Update app.py

app.py

@@ -1,44 +1,49 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from datetime import datetime
-import json
 
 # Initialize the InferenceClient with the model ID from Hugging Face
 client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
-# Load chat history from a file if it exists
-def load_chat_history(filename="chat_history.json"):
-    try:
-        with open(filename, "r") as file:
-            return json.load(file)
-    except FileNotFoundError:
-        return []
-
-# Save chat history to a file
-def save_chat_history(history, filename="chat_history.json"):
-    with open(filename, "w") as file:
-        json.dump(history, file)
-
-def generate_response(
-    messages: list[dict],
+def respond(
+    message: str,
+    history: list[tuple[str, str]],
+    system_message: str,
     max_tokens: int,
     temperature: float,
     top_p: float,
 ):
     """
-    Generates a response from the AI model based on the provided messages.
-
+    Generates a response from the AI model based on the user's message and chat history.
+    
     Args:
-        messages (list): A list of messages representing the conversation history.
+        message (str): The user's input message.
+        history (list): A list of tuples representing the conversation history (user, assistant).
+        system_message (str): A system-level message guiding the AI's behavior.
         max_tokens (int): The maximum number of tokens for the output.
-        temperature (float): Sampling temperature for controlling randomness.
+        temperature (float): Sampling temperature for controlling the randomness.
         top_p (float): Top-p (nucleus sampling) for controlling diversity.
 
     Yields:
         str: The AI's response as it is generated.
     """
+    
+    # Prepare the conversation history for the API call
+    messages = [{"role": "system", "content": system_message}]
+    
+    for user_input, assistant_response in history:
+        if user_input:
+            messages.append({"role": "user", "content": user_input})
+        if assistant_response:
+            messages.append({"role": "assistant", "content": assistant_response})
+
+    # Add the latest user message to the conversation
+    messages.append({"role": "user", "content": message})
+
+    # Initialize an empty response
     response = ""
+
     try:
+        # Generate a response from the model with streaming
         for message in client.chat_completion(
             messages=messages,
             max_tokens=max_tokens,
@@ -53,166 +58,29 @@ def generate_response(
     except Exception as e:
         yield f"An error occurred: {str(e)}"
 
