Update ocr_cpu.py

Error during text extraction: eval() arg 1 must be a string, bytes or code object , Fixing this error

ocr_cpu.py

@@ -21,19 +21,20 @@ model = AutoModel.from_pretrained(
 # Ensure the model is in evaluation mode and loaded on CPU
 device = torch.device("cpu")
 dtype = torch.float32  # Use float32 on CPU
-model = model.eval()
+model = model.eval().to(device)
 
 # OCR function
-
-
 def extract_text_got(uploaded_file):
     """Use GOT-OCR2.0 model to extract text from the uploaded image."""
+    temp_file_path = 'temp_image.jpg'
+    
     try:
-        temp_file_path = 'temp_image.jpg'
+        # Save the uploaded file temporarily
         with open(temp_file_path, 'wb') as temp_file:
-            temp_file.write(uploaded_file.read())  # Save file
+            temp_file.write(uploaded_file.read())
+
+        print(f"Processing image from path: {temp_file_path}")  # Debug info
 
-        # OCR attempts
         ocr_types = ['ocr', 'format']
         fine_grained_options = ['ocr', 'format']
         color_options = ['red', 'green', 'blue']
@@ -42,12 +43,15 @@ def extract_text_got(uploaded_file):
 
         results = []
 
-        # Run the model without autocast (not necessary for CPU)
+        # Run basic OCR types
         for ocr_type in ocr_types:
             with torch.no_grad():
-                outputs = model.chat(
-                    tokenizer, temp_file_path, ocr_type=ocr_type
-                )
+                print(f"Running basic OCR with type: {ocr_type}")  # Debug info
+                outputs = model.chat(tokenizer, temp_file_path, ocr_type=ocr_type)
+                
+                # Debug outputs
+                print(f"Outputs for {ocr_type}: {outputs}")
+                
                 if isinstance(outputs, list) and outputs[0].strip():
                     return outputs[0].strip()  # Return if successful
                 results.append(outputs[0].strip() if outputs else "No result")
@@ -55,9 +59,11 @@ def extract_text_got(uploaded_file):
         # Try FINE-GRAINED OCR with box options
         for ocr_type in fine_grained_options:
             with torch.no_grad():
-                outputs = model.chat(
-                    tokenizer, temp_file_path, ocr_type=ocr_type, ocr_box=box
-                )
+                print(f"Running fine-grained OCR with box, type: {ocr_type}")  # Debug info
+                outputs = model.chat(tokenizer, temp_file_path, ocr_type=ocr_type, ocr_box=box)
+                
+                print(f"Outputs for {ocr_type} with box: {outputs}")
+                
                 if isinstance(outputs, list) and outputs[0].strip():
                     return outputs[0].strip()  # Return if successful
                 results.append(outputs[0].strip() if outputs else "No result")
@@ -66,25 +72,28 @@ def extract_text_got(uploaded_file):
         for ocr_type in fine_grained_options:
             for color in color_options:
                 with torch.no_grad():
-                    outputs = model.chat(
-                        tokenizer, temp_file_path, ocr_type=ocr_type, ocr_color=color
-                    )
+                    print(f"Running fine-grained OCR with color {color}, type: {ocr_type}")  # Debug info
+                    outputs = model.chat(tokenizer, temp_file_path, ocr_type=ocr_type, ocr_color=color)
+                    
+                    print(f"Outputs for {ocr_type} with color {color}: {outputs}")
+                    
                     if isinstance(outputs, list) and outputs[0].strip():
                         return outputs[0].strip()  # Return if successful
-                    results.append(outputs[0].strip()
-                                   if outputs else "No result")
+                    results.append(outputs[0].strip() if outputs else "No result")
 
         # Try MULTI-CROP OCR
         for ocr_type in multi_crop_types:
             with torch.no_grad():
-                outputs = model.chat_crop(
-                    tokenizer, temp_file_path, ocr_type=ocr_type
-                )
+                print(f"Running multi-crop OCR with type: {ocr_type}")  # Debug info
+                outputs = model.chat_crop(tokenizer, temp_file_path, ocr_type=ocr_type)
+                
+                print(f"Outputs for multi-crop {ocr_type}: {outputs}")
+                
                 if isinstance(outputs, list) and outputs[0].strip():
                     return outputs[0].strip()  # Return if successful
                 results.append(outputs[0].strip() if outputs else "No result")
 
-        # If no text was extracted
+        # Return combined results or no text found message
         if all(not text for text in results):
             return "No text extracted."
         else:
@@ -94,5 +103,7 @@ def extract_text_got(uploaded_file):
         return f"Error during text extraction: {str(e)}"
 
     finally:
+        # Clean up temporary file
         if os.path.exists(temp_file_path):
             os.remove(temp_file_path)
+            print(f"Temporary file {temp_file_path} removed.")  # Debug info