Update app.py

app.py

@@ -1,3 +1,83 @@
+# import gradio as gr
+# from pix2text import Pix2Text
+# import logging
+# from PIL import Image
+
+# # Set up logging to WARNING level to suppress excessive output from model libraries
+# logging.basicConfig(level=logging.WARNING)
+
+# # Initialize Pix2Text model globally (expensive operation, do it once)
+# p2t = None
+# try:
+#     # Initialize the Pix2Text model
+#     p2t = Pix2Text()
+# except Exception as e:
+#     print(f"Error initializing Pix2Text model: {e}. Recognition will use a fallback function.")
+
+# # Define the main recognition function
+# def recognize_text(image_path: str) -> str:
+#     """
+#     Performs OCR on the uploaded image and safely parses the output.
+#     This function includes the fix for the "'str' object has no attribute 'text'" error.
+#     """
+#     if p2t is None:
+#         return (
+#             "Model initialization failed at startup. Please check the logs "
+#             "to ensure all dependencies (like ONNX runtime) loaded correctly."
+#         )
+
+#     try:
+#         # Recognize text and formulas
+#         result = p2t.recognize(image_path, save_formula_images=False, use_analyzer=True)
+
+#         extracted_parts = []
+
+#         # Loop through the result list and safely extract text from P2T objects or strings
+#         for item in result:
+#             if hasattr(item, 'text'):
+#                 # P2TOutput object (for formulas or structured text)
+#                 extracted_parts.append(item.text)
+#             elif isinstance(item, str):
+#                 # Simple text string
+#                 extracted_parts.append(item)
+#             # Ignore anything else
+
+#         extracted_text = "\n\n".join(extracted_parts)
+
+#         if not extracted_text.strip():
+#              return "No recognizable text or formulas found in the image."
+
+#         return extracted_text
+
+#     except Exception as e:
+#         # Catch any unexpected errors during the recognition process
+#         return f"An unexpected error occurred during recognition: {e}"
+
+
+# # --- Gradio Interface Setup ---
+
+# iface = gr.Interface(
+#     fn=recognize_text,
+#     # Use type="filepath" to send the local file path to the Python function
+#     inputs=gr.Image(type="filepath", label="Upload Image (Text/Formula/Math)"),
+#     # The output is a standard textbox
+#     outputs=gr.Textbox(label="Extracted Text (LaTeX/Plain Text)"),
+#     title="🔬 Pix2Text OCR Formula and Text Recognition",
+#     description=(
+#         "Upload an image containing text, mathematical formulas, or scientific notation. "
+#         "The app converts the image content into editable text, using LaTeX for formulas."
+#     ),
+#     theme=gr.themes.Soft(),
+#     allow_flagging="never",
+# )
+
+# # Launch the Gradio app
+# if __name__ == "__main__":
+#     iface.launch(show_api=False)
+
+
+
+
 import gradio as gr
 from pix2text import Pix2Text
 import logging
@@ -18,7 +98,7 @@ except Exception as e:
 def recognize_text(image_path: str) -> str:
     """
     Performs OCR on the uploaded image and safely parses the output.
-    This function includes the fix for the "'str' object has no attribute 'text'" error.
+    This function includes debugging to understand the result structure.
     """
     if p2t is None:
         return (
@@ -30,28 +110,64 @@ def recognize_text(image_path: str) -> str:
         # Recognize text and formulas
         result = p2t.recognize(image_path, save_formula_images=False, use_analyzer=True)
 
-        extracted_parts = []
-
-        # Loop through the result list and safely extract text from P2T objects or strings
-        for item in result:
-            if hasattr(item, 'text'):
-                # P2TOutput object (for formulas or structured text)
-                extracted_parts.append(item.text)
-            elif isinstance(item, str):
-                # Simple text string
-                extracted_parts.append(item)
-            # Ignore anything else
+        # DEBUG: Print the actual result structure
+        print(f"DEBUG - Result type: {type(result)}")
+        print(f"DEBUG - Result content: {result}")
+        
+        # Handle different possible return types
+        if isinstance(result, str):
+            # If result is directly a string
+            return result if result.strip() else "No recognizable text or formulas found in the image."
+        
+        if isinstance(result, dict):
+            # If result is a dictionary, try to extract text from common keys
+            print(f"DEBUG - Result keys: {result.keys()}")
+            possible_keys = ['text', 'content', 'result', 'output']
+            for key in possible_keys:
+                if key in result:
+                    return str(result[key])
+            return f"Result is a dict but couldn't find text. Keys: {list(result.keys())}"
+        
+        if isinstance(result, list):
+            # If result is a list, process each item
+            extracted_parts = []
+            
+            for i, item in enumerate(result):
+                print(f"DEBUG - Item {i} type: {type(item)}")
+                print(f"DEBUG - Item {i} content: {item}")
+                
+                if hasattr(item, 'text'):
+                    # P2TOutput object (for formulas or structured text)
+                    extracted_parts.append(item.text)
+                elif isinstance(item, str):
+                    # Simple text string
+                    extracted_parts.append(item)
+                elif isinstance(item, dict):
+                    # Dictionary with text content
+                    if 'text' in item:
+                        extracted_parts.append(item['text'])
+                    elif 'content' in item:
+                        extracted_parts.append(item['content'])
+                    else:
+                        extracted_parts.append(str(item))
+                else:
+                    # Try to convert to string as fallback
+                    extracted_parts.append(str(item))
 
-        extracted_text = "\n\n".join(extracted_parts)
+            extracted_text = "\n\n".join(extracted_parts)
 
-        if not extracted_text.strip():
-             return "No recognizable text or formulas found in the image."
+            if not extracted_text.strip():
+                return "No recognizable text or formulas found in the image."
 
-        return extracted_text
+            return extracted_text
+        
+        # If none of the above, try to convert to string
+        return str(result) if result else "No recognizable text or formulas found in the image."
 
     except Exception as e:
         # Catch any unexpected errors during the recognition process
-        return f"An unexpected error occurred during recognition: {e}"
+        import traceback
+        return f"An unexpected error occurred during recognition: {e}\n\nTraceback:\n{traceback.format_exc()}"
 
 
 # --- Gradio Interface Setup ---
@@ -61,7 +177,7 @@ iface = gr.Interface(
     # Use type="filepath" to send the local file path to the Python function
     inputs=gr.Image(type="filepath", label="Upload Image (Text/Formula/Math)"),
     # The output is a standard textbox
-    outputs=gr.Textbox(label="Extracted Text (LaTeX/Plain Text)"),
+    outputs=gr.Textbox(label="Extracted Text (LaTeX/Plain Text)", lines=10),
     title="🔬 Pix2Text OCR Formula and Text Recognition",
     description=(
         "Upload an image containing text, mathematical formulas, or scientific notation. "