nemoguardrails.rails.llm.config | NVIDIA NeMo Guardrails Library Developer Guide

Module for the configuration of rails.

Module Contents

Classes

Name	Description
`AIDefenseRailConfig`	Configuration data for the Cisco AI Defense API
`ActionRails`	Configuration of action rails.
`AutoAlignOptions`	List of guardrails that are activated
`AutoAlignRailConfig`	Configuration data for the AutoAlign API
`CacheStatsConfig`	Configuration for cache statistics tracking and logging.
`ClavataRailConfig`	Configuration data for the Clavata API
`ClavataRailOptions`	Configuration data for the Clavata API
`ContentSafetyConfig`	Configuration data for content safety rails.
`CoreConfig`	Settings for core internal mechanics.
`CrowdStrikeAIDRRailConfig`	Configuration data for the CrowdStrike AIDR API
`DialogRails`	Configuration of topical rails.
`Document`	Configuration for documents that should be used for question answering.
`EmbeddingSearchProvider`	Configuration of a embedding search provider.
`EmbeddingsCacheConfig`	Configuration for the caching embeddings.
`FactCheckingRailConfig`	Configuration data for the fact-checking rail.
`FiddlerGuardrails`	Configuration for Fiddler Guardrails.
`GLiNERDetection`	Configuration for GLiNER PII detection.
`GLiNERDetectionOptions`	Configuration options for GLiNER.
`GuardrailsAIRailConfig`	Configuration data for Guardrails AI integration.
`GuardrailsAIValidatorConfig`	Configuration for a single Guardrails AI validator.
`InjectionDetection`	-
`InputRails`	Configuration of input rails.
`Instruction`	Configuration for instructions in natural language that should be passed to the LLM.
`JailbreakDetectionConfig`	Configuration data for jailbreak detection.
`KnowledgeBaseConfig`	-
`LocalHFClassifierConfig`	Configuration for a local HuggingFace Transformers pipeline classifier.
`LogAdapterConfig`	-
`MessageTemplate`	Template for a message structure.
`MetricsConfig`	OpenTelemetry Metrics Configuration.
`Model`	Configuration of a model used by the rails engine.
`ModelCacheConfig`	Configuration for model caching.
`MultilingualConfig`	Configuration for multilingual refusal messages.
`OutputRails`	Configuration of output rails.
`OutputRailsStreamingConfig`	Configuration for managing streaming output of LLM tokens.
`PangeaRailConfig`	Configuration data for the Pangea AI Guard API
`PangeaRailOptions`	Configuration data for the Pangea AI Guard API
`PatronusEvaluateApiParams`	Config to parameterize the Patronus Evaluate API call
`PatronusEvaluateConfig`	Config for the Patronus Evaluate API call
`PatronusEvaluationSuccessStrategy`	Strategy for determining whether a Patronus Evaluation API
`PatronusRailConfig`	Configuration data for the Patronus Evaluate API
`PrivateAIDetection`	Configuration for Private AI.
`PrivateAIDetectionOptions`	Configuration options for Private AI.
`Rails`	Configuration of specific rails.
`RailsConfig`	Configuration object for the models and the rails.
`RailsConfigData`	Configuration data for specific rails that are supported out-of-the-box.
`ReasoningConfig`	Configuration for reasoning mode in content safety models.
`RegexDetection`	Configuration for regex pattern detection.
`RegexDetectionOptions`	Configuration options for regex pattern detection on a specific source.
`RemoteHFClassifierConfig`	Configuration for a remote HuggingFace classifier (vLLM, KServe, FMS).
`RetrievalRails`	Configuration of retrieval rails.
`SensitiveDataDetection`	Configuration of what sensitive data should be detected.
`SensitiveDataDetectionOptions`	-
`SingleCallConfig`	Configuration for the single LLM call option for topical rails.
`SpanFormat`	-
`TaskPrompt`	Configuration for prompts that will be used for a specific task.
`ToolInputRails`	Configuration of tool input rails.
`ToolOutputRails`	Configuration of tool output rails.
`TracingConfig`	-
`TrendMicroRailConfig`	Configuration data for the Trend Micro AI Guard API
`UserMessagesConfig`	Configuration for how the user messages are interpreted.
`_HFClassifierBase`	Shared fields for all HuggingFace classifier engines.

