LogitMaxAI Glossary › Embedding

Embedding

Also known as · embeddings · vector embedding

A numeric vector that captures the meaning of text so machines can compare it.

An embedding is a list of numbers (a vector) that represents the meaning of a piece of text — a word, sentence, or document — in a way a computer can work with. Texts with similar meaning end up with vectors that are close together, even if they share no words. 'Car' and 'automobile' land near each other; 'car' and 'banana' don't.

This is enormously useful because it turns the fuzzy notion of 'similar meaning' into simple distance math. Search, recommendation, clustering, and retrieval all become measurable: find the stored vectors closest to your query's vector.

Embeddings are the backbone of semantic search and of RAG systems, where they're used to find the most relevant documents to feed a language model.

Go Deeper

Beyond definitions.

LogitMax teaches the AI frontier in 30 short, plain-English modules — from tokens to agents to where it's all heading.

Start the course