Update app.py

app.py

@@ -5,6 +5,7 @@ import getpass
 import logging
 import openai
 import asyncio
+import pandas as pd
 from typing import Any, List, Tuple, Dict
 import gradio as gr
 import llama_index
@@ -169,7 +170,8 @@ def process_pdf(uploaded_files, llm_model, n_criteria = num_criteria):
     for i, uploaded_file in enumerate(uploaded_files):
         # Process the PDF file
         file_name_without_extension = os.path.splitext(os.path.basename(uploaded_file))[0]
-        file_name_without_extension
+
+        id_number = re.search(r"Id_(\d+)\.", file_name_without_extension)
         
         pdf_processor = PDFProcessor_Unstructured(pdf_processing_config)
         merged_chunks, tables, title = pdf_processor.process_pdf_file(uploaded_file)
@@ -243,8 +245,38 @@ def process_pdf(uploaded_files, llm_model, n_criteria = num_criteria):
         registration_result = nlp_methods.check_registration()
         
         # Evaluate with OpenAI model
-        total_score, criteria_met, score_percentage, reasoning = pdf_criteria_query.evaluate_with_llm(registration_result, peer_journal_result, eq_journal_result, queries)
+        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(scores, 1)})
+        new_row.update({f'reasoning_cr_{i}': reasoning for i, reasoning in enumerate(reasonings, 1)})
 
+        # 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
+            df = pd.DataFrame(columns=['Id'] + [f'score_cr_{i}' for i in range(1, 10)] + [f'reasoning_cr_{i}' for i in range(1, 10)])
+
+        # Append the new data
+        df = df.append(new_row, ignore_index=True)
+
+        # Save the updated DataFrame back to CSV
+        df.to_csv(csv_file_path, index=False)
+
+        print(f"Updated data saved to {csv_file_path}.")
+        
         # Convert reasoning list to plain text
         #reasoning_text = "\n".join([f"{idx + 1}. {reason}" for idx, reason in enumerate(reasoning)])