ReferencePython SDK ReferenceNemoguardrailsLibraryPolicyai

nemoguardrails.library.policyai.actions

View as Markdown

PolicyAI Integration for NeMo Guardrails.

PolicyAI provides content moderation and policy enforcement capabilities for LLM applications. This integration allows using PolicyAI as an input and output rail for content moderation.

For more information, see: https://musubilabs.ai

Module Contents

Functions

NameDescription
_policyai_outcome-
call_policyai_apiCall the PolicyAI API to evaluate content.

Data

log

API

nemoguardrails.library.policyai.actions._policyai_outcome(
    metadata: dict
) -> nemoguardrails.actions.rail_outcome.RailOutcome
 
nemoguardrails.library.policyai.actions.call_policyai_api(
    text: typing.Optional[str] = None,
    tag_name: typing.Optional[str] = None,
    http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None,
    kwargs = {}
) -> nemoguardrails.actions.rail_outcome.RailOutcome
async

Call the PolicyAI API to evaluate content.

Parameters:

text
Optional[str]Defaults to None

The text content to evaluate.

tag_name
Optional[str]Defaults to None

Optional tag name for the PolicyAI evaluation. If not provided, uses POLICYAI_TAG_NAME env var or “prod”.

Returns: RailOutcome

RailOutcome indicating whether the content is blocked. Assessment, category,

nemoguardrails.library.policyai.actions.log = logging.getLogger(__name__)