Skip to main content
Nodes used: Parse, Extract This example reads an invoice and returns its header fields plus every line item as a structured row. One object field captures the line-item table, so each row carries its own values, confidence and evidence.

The workflow

Run it and read the result

Upload the invoice, then poll the run until its status is processed. The results arrive inline on that same read.

Response

The results envelope of a processed run, trimmed to the interesting fields. Every scalar field carries value, confidence, evidence, verification_status and value_override; the line_items rows repeat that shape per cell.

Tips

  • Write specific field descriptions. “Final total amount due including tax” extracts better than “total”.
  • Numbers arrive as strings in the JSON body ("4594.62"). Cast them with the type you declared.
  • List every currency you expect in enum_options. An enum constrains the output to those names.
  • Multi-page invoices need no configuration. The evidence page_number tells you where each value came from.
  • To check that subtotal + tax_amount = total_amount, add a Validate node with an arithmetic rule. See Contract analysis for a graph with validation.

Next steps

Field types

Object, enum and the other field shapes

Runs and results

Every section of the results envelope