app.py

import gradio as gr
from huggingface_hub import InferenceClient
from dotenv import load_dotenv
import os

# $ GRADIO LOCALHOST=http://127.0.0.1:7860/

#Load environment variables from .env file
load_dotenv()
token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
#print(f"Token: {token}")
#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=token)
MODEL_NAME = "HuggingFaceH4/starchat-alpha"
client = InferenceClient(token=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 = ""

    for message in client.chat_completion(
        model="HuggingFaceH4/starchat-alpha",
        messages=messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        if token is not None:
            response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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()




# import requests

# API_URL = "https://router.huggingface.co/nscale/v1/chat/completions"
# headers = {
#     "Authorization": "Bearer" + token,
# }

# def query(payload):
#     response = requests.post(API_URL, headers=headers, json=payload)
#     return response.json()

# response = query({
#     "messages": [
#         {
#             "role": "user",
#             "content": "What is the capital of France?"
#         }
#     ],
#     "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
# })

# print(response)