Walled AI

Walled AI provides an advanced guardrail system for your LLM applications, allowing you to enforce comprehensive safety checks, detect and redact PII, validate greetings, and perform custom compliance checks. To get started with Walled AI, visit their website:

Get Started with Walled AI

Get API Keys

Using Walled AI with Portkey

1. Add Walled AI Credentials to Portkey

Click on the Admin Settings button on Sidebar
Navigate to Plugins tab under Organisation Settings
Click on the edit button for the Walled AI integration
Add your Walled AI API Key (obtain this from your Walled AI dashboard)

2. Add Walled AI’s Guardrail Check

Navigate to the Guardrails page and click the Create button
Search for “Walled AI Guardrail” and click Add
Set any actions you want on your check, configure the parameters, and create the Guardrail!

Guardrail Actions allow you to orchestrate your guardrails logic. You can learn more about them here

Check Name	Description	Supported Hooks
Walled AI Guardrail	Ensure the safety and compliance of your LLM inputs and outputs	`beforeRequestHook` `afterRequestHook`

Parameters:

Parameter	Type	Description	Default
`generic_safety_check`	`boolean`	Enable generic safety checks on the text input.	`true`
`greetings_list`	`array`	List of greetings to be used in the guardrail check.	`["Casual & Friendly"]`
`pii_list`	`array`	PII types that should be checked in the input text.	(All PII types)
`compliance_list`	`array`	Compliance checks to be performed on the text input.	`[]`

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 configuration:

{
  "input_guardrails": ["guardrails-id-xxx"],
  "output_guardrails": ["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
});

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 Walled AI’s protection mechanisms, and you can see the verdict and any actions taken directly in your Portkey logs!

Get Support

If you face any issues with the Walled AI integration, join the Portkey community forum for assistance.

Introduction

Product

Self-Hosting

Support

Get Started with Walled AI

Get API Keys

Using Walled AI with Portkey

1. Add Walled AI Credentials to Portkey

2. Add Walled AI’s Guardrail Check

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

Get Support

Introduction

Product

Self-Hosting

Support

Get Started with Walled AI

Get API Keys

​Using Walled AI with Portkey

​1. Add Walled AI Credentials to Portkey

​2. Add Walled AI’s Guardrail Check

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

​Get Support

Using Walled AI with Portkey

1. Add Walled AI Credentials to Portkey

2. Add Walled AI’s Guardrail Check

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

Get Support