Processing Nodes

Document Format Conversion Documentation

High-fidelity transformation between PDF, Word, Excel, PowerPoint, and Image formats.

Updated 2 min read

Quick Answer: What are the Conversion Nodes?

[!NOTE] Conversion Nodes are specialized processing blocks that change the file format of your documents while preserving as much layout and formatting as possible. Whether you need to turn a spreadsheet into a PDF for sharing or a PDF into an editable Word document, these nodes handle the complex re-encoding automatically.

Core Capabilities

1. Document-to-PDF (✅ High Fidelity)

Convert your Word, Excel, and PowerPoint files into professional PDFs. The conversion engine renders fonts, images, and tables with 99.9% accuracy compared to native applications.

2. PDF Reconstruction (Editable Word)

Unlike simple "text-only" extractors, the PDF to Word node reconstructs the visual layout of your PDF, including text boxes, images, and column structures, making the result truly editable in Microsoft Word.

3. Image Generation

The PDF to Image and Image to PDF nodes allow you to bridge the gap between static documents and visual assets, perfect for generating thumbnails or combining photos into a single report.

Configuration Guide

Node TypeSource FormatTarget FormatKey Setting
PDF to Word.pdf.docxLayout Mode
Word to PDF.docx, .doc.pdfN/A
Excel to PDF.xlsx, .xls.pdfSingle Page / Multi-page
Image to PDF.jpg, .png, .webp.pdfPage Orientation

Best Practices

  • Batch Processing: Use these nodes inside a Loop to convert entire directories of files in one go.
  • Post-Conversion Logic: After converting a document to PDF, consider adding a Watermark Node to protect your intellectual property.

[!TIP] Extracting data rather than layout? Link the AI Extract Node to your PDF to get structured JSON instead of a DOCX file.