LangGraph · Class
Pregel
Pregel is LangGraph's runtime for applications made of actors and channels. It runs actors in synchronized steps and updates channels between steps.
Last updated
- Since
- v1.2
Syntax
Pregel(self, *, nodes: dict[str, PregelNode | NodeBuilder], channels: dict[str, BaseChannel | ManagedValueSpec] | None, auto_validate: bool = True, stream_mode: StreamMode = 'values', stream_eager: bool = False, output_channels: str | Sequence[str], stream_channels: str | Sequence[str] | None = None, interrupt_after_nodes: All | Sequence[str] = (), interrupt_before_nodes: All | Sequence[str] = (), input_channels: str | Sequence[str], step_timeout: float | None = None, debug: bool | None = None, checkpointer: Checkpointer = None, store: BaseStore | None = None, cache: BaseCache | None = None, retry_policy: RetryPolicy | Sequence[RetryPolicy] = (), cache_policy: CachePolicy | None = None, context_schema: type[ContextT] | None = None, config: RunnableConfig | None = None, trigger_to_nodes: Mapping[str, ...] | None = None, name: str = 'LangGraph', stream_transformers: Sequence[Callable] | None = None, deprecated_kwargs: Unpack[DeprecatedKwargs] = {})In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.
SubscribeRelated
PregelNodeNodeBuilderStateGraphFunctional APILastValueTopicEphemeralValueBinaryOperatorAggregate