On: How outdated information hides in LLM token genera...

[scarface_74]

In that case you use RAG and have it tell you the source.

[dotancohen → scarface_74]

A RAG needs to be implemented by the LLM provider. The simple end user has no idea what that means, even though he will be (incorrectly) using the LLM for a vital purpose.

[scarface_74 → dotancohen]

ChatGPT does exactly that with its built in runtime and web search.

But the LLM provider doesn’t have to do that. Langchain - the Python AI library - and OpenAI’s own library has support for third party tools.

It’s up to third parties to build on up of it.