Update app.py

app.py

@@ -245,12 +245,12 @@ 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)
-        logger.info("Total score: %s", total_score)
+        
         
         try:
             # Define the path to your CSV file
             csv_file_path = 'storing_output.csv'
-            print(csv_file_path)
+            logger.info("CSV file path: %s", csv_file_path)
 
             # Create a dictionary for the new row
             new_row = {
@@ -263,16 +263,16 @@ def process_pdf(uploaded_files, llm_model, n_criteria = num_criteria):
 
             # Convert new_row dictionary to a DataFrame for easy appending
             new_row_df = pd.DataFrame([new_row])
-            logger.debug("New row DataFrame:\n%s", new_row_df)
+            logger.info("New row DataFrame:\n%s", new_row_df)
         
             # Check if the CSV file exists
             if os.path.exists(csv_file_path):
                 # Load the existing data
-                logger.debug("CSV file exists. Loading existing data.")
+                logger.info("CSV file exists. Loading existing data.")
                 df = pd.read_csv(csv_file_path)
             else:
                 # Or create a new DataFrame if the file does not exist
-                logger.debug("CSV file does not exist. Creating a new DataFrame.")
+                logger.info("CSV file does not exist. Creating a new DataFrame.")
                 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)