docs: Example on how to apply external OCR as post processing (#2517)

* Example on how to apply to Docling Document OCR as a post-processing with "nanonets-ocr2-3b" via LM Studio

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added support of elements with multiple provenances

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* cleaning up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* improved prompt for nanonets-ocr2-3b

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* cleaning up

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* excluded example from CI

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* updated class name

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Improved usability of the example, added simple cli, and some helper functions

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Fix api_image_request usage

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix pydantic errors

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Improvements and corrections

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added string sanitation, removing break lines from remote OCR, also preserving original text from json

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Added quick and reliable detection of empty image crops (elements, table cells, form items), these are not sent to OCR

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* Example respects ocr_documents.txt, tuned empty crop detection

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

* cleaning api_image_request

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>

---------

Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Co-authored-by: Maksym Lysak <mly@zurich.ibm.com>
Co-authored-by: Christoph Auer <cau@zurich.ibm.com>