AI-200 Data Management Services And Vector Search Practice Question
When configuring an Azure Cosmos DB for NoSQL container to store embeddings, what data type must the vector property be stored as within the JSON document?
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
✓
An array of 32-bit floating-point numbers
In Azure Cosmos DB for NoSQL, vector embeddings must be stored as an array of 32-bit floating-point numbers (float32).
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
A base64 encoded string
Why it's wrong here
Vectors cannot be stored as base64 strings if you want to use the vector distance built-in functions.
- ✗
An array of integers
Why it's wrong here
Embeddings generated by models like OpenAI are floating-point values, not integers.
- ✓
An array of 32-bit floating-point numbers
Why this is correct
Vectors in Cosmos DB must be represented as JSON arrays of floats (float32).
- ✗
A binary blob
Why it's wrong here
Binary blobs are not queryable using vector distance functions like VectorDistance() in SQL queries.
About these practice questions
One of 507 original AI-200 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 August 2026 · checked against the official Microsoft exam blueprint
This AI-200 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-200 exam.