import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
from typing import List, Tuple


model_name = "Hawoly18/Adia_Llama3.1"

# Vérifier si un GPU est disponible
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def respond(
    message: str,
    history: List[Tuple[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
) -> str:
    
    prompt = system_message
    for user_msg, assistant_msg in history:
        prompt += f"\nUser: {user_msg}\nAssistant: {assistant_msg}"
    prompt += f"\nUser: {message}\nAssistant:"

    
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_length=max_tokens,
        temperature=temperature,
        top_p=top_p,
        do_sample=True,
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("Assistant:")[-1].strip()
    return response


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"),  # Fixed syntax error
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
    ],
    title="Chatbot Interface"
)

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