Embedding

A high-dimensional numerical representation of text, image, or audio — used for semantic search and clustering.

Definition

An embedding is a vector (typically 768 to 4096 dimensions) that captures the meaning of a piece of content. Similar things have similar vectors. Embeddings power semantic search, RAG, recommendation. Embeddings are not training data per se — but evaluating embedding-based systems is.

Examples

  • "king - man + woman ≈ queen" in classic word embeddings

Related terms

Looking for actual gigs that use Embedding? Browse all live listings or filter by $100+/hr.