Pdf

This extracts text from PDFs with a practical fallback strategy: it tries pypdf first, then switches to pdfminer.six if it's getting less than 50 characters per page, which usually means CJK fonts that pypdf can't decode. It's triggered automatically when you reference PDF files or mention research papers and documents in your prompt. The dual-parser approach is smart because pypdf is faster for standard PDFs, but you need the heavier pdfminer for certain character sets. If you work with academic papers or mixed-language documents, this handles the edge cases without you thinking about it. AGPL licensed.