app.py

import gradio as gr
from huggingface_hub import InferenceClient
import os
from huggingface_hub import login

# Fetch token from environment (automatically loaded from secrets)
hf_token = os.getenv("gemma")
login(hf_token)

# Initialize the client with your model
client = InferenceClient("hackergeek/gemma-finetuned")

def respond(
    message: str,
    history: list[tuple[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
):
    # Build a prompt from the system message and conversation history
    prompt = f"{system_message}\n"
    for user_msg, assistant_msg in history:
        if user_msg:
            prompt += f"User: {user_msg}\n"
        if assistant_msg:
            prompt += f"Assistant: {assistant_msg}\n"
    prompt += f"User: {message}\nAssistant: "

    # Call the text generation API with updated parameter name
    response = client.text_generation(
        model="hackergeek/gemma-finetuned",
        prompt=prompt,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
    )

    return response["generated_text"]

# Set up the Gradio Chat Interface
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)"),
    ],
)

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