Update app.py

app.py

@@ -20,6 +20,14 @@ summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6", to
 # Function to clean text by keeping only alphanumeric characters and spaces
 def clean_text(text):
     return re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    
+# Function to extract text from PDF files
+def extract_text(pdf_file):
+    pdf_reader = PyPDF2.PdfReader(pdf_file)
+    text = ''
+    for page_num in range(len(pdf_reader.pages)):
+        text += pdf_reader.pages[page_num].extract_text()
+    return text
 
 # Function to split text into chunks of a specified size
 def split_text(text, chunk_size=1024):