app.py

import os,json
import gradio as gr
from huggingface_hub import InferenceClient

# Retrieve the API token from the environment variable
API_TOKEN = os.getenv("HF_READ_TOKEN")
#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
# Initialize the Hugging Face Inference Client
client = InferenceClient(
    "mistralai/Mistral-Nemo-Instruct-2407",
    token=API_TOKEN
)

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 = ""
    try:
        response_stream = client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        )
        for message in response_stream:
            token = message.choices[0].delta.content
            response += token
            yield response
    except (json.JSONDecodeError, ValueError) as e:
        print(f"Error decoding response: {e}")
        yield "An error occurred while processing the request."


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(show_api=True, share=False,show_error=True)