Returns the evaluations Resource.
Returns the operations Resource.
Close httplib2 connections.
copy(parent, body=None, x__xgafv=None)
Copies an already existing Vertex AI Model into the specified Location. The source Model must exist in the same Project. When copying custom Models, the users themselves are responsible for Model.metadata content to be region-agnostic, as well as making sure that any resources (e.g. files) it depends on remain accessible.
Deletes a Model. A model cannot be deleted if any Endpoint resource has a DeployedModel based on the model in its deployed_models field.
deleteVersion(name, x__xgafv=None)
Deletes a Model version. Model version can only be deleted if there are no DeployedModels created from it. Deleting the only version in the Model is not allowed. Use DeleteModel for deleting the Model instead.
export(name, body=None, x__xgafv=None)
Exports a trained, exportable Model to a location specified by the user. A Model is considered to be exportable if it has at least one supported export format.
Gets a Model.
getIamPolicy(resource, options_requestedPolicyVersion=None, x__xgafv=None)
Gets the access control policy for a resource. Returns an empty policy if the resource exists and does not have a policy set.
list(parent, filter=None, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)
Lists Models in a Location.
Lists versions of the specified model.
Retrieves the next page of results.
Retrieves the next page of results.
mergeVersionAliases(name, body=None, x__xgafv=None)
Merges a set of aliases for a Model version.
patch(name, body=None, updateMask=None, x__xgafv=None)
Updates a Model.
setIamPolicy(resource, body=None, x__xgafv=None)
Sets the access control policy on the specified resource. Replaces any existing policy. Can return `NOT_FOUND`, `INVALID_ARGUMENT`, and `PERMISSION_DENIED` errors.
testIamPermissions(resource, permissions=None, x__xgafv=None)
Returns permissions that a caller has on the specified resource. If the resource does not exist, this will return an empty set of permissions, not a `NOT_FOUND` error. Note: This operation is designed to be used for building permission-aware UIs and command-line tools, not for authorization checking. This operation may "fail open" without warning.
updateExplanationDataset(model, body=None, x__xgafv=None)
Incrementally update the dataset used for an examples model.
upload(parent, body=None, x__xgafv=None)
Uploads a Model artifact into Vertex AI.
close()
Close httplib2 connections.
copy(parent, body=None, x__xgafv=None)
Copies an already existing Vertex AI Model into the specified Location. The source Model must exist in the same Project. When copying custom Models, the users themselves are responsible for Model.metadata content to be region-agnostic, as well as making sure that any resources (e.g. files) it depends on remain accessible.
Args:
parent: string, Required. The resource name of the Location into which to copy the Model. Format: `projects/{project}/locations/{location}` (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ModelService.CopyModel.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key options. If this is set, then the Model copy will be encrypted with the provided encryption key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"modelId": "A String", # Optional. Copy source_model into a new Model with this ID. The ID will become the final component of the model resource name. This value may be up to 63 characters, and valid characters are `[a-z0-9_-]`. The first character cannot be a number or hyphen.
"parentModel": "A String", # Optional. Specify this field to copy source_model into this existing Model as a new version. Format: `projects/{project}/locations/{location}/models/{model}`
"sourceModel": "A String", # Required. The resource name of the Model to copy. That Model must be in the same Project. Format: `projects/{project}/locations/{location}/models/{model}`
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}
delete(name, x__xgafv=None)
Deletes a Model. A model cannot be deleted if any Endpoint resource has a DeployedModel based on the model in its deployed_models field.
Args:
name: string, Required. The name of the Model resource to be deleted. Format: `projects/{project}/locations/{location}/models/{model}` (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}
deleteVersion(name, x__xgafv=None)
Deletes a Model version. Model version can only be deleted if there are no DeployedModels created from it. Deleting the only version in the Model is not allowed. Use DeleteModel for deleting the Model instead.
Args:
name: string, Required. The name of the model version to be deleted, with a version ID explicitly included. Example: `projects/{project}/locations/{location}/models/{model}@1234` (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}
export(name, body=None, x__xgafv=None)
Exports a trained, exportable Model to a location specified by the user. A Model is considered to be exportable if it has at least one supported export format.
Args:
name: string, Required. The resource name of the Model to export. The resource name may contain version id or version alias to specify the version, if no version is specified, the default version will be exported. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ModelService.ExportModel.
"outputConfig": { # Output configuration for the Model export. # Required. The desired output location and configuration.
"artifactDestination": { # The Google Cloud Storage location where the output is to be written to. # The Cloud Storage location where the Model artifact is to be written to. Under the directory given as the destination a new one with name "`model-export--`", where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format, will be created. Inside, the Model and any of its supporting files will be written. This field should only be set when the `exportableContent` field of the [Model.supported_export_formats] object contains `ARTIFACT`.
"outputUriPrefix": "A String", # Required. Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
},
"exportFormatId": "A String", # The ID of the format in which the Model must be exported. Each Model lists the export formats it supports. If no value is provided here, then the first from the list of the Model's supported formats is used by default.
