Update app.py

app.py

@@ -1,9 +1,9 @@
 import gradio as gr
+import pandas as pd
 import re
 import os
 import fitz
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
-#dsad
 
 tokenizer = AutoTokenizer.from_pretrained("potsawee/t5-large-generation-squad-QuestionAnswer")
 model = AutoModelForSeq2SeqLM.from_pretrained("potsawee/t5-large-generation-squad-QuestionAnswer")
@@ -20,6 +20,9 @@ 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)
@@ -38,18 +41,22 @@ def generate_question_answer_pairs(pdf_file):
         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"
-
-    return result
+            
+    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,
+    outputs=[output_text, output_file],
     title=title,
 )
 interface.launch()