confident-ai / deepeval

The LLM Evaluation Framework
https://docs.confident-ai.com/
Apache License 2.0
2.91k stars 213 forks source link

Typo in bias metric (too many values to unpack (expected 2)) #909

Open damagode opened 1 month ago

damagode commented 1 month ago

❗BEFORE YOU BEGIN❗ Are you on discord? 🤗 We'd love to have you asking questions on discord instead: https://discord.com/invite/a3K9c8GRGt

Describe the bug I think there is a typo in the bias metric that is causing some issues, here: https://github.com/confident-ai/deepeval/blob/main/deepeval/metrics/bias/bias.py#L164

I think it should be just res = self.model.generate(prompt) since we are not using the native model

To Reproduce Steps to reproduce the behavior:

  1. Create a custom client from DeepEvalBaseLLM
  2. Execute the bias metric
  3. See error ( too many values to unpack (expected 2) )

Expected behavior A clear and concise description of what you expected to happen.

Screenshots If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

Smartphone (please complete the following information):

Additional context Thank you in advance, you are doing a great job!!!!

penguine-ip commented 1 month ago

Hey @damagode , thanks for the error reporting, i'm wondering do you have the error message in full?

damagode commented 1 month ago

@penguine-ip

{ValueError}ValueError('too many values to unpack (expected 2)') 
penguine-ip commented 1 month ago

@damagode i see thanks for bringign it up, fixing !