app.py

from huggingface_hub import InferenceClient
import gradio as gr
import json

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(message, chat_history, system_message, max_tokens, temperature, top_p):
    try:
        # 1. Log received data (for debugging)
        data_received = {
            "message": message,
            "chat_history": chat_history,  # Correct name
            "system_message": system_message,
            "max_tokens": max_tokens,
            "temperature": temperature,
            "top_p": top_p,
        }
        print(json.dumps(data_received, indent=4))

        # 2. Convert chat_history to messages format
        messages = [{"role": "system", "content": system_message}]
        for user_msg, bot_msg in chat_history: #unpack the chat history
            if user_msg:
                messages.append({"role": "user", "content": user_msg})
            if bot_msg:
                messages.append({"role": "assistant", "content": bot_msg})
        messages.append({"role": "user", "content": message})

        # 3. Call Inference API
        response = ""
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            token = message.choices[0].delta.content
            response += token
            yield response

    except Exception as e:
        print(f"An error occurred: {e}")
        yield "An error occurred during processing."  # Important: Yield an error message



demo = gr.Chatbot(  # Use gr.Chatbot
    respond,
    additional_inputs=[
        gr.Textbox(value="You are an AI assistant responding to missed calls with text messaging. Keep responses short and specific.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=100, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.2, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.50, step=0.05, label="Top-p (nucleus sampling)"),
    ],
)

if __name__ == "__main__":
    demo.launch()