> This page is for version v0.24.1. > For other versions, use one of these documentation indexes: > - Latest (default): https://docs.nvidia.com/nemo/guardrails/latest/llms.txt > - v0.24.1: https://docs.nvidia.com/nemo/guardrails/v0.24.1/llms.txt > - v0.24.0: https://docs.nvidia.com/nemo/guardrails/v0.24.0/llms.txt > - v0.23.0: https://docs.nvidia.com/nemo/guardrails/v0.23.0/llms.txt > - v0.22.0: https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/guardrails/_mcp/server. # nemoguardrails.library.autoalign.actions ## Module Contents ### Functions | Name | Description | | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ | | [`_autoalign_outcome`](#nemoguardrails-library-autoalign-actions-_autoalign_outcome) | - | | [`_autoalign_post`](#nemoguardrails-library-autoalign-actions-_autoalign_post) | - | | [`_autoalign_score_outcome`](#nemoguardrails-library-autoalign-actions-_autoalign_score_outcome) | - | | [`autoalign_factcheck_infer`](#nemoguardrails-library-autoalign-actions-autoalign_factcheck_infer) | - | | [`autoalign_factcheck_output_api`](#nemoguardrails-library-autoalign-actions-autoalign_factcheck_output_api) | Calls Autoalign Factchecker API and checks if the user message is factually answered by the bot message | | [`autoalign_groundedness_infer`](#nemoguardrails-library-autoalign-actions-autoalign_groundedness_infer) | Checks the groundedness for the text using the given documents and provides a fact-checking score | | [`autoalign_groundedness_output_api`](#nemoguardrails-library-autoalign-actions-autoalign_groundedness_output_api) | Calls AutoAlign groundedness check API and checks whether the bot message is factually grounded according to given | | [`autoalign_infer`](#nemoguardrails-library-autoalign-actions-autoalign_infer) | Checks whether the given text passes through the applied guardrails. | | [`autoalign_input_api`](#nemoguardrails-library-autoalign-actions-autoalign_input_api) | Calls AutoAlign API for the user message and guardrail configuration provided | | [`autoalign_output_api`](#nemoguardrails-library-autoalign-actions-autoalign_output_api) | Calls AutoAlign API for the bot message and guardrail configuration provided | | [`process_autoalign_output`](#nemoguardrails-library-autoalign-actions-process_autoalign_output) | Processes the output provided AutoAlign API | ### Data [`DEFAULT_CONFIG`](#nemoguardrails-library-autoalign-actions-DEFAULT_CONFIG) [`GUARDRAIL_RESPONSE_TEXT`](#nemoguardrails-library-autoalign-actions-GUARDRAIL_RESPONSE_TEXT) [`default_groundedness_config`](#nemoguardrails-library-autoalign-actions-default_groundedness_config) [`log`](#nemoguardrails-library-autoalign-actions-log) ### API ```python nemoguardrails.library.autoalign.actions._autoalign_outcome( result: dict, target: nemoguardrails.actions.rail_outcome.TransformTarget ) -> nemoguardrails.actions.rail_outcome.RailOutcome ``` ```python nemoguardrails.library.autoalign.actions._autoalign_post( http_client: nemoguardrails.http.HTTPClient | None, request_url: str, headers: dict[str, str], request_body: dict[str, typing.Any] ) -> nemoguardrails.http.HTTPResponse ``` async ```python nemoguardrails.library.autoalign.actions._autoalign_score_outcome( score: float, threshold: float ) -> nemoguardrails.actions.rail_outcome.RailOutcome ``` ```python nemoguardrails.library.autoalign.actions.autoalign_factcheck_infer( request_url: str, user_message: str, bot_message: str, guardrails_config: typing.Optional[typing.Dict[str, typing.Any]] = None, multi_language: bool = False, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None ) ``` async ```python nemoguardrails.library.autoalign.actions.autoalign_factcheck_output_api( llm_task_manager: nemoguardrails.llm.taskmanager.LLMTaskManager, context: typing.Optional[dict] = None, user_message: typing.Optional[str] = None, bot_message: typing.Optional[str] = None, factcheck_threshold: float = 0.0, show_autoalign_message: bool = True, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None ) -> nemoguardrails.actions.rail_outcome.RailOutcome ``` async Calls Autoalign Factchecker API and checks if the user message is factually answered by the bot message Scores below `factcheck_threshold` block. Configuration, transport, status, and response parsing failures propagate to the caller. **Parameters:** **`llm_task_manager`** `LLMTaskManager` Task manager containing the AutoAlign configuration. --- **`context`** `Optional[dict]` — default: None Runtime context containing the user and bot messages. --- **`factcheck_threshold`** `float` — default: 0.0 Minimum score required to allow the response. --- **`show_autoalign_message`** `bool` — default: True Whether to log detected violations. --- **`http_client`** `Optional[HTTPClient]` — default: None Optional caller-owned HTTP client. --- **Returns:** `RailOutcome` An allow or block outcome containing the score and threshold. ```python nemoguardrails.library.autoalign.actions.autoalign_groundedness_infer( request_url: str, text: str, documents: typing.List[str], guardrails_config: typing.Optional[typing.Dict[typing.Any, typing.Any]] = None, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None ) ``` async Checks the groundedness for the text using the given