Ocrolus
A document-extraction vendor, integrated for document classification and field extraction.
Ocrolus reads uploaded documents and returns structured fields. It is one of several extraction vendors integrated for the same document types, which is what makes the scorecard in Document meaningful — accuracy and cost per vendor per document type, measured on real documents rather than asserted.
Because the scorecard is an API rather than a report, routing can consume it: a document type where one vendor measures better is a decision the pipeline makes.
Products it serves
How this integration is built
- connection configuration
- The wire protocol. One repository per vendor API call, not per vendor.
- language configuration
- The field mapping between the vendor's vocabulary and the canonical model.
- flow file
- The four-way translation: canonical request, vendor request, vendor response, canonical response.
- waterfall priority
- One line naming where this vendor sits in the vertical's ordering.
- status call
- Activating the vendor for a lender, optionally with the lender's own credentials.
Evidence
This vendor is on the roster because each of the following resolves to a committed artifact.
ocrolus-partner-data