News for hackers. Stuff that matters.

A comment on Show HN: Morphik – Open-source RAG that understands PDF images, runs locally. Parent comment

Re:Show HN: Morphik – Open-source RAG that understands PDF i... by mnky9800n on Wednesday April 23, 2025 @04:25AM (#43769809)
Why do you convert to image? It’s easy to turn the components of a pdf into separate items and then ingest them individually. I also imagine at some point rasterizing vectors will become a pain point for some reason.
[ Parent | on HN ]
Re:Show HN: Morphik – Open-source RAG that understands PDF i... by Adityav369 on Friday April 25, 2025 @01:27AM (#43790392)
Mainly to maintain layout information. Also search becomes easier this way.
[ Parent | on HN ]