Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

embedding

A vector of numbers standing for a piece of text -- a word, sentence, or document -- positioned so that similar meanings end up as nearby vectors.

An embedding is a fixed-length vector representation of a piece of text, learned so that semantic similarity between two pieces of text corresponds to geometric closeness (by cosine similarity or Euclidean distance) between their embedding vectors.

Examples

  • In a well-trained embedding space, the vectors for "king" and "queen" sit close together, while "king" and "bicycle" sit far apart.

See also

cosine similarity dense retrieval
Read the full section →
Graph settings

Calculator