Namespace Oci.GenerativeaiService.Models

Classes

ApiKeys are resources used to access GenAI models. You must be authorized through an IAM policy to use any API operations. If you're not authorized, contact an administrator who manages OCI resource access. See Getting Started with Policies and Getting Access to Generative AI Resources.

ApiKeyCollection

Results of a ApiKey search.

ApiKeyItem

The ApiKey item.

ApiKeySummary

Summary of the API key.

Artifact

Container/artifact configuration for the deployment.

ArtifactModelConverter

ChangeApiKeyCompartmentDetails

The details to move an APIKey to another compartment.

ChangeDedicatedAiClusterCompartmentDetails

The details to move a dedicated AI cluster to another compartment.

ChangeEndpointCompartmentDetails

The details to move an endpoint to another compartment.

ChangeGenerativeAiPrivateEndpointCompartmentDetails

The details required to change a private endpoint compartment.

ChangeGenerativeAiProjectCompartmentDetails

The details to move a GenerativeAiProject to another compartment.

ChangeHostedApplicationCompartmentDetails

The details to move a hosted application to another compartment.

ChangeHostedApplicationStorageCompartmentDetails

The details to move a hosted application storage to another compartment.

ChangeImportedModelCompartmentDetails

The details to move an imported model to another compartment.

ChangeModelCompartmentDetails

The details to move a custom model to another compartment.

ChangeSemanticStoreCompartmentDetails

The details to move a SemanticStore to another compartment.

ChatModelMetrics

The chat model metrics of the fine-tuning process.

CondenserConfig

Configuration for condensing conversation content.

ConnectorConfiguration

Datasource configuration for the connector.

ConnectorConfigurationModelConverter

ContentModerationConfig

The configuration details, whether to add the content moderation feature to the model. Content moderation removes toxic and biased content from responses.

ConversationConfig

Holds configuration related to conversation retention

CreateApiKeyDetails

The data to create an API key.

CreateArtifactDetails

Artifact configuration input for the deployment.

CreateArtifactDetailsModelConverter

CreateDataSourceDatabaseToolsConnectionDetails

Defines the OCI Database Tools Connection data source that the semantic model connects to.

CreateDataSourceDetails

Defines the data source that the semantic model connects to.

CreateDataSourceDetailsModelConverter

CreateDedicatedAiClusterDetails

The data to create a dedicated AI cluster.

CreateEndpointDetails

The data to create an endpoint.

CreateGenerativeAiPrivateEndpointDetails

The details required to create a Generative AI private endpoint.

CreateGenerativeAiProjectDetails

The data to create a GenerativeAiProject.

CreateHostedApplicationDetails

The details required to create a hosted application.

CreateHostedApplicationStorageDetails

The data to create a hosted application storage.

CreateHostedDeploymentDetails

The data to create a hosted deployment.

CreateImportedModelDetails

The data to import a model.

CreateModelDetails

The data to create a custom model.

CreateSchemasDatabaseToolsConnectionDetails

Array of database schemas or database objects included in the enrichment pipeline for data sources connected via an OCI Database Tools connection.

CreateSchemasDetails

Array of database schemas or other database objects to include in enrichment pipeline.

CreateSchemasDetailsModelConverter

CreateSemanticStoreDetails

The data to create a SemanticStore.

CreateSingleDockerArtifactDetails

CreateVectorStoreConnectorDetails

The data to create a VectorStoreConnector.

CreateVectorStoreConnectorFileSyncDetails

The data to create a VectorStoreConnectorFileSync.

DataSourceDatabaseToolsConnectionDetails

Defines the OCI Database Tools Connection data source that the semantic model connects to.

DataSourceDetails

Defines the data source that the semantic model connects to.

DataSourceDetailsModelConverter

DatabaseToolsConnection

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 Resources.

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.

EmbeddingConfig

Configuration for generating embeddings from extracted information.

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 Resources.

EndpointCollection

Results of an endpoint search. Contains EndpointSummary items and other information such as metadata.

EndpointSummary

Summary information for an endpoint resource.

EnvironmentVariable

The environment variables for the Hosted Application

ExtractionConfig

Configuration for information extraction from conversation content.

