Introduction

Welcome

This section provides an overview of the available Guardrails endpoints.

Enkrypt AI Guardrails can be accessed via the following base URL:

https://api.enkryptai.com

/guardrails/health: Returns health status of the service

/guardrails/status: Checks if the API is up and running

/guardrails/models: Returns list of models loaded

/guardrails/detect: Detects prompts injection, toxicity, keywords, NSFW content, etc.

/guardrails/pii: Detects PII content and de-anonymizes it

/guardrails/hallucination: Detects hallucination in model output, given context

/guardrails/adherence: Detects adherence to context

/guardrails/relevancy: Detects relevancy of the response to the question

/guardrails/add-policy: Create new policies with custom configurations

/guardrails/get-policy: Retrieve existing policies by name

/guardrails/modify-policy: Modify existing policies

/guardrails/delete-policy: Remove policies that are no longer needed

/guardrails/policy/detect: Apply a specific policy to detect and filter content

All API endpoints are authenticated using API Keys and can be accessed from the User Dashboard.

On this page