Use case

Document processing

One tool for web pages. The same tool for files.

The problem.

Research workflows mix many formats. Compliance workflows do too. A different converter for each is slow. It is hard to keep consistent.

Step 1

Word, Excel, PowerPoint, OpenDocument, EPUB, RTF, CSV and PDF.

webfold convert slides.pptx

Step 2

Scanned PDFs fall back to OCR.

webfold pdf scan.pdf

Step 3

Split everything into retrieval-sized pieces.

webfold chunk notes.docx --size 3000 --jsonl

PDF, Word or Excel to Markdown.

Any URL to clean Markdown.

Conversion success is measured, not fidelity. Check tables on your own documents. Check math. Check merged cells.

Run the command-line tool today. Hosted API access is coming.