confident-ai/deepeval

Evaluation Dataset Generation

Aperta

#530 aperta il 26 feb 2024

 (3 commenti) (0 reazioni) (1 assegnatario)Python (1677 fork)auto 404
enhancementhelp wanted

Metriche repository

Star
 (16.939 stelle)
Metriche merge PR
 (Merge medio 4g 16h) (26 PR mergiate in 30 g)

Descrizione

Evaluation dataset generation is coming to deepeval by end of this week. For this feature, we're looking at the following:

  1. Allow users to generate test cases based on their knowledge base
  2. Allow users to choose how to chunk their knowledge base
  3. Allow users to specify how many test cases to generate
  4. Allow users to complicate test cases to make them more realistic (https://arxiv.org/pdf/2304.12244.pdf, https://mlabonne.github.io/blog/notes/Large%20Language%20Models/phi1.htm)

Feedback, suggestions, and contributions for any of the points above are welcomed 😊

Guida contributor