News for hackers. Stuff that matters.

A comment on Show HN: Open-source Rule-based PDF parser for RAG. Parent comment

Re:Show HN: Open-source Rule-based PDF parser for RAG by infecto on Wednesday January 24, 2024 @08:04AM (#39116778)
What is a split point? I use Textract a lot and from my testing, always beats out any of the open source tooling to extract information. That could also be highly dependent on the document format.
[ Parent | on HN ]
Re:Show HN: Open-source Rule-based PDF parser for RAG by batch12 on Wednesday January 24, 2024 @08:12AM (#39116853)
I think it is a reference to the place a larger document is split into chunks for calculating embeddings and storage.
[ Parent | on HN ]