Update app.py

app.py

@@ -13,15 +13,23 @@ import pickle
 # Function to extract text from a PDF file
 def extract_text_from_pdf(pdf_path):
     text = ""
-    doc = fitz.open(pdf_path)
-    for page in doc:
-        text += page.get_text()
+    try:
+        doc = fitz.open(pdf_path)
+        for page_num in range(len(doc)):
+            page = doc.load_page(page_num)
+            text += page.get_text()
+    except Exception as e:
+        print(f"Error extracting text from PDF: {e}")
     return text
 
 # Function to extract text from a Word document
 def extract_text_from_docx(docx_path):
-    doc = Document(docx_path)
-    text = "\n".join([para.text for para in doc.paragraphs])
+    text = ""
+    try:
+        doc = Document(docx_path)
+        text = "\n".join([para.text for para in doc.paragraphs])
+    except Exception as e:
+        print(f"Error extracting text from DOCX: {e}")
     return text
 
 # Initialize the embedding model