-def build_messages(system_message: str, history: list[tuple[str, str]], user_message: str) -> list[dict]:
-    """
-    Builds the list of messages for the model based on system message, history, and latest user message.
-
-    Args:
-        system_message (str): A system-level message guiding the AI's behavior.
-        history (list): A list of tuples representing the conversation history (user, assistant).
-        user_message (str): The latest user message.
-
-    Returns:
-        list: A list of message dictionaries formatted for the API call.
-    """
-    messages = [{"role": "system", "content": system_message}]
-    
-    for user_input, assistant_response in history:
-        if user_input:
-            messages.append({"role": "user", "content": user_input})
-        if assistant_response:
-            messages.append({"role": "assistant", "content": assistant_response})
-
-    messages.append({"role": "user", "content": user_message})
-    return messages
-
-def respond(
-    message: str,
-    history: list[tuple[str, str]],
-    system_message: str,
-    max_tokens: int,
-    temperature: float,
-    top_p: float,
-):
-    """
-    Handles the interaction with the model to generate a response based on user input and chat history.
-
-    Args:
-        message (str): The user's input message.
-        history (list): A list of tuples representing the conversation history (user, assistant).
-        system_message (str): A system-level message guiding the AI's behavior.
-        max_tokens (int): The maximum number of tokens for the output.
-        temperature (float): Sampling temperature for controlling randomness.
-        top_p (float): Top-p (nucleus sampling) for controlling diversity.
-
-    Yields:
-        str: The AI's response as it is generated.
-    """
-    messages = build_messages(system_message, history, message)
-    yield from generate_response(messages, max_tokens, temperature, top_p)
-
-def update_chat_history(user_message: str, assistant_response: str, history: list[tuple[str, str]]) -> list[tuple[str, str]]:
-    """
-    Updates the chat history with the latest user message and assistant response.
-
-    Args:
-        user_message (str): The latest user message.
-        assistant_response (str): The response generated by the assistant.
-        history (list): The existing chat history.
-
-    Returns:
-        list: The updated chat history.
-    """
-    history.append((user_message, assistant_response))
-    save_chat_history(history)
-    return history
-
-# --- Enhanced UI Features ---
-def update_settings(max_tokens, temperature, top_p):
-    """Updates the settings based on user input."""
-    return gr.Markdown(f"**Current Settings:**\n* Max Tokens: {max_tokens}\n* Temperature: {temperature}\n* Top-p: {top_p}")
-
-def display_history(history):
-    """Displays the chat history in a more readable format."""
-    formatted_history = ""
-    for user_msg, assistant_msg in history:
-        formatted_history += f"**User:** {user_msg}\n**Assistant:** {assistant_msg}\n\n"
-    return formatted_history
-
-
-# Define the UI layout with additional features
+# Define the UI layout with a more user-friendly design
 with gr.Blocks() as demo:
     gr.Markdown("# 🧠 AI Chatbot Interface")
     gr.Markdown("### Customize your AI Chatbot's behavior and responses.")
-
+    
     with gr.Row():
+        chatbot = gr.Chatbot()
         with gr.Column():
-            system_message = gr.Textbox(
-                value="You are a helpful assistant knowledgeable in various topics. Provide clear, concise, and friendly responses.",
-                label="System message",
-                lines=3
-            )
+            system_message = gr.Textbox(value="You are a friendly Chatbot.", label="System message", lines=2)
             max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
             temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
             top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
-
-            # Display current settings
-            settings_output = gr.Markdown(f"**Current Settings:**\n* Max Tokens: {max_tokens.value}\n* Temperature: {temperature.value}\n* Top-p: {top_p.value}")
-            max_tokens.change(fn=update_settings, inputs=[max_tokens, temperature, top_p], outputs=settings_output)
-            temperature.change(fn=update_settings, inputs=[max_tokens, temperature, top_p], outputs=settings_output)
-            top_p.change(fn=update_settings, inputs=[max_tokens, temperature, top_p], outputs=settings_output)
-
-    with gr.Row():
-        chatbot = gr.Chatbot()
-        # Display chat history in a separate area
-        history_output = gr.Textbox(label="Chat History", lines=10, interactive=False)
-
+    
     with gr.Row():
-        with gr.Column():
-            sample_prompt = gr.Dropdown(
-                choices=[
-                    "Can you explain the theory of relativity?",
-                    "What are some tips for improving productivity at work?",
-                    "Tell me a fun fact about space.",
-                    "How can I cook a perfect omelette?",
-                    "What's the latest news in technology?"
-                ],
-                label="Sample Prompts",
-                value="Can you explain the theory of relativity?",
-                type="value"
-            )
-            message = gr.Textbox(label="Your message:", lines=1)
-            submit_btn = gr.Button("Send")
-            clear_btn = gr.Button("Clear Chat")
-            feedback = gr.Textbox(label="Feedback:", lines=1)
-            submit_feedback = gr.Button("Submit Feedback")
-
-    # Handle sample prompt selection
-    def update_message(prompt: str) -> str:
-        return prompt
-
-    sample_prompt.change(fn=update_message, inputs=sample_prompt, outputs=message)
+        message = gr.Textbox(label="Your message:", lines=1)
+        submit_btn = gr.Button("Send")
     
     # Update the chatbot with the new message and response
-    def handle_send(message: str, system_message: str, max_tokens: int, temperature: float, top_p: float):
-        history = load_chat_history()
-        response = list(respond(message, history, system_message, max_tokens, temperature, top_p))[0]
-        history = update_chat_history(message, response, history)
-        formatted_history = display_history(history)
-        return response, history, formatted_history
-
-    submit_btn.click(
-        fn=handle_send, 
-        inputs=[message, system_message, max_tokens, temperature, top_p], 
-        outputs=[chatbot, gr.State(), history_output],
-        show_progress=True
-    )
-    
-    # Clear the chat history
-    def clear_chat() -> list:
-        save_chat_history([]) # Clear the saved history as well
-        return [], "" # Return empty list for chatbot and empty string for history output
-
-    clear_btn.click(fn=clear_chat, inputs=None, outputs=[chatbot, history_output])
-    
-    # Handle feedback submission
-    def submit_user_feedback(feedback: str):
-        # In a real application, you would save this feedback to a database or file
-        print(f"Feedback received: {feedback}")
-        return "Thank you for your feedback!"
-
-    submit_feedback.click(fn=submit_user_feedback, inputs=feedback, outputs=[gr.Textbox(value="Feedback submitted! Thank you.", lines=1, placeholder="")])
+    submit_btn.click(respond, 
+                     inputs=[message, chatbot, system_message, max_tokens, temperature, top_p], 
+                     outputs=[chatbot],
+                     show_progress=True)
 
 # Launch the Gradio interface
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()