We are upgrading our data extraction capabilities. We're adding support for documents in Japanese, Chinese, Korean, and Cyrillic script, making our tools more powerful for international customers.
Additionally, we now support TIFF, PNG, and JPEG image files. This unlocks new use cases by streamlining the scanning workflow: previously, extracting data from a scan required you to first convert it into a PDF. With our new file format support, you can now scan and extract data immediately, no conversion needed.
These powerful new capabilities are available for the Extract Structured API and supported for Extract Agents used via the Autofill button in Box Preview. The upgrade is automatic for all customers, with no action required on your part to begin using these new features. It's important to note that these enhancements apply specifically to the structured extract endpoint for both standard and enhanced extraction models.
The enhancements are designed to save your team time, enable more use cases, and empower your business to operate more effectively on a global scale.