from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient("meta-llama/Meta-Llama-3.1-8B")

def format_prompt(message, history):
    fixed_prompt= """            """
    prompt = f"<s>{fixed_prompt}"
    for user_prompt, bot_response in history:
        prompt += f"\n User:{user_prompt}\n LLM Response:{bot_response}"
    prompt += f"\nUser: {message}\nLLM Response:"

    return prompt

def generate(
    prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0,
):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
   
    yield stream



demo = gr.ChatInterface (fn=generate, 
                        title="Mood-Based Music Recommender",
                        retry_btn=None,
                        undo_btn=None,
                        clear_btn=None,
                        description="<span style='font-size: larger; font-weight: bold;'>Hi! I'm your music buddy—tell me about your mood and the type of tunes you're in the mood for today!</span>",
                       )

demo.queue().launch()