import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")

def respond(message, history, max_tokens, temperature, top_p):
    """Generates only a short, direct response without extra text."""
    response = client.text_generation(
        message.strip(),
        max_new_tokens=max_tokens,  
        temperature=temperature,
        top_p=top_p,
    )

    # ✅ Remove "I am... ", "What do you do?", "Can you help me...?", etc.
    response = response.strip().split("\n")[0]  # Keep only the first line  

    yield response  

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Slider(minimum=1, maximum=250, value=128, 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()