Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature/clavata integration #1

Closed
wants to merge 2 commits into from
Closed

Conversation

ilias-t
Copy link

@ilias-t ilias-t commented Mar 4, 2025

Description

This PR introduces an integration for Clavata for customized LLM content moderation. It adds a detect_policy_match action which can be used in input and output flows.

Related Issue(s)

#1025

Checklist

  • I've read the CONTRIBUTING guidelines.
  • I've updated the documentation if applicable.
  • I've added tests if applicable.
  • @mentions of the person or team responsible for reviewing proposed changes.

@ilias-t ilias-t force-pushed the feature/clavata-integration branch from d5fff61 to ae18325 Compare March 5, 2025 21:53
- Users of the Clavata integration can now specify the exact labels that must match for the input/output to cause the rail to trigger and abort the flow.
- Fixing some aspects of how the configuration is put together
- Policy ID aliases make it easier to specify a policy by name instead of ID.
- The new action `EvaluateUserInputWithClavataPolicy` allows you to evaluate the user input against a Clavata policy part of a flow that a user has written.
- Added the ability for a user to specify ANY/ALL logic for label matches.

Co-authored-by: Brett Levenson <[email protected]>
Signed-off-by: Ilias Tsangaris <[email protected]>
@ilias-t ilias-t force-pushed the feature/clavata-integration branch from ae18325 to 465be03 Compare March 5, 2025 21:55
@ilias-t ilias-t closed this Mar 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant