All about evaluating Large language models

Great Piece. Thanks! One clarification though... you've shown "# {'ragas_score': 0.860, 'context_relavency': 0.817, # 'factuality': 0.892, 'answer_relevancy': 0.874}" as part of your ragas.py github snippet.

Does ragas indeed compute "factuality" score as well? Could see all others in the source code, but not this one....

Great overview of the landscape of evaluation approaches.