An approach that enhances generative AI by retrieving relevant information from external knowledge sources before generating responses. RAG combines information retrieval with text generation to produce more accurate, up-to-date, and context-aware outputs.

RAG addresses several limitations of standard generative models, particularly their tendency to hallucinate and their inability to access information beyond their training data. In a RAG system, the generation process is grounded in retrieved facts, improving factual accuracy and enabling access to specialised or current information. This approach is particularly valuable for enterprise applications requiring domain-specific knowledge or access to proprietary information.

‍

An enterprise legal assistant that retrieves relevant case law, regulations, and company policies before generating legal advice or contract language, ensuring outputs reflect the most current and relevant information.