app.py

import gradio as gr
import keras
import keras_nlp

import numpy as np
import pandas as pd

import os
os.environ["KERAS_BACKEND"] = "jax" # you can also use tensorflow or torch
os.environ["XLA_PYTHON_CLIENT_MEM_FRACTION"] = "1" # avoid memory fragmentation on JAX backend.

keras.utils.set_random_seed(42)

gemma_lm = keras_nlp.models.CausalLM.from_preset("hf://soufyane/gemma_2b_instruct_FT_DATA_SCIENCE_lora36_1")


def generate_answer(history, question):
    # Replace this with the actual code to generate the answer using your model
    answer = gemma_lm.generate(f"You are an AI Agent specialized to answer to questions about Data Science and be greatfull and nice and helpfull\n\nQuestion:\n{question}\n\nAnswer:\n", max_length=1024)
    history.append((question, answer))
    return history

# Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Chatbot")
    chatbot = gr.Chatbot()
    with gr.Row():
        txt = gr.Textbox(show_label=False, placeholder="Enter your question here...")
        txt.submit(generate_answer, [chatbot, txt], chatbot)

# Launch the interface
demo.launch()