16:18
2026-07-28
github.com
developer-tools
Show HN: DocSlicer – Structure-aware PDF/DOCX/PPTX parser, 31 pages/SEC on CPU
DocSlicer, a new structure-aware document parser, achieves 31 pages per second on CPU and scored 0.88 overall on the BizDocBench benchmark, outperforming the next-best tool's 0.70. The deterministic p…