REST Resource: publishers.models

Resource: PublisherModel

A Model Garden Publisher Model.

Fields
name string

Output only. The resource name of the PublisherModel.

versionId string

Output only. Immutable. The version id of the PublisherModel. A new version is committed when a new model version is uploaded under an existing model id. It is an auto-incrementing decimal number in string representation.

openSourceCategory enum (OpenSourceCategory)

Required. Indicates the open source category of the publisher model.

parent object (Parent)

Optional. The parent that this model was customized from. E.g., Vision API, Natural Language API, LaMDA, T5, etc. Foundation models don't have parents.

supportedActions object (CallToAction)

Optional. Supported call-to-action options.

frameworks[] string

Optional. Additional information about the model's Frameworks.

launchStage enum (LaunchStage)

Optional. Indicates the launch stage of the model.

versionState enum (VersionState)

Optional. Indicates the state of the model version.

publisherModelTemplate string

Optional. Output only. Immutable. Used to indicate this model has a publisher model and provide the template of the publisher model resource name.

predictSchemata object (PredictSchemata)

Optional. The schemata that describes formats of the PublisherModel's predictions and explanations as given and returned via PredictionService.Predict.

JSON representation 
{
  "name": string,
  "versionId": string,
  "openSourceCategory": enum (OpenSourceCategory),
  "parent": {
    object (Parent)
  },
  "supportedActions": {
    object (CallToAction)
  },
  "frameworks": [
    string
  ],
  "launchStage": enum (LaunchStage),
  "versionState": enum (VersionState),
  "publisherModelTemplate": string,
  "predictSchemata": {
    object (PredictSchemata)
  }
}

OpenSourceCategory

An enum representing the open source category of a PublisherModel.

Enums
OPEN_SOURCE_CATEGORY_UNSPECIFIED The open source category is unspecified, which should not be used.
PROPRIETARY Used to indicate the PublisherModel is not open sourced.
GOOGLE_OWNED_OSS_WITH_GOOGLE_CHECKPOINT Used to indicate the PublisherModel is a Google-owned open source model w/ Google checkpoint.
THIRD_PARTY_OWNED_OSS_WITH_GOOGLE_CHECKPOINT Used to indicate the PublisherModel is a 3p-owned open source model w/ Google checkpoint.
GOOGLE_OWNED_OSS Used to indicate the PublisherModel is a Google-owned pure open source model.
THIRD_PARTY_OWNED_OSS Used to indicate the PublisherModel is a 3p-owned pure open source model.

Parent

The information about the parent of a model.

Fields
displayName string

Required. The display name of the parent. E.g., LaMDA, T5, Vision API, Natural Language API.

reference object (ResourceReference)

Optional. The Google Cloud resource name or the URI reference.

JSON representation 
{
  "displayName": string,
  "reference": {
    object (ResourceReference)
  }
}

ResourceReference

Reference to a resource.

Fields

Union field reference.

reference can be only one of the following:

uri string

The URI of the resource.

resourceName string

The resource name of the Google Cloud resource.

useCase
(deprecated) string

Use case (CUJ) of the resource.

description
(deprecated) string

description of the resource.

JSON representation 
{

  // Union field reference can be only one of the following:
  "uri": string,
  "resourceName": string,
  "useCase": string,
  "description": string
  // End of list of possible types for union field reference.
}

CallToAction

Actions could take on this Publisher Model.

Fields
viewRestApi object (ViewRestApi)

Optional. To view Rest API docs.

openNotebook object (RegionalResourceReferences)

Optional. Open notebook of the PublisherModel.

createApplication object (RegionalResourceReferences)

Optional. Create application using the PublisherModel.

openFineTuningPipeline object (RegionalResourceReferences)

Optional. Open fine-tuning pipeline of the PublisherModel.

openPromptTuningPipeline object (RegionalResourceReferences)

Optional. Open prompt-tuning pipeline of the PublisherModel.

openGenie object (RegionalResourceReferences)

Optional. Open Genie / Playground.

deploy object (Deploy)

Optional. Deploy the PublisherModel to Vertex Endpoint.

deployGke object (DeployGke)

Optional. Deploy PublisherModel to Google Kubernetes Engine.

openGenerationAiStudio object (RegionalResourceReferences)

Optional. Open in Generation AI Studio.

requestAccess object (RegionalResourceReferences)

Optional. Request for access.

openEvaluationPipeline object (RegionalResourceReferences)

Optional. Open evaluation pipeline of the PublisherModel.

openNotebooks object (OpenNotebooks)

Optional. Open notebooks of the PublisherModel.

openFineTuningPipelines object (OpenFineTuningPipelines)

Optional. Open fine-tuning pipelines of the PublisherModel.

JSON representation 
{
  "viewRestApi": {
    object (ViewRestApi)
  },
  "openNotebook": {
    object (RegionalResourceReferences)
  },
  "createApplication": {
    object (RegionalResourceReferences)
  },
  "openFineTuningPipeline": {
    object (RegionalResourceReferences)
  },
  "openPromptTuningPipeline": {
    object (RegionalResourceReferences)
  },
  "openGenie": {
    object (RegionalResourceReferences)
  },
  "deploy": {
    object (Deploy)
  },
  "deployGke": {
    object (DeployGke)
  },
  "openGenerationAiStudio": {
    object (RegionalResourceReferences)
  },
  "requestAccess": {
    object (RegionalResourceReferences)
  },
  "openEvaluationPipeline": {
    object (RegionalResourceReferences)
  },
  "openNotebooks": {
    object (OpenNotebooks)
  },
  "openFineTuningPipelines": {
    object (OpenFineTuningPipelines)
  }
}

ViewRestApi

Rest API docs.

