Pranjal12345's picture
Update app.py
bfca8e7
import gradio as gr
import pandas as pd
import re
import os
import fitz
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("potsawee/t5-large-generation-squad-QuestionAnswer")
model = AutoModelForSeq2SeqLM.from_pretrained("potsawee/t5-large-generation-squad-QuestionAnswer")
def extract_text_from_pdf(pdf_file_path):
doc = fitz.open(pdf_file_path)
text = ""
for page in doc:
text+=page.get_text()
return text
def generate_question_answer_pairs(pdf_file):
if pdf_file is None:
return "Please upload a PDF file"
d = {'Question':[],'Answer':[]}
df = pd.DataFrame(data=d)
pdf_text = extract_text_from_pdf(pdf_file.name)
sentences = re.split(r'(?<=[.!?])', pdf_text)
question_answer_pairs = []
for sentence in sentences:
input_ids = tokenizer.encode(sentence, return_tensors="pt")
outputs = model.generate(input_ids, max_length=100, num_return_sequences=1)
question_answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
question_answer_pairs.append(question_answer)
result = ''
for question_answer in question_answer_pairs:
qa_parts = question_answer.split("?")
if len(qa_parts) >= 2:
question_part = qa_parts[0] + "?"
answer_part = qa_parts[1].strip()
new_data = {'Question': [question_part], 'Answer': [answer_part]}
df = pd.concat([df, pd.DataFrame(new_data)], ignore_index=True)
result += f"Question: {question_part}\nAnswer: {answer_part}\n\n"
df.to_csv("QAPairs.csv")
return result, "QAPairs.csv"
title = "Question-Answer Pairs Generation"
input_file = gr.File(label="Upload a PDF file")
output_file = gr.File(label="Download as csv")
output_text = gr.Textbox()
interface = gr.Interface(
fn=generate_question_answer_pairs,
inputs=input_file,
outputs=[output_text, output_file],
title=title,
)
interface.launch()