Description
Feeding PDFs, Word and PowerPoint to an LLM first means clean text, and a separate tool per format is a pain. markit converts almost any file to Markdown in one command: PDF, DOCX, PPTX, XLSX, HTML, EPUB, Jupyter, RSS, even images, audio and URLs.
Its built-in Rust engines keep headings, tables and images, as a CLI or a library.
Formats:Docs, sheets and ebooks.
Rust:Fast parsing.
Structure:Headings and tables.
CLI and library:Both.
Its built-in Rust engines keep headings, tables and images, as a CLI or a library.
Features
Formats:Docs, sheets and ebooks.
Rust:Fast parsing.
Structure:Headings and tables.
CLI and library:Both.
