BaseOCIModelDeployment#

class langchain_community.llms.oci_data_science_model_deployment_endpoint.BaseOCIModelDeployment[source]#

Bases: Serializable

Base class for LLM deployed on OCI Data Science Model Deployment.

param auth: dict [Optional]#

ADS auth dictionary for OCI authentication: https://accelerated-data-science.readthedocs.io/en/latest/user_guide/cli/authentication.html. This can be generated by calling ads.common.auth.api_keys() or ads.common.auth.resource_principal(). If this is not provided then the ads.common.default_signer() will be used.

param endpoint: str = ''#

The uri of the endpoint from the deployed Model Deployment model.

param max_retries: int = 3#

Maximum number of retries to make when generating.

param streaming: bool = False#

Whether to stream the results or not.

async acompletion_with_retry(run_manager: AsyncCallbackManagerForLLMRun | None = None, **kwargs: Any) → Any[source]#

Use tenacity to retry the async completion call.

Parameters:
Return type:

Any

completion_with_retry(run_manager: CallbackManagerForLLMRun | None = None, **kwargs: Any) → Any[source]#

Use tenacity to retry the completion call.

Parameters:
Return type:

Any