Acuvity is model agnostic GenAI security solution. It is built to secure existing and future GenAI models, apps, services, tools, plugins and more.
Integration
page under Sidebar
Guardrails
page and click the Create
buttonAdd
actions
you want on your check, and create the Guardrail!Check Name | Description | Parameters | Supported Hooks |
---|---|---|---|
Acuvity Scan | Comprehensive content safety and security checks | Prompt Injection , Toxicity , Jail Break , Malicious Url , Biased , Harmful , Language , PII , Secrets , Timeout | beforeRequestHook , afterRequestHook |
input_guardrails
or output_guardrails
params in your Portkey ConfigKey Configuration Properties
Guardrail Name | ID | Description | Parameters |
---|---|---|---|
Acuvity Scan | acuvity.scan | Comprehensive content safety and security checks | Prompt Injection , Toxicity , Jail Break , Malicious Url , Biased , Harmful , Language , PII , Secrets , Timeout |
Key Configuration Properties
type
: Always set to "guardrail"
for guardrail checksid
: A unique identifier for your guardrailcredentials
: Authentication details for Acuvity
api_key
: Your Acuvity API keychecks
: Array of guardrail checks to run
id
: The specific guardrail ID from the table aboveparameters
: Configuration options specific to each guardraildeny
: 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 analyticsweight
: Importance of this feedback (0-1)value
: Feedback score (-10 to 10)