feature: Clavata integration

[ilias-t]

Did you check the docs?

• I have read all the NeMo-Guardrails docs

Is your feature request related to a problem? Please describe.

Add support for Clavata that provides content moderation capabilities to detect and filter inappropriate content.

Describe the solution you'd like

A user can customize the content moderation behavior by:

1. Configuring different policies for input and output flows
2. Specifying which labels must match within a policy
3. Setting the label match logic to either "ALL" (all specified labels must match) or "ANY" (at least one label must match)

Example config

rails:
  config:
    clavata:
      # Only provide this if you've been told to by Clavata.ai
      server_endpoint: "https://some-alt-endpoint.com"
      policies:
        - alias: "Violence"
          id: "00000000-0000-0000-0000-000000000000"
        - alias: "Weapons"
          id: "00000000-0000-0000-0000-000000000000"
      input:
        policy: "Violence"
        # Optional: Specify labels to require specific matches
        labels:
          - "Violence"
          - "Weapons"
          - "Drugs"
        label_match_logic: ALL  # Can be "ALL" or "ANY"
      output:
        policy: "Weapons"
  input:
    flows:
      - clavata check input
  output:
    flows:
      - clavata check output

Details

• server_endpoint: The Clavata API endpoint (only if provided by Clavata.ai)
• policies: List of policy configurations with aliases and IDs
• input/output: Flow-specific configurations
  • policy: The policy alias to use for this flow
  • labels: (Optional) List of specific labels to check for
  • label_match_logic: (Optional) "ALL" requires all specified labels to match, "ANY" requires at least one match

Describe alternatives you've considered

N/A

Additional context

No response