OpenAIModerationMiddleware

OpenAIModerationMiddleware(
  self,
  *,
  model: ModerationModel = 'omni-moderation-latest',
  check_input: bool = True,
  check_output

Bases

AgentMiddleware[AgentState[Any], Any]

Name	Type	Description
`model`	`ModerationModel`	Default:`'omni-moderation-latest'` OpenAI moderation model to use.
`check_input`	`bool`	Default:`True` Whether to check user input messages.
`check_output`	`bool`	Default:`True` Whether to check model output messages.
`check_tool_results`	`bool`	Default:`False`
`exit_behavior`	`Literal['error', 'end', 'replace']`	Default:`'end'`
`violation_message`	`str \| None`	Default:`None`
`client`	`OpenAI \| None`	Default:`None`
`async_client`	`AsyncOpenAI \| None`	Default:`None`

constructor

__init__