LlamaIndex
Log in

Find answers from the community

Updated 10 months ago

Rag

nnshern
·
Hello! I have a general question I hope someone can help me with:

Say I want to do RAG on documents that are meeting notes that are structured so that it is a bunch of verbatim statements from people, structured like

person 1: bla bla bla, 11:46
person2: bla bla bla , 11:47
person1: blablablablabla, 11:50

etc.

Is it a good idea to define each node so that it is a single statement, together with metadata being name of person and time and with no chunk overlap? Or should I just let the node parser do it automatically?

Where can I find some information regarding this and what makes up a "good node"?
W
n
2 comments
WWhiteFang_Jr
Structured data gives better chances for retrieving correct nodes for answering.

So if possible that you can prepare nodes at your side it'll make the retrieval part better thus making response generation much better.


You can learn more about RAG here: https://gradient.ai/blog/rag-101-for-enterprise
nnshern
Thank you!
Add a reply
Sign up and join the conversation on Discord