_create_tool_run() — langchain Function Reference

Architecture documentation for the _create_tool_run() function in core.py from the langchain codebase.

Function python Observability Tracers

Entity Profile

Observability→ Tracers→ _create_tool_run() — langchain Function Reference

Dependency Diagram

graph TD
  bc3cf78f_617c_172b_6dd4_b8ef8845575f["_create_tool_run()"]
  70348e44_de0f_ccb4_c06a_8453289ed93e["_TracerCore"]
  bc3cf78f_617c_172b_6dd4_b8ef8845575f -->|defined in| 70348e44_de0f_ccb4_c06a_8453289ed93e
  style bc3cf78f_617c_172b_6dd4_b8ef8845575f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/tracers/core.py lines 415–453

    def _create_tool_run(
        self,
        serialized: dict[str, Any],
        input_str: str,
        run_id: UUID,
        tags: list[str] | None = None,
        parent_run_id: UUID | None = None,
        metadata: dict[str, Any] | None = None,
        name: str | None = None,
        inputs: dict[str, Any] | None = None,
        **kwargs: Any,
    ) -> Run:
        """Create a tool run."""
        start_time = datetime.now(timezone.utc)
        if metadata:
            kwargs.update({"metadata": metadata})

        if self._schema_format in {"original", "original+chat"}:
            inputs = {"input": input_str}
        elif self._schema_format == "streaming_events":
            inputs = {"input": inputs}
        else:
            msg = f"Invalid format: {self._schema_format}"
            raise AssertionError(msg)

        return Run(
            id=run_id,
            parent_run_id=parent_run_id,
            serialized=serialized,
            # Wrapping in dict since Run requires a dict object.
            inputs=inputs,
            extra=kwargs,
            events=[{"name": "start", "time": start_time}],
            start_time=start_time,
            child_runs=[],
            run_type="tool",
            tags=tags or [],
            name=name,
        )