This example workflow illustrates how to configure an automatic invoice processing solution using Amazon Textract through the integration of KNIME and Boto3. In process, it automatically backs up invoice/receipt images to the AWS cloud, analyzes the document, and extracts specific information such as vendor name, price and invoice number. Users are able to upload invoice images from their local environment with Amazon S3 Connector, and analyze the documents with Amazon Textract through Boto3 SDK leveraging the KNIME Python Script node. The Amazon Textract output is post-processed in KNIME and then delivered into different channels. This workflow follows the example of the blog article, How to use Boto3 in KNIME. See the link below to the specific article. Note: In order to use this workflow in your own environment, follow along with the annotations in the workflow. Also, in order to use the AWS services, you will also need to have AWS credentials to authenticate with the Amazon Authentication node.
This is a companion discussion topic for the original entry at https://kni.me/w/S2JuWTCapDE9aGfN