Update app.py

app.py

@@ -2,30 +2,19 @@ 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"
+def generate_question_answer_pairs(input_text):
+    if input_text is None:
+        return "Please enter a text"
 
     d = {'Question':[],'Answer':[]}
     df = pd.DataFrame(data=d)
 
-    pdf_text = extract_text_from_pdf(pdf_file.name)
-
-    sentences = re.split(r'(?<=[.!?])', pdf_text)
+    sentences = re.split(r'(?<=[.!?])', input_text)
     question_answer_pairs = []
 
     for sentence in sentences:
@@ -49,13 +38,13 @@ def generate_question_answer_pairs(pdf_file):
     return result, "QAPairs.csv"
 
 title = "Question-Answer Pairs Generation"
-input_file = gr.File(label="Upload a PDF file")
+input_text = gr.Textbox(lines=4, label="Text:")
 output_file = gr.File(label="Download as csv")
 output_text = gr.Textbox()
 
 interface = gr.Interface(
     fn=generate_question_answer_pairs,
-    inputs=input_file,
+    inputs=input_text,
     outputs=[output_text, output_file],
     title=title,
 )