An embedding is a numerical representation of text, an image, or other data as a list of numbers (a vector) that captures its meaning in a form a model can process and compare.

AI models convert words, sentences, or documents into vectors — lists of numbers — where similar meanings are represented by similar numbers. This allows models to compare and search content mathematically.

Embeddings are the foundation of semantic search and retrieval-augmented generation systems.

Related Terms

Learn More

← Back to Glossary AI Glossary → Français →