stream() — langchain Function Reference

Architecture documentation for the stream() function in agent.py from the langchain codebase.

Function python AgentOrchestration ToolInterface called by 2

Entity Profile

AgentOrchestration→ ToolInterface→ stream() — langchain Function Reference

Dependency Diagram

graph TD
  fff15887_2a1c_dee2_d5a0_3a5aa4536868["stream()"]
  493d4ce4_2303_08e0_2337_2bee34fe2662["AgentExecutor"]
  fff15887_2a1c_dee2_d5a0_3a5aa4536868 -->|defined in| 493d4ce4_2303_08e0_2337_2bee34fe2662
  f3744a6a_d6e6_3de9_26d0_166fe46f3862["plan()"]
  f3744a6a_d6e6_3de9_26d0_166fe46f3862 -->|calls| fff15887_2a1c_dee2_d5a0_3a5aa4536868
  dd36f14f_cc3c_6f86_0cda_844be39584a3["plan()"]
  dd36f14f_cc3c_6f86_0cda_844be39584a3 -->|calls| fff15887_2a1c_dee2_d5a0_3a5aa4536868
  style fff15887_2a1c_dee2_d5a0_3a5aa4536868 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/agent.py lines 1732–1760

    def stream(
        self,
        input: dict[str, Any] | Any,
        config: RunnableConfig | None = None,
        **kwargs: Any,
    ) -> Iterator[AddableDict]:
        """Enables streaming over steps taken to reach final output.

        Args:
            input: Input to the agent.
            config: Config to use.
            kwargs: Additional arguments.

        Yields:
            Addable dictionary.
        """
        config = ensure_config(config)
        iterator = AgentExecutorIterator(
            self,
            input,
            config.get("callbacks"),
            tags=config.get("tags"),
            metadata=config.get("metadata"),
            run_name=config.get("run_name"),
            run_id=config.get("run_id"),
            yield_actions=True,
            **kwargs,
        )
        yield from iterator