Find the real sections of a PDF (headings, levels, page spans, text) for RAG: PDF outline + rules, optional LLM, hard cost caps. Benchmarked on READoc.
-
Updated
Nov 11, 2026 - Python
Find the real sections of a PDF (headings, levels, page spans, text) for RAG: PDF outline + rules, optional LLM, hard cost caps. Benchmarked on READoc.
To associate your repository with the section-detection topic, visit your repo's landing page and select "manage topics."