8 projects
newspaper-ocr
Modular OCR pipeline for historical newspaper scans
mcp-zotero
MCP server for Zotero — library tools + optional semantic search
vllmocr
OCR using LLMs
describecsv
A tool for analyzing and describing CSV files
describecsv-nc
A tool for analyzing and describing CSV files
webpage2md
Convert HTML files and web pages to Markdown format
pdfimageextractor
Extract high-quality images from PDF files while preserving metadata
pdtext
Helper functions for working with text in pandas