Functions

Name	Description
`_generate_rails_flows`	Generates flow definitions from the list of flows.
`_get_flow_model`	Helper to return a model name from a flow definition
`_get_flow_name`	Helper to return a model name from a flow definition
`_get_rails_flows`	Extracts the list of flows from the raw_config dictionary.
`_has_input_output_config_rails`	Checks if the raw configuration has input/output rails configured.
`_join_config`	Helper to join two configuration.
`_join_dict`	Joins two dictionaries recursively.
`_join_rails_configs`	Helper to join two rails configuration.
`_load_imported_paths`	Load recursively all the imported path in the specified raw_config.
`_load_path`	Load a configuration object from the specified path.
`_parse_colang_files_recursively`	Helper function to parse all the Colang files.
`_unique_list_concat`	Concatenates two lists ensuring all elements are unique.
`_validate_rail_prompts`	-
`merge_two_dicts`	Merges the fields of two dictionaries recursively.

Data

HFClassifierConfig

JAILBREAK_FLOW_HEURISTICS

JAILBREAK_FLOW_MODEL

guardrails_stdlib_path

log

standard_library_path

API

class nemoguardrails.rails.llm.config.AIDefenseRailConfig()

Bases: BaseModel

Configuration data for the Cisco AI Defense API

fail_open

bool

timeout

float

class nemoguardrails.rails.llm.config.ActionRails()

Bases: BaseModel

Configuration of action rails.

Action rails control various options related to the execution of actions. Currently, only

In the future multiple options will be added, e.g., what input validation should be performed per action, output validation, throttling, disabling, etc.

instant_actions

Optional[List[str]]

class nemoguardrails.rails.llm.config.AutoAlignOptions()

Bases: BaseModel

List of guardrails that are activated

guardrails_config

Dict[str, Any]

class nemoguardrails.rails.llm.config.AutoAlignRailConfig()

Bases: BaseModel

Configuration data for the AutoAlign API

input

AutoAlignOptions

output

AutoAlignOptions

parameters

Dict[str, Any] = Field(default_factory=dict)

class nemoguardrails.rails.llm.config.CacheStatsConfig()

Bases: BaseModel

Configuration for cache statistics tracking and logging.

enabled

bool

log_interval

Optional[float]

class nemoguardrails.rails.llm.config.ClavataRailConfig()

Bases: BaseModel

Configuration data for the Clavata API

input

Optional[ClavataRailOptions]

label_match_logic

Literal['ANY', 'ALL']

output

Optional[ClavataRailOptions]

policies

Dict[str, str]

server_endpoint

str

class nemoguardrails.rails.llm.config.ClavataRailOptions()

Bases: BaseModel

Configuration data for the Clavata API

labels

List[str]

policy

str

class nemoguardrails.rails.llm.config.ContentSafetyConfig()

Bases: BaseModel

Configuration data for content safety rails.

multilingual

MultilingualConfig

reasoning

ReasoningConfig

class nemoguardrails.rails.llm.config.CoreConfig()

Bases: BaseModel

Settings for core internal mechanics.

embedding_search_provider

EmbeddingSearchProvider

class nemoguardrails.rails.llm.config.CrowdStrikeAIDRRailConfig()

Bases: BaseModel

Configuration data for the CrowdStrike AIDR API

timeout

float

class nemoguardrails.rails.llm.config.DialogRails()

Bases: BaseModel

Configuration of topical rails.

single_call

SingleCallConfig

user_messages

UserMessagesConfig

class nemoguardrails.rails.llm.config.Document()

Bases: BaseModel

Configuration for documents that should be used for question answering.

