Update app.py

app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 import re
 import os
-from langchain.chains import ConversationalRetrievalChain
 from langchain_chroma import Chroma
 from langchain_community.document_loaders import WebBaseLoader
 from langchain_core.output_parsers import StrOutputParser
@@ -109,9 +108,20 @@ query = st.text_input("Ask a question based on the blog post", placeholder="Type
 if 'chat_history' not in st.session_state:
     st.session_state['chat_history'] = []
 
+# CustomLanguageModel class with proper context argument
+class CustomLanguageModel:
+    def generate(self, prompt, context):
+        # This function should handle both prompt and context
+        # For now, we return a placeholder response for demo purposes
+        return f"Generated response based on '{prompt}' and context provided."
+
 # Submit button for chat
 if st.button("Submit Query"):
-    if query and url_input:
+    if not query:
+        st.warning("Please enter a query before submitting!")
+    elif not url_input:
+        st.warning("Please enter a valid URL in the sidebar.")
+    else:
         # Blog loading logic based on user input URL
         loader = WebBaseLoader(
             web_paths=(url_input,),  # Use the user-input URL
@@ -137,15 +147,9 @@ if st.button("Submit Query"):
         def format_docs(docs):
             return "\n\n".join(doc.page_content for doc in docs)
 
-        # Replace llm with an appropriate model or implement your logic
-        class CustomLanguageModel:
-            def generate(self, prompt, context):
-                # Custom implementation or call to an API
-                # For demonstration, let's use a simple placeholder response
-                return f"Response to query '{prompt}' based on context."
-
+        # Initialize the language model
         custom_llm = CustomLanguageModel()
-        
+
         rag_chain = (
             {"context": retriever | format_docs, "question": RunnablePassthrough()}
             | prompt