Turning off the expensive or broken part and keeping the rest working, and telling the user what they are not getting.
You have done this if
When retrieval failed, the assistant said it could not reach the documents instead of answering from memory.
Say it in a review
If retrieval is down we answer with 'I can't reach the sources right now', never an ungrounded guess.
On the AI Application map Retrieval, Web App
Read Why weak evidence should trigger recovery, not confidence