Update file_processing.py

file_processing.py

@@ -3,6 +3,25 @@ import PyPDF2
 import docx
 import pandas as pd
 from io import BytesIO
+import streamlit as st
+
+MAX_FILE_SIZE_MB = 10
+
+def validate_and_extract(uploaded_file):
+    """
+    Checks size and extracts text. Returns (text, error_message)
+    """
+    # 1. Size Check
+    file_size_mb = uploaded_file.size / (1024 * 1024)
+    if file_size_mb > MAX_FILE_SIZE_MB:
+        return None, f"⚠️ File too large ({file_size_mb:.2f}MB). Limit is {MAX_FILE_SIZE_MB}MB. For larger files, please use the RAG system."
+
+    # 2. Extract Text (Reuse previous logic)
+    try:
+        text = extract_text_from_file(uploaded_file) # Calling your internal function
+        return text, None
+    except Exception as e:
+        return None, f"Error parsing file: {str(e)}"
 
 def extract_text_from_file(uploaded_file):
     """