app.py

import os

# ১. requirements.txt আপডেট করা (Inference API এর জন্য)
with open("requirements.txt", "w") as f:
    f.write("gradio\nhuggingface_hub\n")

# ২. app.py আপডেট করা (InferenceClient ব্যবহার করে)
app_code = """
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,
):
    # Initialize the Inference Client with the provided OAuth token
    # Model: mx-llms/BLM
    client = InferenceClient(token=hf_token.token, model='google/gemma-4-E2B-it')

    messages = [{"role": "system", "content": system_message}]

    # Add history to messages
    for h in history:
        messages.append(h)

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

    response = ""

    # Request streaming completion
    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
        if token:
            response += token
            yield response

# Gradio Interface
chatbot = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are BLM. Created by MD Mushfiqur Rahim.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, value=0.1, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"),
    ],
    type="messages"
)

with gr.Blocks() as demo:
    with gr.Sidebar():
        gr.Markdown("### BLM Assistant Login")
        gr.LoginButton()
    chatbot.render()

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

with open("app.py", "w") as f:
    f.write(app_code)

print("✅ app.py has been updated to use Inference API and OAuth!")