Launches
Products
News
Community
Advertise
Subscribe
  1. Discussions
  2.  → Will RAG be eliminated by long-context models?

Will RAG be eliminated by long-context models?

Stain Lu
11 replies
There seems to be much debate on it among researchers, what do you think? My view is that there will always be a “memory” as retrieval or buffer.

Replies

Gurkaran Singh
It's fascinating to see the ongoing debate among researchers on the future of RAG in the era of long-context models. I believe that the concept of "memory" in the form of retrieval or buffer will continue to play a crucial role in information processing.
Share
Ted Schaefer
@thestarkster @stain it'll also be more expensive until someone figures out a way to improve the architecture - it takes a lot of memory to crunch through 100K tokens!
Share
Aris Nakos
@thestarkster Solid comments. Follow @swyx on Twitter for great ideas on the matter. He aggregates top knowledge from the field. My premonition is that LLM embeddings become more nuanced and thus long context wouldn't need to be a necessary feature in the future of LLM as much. However, I need to read some more!
Share
Ted Schaefer
definitely think RAG will be here forever in some form or another, since an LLM is lossy by definition. it will be pretty cool when LLMs are able to train on new information in real time though
Share
ᗰᗩ᙭ ᒍ.
Launching soon!
I think there will be use case for both, also at what point is long-context long enough, depending on the use case.
Share