Glossary
What is retrieval-augmented generation?
RAG: a method where an AI model first looks up the most relevant passages in your own content, then writes its answer only from those passages.
Retrieval-augmented generation splits your documents into short passages, finds the ones closest to a question (by meaning, by keywords, or both), and gives only those to the model with an instruction to answer from them.
That's how a support assistant can answer from your help center without being retrained: change a page, and the next answer uses the new text. It also makes citations possible, because the system knows which passages it used.
See it in practice in Office Assist.
Where you'll use it
- Train a chatbot on your websitePaste your website's address and the assistant reads it, page by page, with a progress bar. It re-reads your site every day so answers stay current.
- Answers from your help centerConnect your knowledge base and every published article becomes something the assistant can answer from, the moment you hit publish.
- Answers from PDFs and filesUpload PDFs, text, Markdown, HTML or CSV files. Answers cite the file and, for PDFs, link straight to the right page.
Related terms
Try Office Assist with your whole team
7-day trial with every feature. Cancel from the billing page whenever you like.