IBM 开源的文档智能解析工具,支持 PDF、Word、PPT、扫描件(OCR)等 20+ 格式的深度解析,输出结构化 Markdown/JSON,内置布局分析、表格识别与公式识别,是 RAG 数据管道的热门选择。 🔗 文档: https://docling-project.github.io/docling/ | GitHub Stars: 66k+
IBM's open-source document intelligence toolkit. Deeply parses PDF, Word, PPT, and scanned files (OCR) into structured Markdown/JSON with built-in layout analysis, table recognition, and formula extraction — a popular RAG pipeline choice. 🔗 Docs: https://docling-project.github.io/docling/ | GitHub Stars: 66k+
Docling belongs to the Developer Tools category on hedirbase. Tagged with: document,ai,parsing,ocr,pdf.
IBM's open-source document intelligence toolkit. Deeply parses PDF, Word, PPT, and scanned files (OCR) into structured Markdown/JSON with built-in layout analysis, table recognition, and formula extra