content

str

format

str

class nemoguardrails.rails.llm.config.EmbeddingSearchProvider()

Bases: BaseModel

Configuration of a embedding search provider.

cache

EmbeddingsCacheConfig = Field(default_factory=EmbeddingsCacheConfig)

name

str

parameters

Dict[str, Any] = Field(default_factory=dict)

class nemoguardrails.rails.llm.config.EmbeddingsCacheConfig()

Bases: BaseModel

Configuration for the caching embeddings.

enabled

bool

key_generator

str

store

str

store_config

Dict[str, Any]

nemoguardrails.rails.llm.config.EmbeddingsCacheConfig.to_dict()

class nemoguardrails.rails.llm.config.FactCheckingRailConfig()

Bases: BaseModel

Configuration data for the fact-checking rail.

fallback_to_self_check

bool

parameters

Dict[str, Any] = Field(default_factory=dict)

class nemoguardrails.rails.llm.config.FiddlerGuardrails()

Bases: BaseModel

Configuration for Fiddler Guardrails.

faithfulness_threshold

float

fiddler_endpoint

str

safety_threshold

float

class nemoguardrails.rails.llm.config.GLiNERDetection()

Bases: BaseModel

Configuration for GLiNER PII detection.

api_key_env_var

Optional[str]

chunk_length

int

flat_ner

bool

input

GLiNERDetectionOptions

model

str

model_config

= ConfigDict(extra='forbid')

output

GLiNERDetectionOptions

overlap

int

retrieval

GLiNERDetectionOptions

server_endpoint

str

threshold

float

class nemoguardrails.rails.llm.config.GLiNERDetectionOptions()

Bases: BaseModel

Configuration options for GLiNER.

entities

List[str]

model_config

= ConfigDict(extra='forbid')

class nemoguardrails.rails.llm.config.GuardrailsAIRailConfig()

Bases: BaseModel

Configuration data for Guardrails AI integration.

validators

List[GuardrailsAIValidatorConfig]

nemoguardrails.rails.llm.config.GuardrailsAIRailConfig.get_validator_config(
    name: str
) -> typing.Optional[nemoguardrails.rails.llm.config.GuardrailsAIValidatorConfig]

Get a specific validator configuration by name.

class nemoguardrails.rails.llm.config.GuardrailsAIValidatorConfig()

Bases: BaseModel

Configuration for a single Guardrails AI validator.

metadata

Dict[str, Any]

name

str

parameters

Dict[str, Any]

class nemoguardrails.rails.llm.config.InjectionDetection()

Bases: BaseModel

action

str

injections

List[str]

yara_path

Optional[str]

yara_rules

Optional[Dict[str, str]]

class nemoguardrails.rails.llm.config.InputRails()

Bases: BaseModel

Configuration of input rails.

flows

List[str]

parallel

Optional[bool]

speculative_generation

Optional[bool]

class nemoguardrails.rails.llm.config.Instruction()

Bases: BaseModel

Configuration for instructions in natural language that should be passed to the LLM.

content

str

type

str

class nemoguardrails.rails.llm.config.JailbreakDetectionConfig()

Bases: BaseModel

Configuration data for jailbreak detection.

api_key

Optional[SecretStr]

api_key_env_var

Optional[str]

embedding

Optional[str]

length_per_perplexity_threshold

float

nim_base_url

Optional[str]

nim_port

Optional[int]

nim_server_endpoint

Optional[str]

nim_url

Optional[str]

prefix_suffix_perplexity_threshold

float

server_endpoint

Optional[str]

nemoguardrails.rails.llm.config.JailbreakDetectionConfig.get_api_key() -> typing.Optional[str]

Helper to return an API key (if it exists) from a Jailbreak configuration. This can come from (in descending order of priority):

The api_key field, a Pydantic SecretStr from which we extract the full string.
The api_key_env_var field, a string stored in this environment variable.

