app.py

import gradio as gr
from huggingface_hub import InferenceClient


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


system_message = ("This is MUSK-1, developed by a 14 year old AI engineer Arjun Singh at Elieon.")
# Function to generate responses using the LLM
def respond(
    message,
    history: list[tuple[str, str]],
    max_tokens,
    temperature,
    top_p,
):
    # Construct the message history for the API request
    messages = [{"role": "system", "content": system_message}]

    for user_msg, assistant_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if assistant_msg:
            messages.append({"role": "assistant", "content": assistant_msg})

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

    response = ""

    # Stream the response tokens from the model
    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

# Create a Gradio ChatInterface with custom styling
custom_css = """
.css-1rw10a3 {
    height: 500px; /* Adjust height as needed */
    overflow-y: scroll; /* Add scrollbar if content exceeds height */
}
"""

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        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)"),
    ],
    css=custom_css,  # Apply custom CSS styling
)

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