Skip to main content
A field represents one piece of information inside a schema. Examples:
  • Invoice number
  • Issue date
  • Total amount
  • Vendor name
Fields are the most important part of data quality. Clear fields lead to better results and less review. Fields panel

​
The three field properties

Every field has at least three properties.
A human-readable label that still makes sense outside anyformat.Examples: invoice_number, issue_date, total_amount.Use snake_case so the name is safe to use as a JSON key or column header.
Tells anyformat what kind of value to expect (text, date, number, etc.).The type improves consistency, validation, and output quality. See Field types for the full list.
Plain-English guidance for how to extract the value.Example: “Extract the final total including taxes. Ignore subtotals.”See Instructions for how to write good ones.
Field properties

​
Field source — extraction vs. smart lookup

Every field also has a source that tells anyformat where its value comes from:
  • Extraction (default) — the value is read directly from the document.
  • Smart lookup — the value is resolved by matching the document against a reference file you attach (a CSV/catalog), instead of being read off the page. For example, extract a free-text vendor_name from the document, then smart-lookup the canonical vendor_id from your vendor catalog.
A smart-lookup field lives in the same schema as your extraction fields — you just mark it as a lookup field and attach the reference file to the extract step. See Create Workflow for the API shape.

​
What’s next?

Field types

The full list of types — text, date, number, object, enum, multi-select

Instructions

Write effective extraction instructions