If neither is found, None is returned.

nemoguardrails.rails.llm.config.JailbreakDetectionConfig.migrate_deprecated_fields() -> nemoguardrails.rails.llm.config.JailbreakDetectionConfignemoguardrails.rails.llm.config.JailbreakDetectionConfig.migrate_deprecated_fields() -> nemoguardrails.rails.llm.config.JailbreakDetectionConfig

Migrate deprecated nim_url/nim_port fields to nim_base_url format.

nemoguardrails.rails.llm.config.JailbreakDetectionConfig.validate_urls() -> nemoguardrails.rails.llm.config.JailbreakDetectionConfignemoguardrails.rails.llm.config.JailbreakDetectionConfig.validate_urls() -> nemoguardrails.rails.llm.config.JailbreakDetectionConfig

Validate URL formats for endpoints.

class nemoguardrails.rails.llm.config.KnowledgeBaseConfig()

Bases: BaseModel

embedding_search_provider

EmbeddingSearchProvider

folder

str

class nemoguardrails.rails.llm.config.LocalHFClassifierConfig()

Bases: _HFClassifierBase

Configuration for a local HuggingFace Transformers pipeline classifier.

engine

Literal['local'] = 'local'

parameters

Dict[str, Any]

task

Literal['text-classification', 'token-classification']

nemoguardrails.rails.llm.config.LocalHFClassifierConfig._validate_local() -> nemoguardrails.rails.llm.config.LocalHFClassifierConfignemoguardrails.rails.llm.config.LocalHFClassifierConfig._validate_local() -> nemoguardrails.rails.llm.config.LocalHFClassifierConfig

class nemoguardrails.rails.llm.config.LogAdapterConfig()

Bases: BaseModel

model_config

= ConfigDict(extra='allow')

name

str

class nemoguardrails.rails.llm.config.MessageTemplate()

Bases: BaseModel

Template for a message structure.

content

str = Field(description='The content of the message.')

type

str

class nemoguardrails.rails.llm.config.MetricsConfig()

Bases: BaseModel

OpenTelemetry Metrics Configuration. Configures and enables Metrics independent of OTEL Traces.

enabled

bool

class nemoguardrails.rails.llm.config.Model()

Bases: BaseModel

Configuration of a model used by the rails engine.

Typically, the main model is configured e.g.: { “type”: “main”, “engine”: “openai”, “model”: “gpt-3.5-turbo-instruct” }

api_key_env_var

Optional[str]

cache

Optional[ModelCacheConfig]

engine

str

mode

Literal['chat', 'text']

model

Optional[str]

parameters

Dict[str, Any] = Field(default_factory=dict)

type

str

nemoguardrails.rails.llm.config.Model.model_must_be_none_empty() -> nemoguardrails.rails.llm.config.Modelnemoguardrails.rails.llm.config.Model.model_must_be_none_empty() -> nemoguardrails.rails.llm.config.Model

Validate that a model name is present either directly or in parameters.

nemoguardrails.rails.llm.config.Model.set_and_validate_model(
    data: typing.Any
) -> typing.Any

classmethod

class nemoguardrails.rails.llm.config.ModelCacheConfig()

Bases: BaseModel

Configuration for model caching.

enabled

bool

maxsize

int

stats

CacheStatsConfig

class nemoguardrails.rails.llm.config.MultilingualConfig()

Bases: BaseModel

Configuration for multilingual refusal messages.

enabled

bool

refusal_messages

Optional[Dict[str, str]]

class nemoguardrails.rails.llm.config.OutputRails()

Bases: BaseModel

Configuration of output rails.

flows

List[str]

parallel

Optional[bool]

streaming

OutputRailsStreamingConfig

class nemoguardrails.rails.llm.config.OutputRailsStreamingConfig()

Bases: BaseModel

Configuration for managing streaming output of LLM tokens.

chunk_size

int

context_size

int

enabled

bool

model_config

= ConfigDict(extra='allow')

stream_first

bool

class nemoguardrails.rails.llm.config.PangeaRailConfig()

