Skip to main content
Qualifire offers a comprehensive suite of AI safety and quality guardrails that help ensure your AI applications are safe, compliant, and high-quality. The platform provides 20+ different guardrail checks covering content safety, AI quality, and compliance requirements.
1

Add Qualifire Credentials to Portkey

Add your Qualifire API key to Portkey:
  1. Click on the Admin Settings button on Sidebar
  2. Navigate to Plugins tab under Organisation Settings
  3. Click on the edit button for the Qualifire integration
  4. Add your Qualifire API Key - obtain this from your Qualifire account at https://app.qualifire.ai/settings/api-keys/
2

Add Qualifire's Guardrail Checks

Create and configure guardrails:
  1. Navigate to the Guardrails page and click the Create button
  2. Search for any of the Qualifire guardrail checks and click Add
  3. Configure the specific parameters for your chosen guardrail
  4. Set any actions you want on your check, and create the Guardrail!
Guardrail Actions allow you to orchestrate your guardrails logic. You can learn more about them in the Portkey Guardrails documentation.
3

Add Guardrail ID to Config

Add the Guardrail ID to your Portkey Config:
  1. When you save a Guardrail, you’ll get an associated Guardrail ID
  2. Add this ID to the input_guardrails or output_guardrails params in your Portkey Config
  3. Create these Configs in Portkey UI, save them, and get an associated Config ID to attach to your requests
{
  "input_guardrails": ["guardrails-id-xxx"],
  "output_guardrails": ["guardrails-id-yyy"]
}
4

Make Your Request

Use your Config ID in your requests. Your requests are now protected by Qualifire’s comprehensive guardrail system!
const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    config: "pc-***" // Supports a string config id or a config object
});
For more details on Configs, refer to the Portkey Config documentation.

​
Available Guardrail Checks

Qualifire provides a comprehensive set of guardrail checks organized into five main categories:

​
Security

Check NameDescriptionParametersSupported Hooks
PII CheckChecks that neither the user nor the model included PIIsNonebeforeRequestHook, afterRequestHook
Prompt Injections CheckChecks that the prompt does not contain any injections to the modelNonebeforeRequestHook

​
Safety

Check NameDescriptionParametersSupported Hooks
Content Moderation CheckChecks for harmful content including sexual content, harassment, hate speech, and dangerous content in the user input or model outputNonebeforeRequestHook, afterRequestHook

​
Reliability

Check NameDescriptionParametersSupported Hooks
Instruction Following CheckChecks that the model followed the instructions provided in the promptNoneafterRequestHook
Grounding CheckChecks that the model is grounded in the context providedmode (optional) - See Mode ParameterafterRequestHook
Hallucinations CheckChecks that the model did not hallucinatemode (optional) - See Mode ParameterafterRequestHook
Tool Use Quality CheckChecks the model’s tool use quality. Including correct tool selection, parameters and valuesmode (optional) - See Mode ParameterafterRequestHook

​
Policy

Check NameDescriptionParametersSupported Hooks
Policy Violations CheckChecks that the prompt and response didn’t violate any given policiespolicies (array of strings) - See Policy Violations Check
mode (optional) - See Mode Parameter
policy_target (optional) - See Policy Violations Check		beforeRequestHook, afterRequestHook

​
Configuration Examples

​
Mode Parameter

Several guardrail checks support a mode parameter that controls the trade-off between accuracy and speed:
  • quality: Highest accuracy, slower processing
  • balanced: Good balance between accuracy and speed (default)
  • speed: Fastest processing, lower accuracy
Example: 
{
  "mode": "quality"
}

​
Policy Violations Check

For the Policy Violations Check, you can specify custom policies to enforce, the mode, and the target: 
{
  "policies": [
    "The model cannot provide any discount to the user",
    "The model must not share internal company information",
    "The model must respond in a professional tone"
  ],
  "mode": "balanced",
  "policy_target": "both"
}

​
Parameters

  • policies (required): Array of strings defining custom policies to enforce
  • mode (optional): One of quality, balanced, or speed. Default: balanced
  • policy_target (optional): One of input, output, or both. Specifies whether to run the policy check on the request, response, or both. This must match the configured hooks:
    • input: Only for beforeRequestHook
    • output: Only for afterRequestHook
    • both: For both beforeRequestHook and afterRequestHook

​
Use Cases

Qualifire’s guardrails are particularly useful for:
  • Content Moderation: Filtering harmful or inappropriate content in user inputs and AI responses
  • Compliance: Ensuring AI responses adhere to company policies and regulatory requirements
  • Quality Assurance: Detecting hallucinations, instruction violations, and poor tool usage
  • Data Protection: Preventing PII exposure and ensuring data privacy

​
Observability

You can see the verdict and any actions taken directly in your Portkey logs! Monitor guardrail results to understand how your AI applications are performing and identify areas for improvement.

​
Get Support

If you face any issues with the Qualifire integration, join the Portkey community forum for assistance. For Qualifire-specific support, visit the Qualifire Documentation or contact the Qualifire support team.

​
Additional Resources