Glossary | AI & Development
Retrieval-Augmented Generation (RAG)
An AI architecture that retrieves relevant documents from a knowledge base and feeds them to a model so the model answers from your data.
Browse all definitionsIn detail
Retrieval-Augmented Generation (RAG) combines a search step (retrieval) with a generation step. The system converts your documents into vector embeddings and stores them in a vector database. When a user asks a question, the system retrieves the most relevant chunks and feeds them to a language model along with the question, so the model answers using your content rather than its general training data. RAG is the dominant pattern for AI assistants that need to know about a specific organisation's policies, products or knowledge base.
Sources and further reading
Check the source, not just the summary
- Original RAG paperarxiv.org
- OAIC APP 11 guidanceoaic.gov.au
Apply the definition
Want to talk through how this applies to your business?
Start with the decision in front of you. We will help map the fit.