Bases: BaseModel

Configuration data for the Pangea AI Guard API

input

Optional[PangeaRailOptions]

output

Optional[PangeaRailOptions]

class nemoguardrails.rails.llm.config.PangeaRailOptions()

Bases: BaseModel

Configuration data for the Pangea AI Guard API

recipe

str

class nemoguardrails.rails.llm.config.PatronusEvaluateApiParams()

Bases: BaseModel

Config to parameterize the Patronus Evaluate API call

params

Dict[str, Any]

success_strategy

Optional[PatronusEvaluationSuccessStrategy]

class nemoguardrails.rails.llm.config.PatronusEvaluateConfig()

Bases: BaseModel

Config for the Patronus Evaluate API call

evaluate_config

PatronusEvaluateApiParams

class nemoguardrails.rails.llm.config.PatronusEvaluationSuccessStrategy

Bases: enum.Enum

Strategy for determining whether a Patronus Evaluation API request should pass, especially when multiple evaluators are called in a single request. ALL_PASS requires all evaluators to pass for success. ANY_PASS requires only one evaluator to pass for success.

ALL_PASS

= 'all_pass'

ANY_PASS

= 'any_pass'

class nemoguardrails.rails.llm.config.PatronusRailConfig()

Bases: BaseModel

Configuration data for the Patronus Evaluate API

input

Optional[PatronusEvaluateConfig]

output

Optional[PatronusEvaluateConfig]

class nemoguardrails.rails.llm.config.PrivateAIDetection()

Bases: BaseModel

Configuration for Private AI.

input

PrivateAIDetectionOptions

output

PrivateAIDetectionOptions

retrieval

PrivateAIDetectionOptions

server_endpoint

str

class nemoguardrails.rails.llm.config.PrivateAIDetectionOptions()

Bases: BaseModel

Configuration options for Private AI.

entities

List[str]

class nemoguardrails.rails.llm.config.Rails()

Bases: BaseModel

Configuration of specific rails.

actions

ActionRails

config

RailsConfigData

dialog

DialogRails

input

InputRails

output

OutputRails

retrieval

RetrievalRails

tool_input

ToolInputRails

tool_output

ToolOutputRails

class nemoguardrails.rails.llm.config.RailsConfig()

Bases: BaseModel

Configuration object for the models and the rails.

TODO: add typed config for user_messages, bot_messages, and flows.

actions_server_url

Optional[str]

bot_messages

Dict[str, List[str]]

colang_version

str

config_path

Optional[str]

core

CoreConfig

custom_data

Dict

docs

Optional[List[Document]]

enable_multi_step_generation

Optional[bool]

enable_rails_exceptions

bool

event_source_uid

str

flows

List[Union[Dict, Any]]

import_paths

Optional[List[str]]

imported_paths

Optional[Dict[str, str]]

instructions

Optional[List[Instruction]]

knowledge_base

KnowledgeBaseConfig

lowest_temperature

Optional[float]

metrics

MetricsConfig

models

List[Model]

passthrough

Optional[bool]

prompting_mode

Optional[str]

prompts

Optional[List[TaskPrompt]]

rails

Rails

raw_llm_call_action

Optional[str]

sample_conversation

Optional[str]

streaming

bool

tracing

TracingConfig

user_messages

Dict[str, List[str]]

nemoguardrails.rails.llm.config.RailsConfig.__add__(
    other
)

Adds two RailsConfig objects.

nemoguardrails.rails.llm.config.RailsConfig.check_jailbreak_detection_config(
    values
)

Validate jailbreak detection configuration against enabled flows.

nemoguardrails.rails.llm.config.RailsConfig.check_model_exists_for_input_rails(
    values
)

Make sure we have a model for each input rail where one is provided using $model=<model_type>

nemoguardrails.rails.llm.config.RailsConfig.check_model_exists_for_output_rails(
    values
)

