Amazon Textract announces Bulk Document Uploader to test Textract on multiple documents
Amazon Textract is a machine learning service that automatically extracts text, handwriting, and data from any document or image. Today, we’re excited to announce the launch of Bulk Document Uploader feature in the Textract Console that enables customers to quickly evaluate the capabilities of Textract on their own set of documents without writing any code.
Amazon Textract is a machine learning service that automatically extracts text, handwriting, and data from any document or image. Today, we’re excited to announce the launch of Bulk Document Uploader feature in the Textract Console that enables customers to quickly evaluate the capabilities of Textract on their own set of documents without writing any code.
Bulk Document Uploader supports processing of up to 150 documents per request using DetectDocumentText API, AnalyzeDocument API, or AnalyzeExpense API. Customers can submit documents for processing via an existing S3 bucket or upload documents directly from their computer. The output of the Bulk Document Uploader are zip files containing both the standard Textract JSON response and a human readable CSV file with confidence scores for simple evaluation of the results. Output results are available to download for 7 days after processing. AWS charges standard Textract usage rates for using the Bulk Document Uploader.
The Textract Bulk Document Uploader will be available in US East (N. Virginia), US East (Ohio), US West (Northern California), US West (Oregon), Canada (Central), Europe (London), Europe (Paris), Europe (Ireland), Europe (Frankfurt), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Seoul), Asia Pacific (Mumbai), AWS GovCloud (US-East), and AWS GovCloud (US-West) Regions starting April 3rd, 2023.
To get started, log on to the Textract console to try out the new feature. To learn more about Textract capabilities, please visit the Amazon Textract website, developer guide, or resources page.