Update app.py

app.py

@@ -245,40 +245,43 @@ def process_pdf(uploaded_files, llm_model, n_criteria = num_criteria):
         
         # Evaluate with OpenAI model
         total_score, criteria_met, score_percentage, score_list, reasoning = pdf_criteria_query.evaluate_with_llm(registration_result, peer_journal_result, eq_journal_result, queries)
-
-        # Define the path to your CSV file
-        csv_file_path = 'storing_output.csv'
-
-
-        # Create a dictionary for the new row
-        new_row = {
-            'Id': id_number,
-            'Title': title,
-            'Author': author_result
-        }
-        new_row.update({f'score_cr_{i}': score for i, score in enumerate(score_list, 1)})
-        new_row.update({f'reasoning_cr_{i}': reasoning for i, reasoning in enumerate(reasoning, 1)})
-
-        # Convert new_row dictionary to a DataFrame for easy appending
-        new_row_df = pd.DataFrame([new_row])
-        print(new_row_df)
+        try:
+            # Define the path to your CSV file
+            csv_file_path = 'storing_output.csv'
+
+
+            # Create a dictionary for the new row
+            new_row = {
+                'Id': id_number,
+                'Title': title,
+                'Author': author_result
+            }
+            new_row.update({f'score_cr_{i}': score for i, score in enumerate(score_list, 1)})
+            new_row.update({f'reasoning_cr_{i}': reasoning for i, reasoning in enumerate(reasoning, 1)})
+
+            # Convert new_row dictionary to a DataFrame for easy appending
+            new_row_df = pd.DataFrame([new_row])
+            print(new_row_df)
         
-        # Check if the CSV file exists
-        if os.path.exists(csv_file_path):
-            # Load the existing data
-            df = pd.read_csv(csv_file_path)
-        else:
-            # Or create a new DataFrame if the file does not exist
-            columns = ['Id', 'Title', 'Author'] + [f'score_cr_{i}' for i in range(1, 10)] + [f'reasoning_cr_{i}' for i in range(1, 10)]
-            df = pd.DataFrame(columns=columns)
-
-        # Append the new data using pd.concat
-        df = pd.concat([df, new_row_df], ignore_index=True)
+            # Check if the CSV file exists
+            if os.path.exists(csv_file_path):
+                # Load the existing data
+                df = pd.read_csv(csv_file_path)
+            else:
+                # Or create a new DataFrame if the file does not exist
+                columns = ['Id', 'Title', 'Author'] + [f'score_cr_{i}' for i in range(1, 10)] + [f'reasoning_cr_{i}' for i in range(1, 10)]
+                df = pd.DataFrame(columns=columns)
+
+            # Append the new data using pd.concat
+            df = pd.concat([df, new_row_df], ignore_index=True)
         
-        # Save the updated DataFrame back to CSV
-        df.to_csv(csv_file_path, index=False)
+            # Save the updated DataFrame back to CSV
+            df.to_csv(csv_file_path, index=False)
 
-        print(f"Updated data saved to {csv_file_path}.")
+            print(f"Updated data saved to {csv_file_path}.")
+        
+        except Exception as e:
+            print(f"An error occurred: {e}")
         
         # Convert reasoning list to plain text
         #reasoning_text = "\n".join([f"{idx + 1}. {reason}" for idx, reason in enumerate(reasoning)])