Namespace Oci.GenerativeaiService.Models
Classes
ChangeDedicatedAiClusterCompartmentDetails
The details to move a dedicated AI cluster to another compartment.
ChangeEndpointCompartmentDetails
The details to move an endpoint to another compartment.
ChangeModelCompartmentDetails
The details to move a custom model to another compartment.
ChatModelMetrics
The chat model metrics of the fine-tuning process.
ContentModerationConfig
The configuration details, whether to add the content moderation feature to the model. Content moderation removes toxic and biased content from responses. It's recommended to use content moderation.
CreateDedicatedAiClusterDetails
The data to create a dedicated AI cluster.
CreateEndpointDetails
The data to create an endpoint.
CreateModelDetails
The data to create a custom model.
Dataset
DatasetModelConverter
DedicatedAiCluster
Dedicated AI clusters are compute resources that you can use for fine-tuning custom models or for hosting endpoints for custom models. The clusters are dedicated to your models and not shared with users in other tenancies.
To use any of the API operations, you must be authorized in an IAM policy. If you're not authorized, talk to an administrator who gives OCI resource access to users. See
Getting Started with Policies and Getting Access to Generative AI Resouces.
DedicatedAiClusterCapacity
The total capacity for a dedicated AI cluster.
DedicatedAiClusterCapacityModelConverter
DedicatedAiClusterCollection
Results of a dedicate AI cluster search. Contains DedicatedAiClusterSummary items and other information such as metadata.
DedicatedAiClusterHostingCapacity
The capacity of a hosting type dedicated AI cluster.
DedicatedAiClusterSummary
Summary information about a dedicated AI cluster.
Endpoint
To host a custom model for inference, create an endpoint for that model on a dedicated AI cluster of type HOSTING.
To use any of the API operations, you must be authorized in an IAM policy. If you're not authorized, talk to an administrator who gives OCI resource access to users. See
Getting Started with Policies and Getting Access to Generative AI Resouces.
EndpointCollection
Results of an endpoint search. Contains EndpointSummary items and other information such as metadata.
EndpointSummary
Summary information for an endpoint resource.
FineTuneDetails
Details about fine-tuning a custom model.
LoraTrainingConfig
The Lora training method hyperparameters.
Model
You can create a custom model by using your dataset to fine-tune an out-of-the-box text generation base model. Have your dataset ready before you create a custom model. See Training Data Requirements.
To use any of the API operations, you must be authorized in an IAM policy. If you're not authorized, talk to an administrator who gives OCI resource access to users. See
Getting Started with Policies and Getting Access to Generative AI Resouces.
ModelCollection
Results of a model search. Contains ModelSummary items and other information such as metadata.
ModelMetrics
Model metrics during the creation of a new model.
ModelMetricsModelConverter
ModelSummary
Summary of the model.
ObjectStorageDataset
The dataset is stored in an OCI Object Storage bucket.
TFewTrainingConfig
The TFEW training method hyperparameters.
TextGenerationModelMetrics
The text generation model metrics of the fine-tuning process.
TrainingConfig
The fine-tuning method and hyperparameters used for fine-tuning a custom model.
TrainingConfigModelConverter
UpdateDedicatedAiClusterDetails
The data to update a dedicated AI cluster.
UpdateEndpointDetails
The data to update an endpoint.
UpdateModelDetails
The data to update a custom model.
VanillaTrainingConfig
The Vanilla training method hyperparameters.
WorkRequest
An asynchronous work request. When you start a long-running operation, the service creates a work request. Work requests help you monitor long-running operations.
A work request is an activity log that lets you track each step in the operation's progress. Each work request has an OCID that lets you interact with it programmatically and use it for automation.
WorkRequestError
An error encountered while performing an operation that is tracked by this work request.
WorkRequestErrorCollection
A list of work request errors. Can contain errors and other information such as metadata.
WorkRequestLogEntry
The log message from performing an operation that is tracked by this work request.
WorkRequestLogEntryCollection
A list of work request logs. Can contain logs and other information such as metadata.
WorkRequestResource
The resource created or operated on by a work request.
WorkRequestSummary
Summary information about an asynchronous work request.
WorkRequestSummaryCollection
A list of work requests. Can contain work requests and other information such as metadata.
Enums
ActionType
Possible types of actions.
Dataset.DatasetTypeEnum
DedicatedAiCluster.LifecycleStateEnum
DedicatedAiCluster.TypeEnum
DedicatedAiCluster.UnitShapeEnum
DedicatedAiClusterCapacity.CapacityTypeEnum
Endpoint.LifecycleStateEnum
Model.LifecycleStateEnum
Model.TypeEnum
ModelCapability
Describes what this model can be used for.
ModelMetrics.ModelMetricsTypeEnum
OperationStatus
The status of the work request.
OperationType
The resources affected by this work request.
SortOrder
The sort order to use, either ascending (ASC
) or descending (DESC
). The displayName
sort order is case sensitive.
TrainingConfig.TrainingConfigTypeEnum
WorkRequestResourceMetadataKey
Possible metadata keys for work request resource metadata.