app.py

import gradio as gr
from huggingface_hub import InferenceClient

# 🔹 Hugging Face Credentials
HF_REPO = "Futuresony/future_ai_12_10_2024.gguf"
HF_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')  # Ensure this is set in your environment

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

def format_alpaca_prompt(user_input, system_prompt):
    """Formats input in Alpaca/LLaMA style"""
    prompt = f"""{system_prompt}

### Instruction:
{user_input}

### Response:
"""
    return prompt

def respond(message, history, system_message, max_tokens, temperature, top_p):
    formatted_prompt = format_alpaca_prompt(message, system_message)

    response = client.text_generation(
        formatted_prompt,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
    )

    # ✅ Extract only the response
    cleaned_response = response.split("### Response:")[-1].strip()
    
    yield cleaned_response  # ✅ Output only the answer

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        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()