nat.llm.litellm_llm

Classes

LiteLlmModelConfig

A LiteLlm provider to be used with an LLM client.

Functions

litellm_model(...)

Litellm model provider.

Module Contents

class LiteLlmModelConfig(/, **data: Any)

Bases: nat.data_models.llm.LLMBaseConfig, nat.data_models.retry_mixin.RetryMixin, nat.data_models.temperature_mixin.TemperatureMixin, nat.data_models.top_p_mixin.TopPMixin, nat.data_models.thinking_mixin.ThinkingMixin

A LiteLlm provider to be used with an LLM client.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

api_key: str | None = None

base_url: str | None = None

model_name: str = None

seed: int | None = None

async litellm_model(

config: LiteLlmModelConfig,

_builder: nat.builder.builder.Builder,

) → collections.abc.AsyncIterator[nat.builder.llm.LLMProviderInfo]

Litellm model provider.

Args:

config (LiteLlmModelConfig): The LiteLlm model configuration. _builder (Builder): The NAT builder instance.

Returns:

AsyncIterator[LLMProviderInfo]: An async iterator that yields an LLMProviderInfo object.