Skip to content

Glossary

Retrieval-augmented generation

Quick answer

RAG: an AI technique where a model looks up relevant documents at answer time and uses them to write its response.

RAG lets a model answer from current or private knowledge without retraining it. Quality depends heavily on the documents available and how well they are organized.

Data licenses should say whether a buyer may use data for training, evaluation, retrieval or a combination, since each use carries different value and risk.

Why Retrieval-augmented generation matters when licensing company data to AI

Retrieval-augmented generation, or RAG, lets an AI model look up relevant documents at answer time and use them to write its response. The model can answer from current or private knowledge without retraining, so the quality and organization of the documents matter a great deal. The license should say whether records may be used for training, evaluation, retrieval or a combination, since each carries different risk.

  1. 01Your work records
  2. 02Personal details removed
  3. 03You approve the release
  4. 04Licensed to AI developers
How it works with SourceX: Your work records → Personal details removed → You approve the release → Licensed to AI developers.Illustrative

Related terms

Related resources

See if your company qualifies

A short company assessment. No data uploads are needed.

See if your company qualifies Talk to SourceX
See if your company qualifies