LocalLLaMA

11 readers

4 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 2 years ago

MODERATORS

communick@poweruser.forum

ChatGPT RAG Implementation? (alien.top)

submitted 2 years ago by Asleep_Parsley_4720@alien.top to c/localllama@poweruser.forum

1 comments fedilink hide all child comments

Hey everyone, with the few weeks old announcement that ChatGPT can support a knowledge base from user uploaded documents, I assume that this is implemented with a form of RAG. If so, does anyone have an idea as to how how they may likely have implemented this? I figure if it’s good enough for them to launch, it may be worthwhile trying out this method on a local LLM.

Thanks for your time

top 1 comments

sorted by: hot top controversial new old

[–] DarthNebo@alien.top 1 points 2 years ago

Most likely plugs multiple retrievers to figure out best candidates or linked content chunks to derive an answer