capabilities.work

Digitize, Classify, and Extract a Document

A 5-step recipe with UiPath. We can help you get access.

Recipe · 5 steps

Digitize, Classify, and Extract a Document

with UiPath

Digitize a document, then classify and extract it with async polling.

  1. Submit the document for digitization to obtain the document ID used by the classification and extraction steps.
  2. Start an asynchronous classification job for the digitized document and capture the request ID for polling.
  3. Retrieve the classification result by its request ID. Loop back while the job is still NotStarted or Running; otherwise continue to extraction.
  4. Start an asynchronous extraction job for the digitized document using the supplied document type and capture the request ID for polling.
  5. Retrieve the extraction result by its request ID. Loop back while the job is still NotStarted or Running; otherwise record the final result.
What you'll need to have ready
  • projectId: Unique identifier of the Document Understanding project.
  • documentBase64: Base64-encoded document content to digitize.
  • contentType: MIME type of the document (e.g. image/jpeg, application/pdf).
  • documentTypeId: Document type identifier to apply during extraction.
For your developer

Arazzo workflow uipath:digitize-classify-extract, 5 operations: digitizeDocument → classifyDocumentAsync → getClassificationResult → extractDocumentAsync → getExtractionResult. Specs on APIs.io.

More recipes with UiPath

Add and Track a Queue ItemAsset LifecycleBootstrap a Test ProjectFind and Remove a WebhookDiscover Extractors and Extract a DocumentData Service Entity Record LifecycleFleet Readiness AuditProvision a Credential AssetProvision a Queue and Add an ItemRegister a Job Event Webhook