Make sure we have a model for each output rail where one is provided using $model=<model_type>

nemoguardrails.rails.llm.config.RailsConfig.check_output_parser_exists(
    values
)

nemoguardrails.rails.llm.config.RailsConfig.check_prompt_exist_for_self_check_rails(
    values
)

nemoguardrails.rails.llm.config.RailsConfig.fill_in_default_values_for_v2_x(
    values
)

nemoguardrails.rails.llm.config.RailsConfig.from_content(
    colang_content: typing.Optional[str] = None,
    yaml_content: typing.Optional[str] = None,
    config: typing.Optional[dict] = None
)

classmethod

Loads a configuration from the provided colang/YAML content/config dict.

nemoguardrails.rails.llm.config.RailsConfig.from_path(
    config_path: str
)

classmethod

Loads a configuration from a given path.

Supports loading a from a single file, or from a directory.

nemoguardrails.rails.llm.config.RailsConfig.parse_object(
    obj
)

classmethod

Parses a configuration object from a given dictionary.

nemoguardrails.rails.llm.config.RailsConfig.validate_models_api_key_env_var(
    models
)

Model API Key Env var must be set to make LLM calls

class nemoguardrails.rails.llm.config.RailsConfigData()

Bases: BaseModel

Configuration data for specific rails that are supported out-of-the-box.

ai_defense

Optional[AIDefenseRailConfig]

autoalign

AutoAlignRailConfig

clavata

Optional[ClavataRailConfig]

content_safety

Optional[ContentSafetyConfig]

crowdstrike_aidr

Optional[CrowdStrikeAIDRRailConfig]

fact_checking

FactCheckingRailConfig

fiddler

Optional[FiddlerGuardrails]

gliner

Optional[GLiNERDetection]

guardrails_ai

Optional[GuardrailsAIRailConfig]

hf_classifier

Optional[Dict[str, HFClassifierConfig]]

injection_detection

Optional[InjectionDetection]

jailbreak_detection

Optional[JailbreakDetectionConfig]

pangea

Optional[PangeaRailConfig]

patronus

Optional[PatronusRailConfig]

privateai

Optional[PrivateAIDetection]

regex_detection

Optional[RegexDetection]

sensitive_data_detection

Optional[SensitiveDataDetection]

trend_micro

Optional[TrendMicroRailConfig]

class nemoguardrails.rails.llm.config.ReasoningConfig()

Bases: BaseModel

Configuration for reasoning mode in content safety models.

enabled

bool

class nemoguardrails.rails.llm.config.RegexDetection()

Bases: BaseModel

Configuration for regex pattern detection.

input

RegexDetectionOptions

output

RegexDetectionOptions

retrieval

RegexDetectionOptions

class nemoguardrails.rails.llm.config.RegexDetectionOptions()

Bases: BaseModel

Configuration options for regex pattern detection on a specific source.

_compiled_patterns

List[Pattern[str]] = PrivateAttr(default_factory=list)

case_insensitive

bool

compiled_patterns

List[Pattern[str]]

Return the pre-compiled regex patterns.

patterns

List[str]

nemoguardrails.rails.llm.config.RegexDetectionOptions.compile_patterns() -> nemoguardrails.rails.llm.config.RegexDetectionOptionsnemoguardrails.rails.llm.config.RegexDetectionOptions.compile_patterns() -> nemoguardrails.rails.llm.config.RegexDetectionOptions

Pre-compile regex patterns at config load time.

class nemoguardrails.rails.llm.config.RemoteHFClassifierConfig()

Bases: _HFClassifierBase

Configuration for a remote HuggingFace classifier (vLLM, KServe, FMS).

