> For the complete documentation index, see [llms.txt](https://docs.facephi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.facephi.com/docs.facephi-en/sdks/backend-sdk/ocr/release_notes/2.7.0_release_notes.md).

# 2.7.0

In this Version, PDF processing has been improved in the OCR engine. In addition, the licensing backend has been improved, incorporating high availability, and the facephi-recognition library.

### Added

* PDF: the default threshold is reduced to 0.5 to improve text detection.
* PDF: the optional parameter is added `pageNums`. It is a list of page numbers to be processed. Numbering starts at 1. If not specified, all pages will be processed.
* PDF: the "page not parsed" errors are ignored on the 2nd page and beyond.
* PDF: the output is added `warnings`. This field contains information about pages that have not been processed. In the future, it could be expanded to include other types of information.
* text-interpreter update:
  * PDF: the model fields are included even if they are not detected or are empty.
* document-reader-sdk-templates update
  * PDF: the IVA.json and RENTA.json models correctly process multi-word fields.
* Licensing backend Version 2.0.0 update.
  * High availability is added.
* Update of facephi-recognition v3.21.0