Extraction Details

Deeper notes on how extractions are configured and what fields you get back.

Field definition

Each field in the fields array supports these properties:

Property	Type	Required	Notes
`key`	string	yes	Unique field identifier returned in the extracted JSON.
`description`	string	no	Tells the model what to look for. More detail = better accuracy.
`example`	string	no	Shown to the model as a formatting hint, not enforced.

json

{
  "key": "invoice_number",
  "description": "The unique invoice ID from the seller.",
  "example": "INV-2026-00128"
}

Field examples

Adding a one-line example to each field dramatically improves accuracy. The example is shown to the model as a hint, not enforced.

Language

Set language at the extraction level. Options:

"Multi-Lingual" (default) — auto-detect per document.
"English", "French", "German", "Spanish", "Hindi", "Japanese", "Chinese (Simplified)", and more.

Forcing a language gives a small accuracy bump on borderline-quality scans.

Document Options

Per-extraction toggles that influence parsing behavior:

Option	Effect
`ocr_priority`	When `true`, treat the document as scanned (skip text-layer extraction). Useful for low-quality PDFs.
`infer_missing`	Allow the model to infer fields that aren't explicitly written (e.g. `total = subtotal + tax`).
`strict_format`	Reject documents that don't match the expected layout. Returns `status: needs_review` instead.

Confidence scores

Every extracted field comes back with a confidence value in [0, 1]. Treat anything below 0.7 as needing human review.

json

{
  "result": { "total_amount": 4108.26 },
  "confidence": { "total_amount": 0.98 }
}

`needs_review` status

A file lands in needs_review when at least one field has confidence below your configured threshold (defaults to 0.7). The result is still available — but you should surface it in your UI for a human to double-check.

Resubmitting

To re-process documents after editing the schema, call PATCH /api/v1/updateExtraction to update the field definitions and optionally upload new files in the same request. Existing batches are not automatically re-processed — upload files again via POST /api/v1/uploadFiles to create a new batch. Pages are charged again.