“Now, in 2020, the way RAG was done was to combine a…” — Practical AI at 22:55
“Now, in 2020, the way RAG was done was to combine a sequence-to-sequence language model, which was the standard we were doing language modeling back then. And those models could generate text quite convincingly. And you combine those models with the retrieval capabilities of dense embeddings. And the Facebook…”
0:00
55:02