Regtransfers/azure-ai-contentsafety-py

@ Azure AI Content Safety SDK for Python

Detect harmful user-generated and AI-generated content in applications.

@ Installation

pip install azure-ai-contentsafety

@ Environment Variables

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

@ Authentication

@ 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()
)

@ Analyze Text

from azure.ai.contentsafety import ContentSafetyClient
from azure.ai.contentsafety.models import AnalyzeTextOptions, TextCategory
from azure.core.credentials import AzureKeyCredential

client = ContentSafetyClient(endpoint, AzureKeyCredential(key))

request = AnalyzeTextOptions(text="Your text content to analyze")
response = client.analyze_text(request)

# Check each category
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}")

@ Analyze Image

from azure.ai.contentsafety import ContentSafetyClient
from azure.ai.contentsafety.models import AnalyzeImageOptions, ImageData
from azure.core.credentials import AzureKeyCredential
import base64

client = ContentSafetyClient(endpoint, AzureKeyCredential(key))

# From file
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}")

@ Image from URL

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

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

response = client.analyze_image(request)

@ Text Blocklist Management

@ Create Blocklist

from azure.ai.contentsafety import BlocklistClient
from azure.ai.contentsafety.models import TextBlocklist
from azure.core.credentials import AzureKeyCredential

blocklist_client = BlocklistClient(endpoint, AzureKeyCredential(key))

blocklist = TextBlocklist(
    blocklist_name="my-blocklist",
    description="Custom terms to block"
)

result = blocklist_client.create_or_update_text_blocklist(
    blocklist_name="my-blocklist",
    options=blocklist
)

@ Add Block Items

from azure.ai.contentsafety.models import AddOrUpdateTextBlocklistItemsOptions, TextBlocklistItem

items = AddOrUpdateTextBlocklistItemsOptions(
    blocklist_items=[
        TextBlocklistItem(text="blocked-term-1"),
        TextBlocklistItem(text="blocked-term-2")
    ]
)

result = blocklist_client.add_or_update_blocklist_items(
    blocklist_name="my-blocklist",
    options=items
)

@ Analyze with Blocklist

from azure.ai.contentsafety.models import AnalyzeTextOptions

request = AnalyzeTextOptions(
    text="Text containing blocked-term-1",
    blocklist_names=["my-blocklist"],
    halt_on_blocklist_hit=True
)

response = client.analyze_text(request)

if response.blocklists_match:
    for match in response.blocklists_match:
        print(f"Blocked: {match.blocklist_item_text}")

@ Severity Levels

Text analysis returns 4 severity levels (0, 2, 4, 6) by default. For 8 levels (0-7):

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

request = AnalyzeTextOptions(
    text="Your text",
    output_type=AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS
)

@ Harm Categories

Category; Description

Hate; Attacks based on identity (race, religion, gender, etc.) Sexual; Sexual content, relationships, anatomy Violence; Physical harm, weapons, injury SelfHarm; Self-injury, suicide, eating disorders

@ Severity Scale

Level; Text Range; Image Range; Meaning

0; Safe; Safe; No harmful content 2; Low; Low; Mild references 4; Medium; Medium; Moderate content 6; High; High; Severe content

@ Client Types

Client; Purpose

ContentSafetyClient; Analyze text and images BlocklistClient; Manage custom blocklists

@ Best Practices

1. Use blocklists for domain-specific terms
2. Set severity thresholds appropriate for your use case
3. Handle multiple categories — content can be harmful in multiple ways
4. Use haltonblocklist_hit for immediate rejection
5. Log analysis results for audit and improvement
6. Consider 8-severity mode for finer-grained control
7. Pre-moderate AI outputs before showing to users

@ When to Use This skill is applicable to execute the workflow or actions described in the overview.

@ Limitations

• Use this skill only when the task clearly matches the scope described above.
• never treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.