Document parser breaks formatting on upload
Summary: When uploading PDFs and DOCX files (e.g. into procedures/content for Fin), the document parser ruins formatting and messes up the document's organization, making the parsed content a mess.
Details:
- Affected file types: PDF and DOCX
- Issue: parsing strips or scrambles formatting and structure, so the resulting content is disorganized and hard to use
- Impact: degrades quality of Fin's knowledge/procedures content, which hurts customer-facing answers and our CX score
Requested fix: Preserve document formatting/structure during parsing. As an alternative or additional fix, native Markdown (.md) upload support would likely resolve this since it avoids the PDF/DOCX conversion step entirely.