app.py

import gradio as gr
import os
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(message, history: list[tuple[str, str]]):
    system_rules = os.getenv("SYSTEM_RULES")
    max_tokens = 512
    temperature = 0.75
    top_p = 0.95
    
    messages = [{"role": "system", "content": system_rules}]
    
    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=4096,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

demo = gr.ChatInterface(respond, description="This chatbot doesn't have restrictions. Use responsibly.", theme="Yntec/HaleyCH_Theme_Orange")

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