Overview
DeepEval brings unit-test-like evaluation to LLM applications, supporting RAG, agents, Q&A, hallucination, bias, and custom metrics for continuous validation.
Features
- Evaluation test cases
- Multi-dimensional metrics
- CI integration
DeepEval brings unit-test-like evaluation to LLM applications, supporting RAG, agents, Q&A, hallucination, bias, and custom metrics for continuous validation.