Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.zappway.ai/llms.txt

Use this file to discover all available pages before exploring further.

Overview

PDF is one of the most versatile formats for training your AI. Upload reports, ebooks, scanned documents, and more.

Supported Types

  • Text PDFs: Native digital PDFs
  • Scanned PDFs: OCR text extraction
  • Forms: Extract form fields and values
  • Multi-page: Unlimited pages

Quick Upload

1

Prepare PDF

Ensure PDF is not password-protected
2

Upload

Datastore → Add Datasource → File Upload
3

OCR

Scanned PDFs automatically processed with OCR

Features

Smart Text Extraction

  • Maintains document structure
  • Preserves tables and lists
  • Extracts hyperlinks
  • Reads headers and footers

OCR for Scanned Documents

  • Converts images to searchable text
  • Supports 50+ languages
  • Processes handwriting (with limitations)

Best Practices

High-Quality Scans: 300 DPI or higher ✅ Remove Passwords: Unlock PDFs before uploading ✅ Merge Related PDFs: Combine chapters/sections ✅ Bookmarks: Use for long documents

Use Cases

  • 📄 Contracts & Legal Docs
  • 📖 Ebooks & Guides
  • 📊 Annual Reports
  • 🎓 Research Papers

Troubleshooting

OCR Quality Issues:
  • Use high-resolution scans
  • Ensure good lighting
  • Avoid skewed pages
Large File Sizes:
  • Compress PDF (reduce image quality)
  • Split into smaller files

Limits

PlanMax SizeOCR Pages
Free10 MB50
Professional50 MBUnlimited