Function●Since v1.1

piiMiddleware

Creates a middleware that detects and handles personally identifiable information (PII) in conversations.

This middleware detects common PII types and applies configurable strategies to handle them. It can detect emails, credit cards, IP addresses, MAC addresses, and URLs in both user input and agent output.

Built-in PII types:

email: Email addresses
credit_card: Credit card numbers (validated with Luhn algorithm)
ip: IP addresses (validated)
mac_address: MAC addresses
url: URLs (both http/https and bare URLs)

Strategies:

block: Raise an exception when PII is detected
redact: Replace PII with [REDACTED_TYPE] placeholders
mask: Partially mask PII (e.g., ****-****-****-1234 for credit card)
hash: Replace PII with deterministic hash (e.g., <email_hash:a1b2c3d4>)

Strategy Selection Guide:

Strategy	Preserves Identity?	Best For
`block`	N/A	Avoid PII completely
`redact`	No	General compliance, log sanitization
`mask`	No	Human readability, customer service UIs
`hash`	Yes (pseudonymous)	Analytics, debugging

piiMiddleware(
  piiType: string,
  options: __type = {}
): AgentMiddleware<StateDefinitionInit | undefined>

Parameters

Name	Type	Description
`piiType`*	`string`	Type of PII to detect. Can be a built-in type (`email`, `credit_card`, `ip`, `mac_address`, `url`) or a custom type name.
`options`	`__type`	Default:`{}` Configuration options

Example 1

import { piiMiddleware } from "langchain";
import { createAgent } from "langchain";

// Redact all emails in user input
const agent = createAgent({
  model: "openai:gpt-4",
  middleware: [
    piiMiddleware("email", { strategy: "redact" }),
  ],
});

Example 2

const agent = createAgent({
  model: "openai:gpt-4o",
  middleware: [
    piiMiddleware("credit_card", { strategy: "mask" }),
    piiMiddleware("url", { strategy: "redact" }),
    piiMiddleware("ip", { strategy: "hash" }),
  ],
});

Example 3

const agent = createAgent({
  model: "openai:gpt-4",
  middleware: [
    piiMiddleware("api_key", {
      detector: "sk-[a-zA-Z0-9]{32}",
      strategy: "block",
    }),
  ],
});

View source on GitHub

piiMiddleware

Creates a middleware that detects and handles personally identifiable information (PII) in conversations.

Built-in PII types:

email: Email addresses
credit_card: Credit card numbers (validated with Luhn algorithm)
ip: IP addresses (validated)
mac_address: MAC addresses
url: URLs (both http/https and bare URLs)

Strategies:

block: Raise an exception when PII is detected
redact: Replace PII with [REDACTED_TYPE] placeholders
mask: Partially mask PII (e.g., ****-****-****-1234 for credit card)
hash: Replace PII with deterministic hash (e.g., <email_hash:a1b2c3d4>)

Strategy Selection Guide:

Strategy	Preserves Identity?	Best For
`block`	N/A	Avoid PII completely
`redact`	No	General compliance, log sanitization
`mask`	No	Human readability, customer service UIs
`hash`	Yes (pseudonymous)	Analytics, debugging

Name

Type

Description

piiType*

string

Type of PII to detect. Can be a built-in type (email, credit_card, ip, mac_address, url) or a custom type name.

options

__type

Default:{}

Configuration options

import { piiMiddleware } from "langchain"; import { createAgent } from "langchain"; // Redact all emails in user input const agent = createAgent({ model: "openai:gpt-4", middleware: [ piiMiddleware("email", { strategy: "redact" }), ], });

const agent = createAgent({ model: "openai:gpt-4o", middleware: [ piiMiddleware("credit_card", { strategy: "mask" }), piiMiddleware("url", { strategy: "redact" }), piiMiddleware("ip", { strategy: "hash" }), ], });

piiMiddleware

Parameters

Example 1

Example 2

Example 3

LangChain Assistant

Menu

piiMiddleware

Parameters

Example 1

Example 2

Example 3

piiMiddleware

Used in Docs

Parameters

Example 1

Example 2

Example 3

Menu

piiMiddleware

Used in Docs

Parameters

Example 1

Example 2

Example 3