Updating to 4 min.

app.py

@@ -46,7 +46,7 @@ def bot(history, hyde=False):
     document_start = perf_counter()
     if hyde:
         hyde_document = generate(f"Write a wikipedia article intro paragraph to answer this query: {query}").split(
-            '### Response: [|AI|]')[-1]
+                '### Response: [|AI|]')[-1]
 
         logger.warning(hyde_document)
         documents = retriever(hyde_document, top_k=top_k)
@@ -90,7 +90,7 @@ You can see the prompt clearly displayed below the chatbot to understand what is
 
 # Read this if you get an error
 I'm using Inference Endpoint's Scale to Zero to save money on GPUs. If the staus shows its not "Running" send a 
-chat to wake it up. You will get a `500 error` and it will take ~7 min to wake up.
+chat to wake it up. You will get a `500 error` and it will take ~7 minutes to wake up.
 """