Doc AI Classification

Identify what a document is before deciding what to do with it.

Classification identifies a document type before routing it for extraction. Use it when a file arrives without a reliable label.

/classify/sync returns the result in the response. /classify returns a job ID. /classify/bulk processes a set of files.

Use the resulting type as documentType in an extraction request.

Endpoint reference

Use the generated endpoint reference for complete schemas and responses:

• Synchronous document classification

• Get classification details

Use the generated reference navigation for asynchronous and bulk classification.

A ZIP upload is classified per member document. Results include classificationGroupId, classificationGroupIndex, and classificationGroupTotal. Use these fields to reassemble the set. PDF and Excel classifications do not include them.

For categories, confidence behavior, and product review workflows, see Document Classification.

Related pages

• Document Classification — classify documents in the UI.

• Document Types — the classifier’s document-type registry.

• Classify, then extract — a routing recipe.

• Extraction API — submit classified documents for extraction.