Word of the Day

Embeddings

Embeddings turn text into numeric vectors so similar meanings sit close together, powering semantic search and RAG.

Get it free

An embedding is a list of numbers (a vector) that represents the meaning of a piece of text. Texts with similar meaning produce vectors that are close together, so software can measure semantic similarity mathematically rather than matching exact words.

Embeddings are the engine behind semantic search, recommendations, clustering, and the retrieval step in RAG: to find the passages most relevant to a question, a system embeds the question and finds the stored passages whose embeddings are nearest.

Related: rag · token · fine tuning

One of these every weekday

Three minutes. One prompt, one word, one skill. You're now better at AI than you were yesterday.

Free. All terms