Skip to main content
COMPEL Body of Knowledge
Get Certified Platform

COMPEL Glossary / index-algorithm

Index algorithm

The data-structure choice — HNSW, IVF, product quantization (PQ), or flat (brute-force) — that governs a vector store's query latency, memory footprint, and recall-at-k tradeoff.

What this means in practice

Selection is an architectural decision with implications for cost, scale, and update frequency; no index is universally best.

Synonyms

ANN index , vector index algorithm

Related Terms Network

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

Related terms for Index algorithm Network graph showing 3 related glossary terms connected to Index algorithm. Index algorith… Vector sto… Hybrid ret… Reranker
3 related concepts connected to Index algorithm.

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.
  • 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.
  • Reranker — A cross-encoder model that re-scores a candidate set of documents — typically the top-k from an initial vector or hybrid retrieval — to improve ordering by the actual query-document semantic match.

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.
  • 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.
  • Reranker — A cross-encoder model that re-scores a candidate set of documents — typically the top-k from an initial vector or hybrid retrieval — to improve ordering by the actual query-document semantic match.