Document Parser
Document Parser Overview
Document Parser can automatically parse PDF, JPG, and PNG documents to extract fields, tables, values, and barcodes from invoices, statements, orders, and other PDF and scanned documents.
Built-in document parser templates
General Invoice Template
can parse invoices (English only) to invoice id, invoice date, extract total, tax, and line items. Set the templateId
parameter to 1
to use this template.
How to classify incoming documents before parsing them?
Use the /pdf/classifier endpoint (see below) to automatically sort/detect the class of the document based on AI or on custom keywords-based rules.
For example, you can easily define rules to find which vendor provided the document to find which template to apply accordingly. See Document Classifier for more details.