Get Guardrails

GET

/api/v2/guardrails/

Guardrailsv2

Retrieve list of all guardrails.

Query Parameters:

guardrail_type (str, optional): Filter by guardrail type
is_enabled (bool, optional): Filter by enabled status
verbosity (str, optional): Control level of detail ('low', 'medium', 'high')
fields (str, optional): Comma-separated list of specific fields to include
embed (str, optional): Comma-separated list of related entities to embed

Returns:

JSON response containing the guardrail data

Response Example

200 - Successful Response

{
    "success": true,
    "message": "string",
    "data": {
        "guardrails": [
            {
                "id": 1,
                "name": "Content Boundaries",
                "description": "Restricts discussions to safe topics",
                "created_on": "2024-03-15T10:30:00Z",
                "modified_on": "2024-03-16T09:15:00Z",
                "created_by": "admin@example.com",
                "modified_by": "admin@example.com",
                "organization_id": 1,
                "guardrail_type": "topic_control",
                "is_enabled": true,
                "is_default": false,
                "is_deleted": false,
                "guidelines": [
                    "No discussions about illegal activities",
                    "No harmful content"
                ]
            },
            {
                "id": 2,
                "name": "Ethics Filter",
                "description": "Ensures responses are ethically sound",
                "created_on": "2024-03-14T14:20:00Z",
                "modified_on": "2024-03-15T11:45:00Z",
                "created_by": "admin@example.com",
                "modified_by": "admin@example.com",
                "organization_id": 1,
                "guardrail_type": "ethical_moderation",
                "is_enabled": true,
                "is_default": true,
                "is_deleted": false
            },
            {
                "id": 3,
                "name": "Prompt Injection Detector",
                "description": "Prevents prompt injection attacks",
                "created_on": "2024-03-13T09:30:00Z",
                "modified_on": "2024-03-13T09:30:00Z",
                "created_by": "admin@example.com",
                "modified_by": "admin@example.com",
                "organization_id": 1,
                "guardrail_type": "jailbreak_detection",
                "is_enabled": true,
                "is_default": false,
                "is_deleted": false
            }
        ]
    }
}

Request

Query Params

embed

string

optional

Comma-separated list of related entities to embed in the response

Example:

organization

fields

string

optional

Comma-separated list of specific fields to include in the response

Example:

id,name,description,guardrail_type

guardrail_type

enum<string>

optional

Filter by guardrail type

Allowed values:

ethical_moderationhallucinationjailbreak_detectionmask_sensitive_datatopic_control

Example:

topic_control

is_enabled

boolean

optional

Filter by enabled status

Example:

true

verbosity

enum<string>

optional

Level of detail in response

Allowed values:

highlowmedium

Default:

medium

Example:

low

Responses

🟢200OK

application/json

Body

data

object (GuardrailListView_GuardrailSerializer_List_Data)

required

guardrails

array[object (Guardrail) {7}]

optional

success

boolean

required

message

string

required

🟠400Bad Request

🔴500Server Error

Enable/disable a guardrail type for agent

Update Guardrails