Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Issue: Nested Run is Empty Inside Evaluator Function #1440

Open
tobernguyen opened this issue Jan 21, 2025 · 0 comments
Open

Issue: Nested Run is Empty Inside Evaluator Function #1440

tobernguyen opened this issue Jan 21, 2025 · 0 comments

Comments

@tobernguyen
Copy link

tobernguyen commented Jan 21, 2025

Issue you'd like to raise.

For context, we’re using TypeScript Langchain + Langsmith as part of our stack, which allows us to automatically and neatly view all the traces for intermediate steps of our chatbot in the Langsmith portal.

I’m currently working on an evaluation script that inspects a run and retrieves all nested runs (e.g., from a RAG tool) to extract the retrieved documents for evaluation purposes. However, I’ve encountered an issue:

  • The Run passed to the evaluator only contains one child run, which is the root run, and this root run doesn’t contain any other child runs.

Image

  • When I inspect the same experiment in Langsmith, all the expected traces/runs are visible and appear correctly (screenshot attached for reference).

Image

Could you help troubleshoot why the nested traces are not accessible within the evaluator function? Are there additional configurations or steps I might have missed to ensure the evaluator has access to all child runs?

Langsmith version: 0.2.14

Suggestion:

No response

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant