Skip to content

Glossary

What is RAG?

RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.

  • Also called Retrieval-augmented generation

What it means

A language model on its own only knows what it learned in training. RAG adds a search step. When a question arrives, the system searches your documents, usually by meaning with embeddings and often also by keywords, picks the most relevant passages and gives them to the model with the question. The model answers from those passages and can cite them.

Quality depends on each step: how documents are split, how search works, whether results are reranked and how the model is told to use them.

Why it matters for a business

RAG is the most common way to build assistants that answer from company knowledge: policies, manuals, contracts and help content. It keeps answers current, because updating a document updates the answer, and it makes answers checkable through sources.

A business example

Things to watch

  • Retrieval quality matters more than model choice.

  • Keep documents current and remove outdated versions.

  • Respect document permissions in search results.

  • Test with real questions, including ones it should decline.

Keep exploring

FAQ

Questions about RAG

Have a question that is not here? Ask us directly.

Start a project

Tell us what you want to build. We will show you a faster path.

Send a short brief. We reply with questions, a suggested plan and an estimate you can compare with other offers.

Your privacy choices

We use necessary storage to run this site. With your permission we also use Google Analytics to see which pages help people, and load maps from Google. You can change this at any time. Read the cookie policy.