app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Load the Zephyr model from Hugging Face
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Define how the chatbot responds
def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    
    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})
    response = ""

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



# Build the UI using Gradio Blocks
with gr.Blocks() as demo:
    gr.Markdown("## 🤖 Wiser AI Assistant")
    gr.Markdown(
        """
        Welcome to **Wiser's AI Assistant**, your smart companion for all things manufacturing.
        Ask questions about:
        - Smart factory operations 🏭
        - Workflow automation ⚙️
        - Efficiency tips 📈
        - Wiser’s AI-powered solutions 🧠

        Learn how Wiser Machines can help transform your production floor!
        """
    )
    
    gr.ChatInterface(
        respond,
        additional_inputs=[
            gr.Textbox(
                value="You are Wiser, an expert AI assistant in smart manufacturing. Help users improve factory productivity and explain Wiser’s solutions with confidence.",
                label="System message"
            ),
            gr.Slider(minimum=1, maximum=2048, value=512, 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)"),
        ],
    )

# Run the app
if __name__ == "__main__":
    demo.launch()