Skip to main content
Acuvity provides AI Guard service for scanning LLM inputs and outputs to avoid manipulation of the model, addition of malicious content, and other undesirable data transfers. To get started with Acuvity, visit their website:

Get Started with Acuvity AI

​
Using Acuvity with Portkey

​
1. Add Acuvity Credentials to Portkey

  • Navigate to the Integration page under Sidebar
  • Click on the edit button for the Acuvity integration
  • Add your Acuvity API Key

​
2. Add Acuvity’s Guardrail Check

  • Navigate to the Guardrails page and click the Create button
  • Search for Acuvity Scan and click Add
  • Configure your guardrail settings: toxicity, jail break, biased etc.
  • Set any actions you want on your check, and create the Guardrail!
Guardrail Actions allow you to orchestrate your guardrails logic. You can learn them here
Here’s your updated table with just the parameter names:
Check NameDescriptionParametersSupported Hooks
Acuvity ScanComprehensive content safety and security checksPrompt Injection, Toxicity, Jail Break, Malicious Url, Biased, Harmful, Language, PII, Secrets, TimeoutbeforeRequestHook, afterRequestHook

​
3. Add Guardrail ID to a Config and Make Your Request

  • When you save a Guardrail, you’ll get an associated Guardrail ID - add this ID to the input_guardrails or output_guardrails params in your Portkey Config
  • Create these Configs in Portkey UI, save them, and get an associated Config ID to attach to your requests. More here.
Here’s an example config: 
{
  "input_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"],
  "output_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"]
}
  • NodeJS
  • Python
  • OpenAI NodeJS
  • OpenAI Python
  • cURL
const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    config: "pc-***" // Supports a string config id or a config object
});
For more, refer to the Config documentation. Your requests are now guarded by Acuvity AI’s Guardrail and you can see the Verdict and any action you take directly on Portkey logs!

​
Using Raw Guardrails with Acuvity

You can define Acuvity guardrails directly in your code for more programmatic control without using the Portkey UI. This “raw guardrails” approach lets you dynamically configure guardrails based on your application’s needs.
We recommend that you create guardrails using the Portkey UI whenever possible. Raw guardrails are more complex and require you to manage credentials and configurations directly in your code.

​
Available Acuvity Guardrails

Guardrail NameIDDescriptionParameters
Acuvity Scanacuvity.scanComprehensive content safety and security checksPrompt Injection, Toxicity, Jail Break, Malicious Url, Biased, Harmful, Language, PII, Secrets, Timeout

​
Implementation Examples

  • type: Always set to "guardrail" for guardrail checks
  • id: A unique identifier for your guardrail
  • credentials: Authentication details for Acuvity
    • api_key: Your Acuvity API key
  • checks: Array of guardrail checks to run
    • id: The specific guardrail ID from the table above
    • parameters: Configuration options specific to each guardrail
  • deny: Whether to block the request if guardrail fails (true/false)
  • async: Whether to run guardrail asynchronously (true/false)
  • on_success/on_fail: Optional callbacks for success/failure scenarios
    • feedback: Data for logging and analytics
    • weight: Importance of this feedback (0-1)
    • value: Feedback score (-10 to 10)
{
  "before_request_hooks": [
    {
      "type": "guardrail",
      "id": "acuvity-scan-guard",
      "credentials": {
        "api_key": "your_acuvity_api_key",
        "domain": "your_acuvity_domain"
      },
      "checks": [
        {
          "id": "acuvity.scan",
          "parameters": {
            "prompt_injection": true,
            "prompt_injection_threshold": 0.5, // between 0-1
            "toxic": true,
            "toxic_threshold": 0.5, // between 0-1
            "jail_break": true,
            "jail_break_threshold": 0.5, // between 0-1
            "malicious_url": true,
            "malicious_url_threshold": 0.5, // between 0-1
            "biased": true,
            "biased_threshold": 0.5, // between 0-1
            "harmful": true,
            "harmful_threshold": 0.5, // between 0-1
            "language": true,
            "language_values": "eng_Latn",
            "pii": true,
            "pii_redact": false,
            "pii_categories": [
              "email_address",
              "ssn",
              "person",
              "aba_routing_number",
              "address",
              "bank_account",
              "bitcoin_wallet",
              "credit_card",
              "driver_license",
              "itin_number",
              "location",
              "medical_license",
              "money_amount",
              "passport_number",
              "phone_number"
            ],
            "secrets": true,
            "secrets_redact": false,
            "secrets_categories": [
              "credentials",
              "aws_secret_key",
              "private_key",
              "alibaba",
              "anthropic"
              //... and more  refer Acuvity docs for more
            ],
            "timeout": 5000 // timeout in ms
          }
        }
      ],
      "deny": true,
      "async": false,
      "on_success": {
        "feedback": {
          "weight": 1,
          "value": 1,
          "metadata": {
            "user": "user_xyz"
          }
        }
      },
      "on_fail": {
        "feedback": {
          "weight": 1,
          "value": -1,
          "metadata": {
            "user": "user_xyz"
          }
        }
      }
    }
  ]
}
When using raw guardrails, you must provide valid credentials for the Acuvity service directly in your config. Make sure to handle these credentials securely and consider using environment variables or secrets management.

​
Get Support

If you face any issues with the Acuvity integration, just ping the Portkey team on the community forum.

​
Learn More