---

name: azure-ai-contentsafety-ts description: "使用可自定义的屏蔽列表分析文本和图片中的有害内容。" risk: unknown source: community date_added: "2026-02-27"

Azure AI内容安全 REST SDK（TypeScript）

使用可自定义的屏蔽列表分析文本和图片中的有害内容。

安装

npm install @azure-rest/ai-content-safety @azure/identity @azure/core-auth

环境变量

CONTENT_SAFETY_ENDPOINT=https://<resource>.cognitiveservices.azure.com
CONTENT_SAFETY_KEY=<api-key>

认证

重要：这是一个REST客户端。ContentSafetyClient 是一个函数，不是类。

API密钥

import ContentSafetyClient from "@azure-rest/ai-content-safety";
import { AzureKeyCredential } from "@azure/core-auth";

const client = ContentSafetyClient(
  process.env.CONTENT_SAFETY_ENDPOINT!,
  new AzureKeyCredential(process.env.CONTENT_SAFETY_KEY!)
);

DefaultAzureCredential

import ContentSafetyClient from "@azure-rest/ai-content-safety";
import { DefaultAzureCredential } from "@azure/identity";

const client = ContentSafetyClient(
  process.env.CONTENT_SAFETY_ENDPOINT!,
  new DefaultAzureCredential()
);

分析文本

import ContentSafetyClient, { isUnexpected } from "@azure-rest/ai-content-safety";

const result = await client.path("/text:analyze").post({
  body: {
    text: "Text content to analyze",
    categories: ["Hate", "Sexual", "Violence", "SelfHarm"],
    outputType: "FourSeverityLevels"  // or "EightSeverityLevels"
  }
});

if (isUnexpected(result)) {
  throw result.body;
}

for (const analysis of result.body.categoriesAnalysis) {
  console.log(`${analysis.category}: severity ${analysis.severity}`);
}

分析图片

Base64内容

import { readFileSync } from "node:fs";

const imageBuffer = readFileSync("./image.png");
const base64Image = imageBuffer.toString("base64");

const result = await client.path("/image:analyze").post({
  body: {
    image: { content: base64Image }
  }
});

if (isUnexpected(result)) {
  throw result.body;
}

for (const analysis of result.body.categoriesAnalysis) {
  console.log(`${analysis.category}: severity ${analysis.severity}`);
}

Blob URL

const result = await client.path("/image:analyze").post({
  body: {
    image: { blobUrl: "https://storage.blob.core.windows.net/container/image.png" }
  }
});

屏蔽列表管理

创建屏蔽列表

const result = await client.path("/text/blocklists/{blocklistName}", "MyBlocklist").patch({
  contentType: "application/merge-patch+json",
  body: { description: "自定义屏蔽列表" }
});

添加屏蔽项

const result = await client.path("/text/blocklists/{blocklistName}:addOrUpdateBlocklistItems", "MyBlocklist").post({
  body: {
    blocklistItems: [
      { description: "有害词1", text: "harmful_word_1" },
      { description: "有害词2", text: "harmful_word_2" }
    ]
  }
});

使用屏蔽列表分析

const result = await client.path("/text:analyze").post({
  body: {
    text: "要分析的文本",
    blocklistNames: ["MyBlocklist"],
    haltOnBlocklistHit: true
  }
});