capabilities.work

Predict Correct and Re-export

A 3-step recipe with Nanonets. We can help you get access.

Recipe · 3 steps

Predict Correct and Re-export

with Nanonets · Artificial Intelligence Management

Predict, correct extracted fields, and retry the downstream export.

  1. Run a synchronous OCR prediction on the uploaded file.
  2. Patch the file with corrected field values. use_ui_version=true is required and the body mirrors the prediction response structure.
  3. Re-trigger the downstream export for the corrected file.
What you'll need to have ready
  • authorization: HTTP Basic credential header value (Basic <base64 of apiKey:>).
  • modelId: Unique identifier for the Nanonets OCR model.
  • file: Binary contents of the document to run OCR against.
  • correctedFields: Corrected field payload mirroring the structure returned by the file prediction, used to update or add fields on the file.
For your developer

Arazzo workflow nanonets:predict-correct-and-reexport, 3 operations: ocrModelLabelFileByModelIdPost → updateFileFields → retryAllExports. Specs on APIs.io.

More recipes with Nanonets

Async OCR Predict and PollAsync URL Predict Poll and ApproveBatch Review Pending FilesClassify Image and BranchPage-Level Correct and ApprovePredict and Assign ReviewerPredict and Enrich with DatabaseResolve Integration and QuerySync Predict and ReviewUpload Training Images and Train