config_schema() — langchain Function Reference

Architecture documentation for the config_schema() function in base.py from the langchain codebase.

Function python LangChainCore Runnables calls 1 called by 1

Entity Profile

LangChainCore→ Runnables→ config_schema() — langchain Function Reference

Dependency Diagram

graph TD
  4c94bc77_e853_aa1c_d3c6_4a29151af3df["config_schema()"]
  4a62481c_02cb_a5de_1833_50669d5351a6["Runnable"]
  4c94bc77_e853_aa1c_d3c6_4a29151af3df -->|defined in| 4a62481c_02cb_a5de_1833_50669d5351a6
  1258d561_7a56_761f_a8ae_cdd373ea7cb1["get_config_jsonschema()"]
  1258d561_7a56_761f_a8ae_cdd373ea7cb1 -->|calls| 4c94bc77_e853_aa1c_d3c6_4a29151af3df
  255c479b_b9fa_44d8_4de5_2562051e06b5["get_name()"]
  4c94bc77_e853_aa1c_d3c6_4a29151af3df -->|calls| 255c479b_b9fa_44d8_4de5_2562051e06b5
  style 4c94bc77_e853_aa1c_d3c6_4a29151af3df fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/runnables/base.py lines 525–566

    def config_schema(self, *, include: Sequence[str] | None = None) -> type[BaseModel]:
        """The type of config this `Runnable` accepts specified as a Pydantic model.

        To mark a field as configurable, see the `configurable_fields`
        and `configurable_alternatives` methods.

        Args:
            include: A list of fields to include in the config schema.

        Returns:
            A Pydantic model that can be used to validate config.

        """
        include = include or []
        config_specs = self.config_specs
        configurable = (
            create_model_v2(
                "Configurable",
                field_definitions={
                    spec.id: (
                        spec.annotation,
                        Field(
                            spec.default, title=spec.name, description=spec.description
                        ),
                    )
                    for spec in config_specs
                },
            )
            if config_specs
            else None
        )

        # Many need to create a typed dict instead to implement NotRequired!
        all_fields = {
            **({"configurable": (configurable, None)} if configurable else {}),
            **{
                field_name: (field_type, None)
                for field_name, field_type in get_type_hints(RunnableConfig).items()
                if field_name in [i for i in include if i != "configurable"]
            },
        }
        return create_model_v2(self.get_name("Config"), field_definitions=all_fields)