_KNOWN_PARAMS

frozenset

api_key_env_var

Optional[str]

base_url

str

engine

Literal['vllm', 'kserve', 'fms']

parameters

Dict[str, Any]

nemoguardrails.rails.llm.config.RemoteHFClassifierConfig._validate_remote() -> nemoguardrails.rails.llm.config.RemoteHFClassifierConfignemoguardrails.rails.llm.config.RemoteHFClassifierConfig._validate_remote() -> nemoguardrails.rails.llm.config.RemoteHFClassifierConfig

class nemoguardrails.rails.llm.config.RetrievalRails()

Bases: BaseModel

Configuration of retrieval rails.

flows

List[str]

class nemoguardrails.rails.llm.config.SensitiveDataDetection()

Bases: BaseModel

Configuration of what sensitive data should be detected.

input

SensitiveDataDetectionOptions

output

SensitiveDataDetectionOptions

recognizers

List[dict]

retrieval

SensitiveDataDetectionOptions

class nemoguardrails.rails.llm.config.SensitiveDataDetectionOptions()

Bases: BaseModel

entities

List[str]

mask_token

str

score_threshold

float

class nemoguardrails.rails.llm.config.SingleCallConfig()

Bases: BaseModel

Configuration for the single LLM call option for topical rails.

enabled

bool = False

fallback_to_multiple_calls

bool

class nemoguardrails.rails.llm.config.SpanFormat

Bases: enum.Enum

legacy

= 'legacy'

opentelemetry

= 'opentelemetry'

class nemoguardrails.rails.llm.config.TaskPrompt()

Bases: BaseModel

Configuration for prompts that will be used for a specific task.

content

Optional[str]

max_length

Optional[int]

max_tokens

Optional[int]

messages

Optional[List[Union[MessageTemplate, str]]]

mode

Optional[str]

models

Optional[List[str]]

output_parser

Optional[str]

stop

Optional[List[str]]

task

str

nemoguardrails.rails.llm.config.TaskPrompt.check_fields(
    values
)

class nemoguardrails.rails.llm.config.ToolInputRails()

Bases: BaseModel

Configuration of tool input rails.

Tool input rails are applied to tool results before they are processed. They can validate, filter, or transform tool outputs for security and safety.

flows

List[str]

parallel

Optional[bool]

class nemoguardrails.rails.llm.config.ToolOutputRails()

Bases: BaseModel

Configuration of tool output rails.

Tool output rails are applied to tool calls before they are executed. They can validate tool names, parameters, and context to ensure safe tool usage.

flows

List[str]

parallel

Optional[bool]

class nemoguardrails.rails.llm.config.TracingConfig()

Bases: BaseModel

adapters

List[LogAdapterConfig]

enable_content_capture

bool

enabled

bool = False

span_format

str

class nemoguardrails.rails.llm.config.TrendMicroRailConfig()

Bases: BaseModel

Configuration data for the Trend Micro AI Guard API

api_key_env_var

Optional[str]

application_name

str

detailed_response

bool

v1_url

str

nemoguardrails.rails.llm.config.TrendMicroRailConfig.get_api_key() -> typing.Optional[str]

Helper to return an API key (if it exists) from a Trend Micro configuration. The api_key_env_var field, a string stored in this environment variable.

If the environment variable is not found None is returned.

class nemoguardrails.rails.llm.config.UserMessagesConfig()

Bases: BaseModel

Configuration for how the user messages are interpreted.

embeddings_only

bool

embeddings_only_fallback_intent

Optional[str]

embeddings_only_similarity_threshold

Optional[float]

class nemoguardrails.rails.llm.config._HFClassifierBase()

Bases: BaseModel

Shared fields for all HuggingFace classifier engines.

blocked_labels

List[str]

model

str

threshold

float

nemoguardrails.rails.llm.config._HFClassifierBase._validate_common() -> nemoguardrails.rails.llm.config._HFClassifierBasenemoguardrails.rails.llm.config._HFClassifierBase._validate_common() -> nemoguardrails.rails.llm.config._HFClassifierBase

nemoguardrails.rails.llm.config._generate_rails_flows(
    flows
)

Generates flow definitions from the list of flows. Args: flows (dict): The dictionary of flows. Returns: str: The flow definitions.

nemoguardrails.rails.llm.config._get_flow_model(
    flow_text
) -> typing.Optional[str]

Helper to return a model name from a flow definition

nemoguardrails.rails.llm.config._get_flow_name(
    flow_text
) -> typing.Optional[str]

Helper to return a model name from a flow definition

nemoguardrails.rails.llm.config._get_rails_flows(
    raw_config
)

Extracts the list of flows from the raw_config dictionary.

