Feedback Aide API Evaluation Options

Configuration options for moderating sensitive, inappropriate, or crisis-related content in responses.

See Content moderation with Feedback Aide for more information.

Examples

// Example for evaluate endpoints
{
    "options": {
        "agents": {
            "moderation": {
                "inappropriate_content": {
                    "enabled": true
                },
                "critical_safety_content": {
                    "enabled": true
                }
            }
        }
    }
}

// Example using the JavaScript API
const feedbackSession = await feedbackApp.feedbackSession(
    { /* security token */ },
    {
        state: '...',
        session_uuid: '...',
        // ...

        options: {
            agents: {
                moderation: {
                    inappropriate_content: {
                        enabled: true
                    },
                    critical_safety_content: {
                        enabled: true
                    }
                }
            }
        },
    }
);

Values

Type object

Properties

• inappropriate_content object

  Configuration options for content moderation checking for inappropriate content in responses.

• critical_safety_content object

  Configuration options for content moderation checking for critical safety content in responses.