Fields
documentations[] object (Documentation)

Required.

title string

Required. The title of the view rest API.

JSON representation 
{
  "documentations": [
    {
      object (Documentation)
    }
  ],
  "title": string
}

Documentation

A named piece of documentation.

Fields
title string

Required. E.g., OVERVIEW, USE CASES, DOCUMENTATION, SDK & SAMPLES, JAVA, NODE.JS, etc..

content string

Required. Content of this piece of document (in Markdown format).

JSON representation 
{
  "title": string,
  "content": string
}

RegionalResourceReferences

The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc..

Fields
references map (key: string, value: object (ResourceReference))

Required.

title string

Required.

resourceTitle string

Optional. title of the resource.

resourceUseCase string

Optional. Use case (CUJ) of the resource.

resourceDescription string

Optional. description of the resource.

JSON representation 
{
  "references": {
    string: {
      object (ResourceReference)
    },
    ...
  },
  "title": string,
  "resourceTitle": string,
  "resourceUseCase": string,
  "resourceDescription": string
}

OpenNotebooks

Open notebooks.

Fields
notebooks[] object (RegionalResourceReferences)

Required. Regional resource references to notebooks.

JSON representation 
{
  "notebooks": [
    {
      object (RegionalResourceReferences)
    }
  ]
}

OpenFineTuningPipelines

Open fine tuning pipelines.

Fields
fineTuningPipelines[] object (RegionalResourceReferences)

Required. Regional resource references to fine tuning pipelines.

JSON representation 
{
  "fineTuningPipelines": [
    {
      object (RegionalResourceReferences)
    }
  ]
}

Deploy

Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests.

Fields
modelDisplayName string

Optional. Default model display name.

largeModelReference object (LargeModelReference)

Optional. Large model reference. When this is set, modelArtifactSpec is not needed.

containerSpec object (ModelContainerSpec)

Optional. The specification of the container that is to be used when deploying this Model in Vertex AI. Not present for Large Models.

artifactUri string

Optional. The path to the directory containing the Model artifact and any of its supporting files.

title string

Required. The title of the regional resource reference.

publicArtifactUri string

Optional. The signed URI for ephemeral Cloud Storage access to model artifact.

Union field prediction_resources. The prediction (for example, the machine) resources that the DeployedModel uses. prediction_resources can be only one of the following:
dedicatedResources object (DedicatedResources)

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

automaticResources object (AutomaticResources)

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

sharedResources string

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deploymentResourcePool}

deployTaskName string

Optional. The name of the deploy task (e.g., "text to image generation").

deployMetadata object (DeployMetadata)

Optional. metadata information about this deployment config.

JSON representation 
{
  "modelDisplayName": string,
  "largeModelReference": {
    object (LargeModelReference)
  },
  "containerSpec": {
    object (ModelContainerSpec)
  },
  "artifactUri": string,
  "title": string,
  "publicArtifactUri": string,

  // Union field prediction_resources can be only one of the following:
  "dedicatedResources": {
    object (DedicatedResources)
  },
  "automaticResources": {
    object (AutomaticResources)
  },
  "sharedResources": string
  // End of list of possible types for union field prediction_resources.
  "deployTaskName": string,
  "deployMetadata": {
    object (DeployMetadata)
  }
}

LargeModelReference

Contains information about the Large Model.

Fields
name string

Required. The unique name of the large Foundation or pre-built model. Like "chat-bison", "text-bison". Or model name with version id, like "chat-bison@001", "text-bison@005", etc.

JSON representation 
{
  "name": string
}

DeployMetadata

metadata information about the deployment for managing deployment config.

Fields
labels map (key: string, value: string)

Optional. Labels for the deployment. For managing deployment config like verifying, source of deployment config, etc.

sampleRequest string

Optional. Sample request for deployed endpoint.

JSON representation 
{
  "labels": {
    string: string,
    ...
  },
  "sampleRequest": string
}

DeployGke

Configurations for PublisherModel GKE deployment

Fields
gkeYamlConfigs[] string

Optional. GKE deployment configuration in yaml format.

JSON representation 
{
  "gkeYamlConfigs": [
    string
  ]
}

LaunchStage

An enum representing the launch stage of a PublisherModel.

Enums
LAUNCH_STAGE_UNSPECIFIED The model launch stage is unspecified.
EXPERIMENTAL Used to indicate the PublisherModel is at Experimental launch stage, available to a small set of customers.
PRIVATE_PREVIEW Used to indicate the PublisherModel is at Private Preview launch stage, only available to a small set of customers, although a larger set of customers than an Experimental launch. Previews are the first launch stage used to get feedback from customers.
PUBLIC_PREVIEW Used to indicate the PublisherModel is at Public Preview launch stage, available to all customers, although not supported for production workloads.
GA Used to indicate the PublisherModel is at GA launch stage, available to all customers and ready for production workload.

VersionState

An enum representing the state of the PublicModelVersion.

Enums
VERSION_STATE_UNSPECIFIED The version state is unspecified.
VERSION_STATE_STABLE Used to indicate the version is stable.
VERSION_STATE_UNSTABLE Used to indicate the version is unstable.

Methods

computeTokens

 Return a list of tokens based on the input text.

countTokens

 Perform a token counting.

generateContent

 Generate content with multimodal inputs.

get

 Gets a Model Garden publisher model.

list

 Lists publisher models in Model Garden.

streamGenerateContent

 Generate content with multimodal inputs with streaming support.