I implemented this idea as well, but for PDF articles from arXiv. It's one application everyone is doing.
Next level is to select your prompt demonstrations based on the user request. Demonstrations too can be chosen by cosine similarity. The more specific they are, the better. You can "train" such a model by adding more demonstrations, especially adding failing cases (corrected) as demos.
Next level is to select your prompt demonstrations based on the user request. Demonstrations too can be chosen by cosine similarity. The more specific they are, the better. You can "train" such a model by adding more demonstrations, especially adding failing cases (corrected) as demos.