Document_extarctor
This tool is an intelligent document parser that extracts structured data from invoice images using OCR and layout-aware analysis. It automatically identifies key fields such as invoice details, sender and recipient information, itemized charges, totals, and payment terms—without requiring a predefined schema. The output is a clean, well-structured JSON with dates in ISO format and numerical values as numbers. It filters out irrelevant or decorative text, handles missing fields with null, and ensures accuracy by understanding the visual and contextual layout of the invoice.
