vanna
vanna copied to clipboard
[Feature Request] Ability to Evaluate Answers as Correct or Incorrect from Python Modules
I'm using Vanna in my Python application, and I've found that there's currently no way to evaluate the correctness of the AI's answers directly from the Python modules. This makes it difficult to provide feedback and improve the AI's performance.
Just for clarification, you're talking about the vn.ask(..)
function?
Hey this feature is now available on the flask App, but might be added inside the vn.ask function as a simple y/n input for the user after user uses the ask function
Oh yeah, I was referring to the vn.ask function (Python). I have bd using it with SQLite and it's not really possible to do anything with -- it started responding with wrong answers pretty consistently.
Oh yeah, I was referring to the vn.ask function (Python). I have bd using it with SQLite and it's not really possible to do anything with -- it started responding with wrong answers pretty consistently.
What do you have in vn.get_training_data() ?
The results will totally be dependent on what's in there