Pangea
Pangea AI Guard helps analyze and redact text to prevent model manipulation and malicious content.
Pangea 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 Pangea, visit their documentation:
For more, refer to the Config documentation.
Your requests are now guarded by Pangea AI Guard and you can see the Verdict and any action you take directly on Portkey logs! More detailed logs for your requests will also be available on your Pangea dashboard.
Get Started with Pangea AI Guard
Using Pangea with Portkey
1. Add Pangea Credentials to Portkey
- Navigate to the
Pluginspage underSidebar - Click on the edit button for the Pangea integration
- Add your Pangea token and domain information (refer to Pangea’s documentation for how to obtain these credentials)
2. Add Pangea’s Guardrail Check
- Navigate to the
Guardrailspage and click theCreatebutton - Search for Pangea’s AI Guard and click
Add - Configure your guardrail settings: recipe & debug (see Pangea’s API documentation for more details)
- 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
| Check Name | Description | Parameters | Supported Hooks |
|---|---|---|---|
| AI Guard | Analyze and redact text to avoid manipulation of the model and malicious content | recipe (string), debug (boolean) | beforeRequestHook, 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_guardrailsoroutput_guardrailsparams 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.
Using Raw Guardrails with Pangea
You can define Pangea 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.
Key Configuration Properties
Key Configuration Properties
Available Pangea Guardrails
| Guardrail Name | ID | Description | Parameters |
|---|---|---|---|
| Pangea AI Guard | pangea.textGuard | Scans LLM inputs/outputs for malicious content, harmful patterns, etc. | recipe (string), debug (boolean) |
| Pangea PII Guard | pangea.pii | Detects and optionally redacts personal identifiable information | redact (boolean) |
Implementation Examples
Key Configuration Properties
Key Configuration Properties
type: Always set to"guardrail"for guardrail checksid: A unique identifier for your guardrailcredentials: Authentication details for Pangeaapi_key: Your Pangea API keydomain: Your Pangea domain (e.g.,aws.us-east-1.pangea.cloud)
checks: Array of guardrail checks to runid: The specific guardrail ID from the table aboveparameters: 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 scenariosfeedback: Data for logging and analyticsweight: Importance of this feedback (0-1)value: Feedback score (-10 to 10)
When using raw guardrails, you must provide valid credentials for the Pangea service directly in your config. Make sure to handle these credentials securely and consider using environment variables or secrets management.