Middleware that periodically extracts memories from turns into Azure AI Memory.
AgentMiddleware that screens text messages with Azure AI Content Safety.
AgentMiddleware that screens image content with Azure AI Content Safety.
AgentMiddleware that evaluates groundedness of model outputs.
AgentMiddleware that detects prompt injection using Azure AI Content Safety.
AgentMiddleware that detects protected material using Azure AI Content Safety.
Raised when content safety violations with exit_behavior='error'.
Input extracted from an agent state for text content moderation.
Input extracted from an agent state for image content moderation.
Inputs extracted from an agent state for groundedness evaluation.
Input extracted from an agent state for prompt shield evaluation.
