What is Embedding?
An embedding is a numeric vector that represents the meaning of a piece of text, so passages with similar meaning sit close together in vector space. Embeddings let a system retrieve by meaning rather than by exact keyword match.
Also known as: vector embedding, text embeddings.
Semantic search alone is not enough for enterprise content, where exact identifiers, product codes and legal references matter. Hybrid retrieval combines vector similarity with keyword search and then reranks the merged candidates.
Embedding models are also a data-residency question: sending text to a hosted embedding API exports the same content you were trying to protect.
How Uthereal handles it
Cortex runs hybrid retrieval with reranking, and can run embedding inside your own environment when sovereignty is required.
Related reading
Last updated 2026-09-18 · plain-text glossary for AI tools