Evaluation Libraries

This note aggregates libraries used for evaluating LLM applications.

• DeepEval - https://docs.confident-ai.com/
• RAGAS - https://docs.ragas.io/en/stable/
  • [RAGAS: Automated Evaluation]( https://arxiv.org/pdf/2309.15217
• TruLens - https://www.trulens.org/
• Arize AI
• Promptfoo - https://www.promptfoo.dev/