Extractions API
The Extractions API provides access to structured data produced by the extraction pipeline. List results, retrieve row-level data with provenance, and submit corrections.
Endpoints
GET /v1/extractions
List all extractions with pagination and filtering.
GET /v1/extractions/:id
Retrieve metadata for a single extraction.
GET /v1/extractions/:id/data
Get structured row data with per-cell provenance.
PATCH /v1/extractions/:id/data
Submit corrections to extracted values.
How extractions work
An extraction is created when you call the extract endpoint or re-extract a document. The four-phase pipeline processes the document and produces structured rows. Each cell includes a confidence score and per-cell provenance linking it to the source region. The Field Registry resolves field names to canonical entries.