Skip to main content
 print this page

Test a prompt against an AI guard rail

POST 

/ai/guard-rails/:id/chat

Applies the guard rail to InputText. When InvokeModel is false (default), only apply_guardrail runs. When true, the model is invoked with the guard rail attached. Requires at least read-only access.

Request

Responses

Chat response with guard rail protection applied.

Response Headers
    Access-Control-Allow-Origin
    Access-Control-Allow-Methods
    Access-Control-Allow-Headers