app.py

import gradio as gr
import google.generativeai as genai
import os

# Load API key from Hugging Face Secrets
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
genai.configure(api_key=GEMINI_API_KEY)

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

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

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

    # Call Gemini API
    model = genai.GenerativeModel("gemini-1.5-flash")
    response = model.generate_content(message, stream=True)

    output = ""
    for chunk in response:
        if chunk.text:
            output += chunk.text
            yield output  # Stream response in real-time

# Gradio 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()