---
title: "Comment by Shivam Sharma on \"All about evaluating Large language models\" | Hashnode"
description: "Great Piece. Thanks! One clarification though... you&#39;ve shown &quot;# {&#39;ragas_score&#39;: 0.860, &#39;context_relavency&#39;: 0.817, # &#39;factuality&#"
url: "https://hashnode.com/posts/all-about-evaluating-large-language-models/64a41110b768fa68a1d75b8e/comment/64fa2aa7c035cd988c3258b4"
---

[Discussion](https://hashnode.com/posts/all-about-evaluating-large-language-models/64a41110b768fa68a1d75b8e)

Comment [All about evaluating Large language models](https://hashnode.com/posts/all-about-evaluating-large-language-models/64a41110b768fa68a1d75b8e)

[Shivam Sharma](https://hashnode.com/@shiv6891)

[Sep 7, 2023](https://hashnode.com/posts/all-about-evaluating-large-language-models/64a41110b768fa68a1d75b8e/comment/64fa2aa7c035cd988c3258b4)

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....
