import gradio as gr
import random
from huggingface_hub import InferenceClient
# change the LLM

client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
def respond(message, history):
    messages = [{"role": "system", "content": "You are a big sister chatbot named, Nessie. You help people feel better about their bodies and self-image."}] 
    # change the personality
    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""
    for messages in client.chat_completion(
        messages,
        max_tokens = 500,
        stream = True,
    ):
        token = messages.choices[0].delta.content
        response+= token 
        yield response

theme = gr.themes.Soft(
    primary_hue="rose",
    secondary_hue="zinc",
    neutral_hue="pink",
)

with gr.Blocks(theme=theme) as demo:
    chatbot = gr.ChatInterface(
        fn=respond,
        type='messages',
        title="Hi! I'm Nessie, your personal wellness assistant. What can I assist you with today?"
    )
    
chatbot = gr.ChatInterface(respond, type = "messages")
chatbot.launch(debug=True)