Skip to content
Get in touch
  1. Home
  2. Insights
  3. The revenue lexicon
  4. Artificial intelligence
  5. Generative AI
  6. Large language model
  7. Retrieval-augmented generation

Glossary

Retrieval-augmented generation (RAG)

Retrieval-augmented generation: Retrieval augmented generation (RAG) is the technique that makes an artificial intelligence system answer from the company's own documents: the system first searches the archives it has been pointed at for the relevant passages, then writes the answer out of those passages.

Its purpose is to tie every answer to a source that can be checked, and it narrows the room for invention that a model left alone with its training allows itself.

An example

The customer service desk of a machinery manufacturer answers delivery questions by reading the management system and the uploaded manuals, and every answer arrives with the document it came from. Whoever receives it can open that document and check, and whoever signs it knows what they are putting their name to.

Entry map

broader entriesthis entry and narrowertwo levels down← up · → down

cc$BY-NCEnrico Giubertoni. Licensed under CC BY-NC 4.0: you may quote, translate and adapt this entry with the author’s name and a link, stating any changes. For commercial use, write to info@enricogiubertoni.com

Spotted an inaccuracy or something that needs updating? Write to info@enricogiubertoni.com and help make this glossary a better place.

What are your business challenges?

Tell us about your priorities and the objectives you want to reach.
You will receive a free, targeted answer within one working day.