cancel
Showing results forย 
Search instead forย 
Did you mean:ย 
Greater Seattle
cancel
Showing results forย 
Search instead forย 
Did you mean:ย 

Rag vs CPT

SamruddhiPai
New Contributor

How to decide when to go for RAG vs CPT? If we go with CPT and if the training documents change, it is okay to take the CPT model and apply RAG on top of it? Will it unlearn previous information?

1 REPLY 1

cstevens2010
New Contributor II

For large or dynamic knowledge bases RAG is what we have tended to go with. It allows for quite a bit of scalability with little overhead.

CPT is good for building foundational knowledge around a subject, your internal industry information for example. Yes, you can apply RAG on top of CPT, in fact this is probably the most robust implementation. It shouldn't unlearn your CPT learned information, it will supplement with the new documents. There is risk of conflict if there is conflict in the documents but otherwise you should be good! 

Hope that helps ๐Ÿ™‚

"All models are wrong, some are useful"

Connect with Databricks Users in Your Area

Join a Regional User Group to connect with local Databricks users. Events will be happening in your city, and you wonโ€™t want to miss the chance to attend and share knowledge.

If there isnโ€™t a group near you, start one and help create a community that brings people together.

Request a New Group