Product
pdftotext
A command-line tool in the Xpdf/Poppler project used to extract plain text content from PDF files.
Timeline (last 90 days)
Oct 12
In the working wiki, PDF text extraction uses Poppler's pdftotext, the knowledge base has no OCR capability; when a document contains pages in image form, the model can read them directly as images.
Unverified50%