunks, indexes, and retrieves content from your data source and returns citations that reference the source documents, with minimal custom code. Setting citations on ensures answers link back to the retrieved chunks.
- ✗
Deploy a fine-tuned model trained on the internal knowledge base and use it for chat completions.
Why it's wrong here
Fine-tuning adapts model behavior and style but does not reliably store or retrieve large document collections, and it does not generate verifiable inline citations to source chunks. It also requires retraining as data changes, making it unsuitable for a large, frequently updated knowledge base.
- ✗
Set the temperature parameter to a low value and enable content filtering on the deployment.
Why it's wrong here
Temperature controls randomness and content filtering blocks harmful content, but neither retrieves internal documents nor produces citations. This option affects generation style and safety, not grounding or source attribution, so it cannot satisfy the requirement to cite exact source chunks from the knowledge base.
- ✗
Create a system message that instructs the model to answer only from the knowledge base and to include source names.
Why it's wrong here
A system message shapes tone and instructions but does not give the model access to the knowledge base, so it cannot cite real source chunks. Without a retrieval mechanism the model may hallucinate source names, which fails the requirement for verifiable inline citations tied to actual content.
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.