Update app.py

app.py

@@ -8,8 +8,7 @@ import requests
 from typing import List, Dict, Union
 import pandas as pd
 import wikipediaapi
-import pypdf
-from pypdf import PdfReader
+from pdfminer.high_level import extract_text
 from docx import Document
 
 load_dotenv()
@@ -73,24 +72,13 @@ class BasicAgent:
         page = self.wiki.page(query)
         return page.summary if page.exists() else "No Wikipedia page found"
 
-    def extract_pdf_text(file_path: str) -> str:
-        """Works with both pypdf and PyPDF2."""
+   
+    def _process_pdf(self, file_path: str) -> str:
+        """Extract text from PDF using pdfminer.six (no PyPDF2/pypdf needed)."""
         try:
-            # Prefer 'pypdf' (newer)
-            from pypdf import PdfReader
-        except ImportError:
-            try:
-                # Fallback to 'PyPDF2'
-                from PyPDF2 import PdfReader
-            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)
+            return extract_text(file_path)
         except Exception as e:
-            return f"Failed to read PDF: {str(e)}"
+            return f"PDF processing error: {str(e)}"
 
 
     def __call__(self, query: str) -> str: