REST Resource: projects.locations.processors.processorVersions

Resource: ProcessorVersion

A processor version is an implementation of a processor. Each processor can have multiple versions, pretrained by Google internally or uptrained by the customer. A processor can only have one default version at a time. Its document-processing behavior is defined by that version.

JSON representation 
{
  "name": string,
  "displayName": string,
  "documentSchema": {
    object (DocumentSchema)
  },
  "state": enum (State),
  "createTime": string,
  "latestEvaluation": {
    object (EvaluationReference)
  },
  "kmsKeyName": string,
  "kmsKeyVersionName": string,
  "googleManaged": boolean,
  "deprecationInfo": {
    object (DeprecationInfo)
  },
  "modelType": enum (ModelType),
  "satisfiesPzs": boolean,
  "satisfiesPzi": boolean,
  "genAiModelInfo": {
    object (GenAiModelInfo)
  }
}
Fields
name

string

Identifier. The resource name of the processor version. Format: projects/{project}/locations/{location}/processors/{processor}/processorVersions/{processorVersion}
displayName

string

The display name of the processor version.
documentSchema

object (DocumentSchema)

Output only. The schema of the processor version. Describes the output.
state

enum (State)

Output only. The state of the processor version.
createTime

string (Timestamp format)

Output only. The time the processor version was created.

Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".
latestEvaluation

object (EvaluationReference)

Output only. The most recently invoked evaluation for the processor version.
kmsKeyName

string

Output only. The KMS key name used for encryption.
kmsKeyVersionName

string

Output only. The KMS key version with which data is encrypted.
googleManaged

boolean

Output only. Denotes that this ProcessorVersion is managed by Google.
deprecationInfo

object (DeprecationInfo)

Output only. If set, information about the eventual deprecation of this version.
modelType

enum (ModelType)

Output only. The model type of this processor version.
satisfiesPzs

boolean

Output only. Reserved for future use.
satisfiesPzi

boolean

Output only. Reserved for future use.
genAiModelInfo

object (GenAiModelInfo)

Output only. Information about Generative AI model-based processor versions.

State

The possible states of the processor version.

Enums
STATE_UNSPECIFIED The processor version is in an unspecified state.
DEPLOYED The processor version is deployed and can be used for processing.
DEPLOYING The processor version is being deployed.
UNDEPLOYED The processor version is not deployed and cannot be used for processing.
UNDEPLOYING The processor version is being undeployed.
CREATING The processor version is being created.
DELETING The processor version is being deleted.
FAILED The processor version failed and is in an indeterminate state.
IMPORTING The processor version is being imported.

EvaluationReference

Gives a short summary of an evaluation, and links to the evaluation itself.

JSON representation 
{
  "operation": string,
  "evaluation": string,
  "aggregateMetrics": {
    object (Metrics)
  },
  "aggregateMetricsExact": {
    object (Metrics)
  }
}
Fields
operation

string

The resource name of the Long Running Operation for the evaluation.
evaluation

string

The resource name of the evaluation.
aggregateMetrics

object (Metrics)

An aggregate of the statistics for the evaluation with fuzzy matching on.
aggregateMetricsExact

object (Metrics)

An aggregate of the statistics for the evaluation with fuzzy matching off.

DeprecationInfo

Information about the upcoming deprecation of this processor version.

JSON representation 
{
  "deprecationTime": string,
  "replacementProcessorVersion": string
}
Fields
deprecationTime

string (Timestamp format)

The time at which this processor version will be deprecated.

Uses RFC 3339, where generated output will always be Z-normalized and use 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples: "2014-10-02T15:01:23Z", "2014-10-02T15:01:23.045123456Z" or "2014-10-02T15:01:23+05:30".
replacementProcessorVersion

string

If set, the processor version that will be used as a replacement.

ModelType

The possible model types of the processor version.

Enums
MODEL_TYPE_UNSPECIFIED The processor version has unspecified model type.
MODEL_TYPE_GENERATIVE The processor version has generative model type.
MODEL_TYPE_CUSTOM The processor version has custom model type.

GenAiModelInfo

Information about Generative AI model-based processor versions.

JSON representation 
{

  // Union field model_info can be only one of the following:
  "foundationGenAiModelInfo": {
    object (FoundationGenAiModelInfo)
  },
  "customGenAiModelInfo": {
    object (CustomGenAiModelInfo)
  }
  // End of list of possible types for union field model_info.
}
Fields
Union field model_info. The processor version is either a pretrained Google-managed foundation model or a custom Generative AI model created by the user. model_info can be only one of the following:
foundationGenAiModelInfo

object (FoundationGenAiModelInfo)

Information for a pretrained Google-managed foundation model.
customGenAiModelInfo

object (CustomGenAiModelInfo)

Information for a custom Generative AI model created by the user.

FoundationGenAiModelInfo

Information for a pretrained Google-managed foundation model.

JSON representation 
{
  "finetuningAllowed": boolean,
  "minTrainLabeledDocuments": integer
}
Fields
finetuningAllowed

boolean

Whether fine tuning is allowed for this base processor version.
minTrainLabeledDocuments

integer

The minimum number of labeled documents in the training dataset required for fine tuning.

CustomGenAiModelInfo

Information for a custom Generative AI model created by the user. These are created with Create New Version in either the Call foundation model or Fine tuning tabs.

JSON representation 
{
  "customModelType": enum (CustomModelType),
  "baseProcessorVersionId": string
}
Fields
customModelType

enum (CustomModelType)

The type of custom model created by the user.
baseProcessorVersionId

string

The base processor version ID for the custom model.

CustomModelType

The type of custom model created by the user.

Enums
CUSTOM_MODEL_TYPE_UNSPECIFIED The model type is unspecified.
VERSIONED_FOUNDATION The model is a versioned foundation model.
FINE_TUNED The model is a finetuned foundation model.

Methods

batchProcess

 LRO endpoint to batch process many documents.

delete

 Deletes the processor version, all artifacts under the processor version will be deleted.

deploy

 Deploys the processor version.

evaluateProcessorVersion

 Evaluates a ProcessorVersion against annotated documents, producing an Evaluation.

get

 Gets a processor version detail.

list

 Lists all versions of a processor.

process

 Processes a single document.

train

 Trains a new processor version.

undeploy

 Undeploys the processor version.