DeepEval
A testing framework for LLM applications — write unit-test-style assertions on faithfulness, relevancy, hallucination, and custom metrics.
MLOps Intermediate
Category
MLOps
Difficulty
Intermediate
When to use
You want to write automated eval suites for your RAG pipeline or LLM features and run them in CI.
When not to use
You need a one-off human eval or you're evaluating a base model's capabilities — this is for application-level testing.
Alternatives
RAGAS TruLens custom evals