Update app.py

app.py

@@ -8,6 +8,7 @@ import os
 import time
 from langchain_groq import ChatGroq
 from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain
+from bs4 import SoupStrainer
 
 # Load environment variables (optional)
 load_dotenv()
@@ -116,9 +117,11 @@ if process_url_clicked:
             with st.spinner("Processing URL..."):
                 try:
                     st.text("Data Loading...Started...✅✅✅")
+                    # Use SoupStrainer to specify tags to parse
+                    parse_only = SoupStrainer(['title', 'p', 'h1', 'h2', 'h3'])
                     loader = WebBaseLoader(
                         web_paths=[url.strip()],
-                        bs_kwargs={"parse_only": ["title", "p", "h1", "h2", "h3"]},
+                        bs_kwargs={"parse_only": parse_only},
                         requests_kwargs={"headers": {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}}
                     )
                     data = loader.load()