StructuredExtractionRequest

Describes a structured data extraction request for . Carries a schema envelope — {“schema”: } — describing the fields the extracted data must conform to, and optional free-form instructions that steer the extraction.

The envelope’s schema member is a standard JSON Schema object — typically an object root whose properties carry a description telling the extractor what to put there. The envelope shape matches what schema generation produces, so a generated result can be passed straight through; an envelope constraints member is accepted and reserved for future post-extraction validation (it is not evaluated yet). Provider, model, endpoint, and confidence reporting are controlled separately via AiProcessingSettings on the document’s settings.

from nutrient_sdk import StructuredExtractionRequest

Construction

StructuredExtractionRequest()

Creates a new StructuredExtractionRequest instance with default settings.

Properties

instructions

@property
def instructions(self) -> str

@instructions.setter
def instructions(self, value: str) -> None

Optional natural-language instructions that steer the extraction: disambiguation rules, formatting preferences, or domain context — anything you’d tell a colleague doing the extraction by hand.

Type: str

schema

@property
def schema(self) -> str

@schema.setter
def schema(self, value: str) -> None

The schema envelope as a JSON string: {“schema”: }. Required. The inner schema describes the fields to extract; each property’s description tells the extractor what belongs there. An envelope constraints member is accepted and reserved for future post-extraction validation.

Type: str