Document Processing
The document processing action steps enable you to extract data from documents and translate text by using the Amazon Translate and Amazon Textract services.
Action steps that use Amazon Textract services process the document in a synchronous fashion, therefore Amazon does not store the document. These action steps automatically convert PDF files to PNG images. You can adjust the fidelity of the conversion in the properties grid of the action step.
To use these action steps, you need an active subscription to AWS.
-
The Credentials for AWS action step enables you to set up your AWS credentials one time and then reference them in any other AWS action step that requires them.
-
The Entities with AWS action step enables you to use Amazon Comprehend to inspect text for named entities and return information about them.
-
The ERP Docs with AWS enables you to use Amazon Textract to analyze invoices and receipts to extract relevant data.
-
The Key values with AWS action step enables you to extract form data by sending a local file to the AWS Textract service, which returns the extracted key-value pairs.
-
The OCR with AWS action step enables you to recognize the text in a document by sending a local file to the AWS Textract service, which returns the extracted values.
-
The Queries with AWS Action Step enables you to extract specific data from a document by specifying a query parameter so that the response contains the data you need, without having to apply further filtering on the JSON output to get the relevant values.
-
The Tables with AWS action step enables you to recognize the text values inside a table by sending a local file to the AWS Textract service, which returns the extracted values.
-
The translate with AWS action step enables you to use the Amazon Translate service to translate the specified text.