What is Retrieval-augmented generation?

Retrieval-augmented generation retrieves relevant documents at query time and puts them in a language model’s context, so answers can draw on sources outside the model’s training data.

Primary sources

Specifications cited by the tools below whose own titles define Retrieval-augmented generation.

Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksarXiv

6 tools that work with Retrieval-augmented generation

Files never leave your browser.

AI & LLM Tools2

Context Window CalculatorPaste a document and see which models it fits inside, how much of each window it fills, and what is left for the reply.Text Chunker for RAGChunk by tokens, sentences, paragraphs, a separator ladder or markdown headings — with overlap, token counts and embedding cost.

On-Device AI4

Chat with Any DocumentAsk questions about a PDF, Word file, spreadsheet, CSV, Markdown or text file and get answers with the passage each came from.Chat with Excel & CSVAsk questions about a spreadsheet in plain English and get answers with the sheet and row they came from. Runs entirely in your browser.Chat with PDFAsk questions about any PDF and get answers with the page each one came from. The model runs in your browser — the file is never uploaded.Chat with Word DocumentAsk questions about a Word document and get answers with the heading each came from. Runs on your device — nothing is uploaded.

Related terms

Terms that appear alongside Retrieval-augmented generation on the same tools.

← All glossary terms Browse every tool →