init() — langchain Function Reference

Architecture documentation for the __init__() function in pii.py from the langchain codebase.

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ __init__() — langchain Function Reference

Dependency Diagram

graph TD
  fa1679df_f25b_9844_3766_68a5bcbba53c["__init__()"]
  dc527b75_da40_4d1c_e472_82d1252ba70b["PIIMiddleware"]
  fa1679df_f25b_9844_3766_68a5bcbba53c -->|defined in| dc527b75_da40_4d1c_e472_82d1252ba70b
  style fa1679df_f25b_9844_3766_68a5bcbba53c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/langchain/agents/middleware/pii.py lines 100–154

    def __init__(
        self,
        # From a typing point of view, the literals are covered by 'str'.
        # Nonetheless, we escape PYI051 to keep hints and autocompletion for the caller.
        pii_type: Literal["email", "credit_card", "ip", "mac_address", "url"] | str,  # noqa: PYI051
        *,
        strategy: Literal["block", "redact", "mask", "hash"] = "redact",
        detector: Callable[[str], list[PIIMatch]] | str | None = None,
        apply_to_input: bool = True,
        apply_to_output: bool = False,
        apply_to_tool_results: bool = False,
    ) -> None:
        """Initialize the PII detection middleware.

        Args:
            pii_type: Type of PII to detect.

                Can be a built-in type (`email`, `credit_card`, `ip`, `mac_address`,
                `url`) or a custom type name.
            strategy: How to handle detected PII.

                Options:

                * `block`: Raise `PIIDetectionError` when PII is detected
                * `redact`: Replace with `[REDACTED_TYPE]` placeholders
                * `mask`: Partially mask PII (show last few characters)
                * `hash`: Replace with deterministic hash (format: `<type_hash:digest>`)

            detector: Custom detector function or regex pattern.

                * If `Callable`: Function that takes content string and returns
                    list of `PIIMatch` objects
                * If `str`: Regex pattern to match PII
                * If `None`: Uses built-in detector for the `pii_type`
            apply_to_input: Whether to check user messages before model call.
            apply_to_output: Whether to check AI messages after model call.
            apply_to_tool_results: Whether to check tool result messages after tool execution.

        Raises:
            ValueError: If `pii_type` is not built-in and no detector is provided.
        """
        super().__init__()

        self.apply_to_input = apply_to_input
        self.apply_to_output = apply_to_output
        self.apply_to_tool_results = apply_to_tool_results

        self._resolved_rule: ResolvedRedactionRule = RedactionRule(
            pii_type=pii_type,
            strategy=strategy,
            detector=detector,
        ).resolve()
        self.pii_type = self._resolved_rule.pii_type
        self.strategy = self._resolved_rule.strategy
        self.detector = self._resolved_rule.detector