AI-102 Practice Question: Implement natural language processing solutions
Your company uses a custom question answering knowledge base in Azure AI Language to answer employee questions about HR policies. You need to update the knowledge base with a new set of FAQ documents that contain tables and images. What is the best way to ingest the new content?
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 Azure AI Language REST API to add the new QnA pairs programmatically.
The best way because the Azure AI Language REST API allows you to add a source (e.g., a document) to the custom question answering knowledge base, which can include tables and images. This is more efficient than manually adding QnA pairs. Option D is incorrect because Microsoft Foundry Copilot Studio is a separate tool for building copilots and does not directly update Azure AI Language custom question answering knowledge bases. Option A is incorrect because Azure AI Search is used for indexing and searching, not for direct ingestion into the knowledge base. Option B is incorrect because manually adding QnA pairs is time-consuming and does not automatically extract structured content like tables and images from 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 AI Search to index the documents and then import the index into the knowledge base.
Why it's wrong here
Incorrect. Azure AI Search indexes documents but does not directly ingest them into a custom question answering knowledge base. It can be used as a data source for a different service, not for updating the knowledge base.
- ✗
Manually add the new QnA pairs using the Language Studio portal.
Why it's wrong here
Less optimal. Manually adding QnA pairs using the Language Studio portal is possible but not efficient for documents with tables and images. The portal's 'Add source' feature, accessible via the REST API or portal UI, is a better approach.
- ✓
Use the Azure AI Language REST API to add the new QnA pairs programmatically.
Why this is correct
Correct. The Azure AI Language REST API can be used to add a source (e.g., a document containing tables and images) to the custom question answering knowledge base. This method handles structured content effectively and is the recommended approach for bulk updates.
- ✗
Use Microsoft Foundry Copilot Studio to automatically ingest the documents into the knowledge base.
Why it's wrong here
Incorrect. Microsoft Foundry Copilot Studio is used to create and manage copilots, not to directly ingest documents into an Azure AI Language custom question answering knowledge base. It can be linked to a knowledge base but does not update it with new content.
Go deeper
Related to this question
About these practice questions
One of 945 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 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.