In machine learning, an embedding is a dense vector of numbers that represents a piece of text, image, or other data in a way that preserves semantic relationships. Words or phrases with similar meanings produce embeddings that are numerically close together in vector space. Embeddings power semantic search, recommendation systems, and retrieval-augmented generation by enabling AI systems to find conceptually related content rather than relying solely on exact keyword matches. They are a foundational component of modern AI search infrastructure.