Output Formats

Parse4ai provides multiple output formats for parsed documents.

Default Formats

Markdown

• Clean, readable text format
• Preserves document structure
• Easy to process and display

JSON

• Structured data format
• Machine-readable
• Includes metadata and formatting

Additional Formats

You can request additional export formats using the extra_formats parameter:

DOCX

• Microsoft Word format
• Preserves formatting

HTML

• Web-friendly format
• Can be directly displayed in browsers

LaTeX

• Scientific document format
• Ideal for academic papers

Output Package

When parsing is complete, you receive a ZIP file containing:

• Markdown file (default)
• JSON file (default)
• Additional formats (if requested)