Retrieval-Augmented Generation
/rɪˈtrɪvəl ɔːɡˈmentɪd dʒɛnəˈreɪʃən/
Definition
A technique where an LLM retrieves relevant information from an external database before generating responses, ensuring accuracy and currency of output.
Examples
- • RAG enables accurate answers grounded in the latest information.
- • Storing corporate documents in a vector DB and querying with RAG creates expert chatbots.
Origin
Introduced by Meta AI in a 2020 research paper.
Core technique solving LLM hallucination problems. Generates responses grounded in reliable, retrieved information.
TECHNeutral2020AILLM정보검색생성