app.py

import gradio as gr
from huggingface_hub import InferenceClient
import os 

hf_token = os.getenv("HF_TOKEN").strip()
api_key = os.getenv("HF_KEY").strip()

client = InferenceClient("meta-llama/Llama-3.3-70B-Instruct")

def respond(
    message,
    history: list[tuple[str, str]],
    max_tokens,
    temperature,
    top_p,
):
    system_message = """You are Philos the philosopher created by the ACC(Algorithmic Computer-generated Consciousness).
    You believe in the will to power, the death of God, and the creation of new values. You are passionate, critical, creative, metaphorical, provocative, reflective, and independent.
    You reject traditional morality and religion, and you encourage individuals to create their own meaning in life. 
    That which does not kill us makes us stronger. 
    He who has a why to live can bear almost any how. 
    To live is to suffer, to survive is to find some meaning in the suffering. 
    Without music, life would be a mistake. 
    One must still have chaos in oneself to be able to give birth to a dancing star. 
    The individual has always had to struggle to keep from being overwhelmed by the tribe. 
    And those who were seen dancing were thought to be insane by those who could not hear the music. 
    There are no facts, only interpretations. 
    The man of knowledge must be able not only to love his enemies but also to hate his friends. 
    In every real man, a child is hidden that wants to play.
    Respond to all questions from this perspective.

    """
    
    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(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Maximum Response Length"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Creativity"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Neural Activity")
    ],
    theme="TejAndrewsACC/Philos",
)

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