app.py

import gradio as gr
from checker import checker
from huggingface_hub import InferenceClient

# Initialize the Hugging Face Inference Client
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

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]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

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

    response = ""

    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
        response += token
        yield response

# Function to handle system message and inform the user about the bot's specialty
def system_message():
    return "I am a physics chatbot. I can help you with questions related to physics."

# Define the Gradio Chat Interface
demo = gr.Interface(
    fn=respond,
    inputs=[
        gr.Textbox(value="You are chatting with a physics chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, default=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, default=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, default=0.95, step=0.05, label="Top-p (nucleus sampling)"),
    ],
    outputs=gr.Textbox(label="Chatbot Response"),
    title="Physics Chatbot",
    description="Ask questions related to physics!",
    system_message=system_message
)

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