Method●Since v1.0

stream

Executes the agent with streaming, returning an async iterable of state updates as they occur.

This method runs the agent's workflow similar to invoke, but instead of waiting for completion, it streams high-level state updates in real-time. This allows you to:

Display intermediate results to users as they're generated
Monitor the agent's progress through each step
React to state changes as nodes complete

For more granular event-level streaming (like individual LLM tokens), use streamEvents instead.

stream<
  TStreamMode extends StreamMode | StreamMode[] | undefined,
  TSubgraphs extends boolean,
  TEncoding extends "text/event-stream" | undefined
>(
  state: InvokeStateParameter<Types>,
  config: StreamConfiguration<InferContextInput<Types["Context"] extends InteropZodObject | AnyAnnotationRoot  any[any] : AnyAnnotationRoot>  InferMiddlewareContextInputs<Types["Middleware"]>, TStreamMode, TSubgraphs, TEncoding>
): Promise<IterableReadableStream<StreamOutputMap<TStreamMode, TSubgraphs, MergedAgentState<Types>, MergedAgentState<Types>, string, unknown, unknown, TEncoding>>>

Parameters

Name	Type	Description
`state`*	`InvokeStateParameter<Types>`	The initial state for the agent execution. Can be: An object containing `messages` array and any middleware-specific state properties A Command object for more advanced control flow
`config`	`StreamConfiguration<InferContextInput<Types["Context"] extends InteropZodObject \| AnyAnnotationRoot ? any[any] : AnyAnnotationRoot> & InferMiddlewareContextInputs<Types["Middleware"]>, TStreamMode, TSubgraphs, TEncoding>`	Optional runtime configuration including:

Example

const agent = new ReactAgent({
  llm: myModel,
  tools: [calculator, webSearch]
});

const stream = await agent.stream({
  messages: [{ role: "human", content: "What's 2+2 and the weather in NYC?" }]
});

for await (const chunk of stream) {
  console.log(chunk); // State update from each node
}

View source on GitHub

stream

Executes the agent with streaming, returning an async iterable of state updates as they occur.

This method runs the agent's workflow similar to invoke, but instead of waiting for completion, it streams high-level state updates in real-time. This allows you to:

Display intermediate results to users as they're generated
Monitor the agent's progress through each step
React to state changes as nodes complete

For more granular event-level streaming (like individual LLM tokens), use streamEvents instead.

stream< TStreamMode extends StreamMode | StreamMode[] | undefined, TSubgraphs extends boolean, TEncoding extends "text/event-stream" | undefined >( state: InvokeStateParameter<Types>, config: StreamConfiguration<InferContextInput<Types["Context"] extends InteropZodObject | AnyAnnotationRoot any[any] : AnyAnnotationRoot> InferMiddlewareContextInputs<Types["Middleware"]>, TStreamMode, TSubgraphs, TEncoding> ): Promise<IterableReadableStream<StreamOutputMap<TStreamMode, TSubgraphs, MergedAgentState<Types>, MergedAgentState<Types>, string, unknown, unknown, TEncoding>>>

Parameters

Name	Type	Description
`state`*	`InvokeStateParameter<Types>`	The initial state for the agent execution. Can be: An object containing `messages` array and any middleware-specific state properties A Command object for more advanced control flow
`config`	`StreamConfiguration<InferContextInput<Types["Context"] extends InteropZodObject \| AnyAnnotationRoot ? any[any] : AnyAnnotationRoot> & InferMiddlewareContextInputs<Types["Middleware"]>, TStreamMode, TSubgraphs, TEncoding>`	Optional runtime configuration including:

const agent = new ReactAgent({ llm: myModel, tools: [calculator, webSearch] }); const stream = await agent.stream({ messages: [{ role: "human", content: "What's 2+2 and the weather in NYC?" }] }); for await (const chunk of stream) { console.log(chunk); // State update from each node }

stream

Parameters

Example

LangChain Assistant

Menu

stream

Parameters

Example