RAG or retrieval Augmented Generation is emerging as the architecture pattern of choice for enterprise grade LLM applications, due to its ability to significantly reduce hallucinations and introduce citations, both of which increase the trust of the end user in the result. This is of crucial importance for healthcare applications, where the implications of hallucinations can be dire indeed.

In this talk I will describe what RAG is, how it’s implemented, and introduce Vectara’s Hallucination Evaluation Model (HEM) which allows to measure hallucinations in the response. I will demonstrate this over a sample application of RAG with healthcare research data.