Embedding
Also: vector embedding, text embedding
A list of numbers that represents the meaning of a piece of text, so that similar texts have similar numbers. Embeddings are what make search and RAG work.
An embedding turns a piece of text into a list of numbers, called a vector, that captures its meaning. Texts about similar things end up with similar vectors, so you can measure how related two pieces of text are by comparing their embeddings.
This is the foundation of semantic search and of RAG: you embed your documents once, store the vectors, and then embed each query to find the documents whose vectors are closest. A dedicated embedding model does this job, and small ones run comfortably on a CPU.
The number of values in the vector is its dimension. Higher dimensions can capture more nuance but cost more to store and compare. Some models let you choose the dimension to trade one against the other.