API#

The API for FlexEval is still largely undocumented, although the package is not large.

A good place to start is with the Pydantic class EvalRun, which defines the inputs expected by FlexEval.

Packages:

flexeval

FlexEval is a Python package for designing custom metrics, completion functions, and LLM-graded rubrics for evaluating the behavior of LLM-powered systems.