Azure AI 内容安全 TypeScript SDK
Azure AI Content Safety TypeScript REST SDK
通过可自定义的阻止列表分析文本和图像中的有害内容。
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>身份验证
重要提示:这是一个 REST 客户端。ContentSafetyClient 是一个函数,而非类。
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: "待分析的文本内容",
categories: ["Hate", "Sexual", "Violence", "SelfHarm"],
outputType: "FourSeverityLevels" // 或 "EightSeverityLevels"
}
});
if (isUnexpected(result)) {
throw result.body;
}
for (const analysis of result.body.categoriesAnalysis) {
console.log(${analysis.category}: severity ${analysis.severity});
}
分析图像
Base64 内容
import { readFileSync } from "node:fs";
const imageBuffer = readFileSync("./image.png");
const base64Image = imageBuffer.toString("base64");
const result = await client.path("/image:analyze").post({
body: {
image: { content: base64Image }
}
});
if (isUnexpected(result)) {
throw result.body;
}
for (const analysis of result.body.categoriesAnalysis) {
console.log(${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" }
}
});阻止列表管理
创建阻止列表
const result = await client
.path("/text/blocklists/{blocklistName}", "my-blocklist")
.patch({
contentType: "application/merge-patch+json",
body: {
description: "禁止术语的自定义阻止列表"
}
});
if (isUnexpected(result)) {
throw result.body;
}
console.log(已创建: ${result.body.blocklistName});
向阻止列表添加项
const result = await client
.path("/text/blocklists/{blocklistName}:addOrUpdateBlocklistItems", "my-blocklist")
.post({
body: {
blocklistItems: [
{ text: "prohibited-term-1", description: "第一个被阻止的术语" },
{ text: "prohibited-term-2", description: "第二个被阻止的术语" }
]
}
});
if (isUnexpected(result)) {
throw result.body;
}
for (const item of result.body.blocklistItems ?? []) {
console.log(已添加: ${item.blocklistItemId});
}
使用阻止列表进行分析
const result = await client.path("/text:analyze").post({
body: {
text: "可能包含屏蔽词的文本",
blocklistNames: ["my-blocklist"],
haltOnBlocklistHit: false
}
});
if (isUnexpected(result)) {
throw result.body;
}
// 检查屏蔽词匹配情况
if (result.body.blocklistsMatch) {
for (const match of result.body.blocklistsMatch) {
console.log(屏蔽词: "${match.blocklistItemText}" 来自 ${match.blocklistName});
}
}
列出屏蔽列表
const result = await client.path("/text/blocklists").get();
if (isUnexpected(result)) {
throw result.body;
}
for (const blocklist of result.body.value ?? []) {
console.log(${blocklist.blocklistName}: ${blocklist.description});
}
删除屏蔽列表
await client.path("/text/blocklists/{blocklistName}", "my-blocklist").delete();危害类别
| 类别 | API 术语 | 描述 |
|----------|----------|-------------|
| 仇恨与公平性 | Hate | 针对身份群体的歧视性语言 |
| 性内容 | Sexual | 性内容、裸露、色情 |
| 暴力 | Violence | 身体伤害、武器、恐怖主义 |
| 自残 | SelfHarm | 自伤、自杀、饮食失调 |
严重程度级别
| 级别 | 风险 | 建议操作 |
|-------|------|-------------------|
| 0 | 安全 | 允许 |
| 2 | 低 | 审核或带警告允许 |
| 4 | 中 | 屏蔽或需要人工审核 |
| 6 | 高 | 立即屏蔽 |
输出类型:
FourSeverityLevels(默认): 返回 0, 2, 4, 6
EightSeverityLevels: 返回 0-7
内容审核辅助函数
import ContentSafetyClient, {
isUnexpected,
TextCategoriesAnalysisOutput
} from "@azure-rest/ai-content-safety";
interface ModerationResult {
isAllowed: boolean;
flaggedCategories: string[];
maxSeverity: number;
blocklistMatches: string[];
}
async function moderateContent(
client: ReturnType<typeof ContentSafetyClient>,
text: string,
maxAllowedSeverity = 2,
blocklistNames: string[] = []
): Promise<ModerationResult> {
const result = await client.path("/text:analyze").post({
body: { text, blocklistNames, haltOnBlocklistHit: false }
});
if (isUnexpected(result)) {
throw result.body;
}
const flaggedCategories = result.body.categoriesAnalysis
.filter(c => (c.severity ?? 0) > maxAllowedSeverity)
.map(c => c.category!);
const maxSeverity = Math.max(
...result.body.categoriesAnalysis.map(c => c.severity ?? 0)
);
const blocklistMatches = (result.body.blocklistsMatch ?? [])
.map(m => m.blocklistItemText!);
return {
isAllowed: flaggedCategories.length === 0 && blocklistMatches.length === 0,
flaggedCategories,
maxSeverity,
blocklistMatches
};
}
API 终结点
| 操作 | 方法 | 路径 |
|-----------|--------|------|
| 分析文本 | POST | /text:analyze |
| 分析图像 | POST | /image:analyze |
| 创建/更新屏蔽列表 | PATCH | /text/blocklists/{blocklistName} |
| 列出屏蔽列表 | GET | /text/blocklists |
| 删除屏蔽列表 | DELETE | /text/blocklists/{blocklistName} |
| 添加屏蔽项 | POST | /text/blocklists/{blocklistName}:addOrUpdateBlocklistItems |
| 列出屏蔽项 | GET | /text/blocklists/{blocklistName}/blocklistItems |
| 移除屏蔽项 | POST | /text/blocklists/{blocklistName}:removeBlocklistItems |
关键类型
import ContentSafetyClient, {
isUnexpected,
AnalyzeTextParameters,
AnalyzeImageParameters,
TextCategoriesAnalysisOutput,
ImageCategoriesAnalysisOutput,
TextBlocklist,
TextBlocklistItem
} from "@azure-rest/ai-content-safety";最佳实践
1. 始终使用 isUnexpected() —— 用于错误处理的类型守卫。
2. 设置合适的阈值 —— 不同类别可能需要不同的严重程度阈值。
3. 针对特定领域术语使用屏蔽列表 —— 用自定义规则补充 AI 检测。
4. 记录审核决策 —— 为合规性保留审计追踪。
5. 处理边缘情况 —— 如空文本、超长文本或不支持的图像格式。
适用场景
本技能适用于执行概览中所描述的工作流或操作。局限性
- 仅在任务明确符合上述范围时使用此技能。
- 不要将输出结果视为环境特定验证、测试或专家评审的替代方案。
- 如果缺少必要的输入、权限、安全边界或成功标准,请停止操作并请求澄清。