OpenEvals

OpenEvals is an open-source Python library providing ready-made evaluators for Large Language Model (LLM) applications. It offers a structured approach to LLM evaluation, similar to traditional software testing, with built-in functionalities like LLM-as-judge evaluators and prebuilt prompts for common evaluation scenarios such as correctness, conciseness, and hallucination detection. Developed by LangChain, it aims to streamline the process of bringing LLM applications to production by making evaluation more accessible and transparent. The current version is 0.2.0, with ongoing development and updates.