Update app.py

app.py

@@ -1,3 +1,4 @@
+import requests
 import os
 import streamlit as st
 import pickle
@@ -8,7 +9,6 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.document_loaders import UnstructuredURLLoader
 from langchain_groq import ChatGroq
 from langchain.vectorstores import FAISS
-import numpy as np
 
 from dotenv import load_dotenv
 load_dotenv()  # take environment variables from .env (especially openai api key)
@@ -27,11 +27,36 @@ file_path = "faiss_store_openai.pkl"
 main_placeholder = st.empty()
 llm = ChatGroq(model_name="llama-3.3-70b-versatile", temperature=0.9, max_tokens=500)
 
+# Debugging: Check if URLs are accessible
+def check_url(url):
+    try:
+        response = requests.get(url)
+        if response.status_code == 200:
+            return True
+        else:
+            return False
+    except Exception as e:
+        return False
+
 if process_url_clicked:
+    # Debugging: Verify URL accessibility
+    valid_urls = []
+    for url in urls:
+        if check_url(url):
+            valid_urls.append(url)
+        else:
+            main_placeholder.text(f"URL is not accessible: {url}")
+    
+    if not valid_urls:
+        main_placeholder.text("None of the URLs are accessible.")
+    
     # Load data from URLs
-    loader = UnstructuredURLLoader(urls=urls)
+    loader = UnstructuredURLLoader(urls=valid_urls)
     main_placeholder.text("Data Loading...Started...✅✅✅")
-    data = loader.load()
+    try:
+        data = loader.load()
+    except Exception as e:
+        main_placeholder.text(f"Error loading data: {e}")
     
     # Split data into chunks
     text_splitter = RecursiveCharacterTextSplitter(
@@ -66,7 +91,7 @@ if process_url_clicked:
     # Convert embeddings to numpy array (needed by FAISS)
     embeddings_np = np.array(embeddings).astype(np.float32)
     
-    # Check the shape of the embeddings
+    # Check the shape of embeddings
     main_placeholder.text(f"Shape of embeddings: {embeddings_np.shape}")
     
     # Create FAISS index