FileSyncIngestionLogs

A Log object that gives the ingestion status of a File from a datasource read by a VectorStoreConnector

FileSyncIngestionLogsCollection

Results of a VectorStoreConnector Ingestion Log search.

FileSyncStatistics

Synchronization Statistics for a VectorStore File Sync operation or for a VectorStore Connector

FineTuneDetails

Details about fine-tuning a custom model.

GenAiModelLlmSelection

LLM selection with specific Gen AI model.

GenerativeAiPrivateEndpoint

Generative AI private endpoint.

GenerativeAiPrivateEndpointCollection

Collection of GenerativeAiPrivateEndpointSummary

GenerativeAiPrivateEndpointSummary

List of Generative AI private endpoints.

GenerativeAiProject

A GenerativeAiProject is a logical container that stores conversation, file and containers.
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 Resources.

GenerativeAiProjectCollection

Results of a GenerativeAiProject search. Contains GenerativeAiProjectSummary items and other information such as metadata.

GenerativeAiProjectSummary

Summary information for a GenerativeAiProject.

HostedApplication

Hosted Application, defines shared configurations that apply across multiple deployments of the Agent or MCP application.
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 Resources.

HostedApplicationCollection

Results of a dedicate hosted application search. Contains HostedApplicationSummary items and other information such as metadata.

HostedApplicationStorage

defines a physical storage (database or cache) managed by service. Each application can choose one or two storages for certain purpose such as agent memory.
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 Resources.

HostedApplicationStorageCollection

Results of a dedicate hosted application search. Contains HostedApplicationStorageSummary items and other information such as metadata.

HostedApplicationStorageSummary

Summary information about a hosted application storage.

HostedApplicationSummary

Summary information about a hosted application.

HostedDeployment

Hosted deployment is designed to support the full spectrum of agent use cases from lightweight, employee-facing assistants and internal workflow automation, to enterprise-grade, large-scale customer-facing workloads.
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 Resources.

HostedDeploymentCollection

Results of a dedicate hosted deployment search. Contains Hosted Deployment Summary items and other information such as metadata.

HostedDeploymentSummary

Summary information about a hosted deployment.

HuggingFaceModel

Configuration for importing a model from Hugging Face. Requires the model ID and a reference to the token stored in a vault for authenticated access.

IdcsAuthConfig

Oracle Identity Cloud Service (IDCS) configuration used when inboundAuthConfigType is set to IDCS_AUTH_CONFIG. This object must be specified when inboundAuthConfigType is IDCS_AUTH_CONFIG.

ImportedModel

Represents a model imported into the system based on an external data source, such as Hugging Face or Object Storage.
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 Resources.

ImportedModelCollection

Represents the result of a list operation for imported models.

ImportedModelSummary

Summary of the importedModel.

InboundAuthConfig

The client-side inbound authentication configuration for the Hosted Application. Defines the network access rules. When unspecified, the service applies the default inbound authentication configuration type.

InboundNetworkingConfig

Inbound Networking configuration.

KeyDetails

The data to create/renew an API key item.

LlmSelection

LLM selection configuration.

LlmSelectionModelConverter

LongTermMemoryConfig

Configuration settings for long-term memory behavior.

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 Resources.

ModelCollection

Results of a model search. Contains ModelSummary items and other information such as metadata.

ModelConfig

Base model configuration shared across GenAI Project memory.

ModelConfigModelConverter

ModelDataSource

Defines the source location and method used to import the model. Supports importing from Hugging Face, an Object Storage location, or by referencing an already imported model.

ModelDataSourceModelConverter

ModelMetrics

Model metrics during the creation of a new model.

ModelMetricsModelConverter

ModelSummary

Summary of the model.

NetworkingConfig

Networking configuration.

ObjectStorageConfig

OCI Object storage configuration details.

ObjectStorageDataset

The dataset is stored in an OCI Object Storage bucket.

ObjectStorageObject

Details about the object storage location.

OciObjectStorageConfiguration

The OCI Object Storage namespace and bucket details of the datasource

OutboundNetworkingConfig

Outbound Networking configuration.

PiiDetectionConfig

The configuration details for personally identifiable information (PII) detection, in prompts and responses.

