Update app.py

app.py

@@ -34,8 +34,10 @@ states = [
 chatbot = QLearningChatbot(states)
 
 # Function to display Q-table
-def display_q_table(q_values, states):
-    q_table_dict = {"State": states}
+def display_q_table(states):
+    values = [0,1,2]
+    q_table_dict = {"State": states,
+                    "values":values}
     q_table_df = pd.DataFrame(q_table_dict)
     return q_table_df
 
@@ -62,19 +64,11 @@ def speech_recognition_callback():
 
 ## generated stores AI generated responses
 if 'generated' not in st.session_state:
-    st.session_state['generated'] = []
-
+    st.session_state['generated'] = ["I'm your Mental health Assistant, How may I help you?"]
 ## past stores User's questions
 if 'past' not in st.session_state:
-    st.session_state['past'] = []
-
-# Initialize memory
-if "entered_text" not in st.session_state:
-    st.session_state.entered_text = []
-if "entered_mood" not in st.session_state:
-    st.session_state.entered_mood = []
-if "messages" not in st.session_state:
-    st.session_state.messages = []
+    st.session_state['past'] = ['Hi']
+
 if "user_sentiment" not in st.session_state:
     st.session_state.user_sentiment = "Neutral"
 
@@ -91,8 +85,9 @@ def get_text():
     return input_text
 
 def generate_response(prompt):
+    sentiment = mdl.predict_classification(prompt)
     response = mdl.call_conversational_rag(prompt,final_chain)
-    return response['answer']
+    return response['answer'], sentiment
 
 # Collect user input
 # Add a radio button to choose input mode
@@ -115,6 +110,7 @@ else:
 ## Applying the user input box        
 with input_container:
     if user_message:
+        detected_sentiment = None
         st.session_state.entered_text.append(user_message)
         st.session_state.messages.append({"role": "user", "content": user_message})
         
@@ -124,17 +120,22 @@ with input_container:
             
         # Process the user's message and generate a response
         with st.spinner("Processing..."):
-            response = generate_response(user_message)
+            response,detected_sentiment = generate_response(user_message)
             st.session_state.past.append(user_message)
             st.session_state.messages.append({"role": "ai", "content": response})
-            
-            # Detect sentiment
-            user_sentiment = chatbot.detect_sentiment(user_message)
+
 
             # Display the AI's response
             with st.chat_message("ai"):
                 st.markdown(response)
-                st.session_state.user_sentiment = user_sentiment
+                if detected_sentiment == 0:
+                    st.session_state.user_sentiment = 'Negetive'
+                elif detected_sentiment == 1:
+                    st.session_state.user_sentiment = 'Neutral'
+                elif detected_sentiment == 1:
+                    st.session_state.user_sentiment = 'Positive'
+                else:
+                    st.session_state.user_sentiment = 'Neutral'
                 
                 # Convert the response to speech
                 speech_fp = text_to_speech(response)
@@ -143,24 +144,19 @@ with input_container:
                 
 
 # Check if there are generated responses to display
-if st.session_state['generated']:
-    with conversation_history_container:
-        # Display the conversation history
-        for i, (past_message, generated_response) in enumerate(zip(st.session_state['past'], st.session_state['generated'])):
-            message(past_message, is_user=True, key=str(i) + '_user')
-            message(generated_response, key=str(i) + '_ai')
-else:
-    # If no generated responses, display the initial message from the AI
-    if not st.session_state['past']:
-        st.markdown("I'm your Mental health Assistant, How may I help you?")
+with response_container:        
+    if st.session_state['generated']:
+        for i in range(len(st.session_state['generated'])):
+            message(st.session_state['past'][i], is_user=True, key=str(i) + '_user')
+            message(st.session_state["generated"][i], key=str(i))
 
                                                              
                             
 with st.sidebar.expander("Sentiment Analysis"):
         # Use the values stored in session state
         st.write(
-            f"- Detected User Tone: {st.session_state.user_sentiment} ({st.session_state.mood_trend.capitalize()}{st.session_state.mood_trend_symbol})"
+            f"- Detected User Tone: {st.session_state.user_sentiment}"
         )
             
         # Display Q-table
-        st.dataframe(display_q_table(chatbot.q_values, states))
+        st.dataframe(display_q_table(states))