Aporia provides state-of-the-art Guardrails for any AI workload. With Aporia, you can setup powerful, multimodal AI Guardrails and just add your Project ID to Portkey to enable them for your Portkey requests. Aporia supports Guardrails for Prompt Injections, Prompt Leakage, SQL Enforcement, Data Leakage, PII Leakage, Profanity Detection, and many more! Browse Aporia’s docs for more info on each of the Guardrail:

Quickstart - AporiaAporia

Learn more about Patronus AI and their offerings.

​
Using Aporia with Portkey

​
1. Add Aporia API Key to Portkey

  • Navigate to the Integrations page under Settings
  • Click on the edit button for the Aporia integration and add your API key

​
2. Add Aporia’s Guardrail Check

  • Now, navigate to the Guardrails page
  • Search for Validate - Project Guardrail Check and click on Add
  • Input your corresponding Aporia Project ID where you are defining the policies
  • Save the check, set any actions you want on the check, and create the Guardrail!
Check NameDescriptionParametersSupported Hooks
Validate - ProjectsRuns a project containing policies set in Aporia and returns a PASS or FAIL verdictProject ID: stringbeforeRequestHooks afterRequestHooks
Your Aporia Guardrail is now ready to be added to any Portkey request you’d like!

​
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 before_request_hooks or after_request_hooks params in your Portkey Config
  • Save this Config and pass it along with any Portkey request you’re making!
Your requests are now guarded by your Aporia policies 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 Aporia dashboard.

​
Get Support

If you face any issues with the Aporia integration, just ping the @Aporia team on the community forum.