LangChain components

Install with pip install "laya[langchain]". The LangChain & LangGraph guide shows these components in chains and graphs.

Names, types, defaults and code stay in English; the rest is translated (entries not translated yet are shown in the original English).

LayaRouter

LayaRouter(
    criteria: Dict[str, str],
    instructions: str = "Which route should handle this request?",
    confidence_threshold: float = 0.0,
    fallback: Optional[str] = None,
    state_key: Optional[Union[str, Callable[[Any], Any]]] = None,
    agent: Optional[Any] = None,
    base_url: Optional[str] = None,
    api_key: Optional[str] = None,
    model: Optional[str] = None,
    max_len: Optional[int] = None,
    head_max_len: Optional[int] = None,
    hooks: Optional[Any] = None,
    on_predict_start: Optional[Any] = None,
    on_predict_end: Optional[Any] = None,
    hooks_raise: Optional[bool] = None,
    hooks_timeout: Optional[float] = None,
    kwargs: Any,
)

Bases: _BatchedRunnable, RunnableSerializable

Zero-latency LangGraph conditional edge and LangChain LCEL routing runnable.

Evaluates user input against typed criteria in ~33 ms without token generation. Supports confidence threshold gating and fallback routing, and answers a list of inputs in one shared forward pass through batch.

Parameters

criteriaDict[str, str]
instructionsstr= "Which route should handle this request?"
confidence_thresholdfloat= 0.0
fallbackOptional[str]= None
state_keyOptional[Union[str, Callable[[Any], Any]]]= None
agentOptional[Any]= None
base_urlOptional[str]= None
api_keyOptional[str]= None
modelOptional[str]= None
max_lenOptional[int]= None
head_max_lenOptional[int]= None
hooksOptional[Any]= None
on_predict_startOptional[Any]= None
on_predict_endOptional[Any]= None
hooks_raiseOptional[bool]= None
hooks_timeoutOptional[float]= None
kwargsAny

invoke

invoke(input: Any, config: Optional[RunnableConfig] = None) -> str

Route input to a destination branch label.

Parameters

inputAny
configOptional[RunnableConfig]= None

LayaGuardrail

LayaGuardrail(
    questions: Optional[Dict[str, Any]] = None,
    action: str = "raise",
    rejection_message: str = "I cannot fulfill this request because it violates safety guidelines.",
    threshold: float = 0.5,
    state_key: Optional[Union[str, Callable[[Any], Any]]] = None,
    agent: Optional[Any] = None,
    base_url: Optional[str] = None,
    api_key: Optional[str] = None,
    model: Optional[str] = None,
    max_len: Optional[int] = None,
    head_max_len: Optional[int] = None,
    hooks: Optional[Any] = None,
    on_predict_start: Optional[Any] = None,
    on_predict_end: Optional[Any] = None,
    hooks_raise: Optional[bool] = None,
    hooks_timeout: Optional[float] = None,
    kwargs: Any,
)

Bases: _BatchedRunnable, RunnableSerializable

Sub-40ms inline guardrail for LangChain chains and LangGraph nodes.

Screens for prompt injections, jailbreaks, sensitive data, or custom harm criteria before passing inputs downstream. A list of inputs is screened in one shared forward pass through batch.

threshold is a violation probability in [0, 1] for every noul and score question: for a noul question it applies to noul, and for a score question to the probability that the level is at or above the middle of the scale (serious or severe for the default harm_severity; the middle level counts on an odd scale). Levels of a score question must run from harmless to worst.

Parameters

questionsOptional[Dict[str, Any]]= None
actionstr= "raise"
rejection_messagestr= "I cannot fulfill this request because it violates safety guidelines."
thresholdfloat= 0.5
state_keyOptional[Union[str, Callable[[Any], Any]]]= None
agentOptional[Any]= None
base_urlOptional[str]= None
api_keyOptional[str]= None
modelOptional[str]= None
max_lenOptional[int]= None
head_max_lenOptional[int]= None
hooksOptional[Any]= None
on_predict_startOptional[Any]= None
on_predict_endOptional[Any]= None
hooks_raiseOptional[bool]= None
hooks_timeoutOptional[float]= None
kwargsAny

invoke

invoke(input: Any, config: Optional[RunnableConfig] = None) -> Any

Screen input against guardrail questions.

