Retrieval-Augmented Generation

Generating responses using information retrieved from external knowledge sources.

Retrieval-augmented generation first searches a knowledge source for documents relevant to a user’s question. The retrieved information is then placed in the model’s context before it generates an answer.

RAG can connect language models to private, specialised or frequently updated data. It may improve factual accuracy and support citations, but its quality depends on retrieval, chunking, ranking and prompt design.

Also in

Diffusion Models Small Language Models Prompt Engineering Context Engineering Few-Shot Learning Supervised Fine-Tuning

JOIN NOW

Begin the first module

It is free, it is the real curriculum, and if it is not for you, you have lost nothing but an evening.

See the curriculum

Join any time · Build AI skills at your pace