Embedding
A numeric vector representation of a piece of text (or image, audio, or other content), produced by a model trained so that semantically similar inputs produce vectors that are close together in the vector space. Embeddings are the input to semantic search, RAG retrieval, recommendation systems, and AI agent memory.
Defined in 2 GAGE programs, which carry 2 distinct definitions of it. The wording above is taught in Certified AI Data Governance Professional (CADGP).
How each discipline defines it
The same term does different work depending on who is using it. These are the definitions as each program teaches them, unedited.
A numeric vector representation of a piece of text (or image, audio, or other content), produced by a model trained so that semantically similar inputs produce vectors that are close together in the vector space. Embeddings are the input to semantic search, RAG retrieval, recommendation systems, and AI agent memory.
Folding the agreement into the team's existing rituals and workspaces (review checklists, retros, onboarding docs) so it is reinforced in the flow of work rather than forgotten in a standalone file.
Where it is taught
The exact lessons this term appears in. The first module of every program is free with a free account.
- Setting AI Usage Expectations Within Teams · AI in the Workplace and Team Leadership, Certified AI Practitioner: Workplace Foundations
- Embeddings are data too: the vector store as a personal-data system · Feeding the Machines, Certified AI Data Governance Professional (CADGP)
Terms it appears with
Not an alphabetical neighbourhood: these are the terms taught in the same lessons, ranked by how often they appear together.