Embedding
A numerical representation of content — text, image, or audio — as a list of numbers (a vector) that captures its meaning. Similar meanings produce nearby vectors, which is what makes semantic search possible: puppy matches young dog even with zero shared words. Embeddings power reverse image search, recommendation feeds, RAG retrieval, and the way generation models connect your prompt to visual concepts. Practical relevance: whenever a tool finds similar images or a model seems to understand your prompt beyond keywords, embeddings are doing the matching underneath. They are the coordinate system of machine meaning.