Show HN: Ragas – Open-source library for evals and testing RAG systems

  • The synthetic test data generation seems very useful. Do you have any idea of the cost of running this?

  • How does Ragas handle the challenge of adapting traditional ML testing methodologies to suit the intricacies of LLM applications?

  • How is the synthetic test data generation done in ragas?

    Can I use custom Open source models like Mistral 7B to generate synthetic test data?

  • Is there support to open-source models? btw love your work!!

  • How do you actually use models for evaluation?

  • Can I use OSS models like Mixtral with it?