app.py

import gradio as gr
from huggingface_hub import InferenceClient
from transformers import pipeline

# Define the respond function
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Define the initial message for the chat
    messages = [
        {"role": "user", "content": message},
    ]
    
    # Create a pipeline for text generation
    pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-DeepSeek-33B")
    pipe(messages)

    response = ""
    
    # Use the InferenceClient to get responses
    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

# Setup 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)",
        ),
    ],
)

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