API documentation for vertexai package.
Packages
generative_models
API documentation for generative_models package.
language_models
API documentation for language_models package.
preview
API documentation for preview package.
vision_models
API documentation for vision_models package.
evaluation
API documentation for evaluation package.
agent_engines
API documentation for agent_engines package.
resources
API documentation for resources package.
Classes
Client
Gen AI Client for the Vertex SDK.
Use this client to interact with Vertex-specific Gemini features.
Packages Functions
init
init(
*,
project: typing.Optional[str] = None,
location: typing.Optional[str] = None,
experiment: typing.Optional[str] = None,
experiment_description: typing.Optional[str] = None,
experiment_tensorboard: typing.Optional[
typing.Union[
str,
google.cloud.aiplatform.tensorboard.tensorboard_resource.Tensorboard,
bool,
]
] = None,
staging_bucket: typing.Optional[str] = None,
credentials: typing.Optional[google.auth.credentials.Credentials] = None,
encryption_spec_key_name: typing.Optional[str] = None,
network: typing.Optional[str] = None,
service_account: typing.Optional[str] = None,
api_endpoint: typing.Optional[str] = None,
api_key: typing.Optional[str] = None,
api_transport: typing.Optional[str] = None,
request_metadata: typing.Optional[typing.Sequence[typing.Tuple[str, str]]] = None,
enforce_bucket_ownership: typing.Optional[bool] = None
)Updates common initialization parameters with provided options.
| Parameters | |
|---|---|
| Name | Description |
project |
strThe default project to use when making API calls. |
location |
strThe default location to use when making API calls. If not set defaults to us-central-1. |
experiment |
strOptional. The experiment name. |
experiment_description |
strOptional. The description of the experiment. |
experiment_tensorboard |
Union[str, tensorboard_resource.Tensorboard, bool]Optional. The Vertex AI TensorBoard instance, Tensorboard resource name, or Tensorboard resource ID to use as a backing Tensorboard for the provided experiment. Example tensorboard resource name format: "projects/123/locations/us-central1/tensorboards/456" If |
staging_bucket |
strThe default staging bucket to use to stage artifacts when making API calls. In the form gs://... |
credentials |
google.auth.credentials.CredentialsThe default custom credentials to use when making API calls. If not provided credentials will be ascertained from the environment. |
encryption_spec_key_name |
Optional[str]Optional. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: |
network |
strOptional. The full name of the Compute Engine network to which jobs and resources should be peered. E.g. "projects/12345/global/networks/myVPC". Private services access must already be configured for the network. If specified, all eligible jobs and resources created will be peered with this VPC. |
service_account |
strOptional. The service account used to launch jobs and deploy models. Jobs that use service_account: BatchPredictionJob, CustomJob, PipelineJob, HyperparameterTuningJob, CustomTrainingJob, CustomPythonPackageTrainingJob, CustomContainerTrainingJob, ModelEvaluationJob. |
api_endpoint |
strOptional. The desired API endpoint, e.g., us-central1-aiplatform.googleapis.com |
api_key |
strOptional. The API key to use for service calls. NOTE: Not all services support API keys. |
api_transport |
strOptional. The transport method which is either 'grpc' or 'rest'. NOTE: "rest" transport functionality is currently in a beta state (preview). |
enforce_bucket_ownership |
boolOptional. If True, raise an error when an existing GCS bucket that the SDK writes pipeline artifacts to is not owned by the project, or when its owner cannot be verified. If False or not set, only a warning is shown. Can also be enabled with the GOOGLE_CLOUD_AIPLATFORM_ENFORCE_BUCKET_OWNERSHIP=true environment variable. |