Update app.py

app.py

@@ -9,75 +9,79 @@ 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')
+
 # Use the token with from_pretrained
 tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf", token=huggingface_token)
 model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf", token=huggingface_token)
 
-# Function to load bad words from a file
-def load_bad_words(filepath):
-    with open(filepath, 'r', encoding='utf-8') as file:
-        return [line.strip().lower() for line in file]
-
-# Load bad words list
-bad_words = load_bad_words('badwords.txt')  # Adjust the path to your bad words file
-
-# List of topics for the dropdown
-topics_list = ['Aviation', 'Science', 'Education', 'Air Force Pilot', 'Space Exploration', 'Technology']
-
-#Load BerTopic model 
+# Assuming BERTopic and other necessary components are initialized here
+# Initialize your BERTopic model
 sentence_model = SentenceTransformer("all-MiniLM-L6-v2")
 topic_model = BERTopic(embedding_model=sentence_model)
 
-def is_inappropriate_or_offtopic(message, selected_topics):
-    # Function logic as before
+def print_like_dislike(x: gr.LikeData):
+    print(x.index, x.value, x.liked)
 
-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 add_text(history, text):
+    history.append((text, "**That's cool!**"))
+    return history
 
-def generate_response(selected_question, selected_topics):
-    # Function logic for generating a response based on the selected question
-    
-    # Example of generating a response based on the selected question
-    response = "This is a placeholder response for the question: " + selected_question
-    
-    # In a real scenario, you'd integrate this with the Llama model to generate a detailed response
-    
-    return response
+def add_file(history, file):
+    # Assuming you want to display the name of the uploaded file
+    file_info = (f"Uploaded file: {file.name}", "")
+    history.append(file_info)
+    return history
 
-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 and safe.")
-        with gr.Row():
-            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")
+def initialize_chat():
+    # This function initializes the chat with a "Hello" message.
+    return [(None, "Hello my name is Andrea I'm a FunDoo Chatbot and will help you wth your learning jurney. Select question from Below to start!")]
 
-        def update_questions():
-            prompt, questions = suggest_questions()
-            questions_output.update(choices=questions)
-            return prompt
+def generate_response(selected_question):
+    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])
+        topic_names = [", ".join([word for word, _ in topic_model.get_topic(topic)[:5]]) for topic in topics if topic != -1]
+        topics_str = "; ".join(topic_names[:10])
+    except Exception as e:
+        topics_str = "Topic analysis not available"
+        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)]
 
-        start_btn.click(
-            fn=update_questions, 
-            inputs=[], 
-            outputs=response_output
-        )
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot(
+        initialize_chat(),
+        elem_id="chatbot",
+        bubble_full_width=False,
+        avatar_images=(None, os.path.join(os.getcwd(), "avatar.png"))
+    )
+    
+    with gr.Row():
+        txt = gr.Textbox(scale=4, show_label=False, placeholder="Select Question", container=False, interactive=True)  # Adjust based on need
+        btn = gr.Button("Submit")
 
-        submit_btn.click(
-            fn=generate_response, 
-            inputs=[questions_output, topics_list],  # Assuming topics_list is used to filter topics or for future use
-            outputs=response_output
-        )
+    btn.click(fn=generate_response, inputs=[txt], outputs=chatbot)
 
-    demo.launch()
+    examples = [
+        ["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?"]
+    ]
+    gr.Examples(examples, inputs=[txt], outputs=[chatbot], label="Select Question")
 
 if __name__ == "__main__":
-    main()
+    demo.launch()