Joshua Nielsen

Even if we limit queries to the `completions` endpoint to prompts with context in the embeddings db ([as mentioned above](https://github.com/openai/openai-cookbook/issues/157#issuecomment-1444120327)), this doesn't fully prevent the vulnerability of someone co-opting a...

Maybe a solution is to append (opposed to prepend) the context to the user prompt 🤔 Has anyone tried this?