feat(ocr): added support for RapidOCR engine (#415)

* adding rapidocr engine for ocr in docling

Signed-off-by: swayam-singhal <swayam.singhal@inito.com>

* fixing styling format

Signed-off-by: Swaymaw <swaymaw@gmail.com>

* updating pyproject.toml and poetry.lock to fix ci bugs

Signed-off-by: Swaymaw <swaymaw@gmail.com>

* help poetry pinning for python3.9

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* simplifying rapidocr options so that device can be changed using a single option for all models

Signed-off-by: Swaymaw <swaymaw@gmail.com>

* fix styling issues and small bug in rapidOcrOptions

Signed-off-by: Swaymaw <swaymaw@gmail.com>

* use default device until we enable global management

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: swayam-singhal <swayam.singhal@inito.com>
Signed-off-by: Swaymaw <swaymaw@gmail.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: swayam-singhal <swayam.singhal@inito.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>

docling/cli/main.py

@@ -27,6 +27,7 @@ from docling.datamodel.pipeline_options import (
     OcrMacOptions,
     OcrOptions,
     PdfPipelineOptions,
+    RapidOcrOptions,
     TableFormerMode,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
@@ -76,6 +77,7 @@ class OcrEngine(str, Enum):
     TESSERACT_CLI = "tesseract_cli"
     TESSERACT = "tesseract"
     OCRMAC = "ocrmac"
+    RAPIDOCR = "rapidocr"
 
 
 def export_documents(
@@ -262,6 +264,8 @@ def convert(
         ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
     elif ocr_engine == OcrEngine.OCRMAC:
         ocr_options = OcrMacOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.RAPIDOCR:
+        ocr_options = RapidOcrOptions(force_full_page_ocr=force_ocr)
     else:
         raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")