app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("hackergeek98/gemma-finetuned")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Preparing the messages list
    messages = [{"role": "system", "content": system_message}]

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

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

    # Initialize the response string
    response = ""

    # Corrected method for chat completion
    for message in client.chat_completion(
        messages=messages,  # Argument should be named 'messages'
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True  # Stream the response
    ):
        # Accumulate the response from the streaming output
        token = message.choices[0].delta.content
        response += token
        yield response

# Gradio interface setup
demo = gr.ChatInterface(
    respond,
    additional_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)"),
    ],
)

# Run the app
if __name__ == "__main__":
    demo.launch()