Description
Feeding Word, PowerPoint, Excel and PDF to an LLM means a different parser per format with inconsistent output. anydoc is Firecrawl's Rust library that converts office documents into clean GitHub-Flavored Markdown in single-digit milliseconds.
It handles Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF, with Node.js, Python and WebAssembly bindings, and powers Firecrawl Parse.
Many formats:Word, PowerPoint, Excel, ODF, RTF, EPUB, CSV and PDF.
Consistent output:Clean GFM Markdown.
Fast:Milliseconds per document.
Bindings:Node.js, Python and WebAssembly.
It handles Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF, with Node.js, Python and WebAssembly bindings, and powers Firecrawl Parse.
Features
Many formats:Word, PowerPoint, Excel, ODF, RTF, EPUB, CSV and PDF.
Consistent output:Clean GFM Markdown.
Fast:Milliseconds per document.
Bindings:Node.js, Python and WebAssembly.
