[GH-ISSUE #1504] DOC: Defining evaluation "success" #14

Open
opened 2026-02-17 17:18:59 -05:00 by yindo · 1 comment
Owner

Originally created by @angadn on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/1504

This quickstart now shows that evaluator callables can return a dict, optionally naming the metric with the key field. That's great, and saves me the weird fn.__name__ override I was doing previously

However, I notice the UI shows a success badge, and I'm not sure what it means - does this mean no exceptions were thrown, or am I able to somehow define thresholds for each metric to consider an evaluation as a success?

Is this somehow possible with the dict too? I'd expect evaluate/aevaluate to take some kind of lambda that sets the success field, but can't find something to this effect

Originally created by @angadn on GitHub (Jan 28, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/1504 This [quickstart](https://docs.smith.langchain.com/old/evaluation/quickstart) now shows that evaluator callables can return a `dict`, optionally naming the metric with the `key` field. That's great, and saves me the weird `fn.__name__` override I was doing previously However, I notice the UI shows a **success** badge, and I'm not sure what it means - does this mean no exceptions were thrown, or am I able to somehow define thresholds for each metric to consider an evaluation as a success? Is this somehow possible with the dict too? I'd expect `evaluate`/`aevaluate` to take some kind of lambda that sets the `success` field, but can't find something to this effect
yindo added the langsmithexternal labels 2026-02-17 17:18:59 -05:00
Author
Owner

@SeveHo commented on GitHub (Apr 9, 2025):

Same question here

@SeveHo commented on GitHub (Apr 9, 2025): Same question here
yindo changed title from DOC: Defining evaluation "success" to [GH-ISSUE #1504] DOC: Defining evaluation "success" 2026-06-05 17:24:34 -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#14