Update app.py

app.py

@@ -1,4 +1,5 @@
 import streamlit as st
+import pandas as pd
 import io, os
 import subprocess
 import pdfplumber
@@ -19,8 +20,8 @@ import google.generativeai as genai
 from typing import List
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.runnables import Runnable
-
 import google.generativeai as genai
+from datetime import datetime
 
 
 class GeminiLLM(Runnable):
@@ -259,17 +260,42 @@ def main():
             st.session_state.chat_ready = True
             st.success("MODTRAN User Manual loaded successfully!")
 
-    user_question = st.text_input("Ask your question:")
+    user_question = st.text_input("Ask your question:", key="user_input")
 
-    if st.session_state.chat_ready and user_question:
+    if st.button("Submit") and user_question:
         set_global_vectorstore(st.session_state.vectorstore)
         response = handle_user_query(user_question)
         st.session_state.chat_history.append({"user": user_question, "bot": response})
+        
+
+    if "feedback_log" not in st.session_state:
+        st.session_state.feedback_log = []
 
-    for chat in st.session_state.chat_history:
+    for i, chat in enumerate(st.session_state.chat_history):
         st.write(f"**You:** {chat['user']}")
         st.write(f"**Bot:** {chat['bot']}")
 
+        rating = st.radio(
+            "How would you rate this response?",
+            options=["1", "2", "3", "4", "5"],
+            key=f"rating_{i}",
+            horizontal=True
+        )
+
+    
+        st.session_state.feedback_log.append({
+            "question": chat["user"],
+            "answer": chat["bot"],
+            "rating": rating
+        })
+
+
+   
+    if st.session_state.feedback_log:
+        feedback_df = pd.DataFrame(st.session_state.feedback_log)
+        current_date = datetime.now().strftime("%Y%m%d_%H%M%S")
+        feedback_df.to_csv(f"feedback_{current_date}.csv", index=False)
+
 if __name__ == "__main__":
     load_environment()
     main()