From 6796f0a13263281cd48712b3c71579bfd81bb0d1 Mon Sep 17 00:00:00 2001
From: fanszoro <fansluck@qq.com>
Date: Thu, 20 Feb 2025 22:41:41 +0800
Subject: [PATCH] fix: Runtime error when Pandas Series is not always of string
 type (#1024)

Signed-off-by: fan <fansluck@qq.com>
---
 docling/models/tesseract_ocr_cli_model.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/docling/models/tesseract_ocr_cli_model.py b/docling/models/tesseract_ocr_cli_model.py
index cdc5671..ac8dd51 100644
--- a/docling/models/tesseract_ocr_cli_model.py
+++ b/docling/models/tesseract_ocr_cli_model.py
@@ -114,7 +114,9 @@ class TesseractOcrCliModel(BaseOcrModel):
         # _log.info("df: ", df.head())
 
         # Filter rows that contain actual text (ignore header or empty rows)
-        df_filtered = df[df["text"].notnull() & (df["text"].str.strip() != "")]
+        df_filtered = df[
+            df["text"].notnull() & (df["text"].apply(str).str.strip() != "")
+        ]
 
         return df_filtered