nemoguardrails.library.llama_guard.actions

Module Contents

Functions

Name	Description
`llama_guard_check_input`	Checks user messages using the configured Llama Guard model
`llama_guard_check_output`	Check the bot response using the configured Llama Guard model
`llama_guard_check_output_mapping`	Mapping for llama_guard_check_output.
`parse_llama_guard_response`	Parses the response from the Llama Guard LLM and returns a tuple of:

Data

log

API

nemoguardrails.library.llama_guard.actions.llama_guard_check_input(
    llm_task_manager: nemoguardrails.llm.taskmanager.LLMTaskManager,
    context: typing.Optional[dict] = None,
    llama_guard_llm: typing.Optional[nemoguardrails.types.LLMModel] = None,
    kwargs = {}
) -> dict

async

Checks user messages using the configured Llama Guard model and the configured prompt containing the safety guidelines.

nemoguardrails.library.llama_guard.actions.llama_guard_check_output(
    llm_task_manager: nemoguardrails.llm.taskmanager.LLMTaskManager,
    context: typing.Optional[dict] = None,
    llama_guard_llm: typing.Optional[nemoguardrails.types.LLMModel] = None
) -> dict

async

Check the bot response using the configured Llama Guard model and the configured prompt containing the safety guidelines.

nemoguardrails.library.llama_guard.actions.llama_guard_check_output_mapping(
    result: dict
) -> bool

Mapping for llama_guard_check_output.

Returns: bool

True if the response should be blocked (i.e. if “allowed” is False),

nemoguardrails.library.llama_guard.actions.parse_llama_guard_response(
    response: str
) -> typing.Tuple[bool, typing.Optional[typing.List[str]]]

Parses the response from the Llama Guard LLM and returns a tuple of:

Whether the response is safe or not.
If not safe, a list of the violated policies.

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