Skip to content
FREE TEMPLATE

Document extraction schema

Define the meaning, checks and source for each field to extract.

What you’ll prepare

A schema with fields, validation, evidence and missing-data handling.

When to use it

Before extracting document data for business systems.

Fill in the fields below and download your document. The website does not send or save answers: closing the page may lose them. Examples are illustrative and should be replaced with your process data.

Download the complete blank template (.md)

1. Define document and destination

Separate document families that use the same labels with different meanings. Describe the output needed by the process instead of collecting every available detail.

See a worked example

Illustrative example: extract a supplier order confirmation to compare with the original purchase order. Do not treat a quotation as confirmation merely because it contains codes and prices.

List included documents, languages, scans, attachments and versions requiring exclusion or separate handling.

Explain which system receives the data and which decisions or actions depend on it.

Define stable reference, version and how lines, pages and duplicate documents are distinguished.

2. Specify the fields

Complete one entry per field. Distinguish information present in the document from values calculated using an explicit, verifiable rule.

See a worked example

Illustrative example: “delivery_date” means a date explicitly assigned to delivery, not document issue. If the document says “to be agreed”, leave it empty and record why.

Describe field, type and when it is required; clarify ambiguous labels such as date or total.

Specify date format, currency, separators, units and allowed transformations while preserving the original value.

Require a page or text reference; define the result when a field is absent or ambiguous.

3. Check before use

Combine deterministic checks with review of ambiguities. Do not silently correct amounts or identifiers just to pass validation.

See a worked example

Illustrative example: quantity multiplied by unit price differs from the line total. Preserve both values and request review instead of inventing a discount to explain the difference.

List formats, total consistency, master-data matches and rules with explicit tolerances.

Define critical fields, conflicts and unreadable documents that must stop a write.

Prepare ordinary, missing and conflicting examples with results verified by someone familiar with the documents.

Pitfalls to avoid

Check before using it
  • Using a field name without defining its operational meaning.
  • Filling missing information with plausible guesses.
  • Treating valid JSON as proof that the extracted data is correct.

Let’s discuss your project.

Review the text before sending. Only your email is needed alongside the message; other details are optional.