Embedding
A numerical vector representation of data (text, images, etc.) in high-dimensional space, where semantic similarity corresponds to geometric proximity.
Embeddings are the translation layer between human concepts and machine math. Neural networks learn to place semantically similar items close together in vector space, enabling similarity search, recommendations, and retrieval-augmented generation. Modern embedding models produce vectors with hundreds or thousands of dimensions.
Also known as
embeddings, vector embedding, text embedding, semantic embedding