What is Retrieval-Augmented Generation (RAG)?
Retrieval-Augmented Generation (RAG) is a method in which a language model retrieves relevant text passages from a document collection or the web before writing an answer and uses them as its basis. This lets the model answer with information that is not in its training data.
The term goes back to a research paper by Lewis and colleagues, published at NeurIPS 2020. The basic pattern has since become standard: a request is turned into a search, the best results are split into chunks, and the most relevant chunks go to the model together with the question.
For websites one point matters most. The model rarely reads a whole page, it reads individual passages. A paragraph that answers a question completely, without relying on earlier sections, is easier to use than a statement spread over several places.
AI search products such as ChatGPT with web search or Perplexity work on this principle, but vendors do not publish their exact implementation. Claims about the ideal passage length are therefore guesses.
What it means for your website
For your own page: put central statements into clearly separated paragraphs with their own subheading, and name the subject in each answer instead of pointing to “as described above”. The content also has to be in the delivered HTML, since many retrieval systems do not execute JavaScript. Clearly labeled tables and lists also help, because they stay understandable as a standalone chunk.
Related terms
Sources
Terms help you understand. Whether AI crawlers can reach your site is something you measure.
Check your website for freefree · no signup · no credit card