Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 from dotenv import load_dotenv
-from langchain_community.document_loaders.url import UnstructuredURLLoader
+from langchain_community.document_loaders import WebBaseLoader
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores.faiss import FAISS
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -55,11 +55,11 @@ if process_url_clicked:
     else:
         try:
             main_placeholder.text("Data Loading...Started...✅✅✅")
-            loader = UnstructuredURLLoader(urls=urls)
+            loader = WebBaseLoader(urls)
             data = loader.load()
 
-            # Debug: Check loaded data
-            if not data:
+            # Check loaded data
+            if not data or all(len(doc.page_content.strip()) == 0 for doc in data):
                 main_placeholder.error("No content loaded from URLs. Try different URLs.")
                 st.stop()
 
@@ -70,7 +70,6 @@ if process_url_clicked:
             )
             docs = text_splitter.split_documents(data)
 
-            # Debug: Check document count
             main_placeholder.text(f"Split into {len(docs)} document chunks.")
 
             main_placeholder.text("Embedding Vector Started Building...✅✅✅")
@@ -81,7 +80,7 @@ if process_url_clicked:
             st.session_state.index_created = True
             main_placeholder.text("FAISS index saved successfully! ✅✅✅")
             time.sleep(2)
-            main_placeholder.empty()  # Clear status messages
+            main_placeholder.empty()
         except Exception as e:
             main_placeholder.error(f"Error processing URLs: {str(e)}")
 
@@ -97,7 +96,6 @@ if query:
                 chain = RetrievalQAWithSourcesChain.from_llm(llm=llm, retriever=vectorstore.as_retriever())
                 result = chain({"question": query}, return_only_outputs=True)
 
-                # Debug: Check result
                 if not result.get("answer"):
                     main_placeholder.warning("No answer generated. Try a different question or URLs.")
                     st.stop()