Guardrails
Overview
AI safety guardrails API for configuring content moderation and security policies. Set up ban word lists, prompt injection detection, and system prompt leakage prevention. Guardrails apply to all requests from an account and can be tested before deployment.
Available Operations
- getGuardrails - Get guardrails settings
- updateGuardrails - Update guardrails settings
- testGuardrails - Test content against guardrails
getGuardrails
Retrieve the current guardrails configuration for the authenticated user. Returns all configured guardrails including ban words, prompt injection detection, and leakage detection settings.
Example Usage
import { SDK } from "@meetkai/mka1";
const sdk = new SDK({
serverURL: "https://api.example.com",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await sdk.guardrails.getGuardrails();
console.log(result);
}
run();Standalone function
The standalone function version of this method:
import { SDKCore } from "@meetkai/mka1/core.js";
import { guardrailsGetGuardrails } from "@meetkai/mka1/funcs/guardrailsGetGuardrails.js";
// Use `SDKCore` for best tree-shaking performance.
// You can create one instance of it to use across an application.
const sdk = new SDKCore({
serverURL: "https://api.example.com",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const res = await guardrailsGetGuardrails(sdk);
if (res.ok) {
const { value: result } = res;
console.log(result);
} else {
console.log("guardrailsGetGuardrails failed:", res.error);
}
}
run();React hooks and utilities
This method can be used in React components through the following hooks and associated utilities.
Check out this guide for information about each of the utilities below and how to get started using React hooks.
import {
// Query hooks for fetching data.
useGuardrailsGetGuardrails,
useGuardrailsGetGuardrailsSuspense,
// Utility for prefetching data during server-side rendering and in React
// Server Components that will be immediately available to client components
// using the hooks.
prefetchGuardrailsGetGuardrails,
// Utility to invalidate the query cache for this query in response to
// mutations and other user actions.
invalidateAllGuardrailsGetGuardrails,
} from "@meetkai/mka1/react-query/guardrailsGetGuardrails.js";Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
options | RequestOptions | ➖ | Used to set various options for making HTTP requests. |
options.fetchOptions | RequestInit | ➖ | Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed. |
options.retries | RetryConfig | ➖ | Enables retrying HTTP requests under certain failure conditions. |
Response
Promise<components.GetGuardrailsResponse>
Errors
| Error Type | Status Code | Content Type |
|---|---|---|
| errors.APIError | 4XX, 5XX | */* |
updateGuardrails
Update the guardrails configuration for the authenticated user. Configure multiple guardrail modes including ban words (custom word list), prompt injection detection, and system prompt leakage detection. Each guardrail can be individually enabled/disabled with custom thresholds and rejection messages.
Example Usage
import { SDK } from "@meetkai/mka1";
const sdk = new SDK({
serverURL: "https://api.example.com",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await sdk.guardrails.updateGuardrails({
guardrails: [
{
mode: "ban_words",
},
],
});
console.log(result);
}
run();Standalone function
The standalone function version of this method:
import { SDKCore } from "@meetkai/mka1/core.js";
import { guardrailsUpdateGuardrails } from "@meetkai/mka1/funcs/guardrailsUpdateGuardrails.js";
// Use `SDKCore` for best tree-shaking performance.
// You can create one instance of it to use across an application.
const sdk = new SDKCore({
serverURL: "https://api.example.com",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const res = await guardrailsUpdateGuardrails(sdk, {
guardrails: [
{
mode: "ban_words",
},
],
});
if (res.ok) {
const { value: result } = res;
console.log(result);
} else {
console.log("guardrailsUpdateGuardrails failed:", res.error);
}
}
run();React hooks and utilities
This method can be used in React components through the following hooks and associated utilities.
Check out this guide for information about each of the utilities below and how to get started using React hooks.
import {
// Mutation hook for triggering the API call.
useGuardrailsUpdateGuardrailsMutation
} from "@meetkai/mka1/react-query/guardrailsUpdateGuardrails.js";Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
request | components.UpdateGuardrailsRequest | ✔️ | The request object to use for the request. |
options | RequestOptions | ➖ | Used to set various options for making HTTP requests. |
options.fetchOptions | RequestInit | ➖ | Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed. |
options.retries | RetryConfig | ➖ | Enables retrying HTTP requests under certain failure conditions. |
Response
Promise<components.UpdateGuardrailsResponse>
Errors
| Error Type | Status Code | Content Type |
|---|---|---|
| errors.APIError | 4XX, 5XX | */* |
testGuardrails
Test a piece of content against the configured guardrails without making an actual API call. Useful for debugging and validating guardrail configurations. Returns a report indicating whether the content passed and which guardrail was triggered if any.
Example Usage
import { SDK } from "@meetkai/mka1";
const sdk = new SDK({
serverURL: "https://api.example.com",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const result = await sdk.guardrails.testGuardrails({
content: "<value>",
});
console.log(result);
}
run();Standalone function
The standalone function version of this method:
import { SDKCore } from "@meetkai/mka1/core.js";
import { guardrailsTestGuardrails } from "@meetkai/mka1/funcs/guardrailsTestGuardrails.js";
// Use `SDKCore` for best tree-shaking performance.
// You can create one instance of it to use across an application.
const sdk = new SDKCore({
serverURL: "https://api.example.com",
bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});
async function run() {
const res = await guardrailsTestGuardrails(sdk, {
content: "<value>",
});
if (res.ok) {
const { value: result } = res;
console.log(result);
} else {
console.log("guardrailsTestGuardrails failed:", res.error);
}
}
run();React hooks and utilities
This method can be used in React components through the following hooks and associated utilities.
Check out this guide for information about each of the utilities below and how to get started using React hooks.
import {
// Mutation hook for triggering the API call.
useGuardrailsTestGuardrailsMutation
} from "@meetkai/mka1/react-query/guardrailsTestGuardrails.js";Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
request | components.TestGuardrailsRequest | ✔️ | The request object to use for the request. |
options | RequestOptions | ➖ | Used to set various options for making HTTP requests. |
options.fetchOptions | RequestInit | ➖ | Options that are passed to the underlying HTTP request. This can be used to inject extra headers for examples. All Request options, except method and body, are allowed. |
options.retries | RetryConfig | ➖ | Enables retrying HTTP requests under certain failure conditions. |
Response
Promise<components.TestGuardrailsResponse>
Errors
| Error Type | Status Code | Content Type |
|---|---|---|
| errors.APIError | 4XX, 5XX | */* |