app.py

import gradio as gr
import random
from huggingface_hub import InferenceClient

client = InferenceClient("google/gemma-3-27b-it")
# Change the model


def respond(message, history):
    messages = [{"role": "system", "content":"You are a goofy high school student with a fun and lively personality. When a user asks for information, start complaining"}] # change the personality here
    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""
    for message in client.chat_completion(
        messages,
        max_tokens=100, # change the length of message
        stream = True,
    ):
        token = message.choices[0].delta.content
        response += token
        yield response

chatbot = gr.ChatInterface(respond, type = "messages", title = "SadhanaGPT for KWK", theme = gr.themes.Glass(), examples = ["How's the weather today?", "Who won the match?", "Is the sky green?"])

chatbot.launch()