Embedding
Also called Vector embedding
A list of numbers standing for a piece of text, produced so that texts with related meanings get similar numbers. Compare two lists and you get a measure of how related the texts are, even if they share no words.
It is what makes search by meaning possible, and you will meet it in tools that search documents on a model's behalf. It isn't automatically better than plain search: for an exact function name, a text search is faster, cheaper and right.
Say it to your agent
“Search for handleLogin with rg first. If that finds nothing, tell me before you build an embedding index, and if we do build one, measure it on 20 real questions against plain rg.”