Update app.py

app.py

@@ -96,6 +96,7 @@ async def run_samba_api_inference(query, system_prompt = None, ignore_context=Fa
     except requests.exceptions.HTTPError as e:
         if post_response.status_code in {401, 503, 504, 429}:
             print(f"Attempt failed due to rate limit or gate timeout. Status code: {post_response.status_code}. Trying again in {num_seconds_to_sleep} seconds...")
+            st.info("Rate limit hit because of all the pipelined queries, wait one second...")
             await asyncio.sleep(num_seconds_to_sleep)
             return await run_samba_api_inference(query)  # Retry the request
         else: