A numerical (vector) representation of text, images, or other data that captures semantic meaning, enabling similarity search and retrieval.
Friendly Description: An embedding is the AI's way of turning words, pictures, or ideas into a list of numbers that capture their meaning. Things with similar meanings end up with similar numbers, kind of like how houses on the same street have similar addresses. This trick is what lets AI tell that "happy" and "joyful" are basically neighbors, even though they're spelled differently.
Example: When you search a music app for "calm rainy day songs," it doesn't just look for those exact words in song titles. It converts your phrase into an embedding, finds songs whose embeddings live in the same neighborhood, and serves up tracks that match the feeling you described, even if the words "calm" or "rainy" never appear in the song titles.