feat: migrate document_loaders from rapidocr_onnxruntime to rapidocr

libs/community/langchain_community/document_loaders/parsers/images.py

@@ -99,18 +99,18 @@ def _analyze_image(self, img: "Image") -> str:
         """
         if not self.ocr:
             try:
-                from rapidocr_onnxruntime import RapidOCR
+                from rapidocr import RapidOCR
 
                 self.ocr = RapidOCR()
             except ImportError:
                 raise ImportError(
-                    "`rapidocr-onnxruntime` package not found, please install it with "
-                    "`pip install rapidocr-onnxruntime`"
+                    "`rapidocr` package not found, please install it with "
+                    "`pip install rapidocr`"
                 )
-        ocr_result, _ = self.ocr(np.array(img))  # type: ignore[misc]
+        ocr_result = self.ocr(np.array(img))  # type: ignore[misc]
         content = ""
-        if ocr_result:
-            content = ("\n".join([text[1] for text in ocr_result])).strip()
+        if ocr_result and ocr_result.txts:
+            content = ("\n".join(ocr_result.txts)).strip()
         return content
 
 

libs/community/langchain_community/document_loaders/parsers/pdf.py

@@ -73,22 +73,21 @@ def extract_from_images_with_rapidocr(
         Text extracted from images.
 
     Raises:
-        ImportError: If `rapidocr-onnxruntime` package is not installed.
+        ImportError: If `rapidocr` package is not installed.
     """
     try:
-        from rapidocr_onnxruntime import RapidOCR
+        from rapidocr import RapidOCR
     except ImportError:
         raise ImportError(
-            "`rapidocr-onnxruntime` package not found, please install it with "
-            "`pip install rapidocr-onnxruntime`"
+            "`rapidocr` package not found, please install it with "
+            "`pip install rapidocr`"
         )
     ocr = RapidOCR()
     text = ""
     for img in images:
-        result, _ = ocr(img)
-        if result:
-            result = [text[1] for text in result]
-            text += "\n".join(result)
+        result = ocr(img)
+        if result and result.txts:
+            text += "\n".join(result.txts)
     return text