Update app.py

app.py

@@ -17,11 +17,13 @@ vector_store = None
 retriever = None
 
 def extract_text_from_pdf(filepath):
-    loader = UnstructuredLoader([filepath])
+    chunk_size = 1000  # Example chunk size
+    overlap = 100      # Example overlap
+    loader = UnstructuredLoader([filepath], chunk_size=chunk_size, overlap=overlap)
     pages = []
     for doc in loader.lazy_load():
         pages.append(doc)
-    return "\n".join([page.content for page in pages])
+    return "\n".join([page.contents for page in pages])
 
 def extract_tables_from_pdf(filepath):
     tables = camelot.read_pdf(filepath, pages='1-end')