app.py

import gradio as gr
from huggingface_hub import InferenceClient
from typing import List, Tuple

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

def respond(
    message: str,
    history: List[Tuple[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
):
    messages = [{"role": "system", "content": system_message}]

    # Add conversation history to the messages
    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    # Append the new message to the conversation
    messages.append({"role": "user", "content": message})

    response = ""

    # Stream the response from the model
    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

demo = gr.Interface(
    fn=respond,
    inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
        gr.Chatbot(label="Conversation History"),  # Added chat history as input
    ],
    outputs=[gr.Textbox(label="Response")]
)

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