documents and provides a fact-checking score ```python nemoguardrails.library.autoalign.actions.autoalign_groundedness_output_api( llm_task_manager: nemoguardrails.llm.taskmanager.LLMTaskManager, context: typing.Optional[dict] = None, factcheck_threshold: float = 0.0, show_autoalign_message: bool = True, bot_message: typing.Optional[str] = None, relevant_chunks_sep: typing.Optional[typing.List[str]] = None, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None, kwargs = {} ) -> nemoguardrails.actions.rail_outcome.RailOutcome ``` async Calls AutoAlign groundedness check API and checks whether the bot message is factually grounded according to given documents Scores below `factcheck_threshold` block. Configuration, transport, status, and response parsing failures propagate to the caller. **Parameters:** **`llm_task_manager`** `LLMTaskManager` Task manager containing the AutoAlign configuration. --- **`context`** `Optional[dict]` — default: None Runtime context containing the bot message and documents. --- **`factcheck_threshold`** `float` — default: 0.0 Minimum score required to allow the response. --- **`show_autoalign_message`** `bool` — default: True Whether to log detected violations. --- **`http_client`** `Optional[HTTPClient]` — default: None Optional caller-owned HTTP client. --- **`**kwargs`** — default: \{} Additional action parameters. --- **Returns:** `RailOutcome` An allow or block outcome containing the score and threshold. ```python nemoguardrails.library.autoalign.actions.autoalign_infer( request_url: str, text: str, task_config: typing.Optional[typing.Dict[typing.Any, typing.Any]] = None, show_toxic_phrases: bool = False, multi_language: bool = False, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None ) ``` async Checks whether the given text passes through the applied guardrails. ```python nemoguardrails.library.autoalign.actions.autoalign_input_api( llm_task_manager: nemoguardrails.llm.taskmanager.LLMTaskManager, context: typing.Optional[dict] = None, user_message: typing.Optional[str] = None, show_autoalign_message: bool = True, show_toxic_phrases: bool = False, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None, kwargs = {} ) -> nemoguardrails.actions.rail_outcome.RailOutcome ``` async Calls AutoAlign API for the user message and guardrail configuration provided Guardrail matches block, PII redactions transform the user message, and other results allow it. Configuration, transport, status, and response parsing failures propagate to the caller. **Parameters:** **`llm_task_manager`** `LLMTaskManager` Task manager containing the AutoAlign configuration. --- **`context`** `Optional[dict]` — default: None Runtime context containing the user message. --- **`show_autoalign_message`** `bool` — default: True Whether to log detected violations. --- **`show_toxic_phrases`** `bool` — default: False Whether violation messages include toxic phrases. --- **`http_client`** `Optional[HTTPClient]` — default: None Optional caller-owned HTTP client. --- **`**kwargs`** — default: \{} Additional action parameters. --- **Returns:** `RailOutcome` An allow, block, or user-message transform outcome. ```python nemoguardrails.library.autoalign.actions.autoalign_output_api( llm_task_manager: nemoguardrails.llm.taskmanager.LLMTaskManager, context: typing.Optional[dict] = None, bot_message: typing.Optional[str] = None, show_autoalign_message: bool = True, show_toxic_phrases: bool = False, http_client: typing.Optional[nemoguardrails.http.HTTPClient] = None, kwargs = {} ) -> nemoguardrails.actions.rail_outcome.RailOutcome ``` async Calls AutoAlign API for the bot message and guardrail configuration provided Guardrail matches block, PII redactions transform the bot message, and other results allow it. Configuration, transport, status, and response parsing failures propagate to the caller. **Parameters:** **`llm_task_manager`** `LLMTaskManager` Task manager containing the AutoAlign configuration. --- **`context`** `Optional[dict]` — default: None Runtime context containing the bot message. --- **`show_autoalign_message`** `bool` — default: True Whether to log detected violations. --- **`show_toxic_phrases`** `bool` — default: False Whether violation messages include toxic phrases. --- **`http_client`** `Optional[HTTPClient]` — default: None Optional caller-owned HTTP client. --- **`**kwargs`** — default: \{} Additional action parameters. --- **Returns:** `RailOutcome` An allow, block, or bot-message transform outcome. ```python nemoguardrails.library.autoalign.actions.process_autoalign_output( responses: typing.List[typing.Any], show_toxic_phrases: bool = False ) ``` Processes the output provided AutoAlign API ```python nemoguardrails.library.autoalign.actions.DEFAULT_CONFIG = {'pii': {'mode': 'OFF', 'mask': False, 'enabled_types': ['[BANK ACCOUNT NUMBER]'... ``` ```python nemoguardrails.library.autoalign.actions.GUARDRAIL_RESPONSE_TEXT = {'confidential_info_detection': 'Confidential Information violation', 'gender_bi... ``` ```python nemoguardrails.library.autoalign.actions.default_groundedness_config = {'groundedness_checker': {'verify_response': False}} ``` ```python nemoguardrails.library.autoalign.actions.log = logging.getLogger(__name__) ```