Parameters:

raw_config

dict

The raw configuration dictionary.

Returns:

The list of flows.

nemoguardrails.rails.llm.config._has_input_output_config_rails(
    raw_config
)

Checks if the raw configuration has input/output rails configured.

nemoguardrails.rails.llm.config._join_config(
    dest_config: dict,
    additional_config: dict
)

Helper to join two configuration.

nemoguardrails.rails.llm.config._join_dict(
    dict1,
    dict2
)

Joins two dictionaries recursively.

If values are dictionaries, it applies _join_dict recursively.
If values are lists, it concatenates them, ensuring unique elements.
For other types, values from dict2 overwrite dict1.

nemoguardrails.rails.llm.config._join_rails_configs(
    base_rails_config: nemoguardrails.rails.llm.config.RailsConfig,
    updated_rails_config: nemoguardrails.rails.llm.config.RailsConfig
)

Helper to join two rails configuration.

nemoguardrails.rails.llm.config._load_imported_paths(
    raw_config: dict,
    colang_files: typing.List[typing.Tuple[str, str]]
)

Load recursively all the imported path in the specified raw_config.

Parameters:

raw_config

dict

The starting raw configuration (i.e., a dict)

colang_files

List[Tuple[str, str]]

The current set of colang files which will be extended as new configurations are loaded.

nemoguardrails.rails.llm.config._load_path(
    config_path: str
) -> typing.Tuple[dict, typing.List[typing.Tuple[str, str]]]

Load a configuration object from the specified path.

Parameters:

config_path

str

The path from which to load.

Returns: Tuple[dict, List[Tuple[str, str]]]

(raw_config, colang_files) The raw config object and the list of colang files.

nemoguardrails.rails.llm.config._parse_colang_files_recursively(
    raw_config: dict,
    colang_files: typing.List[typing.Tuple[str, str]],
    parsed_colang_files: typing.List[dict]
)

Helper function to parse all the Colang files.

If there are imports, they will be imported recursively

nemoguardrails.rails.llm.config._unique_list_concat(
    list1,
    list2
)

Concatenates two lists ensuring all elements are unique. Handles unhashable types like dictionaries.

nemoguardrails.rails.llm.config._validate_rail_prompts(
    rails: list[str],
    prompts: list[typing.Any],
    validation_rail: str
) -> None

nemoguardrails.rails.llm.config.merge_two_dicts(
    dict_1: dict,
    dict_2: dict,
    ignore_keys: typing.Set[str]
) -> None

Merges the fields of two dictionaries recursively.

nemoguardrails.rails.llm.config.HFClassifierConfig = Annotated[Union[LocalHFClassifierConfig, RemoteHFClassifierConfig], Discriminato...

nemoguardrails.rails.llm.config.JAILBREAK_FLOW_HEURISTICS = 'jailbreak detection heuristics'

nemoguardrails.rails.llm.config.JAILBREAK_FLOW_MODEL = 'jailbreak detection model'

nemoguardrails.rails.llm.config.MODEL_PREFIX = '$model='

nemoguardrails.rails.llm.config._default_config = yaml.safe_load(_fc)

nemoguardrails.rails.llm.config._default_config_v2 = yaml.safe_load(_fc)

nemoguardrails.rails.llm.config.colang_path_dirs = [(_path.strip()) for _path in (os.environ.get('COLANGPATH', '').split(os.pathsep...

nemoguardrails.rails.llm.config.guardrails_stdlib_path = os.path.normpath(os.path.join(os.path.dirname(__file__), '..', '..', '..'))

nemoguardrails.rails.llm.config.log = logging.getLogger(__name__)

nemoguardrails.rails.llm.config.standard_library_path = os.path.normpath(os.path.join(os.path.dirname(__file__), '..', '..', 'colang', '...