app.py

import gradio as gr
from huggingface_hub import InferenceClient

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

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

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

    messages.append({"role": "user", "content": message})

    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

demo = gr.ChatInterface(
    fn=respond,
    additional_inputs=[
        gr.Textbox(lines=2, label="System Message", placeholder="You are a helpful assistant."),
        gr.Slider(0, 1024, value=256, step=1, label="Max Tokens"),
        gr.Slider(0, 1, value=0.7, step=0.01, label="Temperature"),
        gr.Slider(0, 1, value=0.9, step=0.01, label="Top-p")
    ],
    title="Chat with Zephyr-7b",
    description="Chatbot powered by Hugging Face Inference API."
)

demo.launch()  # Remove or set share=False