An embedding is what you get when you convert a piece of text into a list of numbers. Those numbers are arranged so that text with similar meaning produces similar numbers. "Invoice is overdue" and "payment is past due" will have embeddings that are close together in vector space. "Invoice is overdue" and "employee onboarding checklist" will be far apart.
This is what makes semantic search possible: instead of matching keywords, the system compares meaning. Embeddings are the foundational technology behind retrieval-augmented generation, enterprise search, and any AI system that needs to find relevant information based on intent rather than exact wording.
