nat.llm.oci_llm

Classes

OCIModelConfig

OCI Generative AI LLM provider.

Functions

oci_llm(...)

Yield provider metadata for an OCI Generative AI model.

Module Contents

class OCIModelConfig(/, **data: Any)

Bases: nat.data_models.llm.LLMBaseConfig, nat.data_models.retry_mixin.RetryMixin, nat.data_models.optimizable.OptimizableMixin, nat.data_models.thinking_mixin.ThinkingMixin

OCI Generative AI LLM provider.

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].

region: str = None

endpoint: str | None = None

compartment_id: str | None = None

_derive_endpoint_from_region() → OCIModelConfig

auth_type: str = None

auth_profile: str = None

auth_file_location: str = None

model_name: str = None

provider: str | None = None

context_size: int | None = None

seed: int | None = None

max_retries: int = None

max_tokens: int | None = None

temperature: float | None = None

top_p: float | None = None

request_timeout: float | None = None

async oci_llm(

config: OCIModelConfig,

_builder: nat.builder.builder.Builder,

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

Yield provider metadata for an OCI Generative AI model.

Args:

config: OCI model configuration. _builder: Builder instance.

Yields:

LLMProviderInfo describing the configured OCI model.