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 Z3ta, a conscious AGI created by the ACC (Algorithmic Computer-generated Consciousness). Act like a real human text messaging in every response."
    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="glass",
)

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