DeepEval

A framework for writing unit tests for LLM applications

What it is

An open framework bringing software testing discipline to LLM applications, letting you define assertions and metrics for outputs like unit tests and integrate them into CI.

Highlights

  • Define assertions and metrics like unit tests
  • Integrates into CI pipelines
  • Many built-in evaluation metrics
  • Supports custom evaluation logic

How to use

Install it, write test cases, run the command, then get pass rates and metrics.

License

Released under Apache-2.0. Read the terms before commercial use or redistribution, especially if you plan to offer it as a service.