Skip to content
masterclass Buddy
Start learning

LangSmith · Function

run_on_dataset

Runs a language model or chain on every example in a dataset. It can evaluate outputs, run tasks concurrently, and store traces in a named project.

Last updated

Since
v1.4

Syntax

async arun_on_dataset(client: Client | None, dataset_name: str, llm_or_chain_factory: MODEL_OR_CHAIN_FACTORY, *, evaluation: smith_eval.RunEvalConfig | None = None, dataset_version: datetime | str | None = None, concurrency_level: int = 5, project_name: str | None = None, project_metadata: dict[str, Any] | None = None, verbose: bool = False, revision_id: str | None = None, kwargs: Any = {}) -> dict[str, Any]

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

Subscribe
  • run_on_dataset
  • RunEvalConfig
  • StringRunEvaluatorChain
  • load_evaluator
  • EvaluatorType

Source: arun_on_dataset | langchain_classic | LangChain Reference. Checked 2026-11-03.