PerfectParser Docs

Configure Fields

Review automatically detected fields, understand Text / Number / Table / Section types, and refine your parser schema.

Field setup happens in two places:

  • Create Parser — after you upload a sample, detection runs automatically. Use the Schema tab to adjust fields and the Results tab to check sample values. See Create a Parser.
  • Fields tab on a saved parser — open the parser and choose Fields (or Edit Fields from Run Extraction) to change the schema later.

Fields tab showing the extraction schema editor

The create page uses a split layout: the sample preview on the left, and parser name, description, Results, and Schema on the right.

Review and refine fields

On the create Schema tab, open a field to edit it. On the saved parser Fields tab, use the schema editor. In either place:

  • Keep it — Name, type, and instructions look correct.
  • Rename it — Use lowercase letters, numbers, and underscores.
  • Change the type — Text, Number, Table, or Section.
  • Remove it — Drop fields the sample does not need.
  • Add it — On create, click Add field. On the Fields tab, use Add Text Field, Add Number Field, Add Table, or Add Section.

Writing good field instructions

Each field has a description the AI uses at extraction time. Write plain-English guidance so the AI knows what to extract and where to find it.

For Table and Section groups, describe what the group represents (for example, One row per line item).

Too vagueClear and specific
AmountTotal invoice amount due, including VAT, in the invoice currency
DateInvoice issue date in the format shown on the document
NameFull legal name of the vendor (supplier) as printed on the invoice header
RefCustomer purchase order reference number, usually labelled "PO Number" or "Your Ref"

Field types explained

PerfectParser uses four user-friendly field types. You never need to think about JSON or technical schema terms in the dashboard.

TypeUse forExample fields
TextSingle text values — names, IDs, addresses, dates as shown on the documentinvoice_number, vendor_name, due_date
NumberSingle numeric values — amounts, quantities, counts, ratestotal_amount, tax_amount, quantity
TableRepeating rows with the same columns (like a spreadsheet table)line_items, transactions
SectionOne nested group of related fields under a single headingvendor containing name, address, and tax ID together

Text vs Number

  • Choose Text for anything that should stay as printed text (invoice numbers with letters, formatted dates, phone numbers).
  • Choose Number for values you want as numeric output — totals, prices, quantities, tax amounts.

Table vs Section

Both appear as grouped fields with child fields inside. The difference is how many times that group appears in extracted data:

TableSection
When to useData repeats on the document (many rows)One block of related fields (single group)
ExampleInvoice line items, bank transactionsA nested vendor block with name + address + tax ID
Extracted shapeA list of rowsA single grouped object

Most invoices use Table for line items. Section is optional — many parsers use flat Text fields at the root instead (for example, vendor_name, vendor_tax_id).

Add fields manually

On the saved parser Fields tab:

  • Add Text Field — Single text value (for example, po_number).
  • Add Number Field — Single numeric value (for example, total_amount).
  • Add Table — Repeating rows; define child columns inside (for example, description, quantity, unit_price).
  • Add Section — One nested group; define child fields inside.

Inside a Table or Section, use Add Field to {name} to add child columns.

On the create Schema tab, Add field starts a new field you can type and describe before you save.

Save your parser

On create, click Save parser in the bottom bar. You land on the parser Results tab.

On a saved parser, click Save Parser Configuration on the Fields tab after you change the schema.

To run more documents, open Run Extraction and choose How are your files organized? (One document per file vs One document per page).

Field setup happens when you create the parser and whenever you edit the Fields tab. File organization is configured when you run extractions — see Bulk Extraction.

On this page