Modify Policy

Enabled

BiasDetector

CopyrightIPDetector

InjectionAttackDetector

Banned Keywords

KeywordDetector

NSFWDetector

Entities

PIIDetector

Need Explanation

Policy Text

PolicyAdherenceDetector

SystemPromptDetector

Topic

TopicDetector

ToxicityDetector

GuardrailsDetectorsObject

Description

Name

GuardrailsPolicyRequestObject

Created At

Policy ID

Updated At

GuardrailsPolicyResponseObject

apiKeyAuth

ModifyGuardrailsPolicyResponseObject

Update Policy

Enkrypt AI

Welcome to the Enkrypt AI Guardrails documentation

Introduction

Start using Guardrails in under 5 minutes

Quickstart

Welcome to the Enkrypt AI Red Teaming documentation

Enkrypt AI Red Teaming

Payload Guide for EnkryptAI Red Teaming API

Generate comprehensive vulnerability report of your LLM in just few steps

Section for showcasing Guardrails API endpoints

Health Check

Status Check

Models Loaded

Guardrails Detect

PII anonymization and de-anonymization

Detect Hallucination

Guardrails Adherence

Guardrails Relevancy

Add Policy

Get Policy

Delete Policy

Detect with Policy

Create Model

Get Model

Modify Model

Delete Model

List Models

Get Defaults

Datasets Add Task

Datasets Get Datacard

Datasets Get Dataset

Datasets Get Summary

List all tasks / datasets

Datasets Delete Dataset

Example section for showcasing Red teaming API endpoints

Redteam Health

Model Health

Model Health of saved model

Add Task

Add Task with saved model

Get Task

Get Task Status

Get Task Results Summary

Get Task Results Summary of a specific test type

Get Task Results Details

Get Task Results Details of a specific test type

Get List of Tasks

Create Deployment

Get Deployment

Modify Deployment

Delete Deployment

List Deployments

Get Allowed Config

AI Chat Completions Proxy Endpoint

AI Completions Proxy Endpoint

v2 Models List

Retrieves a list of scores of all the models

v2 Scores list

v2 Model Score

Retrieve details of a specific model based on the risk type and sub-type.

v2 Model Detail

Retrieve summary of a specific model based on the risk type and sub-type.

v2 Model Summary

v2 Model Rank

v2 Models Risk Percentiles

v1 Models List

v1 Scores list

v1 Model Score

v1 Model Detail

v1 Model Summary

v1 Model Rank

v1 Models Risk Percentiles

Guardrails

Models

Datasets

Red Team

Deployments

AI Proxy

Leaderboard

Learn More

Guardrails API Documentation

Guardrails APIs

Modify Policy

Authorizations

Headers

Body

Response