Retrieval-Augmented Generation

A generation technique that supplements a language model’s internal (parametric) knowledge by retrieving relevant external information before generation. RAG systems first search knowledge sources such as databases or knowledge graphs and then use the retrieved context as input for text generation.

In SimpleModeling, RAG serves as the knowledge bridge between the AI model’s pretrained parametric knowledge and the structured knowledge of the BoK generated from SmartDox. The retrieval component searches SmartDox or BoK documents, while the generation component produces context-aware outputs that integrate both implicit and explicit knowledge.