Update app.py

app.py

@@ -10,6 +10,15 @@ import io
 # Load pre-trained model for question-answering
 qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
 
+# Extract text from PDF (text-based and image-based)
+def extract_text_from_pdf(pdf_path):
+    with open(pdf_path, 'rb') as file:
+        reader = PyPDF2.PdfReader(file)
+        text = ''
+        for page in reader.pages:
+            text += page.extract_text()
+    return text
+
 def extract_text_from_image_pdf(pdf_path):
     images = convert_from_path(pdf_path)
     text = ''
@@ -49,7 +58,7 @@ def extract_questions_from_text(text):
     questions = list(set(questions))  # Remove duplicates
     questions = [q for q in questions if not any(keyword in q.lower() for keyword in ['name', 'roll no', 'school'])]
     
-    return 
+    return questions
 
 # Streamlit Interface
 st.title('Student Answer Grading System')