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:

Get Started with Pangea AI Guard

Using Pangea with Portkey

1. Add Pangea Credentials to Portkey

• Navigate to the Plugins page under Sidebar
• 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 Guardrails page and click the Create button
• 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_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

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    config: "pc-***" // Supports a string config id or a config object
});

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    config: "pc-***" // Supports a string config id or a config object
});

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    config="pc-***" # Supports a string config id or a config object
)

const openai = new OpenAI({
  apiKey: 'OPENAI_API_KEY',
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    apiKey: "PORTKEY_API_KEY",
    config: "CONFIG_ID"
  })
});

client = OpenAI(
    api_key="OPENAI_API_KEY", # defaults to os.environ.get("OPENAI_API_KEY")
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY", # defaults to os.environ.get("PORTKEY_API_KEY")
        config="CONFIG_ID"
    )
)

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-config: $CONFIG_ID" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{
        "role": "user",
        "content": "Hello!"
      }]
  }'

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.

---

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

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

• type: Always set to "guardrail" for guardrail checks
• id: A unique identifier for your guardrail
• credentials: Authentication details for Pangea
  • api_key: Your Pangea API key
  • domain: Your Pangea domain (e.g., aws.us-east-1.pangea.cloud)
• 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": "pangea-org-guard",
      "credentials": {
        "api_key": "your_pangea_api_key",
        "domain": "your_pangea_domain"
      },
      "checks": [
        {
          "id": "pangea.textGuard",
          "parameters": {
            "recipe": "security_recipe",
            "debug": true,
          }
        }
      ],
      "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 Pangea 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 Pangea integration, just ping the @pangea team on the community forum.

Learn More

• Pangea Documentation
• AI Guard Service Overview