Improve responsiveness by asynchronously retrieving web search context

- Run web search lookup in a background thread to decouple it from prompt construction.
- Add a 2-second timeout using thread.join(timeout=2) to prevent delaying response generation.
- Fallback to using only the system prompt and user query if web search results aren't retrieved in time.
- Update sidebar UI to show the fetched context or a "No context found" message.
- Retain current streaming and chat history functionalities for model inference.

app.py

@@ -267,10 +267,20 @@ if user_input:
         
         st.session_state.pending_response = True
         
-        # Retrieve web search context if enabled
+        # Retrieve web search context asynchronously, with a timeout, if enabled
         retrieved_context = ""
         if enable_search:
-            retrieved_context = retrieve_context(user_input, max_results=max_results, max_chars_per_result=max_chars_per_result)
+            result_list = []
+            def run_search():
+                result = retrieve_context(user_input, max_results=max_results, max_chars_per_result=max_chars_per_result)
+                result_list.append(result)
+            search_thread = threading.Thread(target=run_search)
+            search_thread.start()
+            # Wait only up to 2 seconds for the search to return
+            search_thread.join(timeout=2)
+            if result_list:
+                retrieved_context = result_list[0]
+            # Display whichever result (or lack thereof) in the sidebar
             with st.sidebar:
                 st.markdown("### Retrieved Context")
                 st.text_area("", value=retrieved_context or "No context found.", height=150)