RAG
RAG is a method that retrieves relevant information and supplies it to a language model as it generates an answer.
2 articles
Last mentioned RAG, or retrieval-augmented generation, retrieves relevant material from documents or databases and includes it in a language model’s input before the model answers. It uses retrieved information without changing the model’s weights, unlike fine-tuning.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.
Articles covering this entry
Retrieval-augmented generation (RAG) lets a chatbot search a document collection and include matching passages in its response context.