Glossary

What are embeddings?

An embedding is a list of numbers that represents the meaning of a piece of text or an image. Items with similar meanings get similar numbers, even when they use different words, so “refund” and “money back” end up close together. This is what lets AI systems search by meaning rather than by exact words.

Why it matters for a business

Embeddings sit underneath most systems that answer questions from a company’s documents. Every document is cut into passages, each passage is embedded, and the results are stored in a vector database ready to be searched. Which passages come back for a question decides most of the quality of the answer. The stored numbers are derived from the original text and carry its sensitivity, so the store needs the same access rules and deletion policy as the documents.