Glossary · Research & AI
RAG
Retrieval-Augmented Generation
RAG is the pattern in which a language model is given retrieved documents or records relevant to the question before it answers, instead of relying on what it learned in training.
On a medical record it means fetching the right FHIR resources, with their provenance, into the prompt, which is what keeps answers grounded in the patient's own data.
Official source
See also
Explained in depth
Definitions written by Anpheros from the official sources linked on each page. General information about standards and regulation, not legal or medical advice. All terms →