AI-900 Practice Question: Describe features of generative AI workloads on Azure
What is a vector database and why is it important for generative AI applications?
⚠ Common exam trap
It's easy for candidates to confuse a vector database with a traditional database or with model storage, because the term 'vector' is overloaded—it can refer to mathematical vectors (embeddings) in AI, but also to vector graphics or data structures in other contexts.
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
✓
A database optimized for storing and searching high-dimensional embeddings for semantic similarity search
A vector database is specifically designed to store and index high-dimensional embeddings—numerical representations of data such as text, images, or audio—and to perform efficient similarity searches using distance metrics like cosine similarity or Euclidean distance. In generative AI applications, vector databases enable retrieval-augmented generation (RAG), where relevant context is retrieved from a knowledge base to ground the model's output, reducing hallucinations and improving accuracy.
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 database that stores traditional relational tables for AI training data
Why it's wrong here
This option confuses the role of a vector database with a traditional relational database management system (RDBMS), which stores data in structured tables with rows and columns and enforces strict schemas and ACID transactions. A vector database is specifically designed to handle unstructured, high-dimensional embeddings that do not fit into tabular formats, and it uses specialized indexing and query algorithms such as HNSW or IVF for fast similarity search. While a relational database can technically store vectors as blobs or arrays, it lacks the optimized nearest-neighbor retrieval mechanisms that make vector databases indispensable for semantic search.
- ✓
A database optimized for storing and searching high-dimensional embeddings for semantic similarity search
Why this is correct
A vector database is purpose-built to index and query high-dimensional vectors, also known as embeddings, using similarity metrics like cosine similarity or Euclidean distance. It leverages techniques such as approximate nearest neighbor (ANN) search to efficiently retrieve the closest vectors to a given query, which is the foundation for semantic search, retrieval-augmented generation (RAG), and recommendation engines. Unlike traditional databases, it does not optimize for exact matches or relational joins, but rather for finding semantic neighbors in a continuous vector space.
- ✗
A database that stores the weights of trained neural networks
Why it's wrong here
This is incorrect because trained neural network weights are persisted as serialized model files (e.g., .h5, .pt, or .bin) and represent the learned parameters of a model, not the content embeddings used for retrieval. While embeddings are also vectors, they are derived from data objects like text, images, or audio, whereas the weights themselves are never used as queryable entities in a vector database. A vector database may store the embeddings produced by a model, but it does not manage or store the model's internal parameters.
- ✗
A database using vector graphics for visualizing AI models
Why it's wrong here
This is a semantic mix-up of the term 'vector.' In computer graphics, a vector graphic is a geometric representation using paths and shapes (e.g., SVG or EPS files), which is entirely unrelated to the high-dimensional mathematical vectors used in AI embeddings. Vector databases deal with numerical arrays, often with hundreds or thousands of dimensions, that encode the meaning of data for similarity search—they do not process or visualize graphical images. Therefore, this option describes a rendering technology, not a storage and retrieval system for embeddings.
Go deeper
Related to this question
Learn chapter
What is Generative AI?
Key term
RAG
Retrieval-Augmented Generation (RAG) is a technique that combines information retrieval with text generation to produce more accurate and contextually relevant answers from large language models.
Key term
Generative AI
Generative AI is a type of artificial intelligence that creates new content—like text, images, or code—by learning patterns from existing data.
About these practice questions
This AI-900 question is part of Courseiva's 985-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 →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 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-900 exam.