Arcjet 红除

该 Arcjet 红除集成允许您在将敏感用户资料发送到 LLM 之前将其从提示中红除。

Arcjet 红除完全在您的机器上运行，绝不会将资料发送到任何其他地方，从而确保最佳的隐私和性能。

Arcjet 红除对象本身不是 LLM，而是包装了 LLM。它会红除输入到它的文字，然后在返回之前对包装的 LLM 的输出进行解除红除。

概述

集成详情

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

安装

安装 Arcjet 红除库

提示

参见 此部分了解安装集成包的通用说明。

npm

npm i @arcjet/redact

yarn

yarn add @arcjet/redact

pnpm

pnpm add @arcjet/redact

并安装 LangChain 社区

提示

参见 此部分了解安装集成包的通用说明。

npm

npm i @langchain/community

yarn

yarn add @langchain/community

pnpm

pnpm add @langchain/community

现在您已准备好开始使用 Arcjet 红除保护您的 LLM 调用！

用法

import {
  ArcjetRedact,
  ArcjetSensitiveInfoType,
} from "@langchain/community/llms/arcjet";
import { OpenAI } from "@langchain/openai";

// Create an instance of another LLM for Arcjet to wrap
const openai = new OpenAI({
  modelName: "gpt-3.5-turbo-instruct",
  openAIApiKey: process.env.OPENAI_API_KEY,
});

const arcjetRedactOptions = {
  // Specify a LLM that Arcjet Redact will call once it has redacted the input.
  llm: 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",
    "credit-card",
  ] 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

• LLM 概念指南
• LLM 操作指南