Module docs 

Document understanding types and traits — VLM-based extraction and OCR.

Structs

DocBlock

One block within a DocExtractResult.

DocExtractOptions

Options for a DocumentExtractionModel::extract call.

DocExtractResult

Per-page result of a document extraction call.

OcrBlock

One text region within an OcrResult.

OcrResult

Per-image result of an OCR call.

Enums

DocBlockKind

Kind of block returned by a DocumentExtractionModel.

DocOutputFormat

Output format for the in-block content string of DocBlock.

Traits

DocumentExtractionModel

A vision-language model that extracts structured blocks from document page images.

OcrModel

A model that recognizes text in images (optical character recognition).