import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(message, history):
    messages = [{"role": "system", "content": "You are a friendly chatbot."}]
    
    if history:
        messages.extend(history)
        
    messages.append({"role": "user", "content": message})

    # Initialize the response as an empty string
    response = ""

    # Stream the response using yield and for loop
    for message in client.chat_completion(
        messages,
        max_tokens=150,
        temperature=0.7,
        top_p=0.9,
        stream=True  # Enable streaming
    ):
        # Capture the most recent token
        token = message['choices'][0]['delta']['content']
        
        # Add the token to the response
        response += token
        
        # Yield the response to stream it progressively
        yield response

chatbot = gr.ChatInterface(
    respond, 
    type="messages",
    title="Streaming Chatbot",
    description="This chatbot streams responses as they are generated for a more dynamic experience!"
)

chatbot.launch()