cernodatainc/cernodata

Open-source control layer over PDF parsing that picks the right method, verifies output quality, and falls back automatically when results fall short

1 best points · 1 comments · 1 Hacker News post · 22 GitHub stars · View on GitHub

Hacker News discussions

• Why PDF extraction for RAG breaks, and one approach to make it verifiable (1 points, 1 comments, by nattanko, 2026-08-17)