Nanonets · Arazzo Workflow

Nanonets Predict Correct and Re-export

Version 1.0.0

Predict on a file, correct its extracted fields, and retry the export.

1 workflow 3 source APIs 1 provider
View Spec View on GitHub Artificial IntelligenceOCRDocument AIIntelligent Document ProcessingData ExtractionWorkflow-AutomationComputer-VisionNo-CodeArazzoWorkflows

Provider

nanonets

Workflows

predict-correct-and-reexport
Predict, correct extracted fields, and retry the downstream export.
Runs a sync prediction, patches the file's fields with corrected values, and retries the export for the file.
3 steps inputs: authorization, correctedFields, file, modelId outputs: exportResponse, requestFileId, updateResponse
1
predict
Run a synchronous OCR prediction on the uploaded file.
2
updateFields
Patch the file with corrected field values. use_ui_version=true is required and the body mirrors the prediction response structure.
3
retryExport
Re-trigger the downstream export for the corrected file.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Nanonets Predict Correct and Re-export
  summary: Predict on a file, correct its extracted fields, and retry the export.
  description: >-
    A correction-and-export loop for downstream integrations. The workflow runs a
    sync OCR prediction on a file, applies a corrected field payload (derived from
    the prediction structure) back onto the file, and then re-triggers the
    downstream export for that file. Every step spells out its request inline so
    the flow can be read and executed without opening the underlying OpenAPI
    description.
  version: 1.0.0
sourceDescriptions:
- name: fileExportApi
  url: ../openapi/nanonets-file-export-api-openapi.yml
  type: openapi
- name: fileUpdateApi
  url: ../openapi/nanonets-file-update-api-openapi.yml
  type: openapi
- name: ocrPredictApi
  url: ../openapi/nanonets-ocr-predict-api-openapi.yml
  type: openapi
workflows:
- workflowId: predict-correct-and-reexport
  summary: Predict, correct extracted fields, and retry the downstream export.
  description: >-
    Runs a sync prediction, patches the file's fields with corrected values, and
    retries the export for the file.
  inputs:
    type: object
    required:
    - authorization
    - modelId
    - file
    - correctedFields
    properties:
      authorization:
        type: string
        description: HTTP Basic credential header value (Basic <base64 of apiKey:>).
      modelId:
        type: string
        description: Unique identifier for the Nanonets OCR model.
      file:
        type: string
        description: Binary contents of the document to run OCR against.
      correctedFields:
        type: object
        description: >-
          Corrected field payload mirroring the structure returned by the file
          prediction, used to update or add fields on the file.
  steps:
  - stepId: predict
    description: Run a synchronous OCR prediction on the uploaded file.
    operationId: ocrModelLabelFileByModelIdPost
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: model_id
      in: path
      value: $inputs.modelId
    requestBody:
      contentType: multipart/form-data
      payload:
        file: $inputs.file
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      requestFileId: $response.body#/result/0/request_file_id
  - stepId: updateFields
    description: >-
      Patch the file with corrected field values. use_ui_version=true is required
      and the body mirrors the prediction response structure.
    operationId: updateFileFields
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: model_id
      in: path
      value: $inputs.modelId
    - name: use_ui_version
      in: query
      value: true
    requestBody:
      contentType: application/json
      payload: $inputs.correctedFields
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      updateResponse: $response.body
  - stepId: retryExport
    description: Re-trigger the downstream export for the corrected file.
    operationId: retryAllExports
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: model_id
      in: path
      value: $inputs.modelId
    requestBody:
      contentType: application/json
      payload:
        file_ids:
        - $steps.predict.outputs.requestFileId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      exportResponse: $response.body
  outputs:
    requestFileId: $steps.predict.outputs.requestFileId
    updateResponse: $steps.updateFields.outputs.updateResponse
    exportResponse: $steps.retryExport.outputs.exportResponse

Work with this as data

Every workflow here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for arazzo workflows

4 MCP tools reach this
  • find_arazzoBrowse and filter every workflow in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This workflow
curl "https://apis.io/api/v1/arazzo/nanonets-predict-correct-and-reexport-workflow"
All arazzo workflows
curl "https://apis.io/api/v1/arazzo?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.