The broken link is the bolded portion of this text:
See the tactic “Instruct the model to use retrieved knowledge to answer queries” for an example of how to use knowledge retrieval to minimize the likelihood that a model will make up incorrect facts.
They can just select that whole section and press “delete”.
Vector database knowledge retrieval injection doesn’t belong under “prompt engineering”.
There were better “how to: embeddings” cookbook examples a while ago when it was on github, but they toasted that and just put up a list of vector databases from third parties.