OCR mode
Theocr_mode
parameter controls how OCR is performed on your documents:
- standard (default): Uses the standard OCR process for all document content.
- agentic: Enables automatic editing of OCR results, which can improve accuracy for complex tables (merged cells, nested headers, etc) and tricky text (handwriting, small symbols).
When to use agentic OCR mode?
Consider using the agentic OCR mode when:- Accuracy is critical for your application, and you’re seeing small discrepancies in standard OCR.
- You’re willing to accept a small increase in processing time and cost (2x credits) for improved accuracy.
Extract mode
Theextraction_mode
parameter controls the method used for text extraction:
- ocr (default): Uses only OCR to extract text from the document.
- metadata: Uses only the document’s embedded text (if available).
- hybrid: Attempts to use the document’s embedded text first, then falls back to OCR if needed.
OCR system
For advanced users, theocr_system
parameter (in the advanced options) allows you to specify which OCR system to use:
- highres: Recommended for documents with English, Spanish, Italian, Portuguese, French, or German characters.
- multilingual: Handles documents with languages of all kinds, including the ones covered by
highres
mode. - combined: Generally not recommended, as
multilingual
mode should cover most cases.