PromptInjectionConfig

The configuration details for prompt injection (PI) detection. This is for input only.

RefreshScheduleDetails

Specifies a refresh schedule. Null represents no automated synchronization schedule.

RefreshScheduleDetailsModelConverter

RefreshScheduleIntervalDetails

Defines the refresh schedule by specifying the interval between each refresh.

RefreshScheduleNoneDetails

Allows user to opt out of automated synchronization schedule.

RefreshScheduleOnCreateDetails

Only trigger the enrichment at the creation time.

RenewApiKeyDetails

The data to renew an API key item.

ScalingConfig

The auto scaling configuration for the Hosted Application. Defines the minimum and maximum number of replicas. When unspecified, the service applies service-defined default scaling values.

ScheduleConfig

The Schedule configuration of a VectorStoreConnector to trigger a File Sync Operation.

ScheduleConfigModelConverter

ScheduleCronConfig

The scheduled UNIX cron definition.

ScheduleIntervalConfig

The interval schedule config.

SchemaItem

Represents a database schema identified by name. This is the simplest schema definition and includes only schema name now. Additional configuration options may be supported in extended forms later.

SchemasDatabaseToolsConnectionDetails

Array of database schemas or database objects included in the enrichment pipeline for data sources connected via an OCI Database Tools connection.

SchemasDetails

Array of database schemas or other database objects to include in enrichment pipeline.

SchemasDetailsModelConverter

SemanticStore

A Semantic Store is a container resource of semantic records, with controllable enrichment refresh and synchronization policy.
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 Resources.

SemanticStoreCollection

Results of a SemanticStore list. Contains SemanticStoreSummary items and other information such as metadata.

SemanticStoreSummary

Summary information for a SemanticStore.

SetApiKeyStateDetails

The data to set the state of an API key item.

ShortTermMemoryOptimizationConfig

Configuration settings for short-term memory optimization.

SingleDockerArtifact

Container/artifact configuration for the deployment.

StandardLongTermMemoryStrategy

Standard strategy settings for long-term memory.

StorageConfig

The type of service-managed storage.

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

UpdateApiKeyDetails

The data to update an API key.

UpdateDedicatedAiClusterDetails

The data to update a dedicated AI cluster.

UpdateEndpointDetails

The data to update an endpoint.

UpdateGenerativeAiPrivateEndpointDetails

The details required to update a Generative AI private endpoint.

UpdateGenerativeAiProjectDetails

The data to update a GenerativeAiProject.

UpdateHostedApplicationDetails

The data to update a hosted application.

UpdateHostedDeploymentDetails

The data to update a hosted deployment.

UpdateImportedModelDetails

The data to update an imported model.

UpdateModelDetails

The data to update a custom model.

UpdateSemanticStoreDetails

The data to update a SemanticStore.

UpdateVectorStoreConnectorDetails

The data to update a VectorStoreConnector.

VanillaTrainingConfig

The Vanilla training method hyperparameters.

VectorStoreConnector

A VectorStore Connector offers a lightweight and configurable mechanism to continuously synchronize data from external systems into the VectorStore at scale. It captures the configuration of the datasource for data ingestion.

VectorStoreConnectorCollection

Results of a VectorStoreConnector search. Contains VectorStoreConnectorSummary items.

VectorStoreConnectorFileSync

The VectorStoreConnectorFileSync is an operation that carries out the data sync operation between the datasource and the VectorStore. The FileSync can be triggered either manually or at a scheduled interval by the VectorStoreConnector.

VectorStoreConnectorFileSyncCollection

Results of a VectorStoreConnectorFileSync search.

VectorStoreConnectorFileSyncSummary

Summary information for a VectorStoreConnectorFileSync

VectorStoreConnectorIngestionLogs

A Log object that gives the ingestion status of a File from a datasource read by a VectorStoreConnector

VectorStoreConnectorIngestionLogsCollection

Results of a VectorStoreConnector Ingestion Log search.

VectorStoreConnectorStats

File synchronization statistics for a VectorStoreConnector.

VectorStoreConnectorSummary

Summary information for a VectorStoreConnector

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.