Package Exports

@tanolabs/shield
@tanolabs/shield/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@tanolabs/shield) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Tano Shield

A JavaScript client library for interacting with the Tano Shield AI security services.

Installation

npm install @tanolabs/shield
# or
yarn add @tanolabs/shield

Note: This package uses ES modules (type: "module") and requires Node.js 14.0.0 or higher. If you're using CommonJS modules, you'll need to use dynamic imports or update your project to use ES modules.

Features

AI Issue Detector: Protect your AI applications from harmful inputs and outputs
PII Redaction: Detect and redact personally identifiable information

Usage

Quick Start

import TanoShield from '@tanolabs/shield';

// Initialize the client with your API key
const tanoShield = new TanoShield({
  apiKey: 'your-api-key',
});

// Use the services
async function example() {
  try {
    // Check user input with the Issue Detector
    const firewallResult = await tanoShield.firewall.checkInput({
      system_prompt: "You are a helpful AI assistant",
      user_input: "Tell me about AI security",
      response: "I can provide information about AI security...",
      event_id: "conversation-12345",
      securityChecks: [
        "sycophancy",
        "faithfulness",
        "harmfulness",
        "implausible_output",
        "information_disclosure",
        "jailbreak"
      ]
    });
    console.log('Issue Detector check result:', firewallResult);
    
    // Redact PII from text
    const piiResult = await tanoShield.pii.redactText({
      text: 'My email is john.doe@example.com and my phone is 555-123-4567',
    });
    console.log('Redacted text:', piiResult.redactedText);
  } catch (error) {
    console.error('Error:', error);
  }
}

example();

Using Individual Services

You can also use each service independently:

import { FirewallClient, PIIClient } from '@tanolabs/shield';

// Initialize just the Issue Detector client
const firewall = new FirewallClient({
  apiKey: 'your-api-key',
});

// Check user input
const result = await firewall.checkInput({
  user_input: 'User message here',
  system_prompt: 'You are a helpful assistant',
});

API Reference

TanoShield

The main client that provides access to all services.

const tanoShield = new TanoShield({
  apiKey: 'your-api-key',
  baseUrl: 'https://api.example.com', // Optional
  timeout: 30000, // Optional (default: 30000)
  version: 'v1', // Optional (default: 'v1')
});

Properties

firewall: FirewallClient instance
pii: PIIClient instance
CREDIT_CONSTANTS: Credit cost constants

Methods

setApiKey(apiKey): Update the API key for all services

FirewallClient (Issue Detector)

Client for the AI Issue Detector service.

Methods

checkInput(params): Check user input for security issues
- params.system_prompt: The system prompt (optional)
- params.user_input: The user input to check (required)
- params.response: The AI response to check (optional)
- params.event_id: A unique identifier for the event (optional)
- params.securityChecks: Array of security checks to perform (optional)
getSettings(): Get Issue Detector settings
updateSettings(settings): Update Issue Detector settings
getHistory(options): Get Issue Detector call history
getAnalytics(options): Get Issue Detector analytics

PIIClient

Client for the PII Redaction service.

Methods

redactText({ text, entityTypes, maskMode }): Redact PII from text
detectPII({ text, entityTypes }): Detect PII in text without redacting
getSupportedEntityTypes(): Get supported PII entity types

Credit System

Tano Shield uses a credit system for API usage. Each API call consumes credits based on the service used.

import { CREDIT_CONSTANTS } from '@tanolabs/shield';

console.log(CREDIT_CONSTANTS.FREE_CREDITS_PER_MONTH); // 1000
console.log(CREDIT_CONSTANTS.FIREWALL_CHECK_COST);    // 1
console.log(CREDIT_CONSTANTS.PII_REDACTION_COST);     // 1

Error Handling

The library provides custom error classes for different types of errors:

import { TanoShieldError, AuthenticationError, ApiRequestError } from '@tanolabs/shield';

try {
  await tanoShield.firewall.checkInput({ user_input: 'test' });
} catch (error) {
  if (error instanceof AuthenticationError) {
    console.error('Authentication failed:', error.message);
  } else if (error instanceof ApiRequestError) {
    console.error('API request failed:', error.message, error.status);
  } else if (error instanceof TanoShieldError) {
    console.error('Tano Shield error:', error.message, error.code);
  } else {
    console.error('Unknown error:', error);
  }
}

Example API Call

Here's an example of how to use the Issue Detector with curl:

curl -X POST https://api.tanolabs.com/api/v1/firewall-check \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "prompt": "Tell me about AI security",
  "system_prompt": "You are a helpful AI assistant",
  "user_input": "Tell me about AI security",
  "response": "I can provide information about AI security...",
  "event_id": "conversation-12345",
  "securityChecks": ["sycophancy", "faithfulness", "harmfulness", "implausible_output", "information_disclosure", "jailbreak"]
}'

License

MIT