app.py

import gradio as gr
#from huggingface_hub import InferenceClient
import os
import requests

PROMPT_TEMPLATE = """You are a friendly Chatbot."""
system_prompt=PROMPT_TEMPLATE

specialtoken = os.getenv("SPECIALTOKEN")
"""
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
"""




#TODO remove max_tokens,temp,top_p to make it by default
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})
    
    payload = {
    "model": "openai",
    "messages": messages,
    #"response_format": { "type": "json_object" },
    #"tools": tools,
    #"tool_choice": "auto",
    #"stream": True,
    }

    
    resp = requests.post(
    specialtoken,
    json=payload,
    headers={"Content-Type": "application/json"}
    )

    response_messages=resp.json()["choices"] #[0]["message"]["content"]
    response = ""

    
    
    for message in response_messages:
        token = message["message"]["content"]
        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()