import transformers
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import gradio as gr 
from gradio import Interface
from pathlib import Path
from fastai.text.all import *
from datasets import load_dataset


# Download and prepare SQuAD dataset (not used directly here)
squad = load_dataset("squad")

# Load the pre-trained summarization model (adjust model name as needed)
model_name = "laptop_summarizer_1.pkl"  # Choose a suitable summarization model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

# Define a function to generate summaries using the model
def generate_summary(input_text):
  # Tokenize the input text
  inputs = tokenizer(input_text, return_tensors="pt")

  # Generate summary using the pre-trained model
  output = model.generate(**inputs)

  # Decode the generated tokens back to text
  summary_text = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
  return summary_text

# Create an interface for the model
interfaces = gr.Interface(
    fn=generate_summary,  # The function to generate summaries
    inputs=gr.inputs.Textbox(),  # Input field for text
    outputs=gr.outputs.Textbox(),  # Output field for generated text
    live=True,  # Whether to update results in real-time
    title="Laptop Guru",  # Title of the interface
    description="Enter your requirements & get valuable insight from Guru."  # Description of the interface
)

# Start the Gradio app
interface.launch(inline=True)