The open-source LLM evaluation framework
Pytest-style testing for LLM apps: the de facto standard for evals, by Confident AI.
Who it's for
Python teams who want unit-test-style LLM evaluation with many research-backed metrics.
Official links
Keep exploring
Concepts in the glossary
1 in catalog
DeepEval is written in
1 in catalog
DeepEval features
1 in catalog
DeepEval has a pricing
1 in catalog