TabularEndpoint¶

class autogluon.cloud.TabularEndpoint(endpoint_name: str, session: Session | None = None)[source]¶

High-level handle for an AutoGluon-Cloud tabular endpoint.

Returned by autogluon.cloud.TabularCloudPredictor.deploy() and autogluon.cloud.TabularFoundationModel.deploy(). Construct it directly to attach to an existing endpoint by name.

Trained predictor endpoints (TabularCloudPredictor.deploy()) serve the fitted predictor: pass only data.
Foundation model endpoints (TabularFoundationModel.deploy()) fit a request-scoped predictor on the labeled examples sent with each request: pass train_data and label along with data.

Parameters:

endpoint_name (str) – Name of an existing SageMaker endpoint deployed through AutoGluon-Cloud, either with deploy() of a cloud predictor (e.g. autogluon.cloud.TabularCloudPredictor.deploy()) or of a foundation model (e.g. autogluon.cloud.TabularFoundationModel.deploy()).
session (boto3.Session | None, default = None) – boto3.Session used to invoke and delete the endpoint. If None, the default ambient session is used.

Methods

`delete_endpoint`	Delete the endpoint along with the endpoint config and model created with it.
`predict`	Predict `data` with the deployed endpoint.
`predict_proba`	Predict class probabilities for `data` with the deployed endpoint.

Attributes

endpoint_name

Name of the SageMaker endpoint.