Adapter

Adapter for guardrail components.

NeMoLMAdapter(**kwargs)

Bases: BaseChatModel

LangChain ChatModel that delegates to a gllm_inference LM invoker.

Pass lm_invoker to supply the primary invoker; the model identifier is derived from it automatically via lm_invoker.model_id. The model field is optional and exists so NeMo's initializer can set it when the adapter is registered as a provider — you do not need to pass it directly.

Attributes:

Name	Type	Description
model	str | None	Model identifier string.
temperature	float | None	Sampling temperature.
max_tokens	int | None	Maximum tokens to generate.
top_p	float | None	Top-p sampling parameter.
lm_invoker	BaseLMInvoker | None	Primary LM invoker.
fallback_lms	list[BaseLMInvoker]	Ordered fallback invokers tried on BaseInvokerError or TimeoutError from the primary.

Initializes a new instance of the NeMoLMAdapter class.

Parameters:

Name	Type	Description	Default
**kwargs	Any	Additional configuration for the language model.	{}