AI 101

Embedding

Also known as: embeddings · vector embedding

Basics

An embedding is a list of numbers that captures the meaning of a word, sentence, or whole document. Similar meanings land close together in this number-space; unrelated things land far apart.

This is what makes search-by-meaning possible: instead of matching exact keywords, you compare embeddings and find the nearest neighbors.

  • “king” − “man” + “woman” ≈ “queen” (the classic demo).
  • RAG works by embedding your documents, then retrieving the ones closest to your question.

Why beginners should care: embeddings are the bridge between "a pile of documents" and "an AI that can answer from them". If RAG puzzles you, start here.