Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, with Patrick Lewis, Facebook AI

[@TheMriganks]

Good session, possible to get the slides?

[@JohnCrafts-c7s]

Use a pre-completion document, that stores the cached response of the model to write to as a sort of reverse RAG (gives a space for multi-hop to happen, and stores context for cross document RAGs)

[@_HarshVerma]

Now this guy knows what he is talking about otherwise every other person talkin rag on UA-cam is just saying gibrish

[@bhaumikpatel4902]

Probably because he was a co-author 😅

[@ZKYQUQ]

You're right bro. Love u.@@bhaumikpatel4902

[@FunCodingwithRahul]

Can I integrate any LLM as generator model e.g. Falcon? I am getting errors while doing it. any lead would be of great help !!

[@DistortedV12]

Awesome work