Courseiva
Data Management Services And Vector SearchhardMultiple ChoiceObjective-mapped

AI-200 Data Management Services And Vector Search Practice Question

You are designing a multi-tenant AI application using Azure Cosmos DB for NoSQL. Each tenant has their own set of embeddings, and you need to filter vector search results strictly by tenantId while maintaining high query performance. How should you structure your vector index definition?

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

Include tenantId in the container's standard indexing policy with a range index, and filter using a WHERE clause alongside ORDER BY VectorDistance()

When configuring vector embeddings in Azure Cosmos DB for NoSQL, you must specify the dataType, dimensions, distanceFunction, and similarity metric. To filter efficiently, you combine VectorDistance() with a traditional WHERE clause on tenantId, ensuring the property is indexed.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Store tenantId inside the vector array as the first element

    Why it's wrong here

    Vector arrays must contain strictly numeric floating-point values representing dimensions.

  • Use spatial indexes on tenantId

    Why it's wrong here

    Spatial indexes are for geographic data, not tenant identifiers.

  • Create a separate container for every tenant automatically

    Why it's wrong here

    Creating a container per tenant is an anti-pattern for scale when multi-tenancy can be handled via logical partitioning or indexing.

  • Include tenantId in the container's standard indexing policy with a range index, and filter using a WHERE clause alongside ORDER BY VectorDistance()

    Why this is correct

    Combining a range index on tenantId for filtering with VectorDistance in the ORDER BY clause ensures tenant isolation and performance.

About these practice questions

This AI-200 question is part of Courseiva's 507-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

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.