Skip to main content

Ragas

Ragas is a framework to help you evaluate your retrieval augmented generation (RAG) applications.

Ragas and Weaviate​

The Ragas metrics are:

  • faithfulness
  • answer_relevancy
  • context_precision
  • context_recall

To use Ragas, you'll need to store the question, answer, ground_truths, and contexts in a json object to send to Ragas.

Our Resources​

Hands on Learning: Build your technical understanding with end-to-end tutorials.

Hands on Learning​

TopicDescriptionResource
Introduction Ragas DemoLearn how to use Weaviate and RagasNotebook
Ragas and LangChainLearn how to connect Ragas and LangChain.Notebook