[GH-ISSUE #1490] How to load pairwise evaluation results with Python SDK? #33

Open
opened 2026-02-17 17:19:02 -05:00 by yindo · 0 comments
Owner

Originally created by @lilavocado on GitHub (May 15, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/1490

Hello,

I would like to be able to load the pairwise evaluation results via Python SDK similar to how one could load individual experiments.

The pairwise evaluation result contains following information:

  • response from both experiments (Assistant A and Assistant B)
  • which response was better (judged by LLM-as-a-judge)
  • reason why one is better than the other (from LLM-as-a-judge)

Is there a way to do this?

Thank you?

Originally created by @lilavocado on GitHub (May 15, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/1490 Hello, I would like to be able to load the pairwise evaluation results via Python SDK similar to how one could load individual experiments. The pairwise evaluation result contains following information: - response from both experiments (Assistant A and Assistant B) - which response was better (judged by LLM-as-a-judge) - reason why one is better than the other (from LLM-as-a-judge) Is there a way to do this? Thank you?
yindo added the external label 2026-02-17 17:19:02 -05:00
yindo changed title from How to load pairwise evaluation results with Python SDK? to [GH-ISSUE #1490] How to load pairwise evaluation results with Python SDK? 2026-06-05 17:24:40 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#33