Update app.py

app.py

@@ -1,6 +1,15 @@
 import gradio as gr
 import requests
 import re
+import fitz
+
+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
 
 API_URL = "https://api-inference.huggingface.co/models/potsawee/t5-large-generation-squad-QuestionAnswer"
 headers = {"Authorization": "Bearer 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"}
@@ -9,11 +18,13 @@ def query(payload):
 	response = requests.post(API_URL, headers=headers, json=payload)
 	return response.json()
     
-def generate_question_answer_pairs(input_text):
-    if input_text is None:
-        return "Please enter a text"
+def generate_question_answer_pairs(input_file):
+    if input_file is None:
+        return "Please upload a file"
+
+    pdf_text = extract_text_from_pdf(input_file)
 
-    sentences = re.split(r'(?<=[.!?])', input_text)
+    sentences = re.split(r'(?<=[.!?])', pdf_text)
     outputs = [] 
 
     for sentence in sentences:
@@ -26,12 +37,12 @@ def generate_question_answer_pairs(input_text):
     return outputs
 
 title = "Question-Answer Pairs Generation"
-input_text = gr.Textbox(lines=4, label="Text:")
+input_file = gr.File(label="Upload a PDF file")
 output_text = gr.Textbox()
 
 interface = gr.Interface(
     fn=generate_question_answer_pairs,
-    inputs=input_text,
+    inputs=input_file,
     outputs=output_text,
     title=title,
 )