I read on https://mistral.ai/news/mistral-large/:

Mistral Small benefits from the same innovation as Mistral Large regarding RAG-enablement and function calling.

What do they mean by RAG-enablement? I'm familiar with RAG-QA, but any LLM can be used for RAG-QA. So why are they talking about RAG-enablement? Do the Mistral models have some special training/performance/etc. for RAG-QA?



You must log in to answer this question.