AI-900 Practice Question: Describe features of generative AI workloads on Azure
What are 'embeddings' in Azure OpenAI and what are they used for?
⚠ Common exam trap
The trap here is that the term 'embeddings' sounds like 'embedded systems' or 'embed tags,' leading candidates to confuse a core AI concept with unrelated hardware or web development terms.
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
✓
Numerical vector representations of text that capture semantic meaning for search and similarity tasks
Embeddings in Azure OpenAI are numerical vector representations of text that capture semantic meaning, enabling tasks like semantic search, clustering, and similarity comparisons. They convert words, sentences, or documents into high-dimensional vectors so that similar meanings are represented by vectors close to each other in the vector space. This is correct because embeddings are fundamental to modern AI search and recommendation systems, not related to hardware or web embedding tags.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Embedded systems software that runs AI models on IoT devices
Why it's wrong here
This confuses the term 'embedded' with 'embedding.' Embedded systems are specialized hardware/software combinations that run AI inference on IoT or edge devices, handling latency, power, and resource constraints. In contrast, an AI embedding is not executable software; it is a mathematical—typically dense vector—representation of a piece of content, such as text, produced by a neural encoder and used for semantic comparison.
- ✓
Numerical vector representations of text that capture semantic meaning for search and similarity tasks
Why this is correct
Correct. Embeddings are generated by neural network encoders that map text into a high-dimensional continuous vector space, where semantically related phrases cluster together. These numerical vectors allow systems to compute similarity (commonly via cosine distance), which enables search, clustering, recommendations, and retrieval-augmented generation by comparing meaning rather than literal keyword matches.
- ✗
HTML embed tags for displaying AI model outputs in web applications
Why it's wrong here
This mistakenly imports web development, where HTML <embed> or iframe tags insert external media or entire documents into web pages. Those tags control browser rendering and have nothing to do with how AI systems encode meaning. An AI embedding is an array of floating-point numbers learned by a model, not a markup element, and it carries no presentation or display instructions.
- ✗
Compressed versions of large language models that use fewer parameters
Why it's wrong here
This describes model compression techniques such as quantization (reducing numerical precision) or distillation (training a smaller student model). These methods shrink the parameter count and memory footprint of a trained neural network. Embeddings are different: they are dense vectors—often learned outputs of an encoder—that numerically represent content meaning, and they are not standalone models capable of inference.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Semantic search
Semantic search is a search method that understands the intent and contextual meaning of a user's query, rather than just matching exact keywords.
Key term
Embedding
Embedding is the process of converting high-dimensional data like text or images into a lower-dimensional numerical vector that captures semantic meaning for use in machine learning models.
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.