Arcjet Redact

The Arcjet redact 集成允许您在将提示发送到聊天模型之前，从提示中删除敏感的用户数据。

Arcjet Redact 完全在您自己的机器上运行，绝不会将数据发送到任何其他地方，从而确保最佳的隐私和性能。

Arcjet Redact 对象本身不是聊天模型，而是包装了 LLM。它会删除输入到它的文本，然后在返回之前取消删除包装的聊天模型的输出。

概述

集成详细信息

类	包	本地	可序列化	PY 支持	包下载	包最新
Arcjet	@langchain/community	❌	✅	❌

安装

安装 Arcjet Redaction 库

提示

查看此部分以获取有关安装集成包的一般说明。

npm

npm i @arcjet/redact

yarn

yarn add @arcjet/redact

pnpm

pnpm add @arcjet/redact

并安装 LangChain Community

提示

查看此部分以获取有关安装集成包的一般说明。

npm

npm i @langchain/community

yarn

yarn add @langchain/community

pnpm

pnpm add @langchain/community

现在您可以开始使用 Arcjet Redaction 保护您的聊天模型调用了！

用法

import {
  ArcjetRedact,
  ArcjetSensitiveInfoType,
} from "@langchain/community/chat_models/arcjet";
import { ChatOpenAI } from "@langchain/openai";

// Create an instance of another chat model for Arcjet to wrap
const openai = new ChatOpenAI({
  temperature: 0.8,
  model: "gpt-3.5-turbo-0125",
});

const arcjetRedactOptions = {
  // Specify a LLM that Arcjet Redact will call once it has redacted the input.
  chatModel: openai,

  // Specify the list of entities that should be redacted.
  // If this isn't specified then all entities will be redacted.
  entities: [
    "email",
    "phone-number",
    "ip-address",
    "custom-entity",
  ] as ArcjetSensitiveInfoType[],

  // You can provide a custom detect function to detect entities that we don't support yet.
  // It takes a list of tokens and you return a list of identified types or undefined.
  // The undefined types that you return should be added to the entities list if used.
  detect: (tokens: string[]) => {
    return tokens.map((t) =>
      t === "some-sensitive-info" ? "custom-entity" : undefined
    );
  },

  // The number of tokens to provide to the custom detect function. This defaults to 1.
  // It can be used to provide additional context when detecting custom entity types.
  contextWindowSize: 1,

  // This allows you to provide custom replacements when redacting. Please ensure
  // that the replacements are unique so that unredaction works as expected.
  replace: (identifiedType: string) => {
    return identifiedType === "email" ? "[email protected]" : undefined;
  },
};

const arcjetRedact = new ArcjetRedact(arcjetRedactOptions);

const response = await arcjetRedact.invoke(
  "My email address is [email protected], here is some-sensitive-info"
);

相关

• 聊天模型 概念指南
• 聊天模型 操作指南