Ragas

Evaluation toolkit for RAG pipelines and LLM applications.

Ragas is an open-source framework for evaluating and testing LLM applications, with a strong focus on retrieval-augmented generation. It provides reference-free metrics such as faithfulness, answer relevancy, and context precision/recall, plus tooling to generate synthetic test sets. It integrates with LangChain, LlamaIndex, and observability tools to bring objective scoring into CI and experiment loops.