Update app.py

app.py

@@ -8,7 +8,7 @@ import requests
 from typing import List, Dict, Union
 import pandas as pd
 import wikipediaapi
-import PyPDF
+from pypdf import PdfReader
 from docx import Document
 
 load_dotenv()
@@ -72,26 +72,24 @@ class BasicAgent:
         page = self.wiki.page(query)
         return page.summary if page.exists() else "No Wikipedia page found"
 
-    def process_document(self, file_path: str) -> str:
-        """Extract text from PDF (works with PyPDF2 or pypdf)"""
-        if not os.path.exists(file_path):
-            return "File not found"
-    
-        if file_path.lower().endswith('.pdf'):
+    def extract_pdf_text(file_path: str) -> str:
+        """Works with both pypdf and PyPDF2."""
+        try:
+            # Prefer 'pypdf' (newer)
+            from pypdf import PdfReader
+        except ImportError:
             try:
-                # Try modern pypdf first
-                from pypdf import PdfReader
-            except ImportError:
-                # Fallback to PyPDF2
+                # Fallback to 'PyPDF2'
                 from PyPDF2 import PdfReader
-        
-            try:
-                with open(file_path, 'rb') as f:
-                    reader = PdfReader(f)
-                    text = "\n".join([page.extract_text() for page in reader.pages])
-                    return text if text.strip() else "PDF has no extractable text"
-            except Exception as e:
-                return f"PDF processing error: {str(e)}"
+            except ImportError:
+                return "Error: Install 'pypdf' or 'PyPDF2' first (pip install pypdf)."
+    
+        try:
+            with open(file_path, 'rb') as f:
+                reader = PdfReader(f)
+                return "\n".join(page.extract_text() for page in reader.pages)
+        except Exception as e:
+            return f"Failed to read PDF: {str(e)}"
 
 
     def __call__(self, query: str) -> str: