Skip to content

Instantly share code, notes, and snippets.

@hshujuan
Last active February 20, 2024 23:32
Show Gist options
  • Save hshujuan/4ed8e76a3dc082075a4d97a11ed3bf20 to your computer and use it in GitHub Desktop.
Save hshujuan/4ed8e76a3dc082075a4d97a11ed3bf20 to your computer and use it in GitHub Desktop.
Evaluation frameworks Details Reference
RAGAs A framework that helps us evaluate our Retrieval Augmented Generation (RAG) pipeline Docs, Code
ARES An Automated Evaluation Framework for Retrieval-Augmented Generation Systems Link
RAG Triad of metrics RAG Triad of metrics RAG triad: Answer Relevance (Is the final response useful), Context Relevance (How good is the retrieval), and Groundedness (Is the response supported by the context). Trulens and LLMA index work together for the evaluation. DeepLearning.AI Course
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment