Creates a new version of a model from a trained TensorFlow model. If the version created in the cloud by this call is the first deployed version of the specified model, it will be made the default version of the model. When you add a version to a model that already has one or more versions, the default version does not automatically change. If you want a new version to be the default, you must call projects.models.versions.setDefault.

Scopes

You will need authorization for the https://www.googleapis.com/auth/cloud-platform scope to make a valid call.

If unset, the scope for this method defaults to https://www.googleapis.com/auth/cloud-platform. You can set the scope for this method like this: ml1 --scope <scope> projects models-versions-create ...

Required Scalar Argument

  • <parent> (string)
    • Required. The name of the model.

Required Request Value

The request value is a data-structure with various fields. Each field may be a simple scalar or another data-structure. In the latter case it is advised to set the field-cursor to the data-structure's field to specify values more concisely.

For example, a structure like this:

GoogleCloudMlV1__Version:
  accelerator-config:
    count: string
    type: string
  auto-scaling:
    max-nodes: integer
    min-nodes: integer
  container:
    args: [string]
    command: [string]
    image: string
  create-time: string
  deployment-uri: string
  description: string
  error-message: string
  etag: string
  explanation-config:
    integrated-gradients-attribution:
      num-integral-steps: integer
    sampled-shapley-attribution:
      num-paths: integer
    xrai-attribution:
      num-integral-steps: integer
  framework: string
  is-default: boolean
  labels: { string: string }
  last-migration-model-id: string
  last-migration-time: string
  last-use-time: string
  machine-type: string
  manual-scaling:
    nodes: integer
  name: string
  package-uris: [string]
  prediction-class: string
  python-version: string
  request-logging-config:
    bigquery-table-name: string
    sampling-percentage: number
  routes:
    health: string
    predict: string
  runtime-version: string
  service-account: string
  state: string

can be set completely with the following arguments which are assumed to be executed in the given order. Note how the cursor position is adjusted to the respective structures, allowing simple field names to be used most of the time.

  • -r .accelerator-config count=ipsum
    • The number of accelerators to attach to each machine running the job.

  • type=ea

    • The type of accelerator to use.

  • ..auto-scaling max-nodes=74

    • The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.

  • min-nodes=48

    • Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json

  • ..container args=sit

    • Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
    • Each invocation of this argument appends the given value to the array.
  • command=lorem
    • Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
    • Each invocation of this argument appends the given value to the array.

  • image=stet

    • URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.

  • .. create-time=duo

    • Output only. The time the version was created.
  • deployment-uri=elitr
    • The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
  • description=aliquyam
    • Optional. The description specified for the version when it was created.
  • error-message=erat
    • Output only. The details of a failure or a cancellation.
  • etag=ut
    • etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.

  • explanation-config.integrated-gradients-attribution num-integral-steps=83

    • Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.

  • ..sampled-shapley-attribution num-paths=50

    • The number of feature permutations to consider when approximating the Shapley values.

  • ..xrai-attribution num-integral-steps=35

    • Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.

  • ... framework=et

    • Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
  • is-default=true
    • Output only. If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
  • labels=key=aliquyam
    • Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
    • the value will be associated with the given key
  • last-migration-model-id=kasd
  • last-migration-time=lorem
  • last-use-time=sit
    • Output only. The time the version was last used for prediction.
  • machine-type=kasd
    • Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.

  • manual-scaling nodes=62

    • The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.

  • .. name=dolor

    • Required. The name specified for the version when it was created. The version name must be unique within the model it is created in.
  • package-uris=amet
    • Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
    • Each invocation of this argument appends the given value to the array.
  • prediction-class=sit
    • Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
  • python-version=rebum.
    • Required. The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
  • request-logging-config bigquery-table-name=sea
    • Required. Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE

  • sampling-percentage=0.012890508443760607

    • Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.

  • ..routes health=et

    • HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.

  • predict=elitr

    • HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.

  • .. runtime-version=eirmod

  • service-account=dolor
    • Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.
  • state=sadipscing
    • Output only. The state of a version.

About Cursors

The cursor position is key to comfortably set complex nested structures. The following rules apply:

  • The cursor position is always set relative to the current one, unless the field name starts with the . character. Fields can be nested such as in -r f.s.o .
  • The cursor position is set relative to the top-level structure if it starts with ., e.g. -r .s.s
  • You can also set nested fields without setting the cursor explicitly. For example, to set a value relative to the current cursor position, you would specify -r struct.sub_struct=bar.
  • You can move the cursor one level up by using ... Each additional . moves it up one additional level. E.g. ... would go three levels up.

Optional Output Flags

The method's return value a JSON encoded structure, which will be written to standard output by default.

  • -o out
    • out specifies the destination to which to write the server's result to. It will be a JSON-encoded structure. The destination may be - to indicate standard output, or a filepath that is to contain the received bytes. If unset, it defaults to standard output.

Optional General Properties

The following properties can configure any call, and are not specific to this method.

  • -p $-xgafv=string

    • V1 error format.

  • -p access-token=string

    • OAuth access token.

  • -p alt=string

    • Data format for response.

  • -p callback=string

    • JSONP

  • -p fields=string

    • Selector specifying which fields to include in a partial response.

  • -p key=string

    • API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.

  • -p oauth-token=string

    • OAuth 2.0 token for the current user.

  • -p pretty-print=boolean

    • Returns response with indentations and line breaks.

  • -p quota-user=string

    • Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.

  • -p upload-type=string

    • Legacy upload protocol for media (e.g. "media", "multipart").

  • -p upload-protocol=string

    • Upload protocol for media (e.g. "raw", "multipart").