import gradio as gr
import numpy as np
import pytesseract as pt
import pdf2image
from fpdf import FPDF
import re
import nltk
from nltk.tokenize import sent_tokenize
from nltk.tokenize import word_tokenize
import os
import pdfkit
import yake
from summarizer import Summarizer,TransformerSummarizer
from transformers import pipelines
#nltk.download('punkt')

from transformers import AutoTokenizer, AutoModelForPreTraining
model_name = 'nlpaueb/legal-bert-base-uncased'


tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForPreTraining.from_pretrained(model_name)
bert_legal_model = Summarizer(custom_model=model, custom_tokenizer=tokenizer)
 


def get_response(input_text):
    output_text= bert_legal_model(input_text,  min_length = 8, ratio = 0.05)
    return output_text
    
    
iface = gr.Interface(
    get_response, 
    "text", 
    "text"
   )

if __name__ == "__main__":
    iface.launch(share=False)