azure-ai-contentsafety-py

You can detect harmful content in text and images using Azure AI by analyzing inputs for hate, self-harm, sexual, and violence categories. This Skill leverages the Python SDK to provide configurable severity levels and safety auditing results.

Yes, you can configure severity levels for text moderation in Azure Content Safety. The Skill analyzes text for hate speech, self-harm, sexual content, and violence, allowing you to set thresholds to meet your specific safety requirements.

Yes, the Azure AI Content Safety Python SDK supports custom blocklists. You can create and manage custom lists of terms to block, enabling domain-specific moderation for your application's unique content filtering needs.

The best way to moderate user-generated images for violence and adult content is using Azure AI image moderation. This Skill detects adult, violence, and gore within images to prevent the spread of offensive material and maintain community standards.

Yes, you need the Python SDK to perform content safety auditing with this Skill. It requires the Python SDK to execute content moderation and safety auditing tasks for both text and image analysis.