Loading...
Found 1 Skills
Two primitives of the Nutrient Data Extraction API. `parse` (`/extraction/parse`) returns the whole-document model — a structural JSON of typed elements with bounding boxes, or whole-document Markdown — for RAG ingestion, search indexing, content migration, or layout-aware understanding. `extract` (`/extraction/extract`) returns just the fields you define in a JSON Schema, each with a per-field citation grounding it to a page region. Route to `extract` for "pull the invoice number and total", "extract these fields", "map to my schema", or "with citations"; route to `parse` for "parse this document", "whole-document Markdown", "chunk for embeddings", or "extract every table/element" (no target schema). Triggers include parse this document, extract layout, RAG pipeline, schema extraction, field extraction, cited fields, invoice/form field extraction, document understanding.