DeepEval
evaluation framework
Evaluation framework for LLM applications with unit test metrics
Supported languages
Pros and Cons
Ventajas
- + Metrics as unit tests
- + Pytest integration
- + Multiple metrics available
- + Red teaming included
Desventajas
- - Relatively new
- - Some metrics require LLMs
Casos de Uso
- LLM application testing
- RAG evaluation
- CI/CD for AI