From e30a703759b5c427b1c3cc79395f47e524fd3ebe Mon Sep 17 00:00:00 2001
From: jimkarag02 <112767673+jimkarag02@users.noreply.github.com>
Date: Wed, 14 May 2025 16:05:52 +0300
Subject: [PATCH] fix(ocr): orig field in TesseractOcrCliModel as str (#1553)

fix: ensure orig and text are both strings in TesseractOcrCliModel

Signed-off-by: Dimitris Karagatslis <dimo9.dk@gmail.com>
Signed-off-by: Nikhil Khandelwal <nikhil.khandelwal3@ibm.com>
---
 docling/models/tesseract_ocr_cli_model.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docling/models/tesseract_ocr_cli_model.py b/docling/models/tesseract_ocr_cli_model.py
index 91b4555f..33ca0c10 100644
--- a/docling/models/tesseract_ocr_cli_model.py
+++ b/docling/models/tesseract_ocr_cli_model.py
@@ -249,7 +249,7 @@ class TesseractOcrCliModel(BaseOcrModel):
                             cell = TextCell(
                                 index=ix,
                                 text=str(text),
-                                orig=text,
+                                orig=str(text),
                                 from_ocr=True,
                                 confidence=conf / 100.0,
                                 rect=BoundingRectangle.from_bounding_box(