AI Governance Engineer
GitHub

Retrieval-augmented generation (RAG)

By Updated

A system that combines a model's learned memory with a retrievable store of documents at answer time 1. The corpus becomes behaviour, so it is governed like a model: versioned, carded, tied to the eval that tested it, with an entitlement check on what each user may retrieve.

Developed in
ch. 11, RAG systems
Chapters
ch. 11, AI Defined · ch. 16, Fairness & XAI
Source
1 numbered reference, listed below

Where it is used

8 chapters of the Body of Knowledge use the term. Each link opens the first section that does.

Retrieval-augmented generation (RAG): mentions per chapter22 mentions of the term across 8 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter04 The Stack: 1 mention04 The Stack111 AI Defined: 5 mentions11 AI Defined514 Development: 1 mention14 Development115 Deployment: 5 mentions15 Deployment516 Fairness & XAI: 3 mentions16 Fairness & XAI319 Privacy & AI: 5 mentions19 Privacy & AI520 Existing Law: 1 mention20 Existing Law123 AI Agents: 1 mention23 AI Agents1No mentions in the other 15 chaptersSource: the Body of Knowledgev0.5.0
Retrieval-augmented generation (RAG): mentions per chapter22 mentions of the term across 8 of the 23 chapters of the Body of Knowledge; the chapters the glossary cross-references are drawn solid.Cross-referenced chapterOther chapter0001020304 The Stack: 1 mention104050607081011 AI Defined: 5 mentions511121314 Development: 1 mention11415 Deployment: 5 mentions51516 Fairness & XAI: 3 mentions316171819 Privacy & AI: 5 mentions51920 Existing Law: 1 mention120212223 AI Agents: 1 mention123Source: the Body of Knowledge v0.5.0
Mentions per chapter How often each chapter names the term, with the chapters the glossary cross-references drawn solid. The longest bar is where to read the term in use; bars spread across many chapters mark a term that runs through the discipline.
Mentions as a table
Mentions of Retrieval-augmented generation (RAG) per chapter
ChapterMentionsCross-referenced
00 Preface0No
01 Definition0No
02 Why Now0No
03 Values & Principles0No
04 The Stack1No
05 Patterns0No
06 The Role0No
07 Maturity Model0No
08 Regulatory Map0No
10 Reading List0No
11 AI Defined5Yes
12 Governance Program0No
13 Risk Management0No
14 Development1No
15 Deployment5No
16 Fairness & XAI3Yes
17 Incidents0No
18 EU AI Act0No
19 Privacy & AI5No
20 Existing Law1No
21 AI Laws Worldwide0No
22 Principles & Standards0No
23 AI Agents1No

Sources

  1. [1] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (parametric and non-parametric memory; arXiv 2005.11401). Lewis et al.. 2020-05-22. https://arxiv.org/abs/2005.11401 (verified: primary)

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Retrieval-augmented generation (RAG). In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/retrieval-augmented-generation-rag. CC BY 4.0

BibTeX

@misc{aige2026retrievalaugmentedgenerationrag,
  author  = {Jorge García Aibar},
  title   = {{Retrieval-augmented generation (RAG)}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/retrieval-augmented-generation-rag}
}