================================================================================
                         NEW DOCUMENTS IMPORT FOLDER
================================================================================

Drop your documents here for processing!

SUPPORTED FORMATS:
  - PDF files (.pdf)
  - Word documents (.docx)
  - Plain text (.txt)
  - Markdown (.md)
  - EPUB e-books (.epub)
  - HTML files (.html)

HOW TO USE:
  1. Copy or move your documents into this folder
  2. Run the ingestion pipeline:

     cd /var/www/html/research/Research_development
     python pipeline/ingest_documents.py

  3. Documents will be processed and moved to library/ORGANIZED/

WHAT HAPPENS:
  - Documents are analyzed and classified automatically
  - Text is extracted and chunked for searching
  - Metadata (author, year, title) is extracted from filename/content
  - Files are organized into category folders

TIPS:
  - Name files descriptively: "Author Name - Title (Year).pdf"
  - Subfolders are processed recursively
  - Duplicate documents (by hash) are skipped automatically

ALTERNATIVE IMPORT LOCATIONS:
  - library/NEW_DOCS/incoming/  (legacy location, still supported)

================================================================================
