Document Format Conversion & Parsing
13 repos
Tools and libraries for converting between document formats—primarily PDF, Markdown, DOCX, and XLSX—with a focus on extraction, parsing, and format transformation. The cluster spans Python-based conversion utilities, LLM-integrated document processors, and JavaScript/TypeScript implementations for web and Node.js environments. Central projects like Docling and pdf2md_llm demonstrate the prevalence of PDF-to-Markdown pipelines and AI-assisted document understanding, while broader coverage includes generic multi-format converters and specialized inspectors for PDF content analysis.
Python · 10
Rust · 2
Java · 1
pdf-parser ·231,029
ocr ·212,194
pdf-extractor-rag ·169,064
ai4science ·169,064
pdf ·140,205
document-parsing ·120,059
rag ·118,435
pdf-converter ·108,877
python ·98,753
paddleocr-vl ·89,476
