AWS Textract#
AWS Textract is a service that extracts printed text, handwriting, and data from any document.
Credentials
You can find authentication information for this node here.
Basic Operations#
- Analyze Receipt or Invoice
Example Usage#
This workflow allows you to extract data from a an invoice stored in AWS S3. You can also find the workflow on n8n.io. This example usage workflow uses the following nodes. - Start - AWS S3 - AWS Textract
The final workflow looks like the following image.
1. Start node#
The start node exists by default when you create a new workflow.
2. AWS S3 node (download: file)#
This node will retrieve an image file with a receipt from an S3 bucket.
- Choose your credentials for the AWS S3 node. See here for information on how to create these credentials.
- Enter the bucket name in the Bucket Name field.
- Enter the file key in the File Key field.
- Click on Execute Node to run the node.
In the screenshot below you can see the file returned by the node.
3. AWS Textract node (analyzeExpense)#
This node will extract data from the receipt returned by the previous node.
- Choose your AWS credentials.
- Click on Execute Node to run the node.
In the screenshot below, you can see the receipt data extracted by AWS Textract and returned by the node.