Update app.py

app.py

@@ -29,56 +29,55 @@ sentence_model = SentenceTransformer("all-MiniLM-L6-v2")
 topic_model = BERTopic(embedding_model=sentence_model)
 
 def is_inappropriate_or_offtopic(message, selected_topics):
-    # Assume bad_words loading and check_content function are defined here
+    # Function logic as before
 
-    topics, probabilities = topic_model.transform([message])
-    # Assuming -1 is the outlier class, filter relevant topics
-    relevant_topics = [topic for topic in topics if topic != -1]
-    
-    # Compare generated topics against selected topics
-    is_offtopic = True  # Default to True, prove it's on topic
-    for topic_num in relevant_topics:
-        topic_info = topic_model.get_topic(topic_num)
-        if topic_info:
-            topic_keywords = [word for word, _ in topic_info]
-            if any(selected_topic.lower() in topic_keywords for selected_topic in selected_topics):
-                is_offtopic = False
-                break  # If any one of the topics matches, it's not off-topic
-    
-    return is_offtopic or any(bad_word in message.lower() for bad_word in bad_words)
+def suggest_questions():
+    predefined_prompt = "Hello! My name is Andrea. So you want to learn how to become an airforce pilot? Select a question and let's start your learning journey."
+    questions = [
+        "What are the basic requirements to become an airforce pilot?",
+        "How long does it take to train as an airforce pilot?",
+        "Can you describe a day in the life of an airforce pilot?"
+    ]
+    return predefined_prompt, questions
 
-def generate_response(message, selected_topics):
-    # Checks if the message is inappropriate or off-topic
-    if is_inappropriate_or_offtopic(message, selected_topics):
-        response = "Sorry, let's try to keep our conversation focused on positive and relevant topics!"
-    else:
-        inputs = tokenizer.encode(message, return_tensors="pt")
-        outputs = model.generate(inputs, max_length=50, do_sample=True)
-        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+def generate_response(selected_question, selected_topics):
+    # Function logic for generating a response based on the selected question
     
-    # Predict topics again to display them (could optimize by reusing earlier prediction)
-    topics, _ = topic_model.transform([message])
-    topic_names = [topic_model.get_topic(topic)[0][0] for topic in topics if topic != -1]  # Top word for each topic
+    # Example of generating a response based on the selected question
+    response = "This is a placeholder response for the question: " + selected_question
     
-    return response, ", ".join(topic_names)
-
-
+    # In a real scenario, you'd integrate this with the Llama model to generate a detailed response
+    
+    return response
 
 def main():
     with gr.Blocks() as demo:
         gr.Markdown("### Child-Safe Chatbot | BETA")
-        gr.Markdown("This chatbot uses BERTopic to identify topics in your messages and ensures the conversation stays relevant.")
+        gr.Markdown("This chatbot uses BERTopic to identify topics in your messages and ensures the conversation stays relevant and safe.")
         with gr.Row():
-            message_input = gr.Textbox(label="Your Message")
-            topics_dropdown = gr.Dropdown(choices=topics_list, label="Select Topics", multiselect=True)
-            submit_btn = gr.Button("Send")
+            start_btn = gr.Button("Start Conversation")
+        questions_output = gr.Radio(label="Select a question", choices=[])
+        submit_btn = gr.Button("Submit Question")
         response_output = gr.Textbox(label="Bot Response")
-        topics_output = gr.Textbox(label="Identified Topics", placeholder="Topics will be displayed here...")
+
+        def update_questions():
+            prompt, questions = suggest_questions()
+            questions_output.update(choices=questions)
+            return prompt
+
+        start_btn.click(
+            fn=update_questions, 
+            inputs=[], 
+            outputs=response_output
+        )
 
         submit_btn.click(
             fn=generate_response, 
-            inputs=[message_input, topics_dropdown], 
-            outputs=[response_output, topics_output]
+            inputs=[questions_output, topics_list],  # Assuming topics_list is used to filter topics or for future use
+            outputs=response_output
         )
 
-    demo.launch()
+    demo.launch()
+
+if __name__ == "__main__":
+    main()