Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / embedding-model

Embedding model

A model that maps text, images, or multimodal content to dense vector representations used for retrieval, clustering, and similarity search.

What this means in practice

Distinct from the concept of an embedding (a single vector): the embedding model is the artefact with a version, training corpus, dimensionality, and licensing footprint that governance must track.

Synonyms

text embedding model , encoder model

Related Terms Network

This diagram shows how Embedding model connects to other concepts in the COMPEL body of knowledge. Each linked node is a term you can explore in turn.

Related terms for Embedding model Network graph showing 4 related glossary terms connected to Embedding model. Embedding mode… Vector sto… Embedding … Chunking Hybrid ret…
4 related concepts connected to Embedding model.

The COMPEL Glossary Graph visualizes relationships between framework terminology, showing how concepts interconnect across domains, stages, and pillars. Term nodes cluster by pillar affiliation while cross-references reveal semantic dependencies — for example, how risk appetite connects to control effectiveness, model governance, and assurance requirements. This network representation helps practitioners navigate the framework vocabulary and understand that COMPEL terminology forms a coherent conceptual system rather than isolated definitions.

Accessible list of related terms
  • Vector store — A governed index of embeddings — numeric vector representations of text, image, or multimodal content — that supports similarity search used by retrieval-augmented generation.
  • Embedding governance — Readiness criteria specific to vector-store operations — choice of chunking strategy, embedding-model version pinning, index refresh and re-embedding cadence on model upgrades, per-namespace access control, and retention/deletion workflow consistent with data-subject rights.
  • Chunking — The process of dividing documents into units — typically fixed-token windows or paragraph-level segments — suitable for embedding and retrieval.
  • Hybrid retrieval — A retrieval pattern combining dense (vector-based, e.g., dense passage retrieval) and sparse (term-based, e.g., BM25) retrieval methods, whose candidate sets are fused — typically via reciprocal rank fusion — before reranking.

See also

  • Vector store — A governed index of embeddings — numeric vector representations of text, image, or multimodal content — that supports similarity search used by retrieval-augmented generation.
  • Embedding governance — Readiness criteria specific to vector-store operations — choice of chunking strategy, embedding-model version pinning, index refresh and re-embedding cadence on model upgrades, per-namespace access control, and retention/deletion workflow consistent with data-subject rights.
  • Chunking — The process of dividing documents into units — typically fixed-token windows or paragraph-level segments — suitable for embedding and retrieval.
  • Hybrid retrieval — A retrieval pattern combining dense (vector-based, e.g., dense passage retrieval) and sparse (term-based, e.g., BM25) retrieval methods, whose candidate sets are fused — typically via reciprocal rank fusion — before reranking.