app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Function to create InferenceClient dynamically based on model selection
def get_client(model_name):
    return InferenceClient(model_name)

def respond(
    message,
    history: list[tuple[str, str]],
    max_tokens,
    temperature,
    top_p,
    model_name,  # Added model_name to the function arguments
):
    # Statically defined system message
    system_message = "You are a friendly Chatbot."
    
    # Create client for the selected model
    client = get_client(model_name)
    
    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]})
    
    # Add the latest user message
    messages.append({"role": "user", "content": message})
    
    # Make the request
    response = client.chat_completion(
        messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=False
    )
    
    # Extract the full response for chat models
    full_response = response.choices[0].message["content"]
    
    return full_response


# Gradio ChatInterface setup with static system message and no Textbox for system message
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=2.0, value=1.0, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95, step=0.05, label="Top-p (nucleus sampling)"
        ),
        # Dropdown to select model
        gr.Dropdown(
            choices=[
                "meta-llama/Meta-Llama-3-8B-Instruct",
                "mistralai/Mistral-7B-Instruct-v0.3",
                "HuggingFaceH4/zephyr-7b-beta",
                "microsoft/Phi-3.5-mini-instruct"
            ],
            value="meta-llama/Meta-Llama-3-8B-Instruct",
            label="Choose Model"
        ),
    ],
)

if __name__ == "__main__":
    demo.launch()