Ask HN: What is the best way to chunk documents for RAG?

Posted by matt_heyqq on Wednesday October 09, 2024 @07:46AM
from the ask-hn dept.

What do you think is the best way for chunking in RAG systems of documents of varying length and content?

( 1 comment | 2 points | on HN )

Re:Ask HN: What is the best way to chunk documents for RAG? by chiccomagnus on Wednesday October 09, 2024 @09:06AM (#41787537)

If for "documents" you mean PDF, Word, Powerpoints, Excel you should try preprocess.co

If that’s not what you meant, can you please clarify?

[ Parent | on HN ]