Parameters

inputAny
configOptional[RunnableConfig]= None

LayaGuardrailError

LayaGuardrailError(
    message: str,
    violations: Dict[str, Any],
    raw_decision: Dict[str, Any],
)

Bases: ValueError

Raised when an input violates a Laya guardrail policy.

Parameters

messagestr
violationsDict[str, Any]
raw_decisionDict[str, Any]

LayaTriage

LayaTriage(
    state_key: Optional[Union[str, Callable[[Any], Any]]] = None,
    agent: Optional[Any] = None,
    base_url: Optional[str] = None,
    api_key: Optional[str] = None,
    model: Optional[str] = None,
    max_len: Optional[int] = None,
    head_max_len: Optional[int] = None,
    hooks: Optional[Any] = None,
    on_predict_start: Optional[Any] = None,
    on_predict_end: Optional[Any] = None,
    hooks_raise: Optional[bool] = None,
    hooks_timeout: Optional[float] = None,
    kwargs: Any,
)

Bases: _BatchedRunnable, RunnableSerializable

Customer support ticket and incoming message triage node for LangGraph.

Analyzes intent, urgency, customer frustration, and churn risk in one single forward pass and enriches the graph state dictionary. A backlog is triaged in one shared forward pass through batch.

Parameters

state_keyOptional[Union[str, Callable[[Any], Any]]]= None
agentOptional[Any]= None
base_urlOptional[str]= None
api_keyOptional[str]= None
modelOptional[str]= None
max_lenOptional[int]= None
head_max_lenOptional[int]= None
hooksOptional[Any]= None
on_predict_startOptional[Any]= None
on_predict_endOptional[Any]= None
hooks_raiseOptional[bool]= None
hooks_timeoutOptional[float]= None
kwargsAny

invoke

invoke(state: Any, config: Optional[RunnableConfig] = None) -> Dict[str, Any]

Triage the state and return enriched fields.

Parameters

stateAny
configOptional[RunnableConfig]= None

LayaEvaluator

LayaEvaluator(
    questions: Dict[str, Any],
    state_key: Optional[Union[str, Callable[[Any], Any]]] = None,
    agent: Optional[Any] = None,
    base_url: Optional[str] = None,
    api_key: Optional[str] = None,
    model: Optional[str] = None,
    max_len: Optional[int] = None,
    head_max_len: Optional[int] = None,
    hooks: Optional[Any] = None,
    on_predict_start: Optional[Any] = None,
    on_predict_end: Optional[Any] = None,
    hooks_raise: Optional[bool] = None,
    hooks_timeout: Optional[float] = None,
    kwargs: Any,
)

Bases: _BatchedRunnable, RunnableSerializable

Rubric-based output grading and hallucination evaluation for LangChain.

Evaluates LLM responses against criteria without generating text. A list of responses is graded in one shared forward pass through batch.

Parameters

questionsDict[str, Any]
state_keyOptional[Union[str, Callable[[Any], Any]]]= None
agentOptional[Any]= None
base_urlOptional[str]= None
api_keyOptional[str]= None
modelOptional[str]= None
max_lenOptional[int]= None
head_max_lenOptional[int]= None
hooksOptional[Any]= None
on_predict_startOptional[Any]= None
on_predict_endOptional[Any]= None
hooks_raiseOptional[bool]= None
hooks_timeoutOptional[float]= None
kwargsAny

evaluate_strings

evaluate_strings(
    prediction: str,
    input: Optional[str] = None,
    kwargs: Any,
) -> Dict[str, Any]

LangChain standard string evaluation interface.

Parameters

predictionstr
inputOptional[str]= None
kwargsAny