AI Glossary
What is an embedding?
Embedding: An embedding turns text into a long list of numbers that captures its meaning, so computers can measure how similar two pieces of text are.
In plain English
Imagine giving every sentence coordinates on a giant map of meaning. "How do I reset my password?" and "I can't log in" land close together on that map even though they share no words. Once meaning is geometry, "find similar text" becomes "find nearby points" — something computers do brilliantly.
Why it matters
- The engine behind semantic search — matching by meaning, not keywords
- Step one of every RAG system: find the passages worth retrieving
- Also powers recommendations, deduplication and clustering
A concrete example
Search a help center for "money back" and embedding search surfaces the refund policy — a keyword search would have missed it entirely.
Related terms
Learning AI from scratch? Start with the free Learn AI course picks, then put it to work with 50 tested prompts — or get the daily 2-minute briefing, free →