开发者开源保留版式与坐标的轻量 PDF 解析工具
Lightweight PDF parser with layout, tables, formulas and bounding boxes
开发者发布一款开源轻量 PDF 解析工具，目标是在导出 Markdown、JSON、Excel 和 Word 时保留阅读顺序、表格、公式、图形及其原始位置（bounding boxes）。作者同时在做面向 RAG 的结构感知语义分块，让检索到的分块保留章节、页码和 PDF 中的精确视觉位置，并公开征求架构、抽取质量和应用场景方面的反馈。
I built this because extracting PDFs into Markdown/JSON often loses reading order, tables, formulas, figures, and their original locations.
The goal is a lightweight document extraction pipeline that preserves document structure and bounding boxes while exporting to Markdown, JSON, Excel and Word.
I'm also working on structure-aware semantic chunking for RAG, so retrieved chunks can retain their section, page and exact visual location in the PDF.
The project is open source and I'd love feedback on the architecture, extraction quality, and useful use cases.
来源：Hacker News · 首页 · news.ycombinator.com