azure-ai-contentsafety-py

To detect harmful content in text and images within Python, use the Azure Content Safety SDK to analyze user-generated content for hate, self-harm, sexual content, and violence across chat apps and forums.

Analyzing image safety requires an Azure endpoint and key or DefaultAzureCredential. You must install the azure-ai-contentsafety package to start evaluating uploaded media across safety categories in your Python application.

Yes, you can enforce custom content moderation policies using blocklist management. This feature allows you to maintain and apply custom term lists to block specific text within your enterprise workflows or social platforms.

Text analysis classifies harmful content by evaluating text for hate, self-harm, sexual content, and violence, assigning severity levels to each category to help you enforce compliant content policies.

The best way to moderate content in chat applications and forums is integrating the Azure Content Safety SDK in Python to automatically detect and classify harmful text and images, ensuring safe user interactions.

Yes, Azure Content Safety works with DefaultAzureCredential as well as standard Azure endpoint and key authentication, allowing flexible access management when applying text moderation and blocklist features in Python.