---

name: azure-ai-contentsafety-py description: "Azure AI内容安全Python SDK。用于检测文本和图像中的有害内容，支持多严重级别分类。" risk: unknown source: community date_added: '2026-02-27'

Azure AI 内容安全 Python SDK

检测应用程序中有害的用户生成和AI生成内容。

安装

pip install azure-ai-contentsafety

环境变量

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

认证

API Key

from azure.ai.contentsafety import ContentSafetyClient
from azure.core.credentials import AzureKeyCredential
import os

client = ContentSafetyClient(
    endpoint=os.environ["CONTENT_SAFETY_ENDPOINT"],
    credential=AzureKeyCredential(os.environ["CONTENT_SAFETY_KEY"])
)

Entra ID

from azure.ai.contentsafety import ContentSafetyClient
from azure.identity import DefaultAzureCredential

client = ContentSafetyClient(
    endpoint=os.environ["CONTENT_SAFETY_ENDPOINT"],
    credential=DefaultAzureCredential()
)

分析文本

from azure.ai.contentsafety.models import AnalyzeTextOptions, TextCategory

request = AnalyzeTextOptions(text="要分析的文本内容")
response = client.analyze_text(request)

# 检查每个类别
for category in [TextCategory.HATE, TextCategory.SELF_HARM,
                 TextCategory.SEXUAL, TextCategory.VIOLENCE]:
    result = next((r for r in response.categories_analysis
                   if r.category == category), None)
    if result:
        print(f"{category}: severity {result.severity}")

分析图像

from azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData
import base64

# 从文件
with open("image.jpg", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

request = AnalyzeImageOptions(image=ImageData(content=image_data))
response = client.analyze_image(request)

for result in response.categories_analysis:
    print(f"{result.category}: severity {result.severity}")

从URL分析图像

request = AnalyzeImageOptions(
    image=ImageData(blob_url="https://example.com/image.jpg")
)

严重级别

| 级别 | 含义 | |------|------| | 0 | 安全 | | 2 | 低严重度 | | 4 | 中严重度 | | 6 | 高严重度 |

类别

• Hate：仇恨和歧视内容
• SelfHarm：自我伤害相关内容
• Sexual：性相关内容
• Violence：暴力内容

自定义黑名单

from azure.ai.contentsafety.models import (
    TextBlocklist, AddOrUpdateTextBlocklistItemsOptions,
    TextBlocklistItem
)

# 创建黑名单
client.create_or_update_text_blocklist(
    blocklist_name="custom-blocklist",
    options=TextBlocklist(description="自定义屏蔽词列表")
)

# 添加屏蔽项
client.add_or_update_blocklist_items(
    blocklist_name="custom-blocklist",
    options=AddOrUpdateTextBlocklistItemsOptions(
        blocklist_items=[TextBlocklistItem(text="屏蔽词")]
    )
)

常见问题

• 401错误：检查API密钥或Entra ID凭证
• 严重级别为0：内容被判定为安全
• 超时：大文本建议分段分析