AI Guardrails
No security coverage
Ai ecosystem
This module provides AI guardrails to control the output of AI models used in Drupal. It includes features to restrict text to specific topics and to integrate with AWS Bedrock for more advanced content filtering.
Collection of AI guardrails.
Implemented guardrails:
- Restrict to Topic: Checks if text's main topic is specified within a list of valid topics
- Aws Bedrock: Calls AWS Bedrock to apply guardrails to the input or output text (requires an AWS account and a Bedrock guardrail configured)
To use this module, you need to apply a patch to the AI module. And if you want to use guardrails in agents too, you need this other patch.