app.py

import gradio as gr
from huggingface_hub import InferenceClient

def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token: gr.OAuthToken,
):
    """
    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
    """
    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
    messages = [{"role": "system", "content": system_message}]

    messages.extend(history)

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


    # Stream the text response
    response = ""


    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        choices = message.choices
        token = ""
        if len(choices) and choices[0].delta.content:
            token = choices[0].delta.content

        response += token
        yield response 
	

with gr.Blocks() as demo:
    with gr.Row():
        with gr.Column(scale=1):
            gr.LoginButton()
        with gr.Column(scale=4):
            chatbot = gr.Chatbot(height=500)

            msg = gr.Textbox(label="Your message")
            submit_btn = gr.Button("Send")

            system_message = gr.Textbox(value="You are a friendly Chhattishgarhi Chatbot.", label="System message")
            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)")

            # On submit, call respond with history, update chatbot and audio
            submit_btn.click(
                respond,
                inputs=[msg, chatbot, system_message, max_tokens, temperature, top_p, gr.State(gr.OAuthToken())],
                outputs=[chatbot, audio_output],
            ).then(
                fn=lambda: "",  # Clear input box after submit
                outputs=msg
            )

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