Scorers are used to score the output of your LLM call.
Autoevals is a great library of scorers to get you started.
You can create your own using createScorer
:
The name
and description
of the scorer will be displayed in the Evalite UI.
Score Properties
The score
function receives three properties on the object passed:
Type Arguments
In TypeScript, createScorer
takes two type arguments, the input and output type:
You can provide metadata along with your custom scorer:
This will be visible along with the score in the Evalite UI.