app.py

import gradio as gr
from huggingface_hub import InferenceClient

client = InferenceClient("google/gemma-2-2b-it")

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

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

    response = client.chat_completion(
        messages,
        max_tokens = 800,
        temperature = 1.1,
        top_p = 0.5
    )
    
    return response['choices'][0]['message']['content'].strip()

chatbot = gr.ChatInterface(respond, type = "messages")

chatbot.launch()