Embedding
Also called embeddings, vector embedding.
In plain English
An embedding turns text into a list of numbers so a computer can measure how close two pieces of text are in meaning.
Example
A search for "fix a flat tire" finds a page titled "repair a bike puncture" because their embeddings are close, even though the words differ.
Why it matters
OpenAI's embeddings guide describes an embedding as a vector, a list of floating point numbers. Texts with similar meaning get vectors that are close together. Search, recommendations, and retrievalRetrieval is finding and returning information relevant to a request from stored or connected material, so an AI app can use it as context. for AI answers often use embeddings.
How it shows up on bot.ski
Botski keeps live AI off on bot.ski. The RetrievalRetrieval is finding and returning information relevant to a request from stored or connected material, so an AI app can use it as context. guide on bot.ski explains where embeddings fit when an AI looks things up.
Common confusion
An embedding is not a summary you can read. It is only numbers, useful for comparing meaning.
Sources
Updated October 11, 2026.