LangWatch Evaluation icon

LangWatch Evaluation

Check if evaluating, record results, run and record evaluators; optionally set outputs to dataset (auto writes to dataset only when not running from a dataset/batch).

Actions5

Check If Evaluating

AI-generated

Summary

Routes each incoming item based on whether a LangWatch evaluation run context is present.

Inputs

None.

Output shape

Two parallel arrays of items. Output 1 contains items where evaluation is in progress; Output 2 contains items where it is not.

Each output item has its JSON augmented with isEvaluating: boolean reflecting the check result.

Examples

Example 1: Item with _langwatch.batch.runId present

Item routes to evaluating output with isEvaluating: true

Example 2: Item without evaluation context

Item routes to else output with isEvaluating: false

Discussion