Update app.py

app.py

@@ -9,12 +9,6 @@ from sentence_transformers import SentenceTransformer
 # Retrieve the token from environment variables
 huggingface_token = os.getenv('LLAMA_ACCES_TOKEN')
 
-import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import os
-from bertopic import BERTopic
-from sentence_transformers import SentenceTransformer
-
 # Assuming necessary initializations and model loading here
 # Retrieve the token from environment variables
 huggingface_token = os.getenv('LLAMA_ACCES_TOKEN')
@@ -45,12 +39,16 @@ def initialize_chat():
     # This function initializes the chat with a "Hello" message.
     return [(None, "Hello, my name is <strong>Andrea</strong>, I'm a <em>Friendly Chatbot</em> and will help you with your learning journey. <br>Select a question from below to start!")]
 
+chat_history = initialize_chat()
 
 def generate_response(selected_question):
+    global chat_history
     prompt = selected_question  # Ensure selected_question is a string
     inputs = tokenizer(prompt, return_tensors="pt", max_length=512, truncation=True)
     outputs = model.generate(**inputs, max_length=100, do_sample=True, top_p=0.95, top_k=50)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    
     
     try:
         topics, _ = topic_model.transform([response])
@@ -61,7 +59,11 @@ def generate_response(selected_question):
         print(f"Error during topic analysis: {e}")
     
     # Adjusted to return a list of tuples as expected by the Chatbot component
-    return [(prompt, response + "\n\nTopics: " + topics_str)]
+    new_response = (prompt, response + "\n\nTopics: " + topics_str)
+    chat_history.append(new_response)
+    
+    
+    return chat_history
 
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot(