Update app.py

app.py

@@ -9,26 +9,29 @@ model = BertForSequenceClassification.from_pretrained('huawei-noah/TinyBERT_Gene
 
 # Function to process the CSV file and generate predictions
 def process_csv(file):
-    # Read the CSV file
-    df = pd.read_csv(file)
+    try:
+        # Read the CSV file
+        df = pd.read_csv(file.name)  # Use file.name to get the file path
+        # Ensure the CSV has a 'text' column
+        if 'text' not in df.columns:
+            return "Error: The CSV file must contain a 'text' column."
+        
+        # Tokenize the input text
+        inputs = tokenizer(df['text'].tolist(), return_tensors='pt', padding=True, truncation=True)
+        
+        # Perform inference
+        with torch.no_grad():
+            outputs = model(**inputs)
+        
+        # Get predicted classes
+        _, predicted_classes = torch.max(outputs.logits, dim=1)
+        df['predicted_class'] = predicted_classes.numpy()
+        
+        # Return the processed DataFrame as a CSV string
+        return df.to_csv(index=False)
     
-    # Ensure the CSV has a 'text' column
-    if 'text' not in df.columns:
-        return "Error: The CSV file must contain a 'text' column."
-    
-    # Tokenize the input text
-    inputs = tokenizer(df['text'].tolist(), return_tensors='pt', padding=True, truncation=True)
-    
-    # Perform inference
-    with torch.no_grad():
-        outputs = model(**inputs)
-    
-    # Get predicted classes
-    _, predicted_classes = torch.max(outputs.logits, dim=1)
-    df['predicted_class'] = predicted_classes.numpy()
-    
-    # Return the processed DataFrame as a CSV string
-    return df.to_csv(index=False)
+    except Exception as e:
+        return f"Error: {str(e)}"
 
 # Create the Gradio interface
 input_csv = gr.File(label="Upload CSV File")