You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm noticing extract_fields sometimes get back N/A or None values instead of strings. We can tweak the prompt, but this also helps:
define_fields_from_dict({k: v for k,v in answers.items() if (v is not None) and str(v).lower() != "n/a"})
The GoalSatisficationList is a bit too lazy. We should be able to tweak how aggressive we want to be in getting good responses. It's a big difference if it's a student reflection or a legal document. Check the prompt to see if it can be improved but also we should add a parameter somewhere for custom instructions or just to tune how aggressive it will be.
The text was updated successfully, but these errors were encountered:
I'm noticing extract_fields sometimes get back N/A or None values instead of strings. We can tweak the prompt, but this also helps:
The GoalSatisficationList is a bit too lazy. We should be able to tweak how aggressive we want to be in getting good responses. It's a big difference if it's a student reflection or a legal document. Check the prompt to see if it can be improved but also we should add a parameter somewhere for custom instructions or just to tune how aggressive it will be.
The text was updated successfully, but these errors were encountered: