Retrieval
The selection of relevant material from a corpus and its supply to a model as context, determining what evidence the model sees before it answers.
Why it matters
The least governed component in the agentic stack and the one where financial AI actually fails. Model risk management scrutinizes the model and waves through the layer that decides what the model is allowed to know. A reranker change alters outputs as surely as a weight update, ships without review, and leaves no trace in any model inventory. Retrieval configuration belongs under change control.
Relationships
Typed edges into the rest of the ontology. These are what make the canon traversable rather than merely readable.
| Verb | Target | Meaning |
|---|---|---|
relatedTo | Retrieval Pipelines | An association too weak or too general for a stronger verb. |
addresses | Auditability | The subject speaks to the object as a question or concern. |
Record
| Canonical identifier | QIS-TERM-00044 |
| Status | Canonical industry term |
| Adoption | Widely used |
| Domain · Layer | Stack categories · Intelligence |
| Origin | Information retrieval; central to RAG architectures from 2023. |
| Semantic aliases | None recorded. |
| First published | 2026-08-02 |
| Last reviewed | 2026-08-02 · 180-day cycle |
Cite the identifier, not the URL. Identifiers are stable; URLs may change. This entry is free to read, quote and index under the dual license. Corrections to [email protected] are published.