_parse_with_schema() — langchain Function Reference

Architecture documentation for the _parse_with_schema() function in structured_output.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 2

Entity Profile

LangChainCore→ MessageInterface→ _parse_with_schema() — langchain Function Reference

Dependency Diagram

graph TD
  b2dc3213_a7ed_bba2_9b4e_51f17afe2086["_parse_with_schema()"]
  c2936c24_74cd_6911_037b_0f67eebfefee["structured_output.py"]
  b2dc3213_a7ed_bba2_9b4e_51f17afe2086 -->|defined in| c2936c24_74cd_6911_037b_0f67eebfefee
  2e00e1b4_350b_ee3e_5dc5_f7ce23fc8893["parse()"]
  2e00e1b4_350b_ee3e_5dc5_f7ce23fc8893 -->|calls| b2dc3213_a7ed_bba2_9b4e_51f17afe2086
  0fda5ec1_1f54_5091_4c3c_0202a78dacb3["parse()"]
  0fda5ec1_1f54_5091_4c3c_0202a78dacb3 -->|calls| b2dc3213_a7ed_bba2_9b4e_51f17afe2086
  style b2dc3213_a7ed_bba2_9b4e_51f17afe2086 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/langchain/agents/structured_output.py lines 77–102

def _parse_with_schema(
    schema: type[SchemaT] | dict[str, Any], schema_kind: SchemaKind, data: dict[str, Any]
) -> Any:
    """Parse data using for any supported schema type.

    Args:
        schema: The schema type (Pydantic model, `dataclass`, or `TypedDict`)
        schema_kind: One of `'pydantic'`, `'dataclass'`, `'typeddict'`, or
            `'json_schema'`
        data: The data to parse

    Returns:
        The parsed instance according to the schema type

    Raises:
        ValueError: If parsing fails
    """
    if schema_kind == "json_schema":
        return data
    try:
        adapter: TypeAdapter[SchemaT] = TypeAdapter(schema)
        return adapter.validate_python(data)
    except Exception as e:
        schema_name = getattr(schema, "__name__", str(schema))
        msg = f"Failed to parse data to {schema_name}: {e}"
        raise ValueError(msg) from e