Skip to content
masterclass Buddy
Start learning

LangSmith · Function

aevaluate

Use LangSmith evaluate() to run an application on a dataset and score its outputs with evaluators. Use aevaluate() for larger Python jobs and set concurrency to parallelize work.

Last updated

Syntax

evaluate(target, data=..., evaluators=[...], metadata=..., max_concurrency=...)
aevaluate(target, data=..., evaluators=[...], metadata=..., max_concurrency=...)

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • evaluate()
  • aevaluate()
  • max_concurrency
  • maxConcurrency
  • evaluators
  • metadata

Source: How to evaluate agents - Docs by LangChain. Checked 2026-11-03.