extract
Extracts structured data from the document, shaped to the JSON Schema carried by the 's {"schema": ...} envelope. The document is first read by the extraction pipeline selected by , then an AI model fills the schema from the recognized content. Provider, model, endpoint, and confidence reporting are driven by AiProcessingSettings on the document's settings.
Return
A JSON string with two top-level nodes: extraction (the schema-shaped extracted fields) and metadata (per-field source locations and grounding labels).
Parameters
request
The extraction request carrying the schema envelope (required) and optional instructions.