"imageDestination": { # The Container Registry location for the container image. # The Google Container Registry or Artifact Registry uri where the Model container image will be copied to. This field should only be set when the `exportableContent` field of the [Model.supported_export_formats] object contains `IMAGE`.
"outputUri": "A String", # Required. Container Registry URI of a container image. Only Google Container Registry and Artifact Registry are supported now. Accepted forms: * Google Container Registry path. For example: `gcr.io/projectId/imageName:tag`. * Artifact Registry path. For example: `us-central1-docker.pkg.dev/projectId/repoName/imageName:tag`. If a tag is not specified, "latest" will be used as the default tag.
},
},
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}
get(name, x__xgafv=None)
Gets a Model.
Args:
name: string, Required. The name of the Model resource. Format: `projects/{project}/locations/{location}/models/{model}` In order to retrieve a specific version of the model, also provide the version ID or version alias. Example: `projects/{project}/locations/{location}/models/{model}@2` or `projects/{project}/locations/{location}/models/{model}@golden` If no version ID or alias is specified, the "default" version will be returned. The "default" version alias is created for the first version of the model, and can be moved to other versions later on. There will be exactly one default version. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A trained machine learning Model.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
}
getIamPolicy(resource, options_requestedPolicyVersion=None, x__xgafv=None)
Gets the access control policy for a resource. Returns an empty policy if the resource exists and does not have a policy set.
Args:
resource: string, REQUIRED: The resource for which the policy is being requested. See [Resource names](https://cloud.google.com/apis/design/resource_names) for the appropriate value for this field. (required)
options_requestedPolicyVersion: integer, Optional. The maximum policy version that will be used to format the policy. Valid values are 0, 1, and 3. Requests specifying an invalid value will be rejected. Requests for policies with any conditional role bindings must specify version 3. Policies with no conditional role bindings may specify any valid value or leave the field unset. The policy in the response might use the policy version that you specified, or it might use a lower policy version. For example, if you specify version 3, but the policy has no conditional role bindings, the response uses version 1. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources. A `Policy` is a collection of `bindings`. A `binding` binds one or more `members`, or principals, to a single `role`. Principals can be user accounts, service accounts, Google groups, and domains (such as G Suite). A `role` is a named list of permissions; each `role` can be an IAM predefined role or a user-created custom role. For some types of Google Cloud resources, a `binding` can also specify a `condition`, which is a logical expression that allows access to a resource only if the expression evaluates to `true`. A condition can add constraints based on attributes of the request, the resource, or both. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies). **JSON example:** ``` { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "serviceAccount:my-project-id@appspot.gserviceaccount.com" ] }, { "role": "roles/resourcemanager.organizationViewer", "members": [ "user:eve@example.com" ], "condition": { "title": "expirable access", "description": "Does not grant access after Sep 2020", "expression": "request.time < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } ``` **YAML example:** ``` bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - serviceAccount:my-project-id@appspot.gserviceaccount.com role: roles/resourcemanager.organizationAdmin - members: - user:eve@example.com role: roles/resourcemanager.organizationViewer condition: title: expirable access description: Does not grant access after Sep 2020 expression: request.time < timestamp('2020-10-01T00:00:00.000Z') etag: BwWWja0YfJA= version: 3 ``` For a description of IAM and its features, see the [IAM documentation](https://cloud.google.com/iam/docs/).
"bindings": [ # Associates a list of `members`, or principals, with a `role`. Optionally, may specify a `condition` that determines how and when the `bindings` are applied. Each of the `bindings` must contain at least one principal. The `bindings` in a `Policy` can refer to up to 1,500 principals; up to 250 of these principals can be Google groups. Each occurrence of a principal counts towards these limits. For example, if the `bindings` grant 50 different roles to `user:alice@example.com`, and not to any other principal, then you can add another 1,450 principals to the `bindings` in the `Policy`.
{ # Associates `members`, or principals, with a `role`.
"condition": { # Represents a textual expression in the Common Expression Language (CEL) syntax. CEL is a C-like expression language. The syntax and semantics of CEL are documented at https://github.com/google/cel-spec. Example (Comparison): title: "Summary size limit" description: "Determines if a summary is less than 100 chars" expression: "document.summary.size() < 100" Example (Equality): title: "Requestor is owner" description: "Determines if requestor is the document owner" expression: "document.owner == request.auth.claims.email" Example (Logic): title: "Public documents" description: "Determine whether the document should be publicly visible" expression: "document.type != 'private' && document.type != 'internal'" Example (Data Manipulation): title: "Notification string" description: "Create a notification string with a timestamp." expression: "'New message received at ' + string(document.create_time)" The exact variables and functions that may be referenced within an expression are determined by the service that evaluates it. See the service documentation for additional information. # The condition that is associated with this binding. If the condition evaluates to `true`, then this binding applies to the current request. If the condition evaluates to `false`, then this binding does not apply to the current request. However, a different role binding might grant the same role to one or more of the principals in this binding. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
"location": "A String", # Optional. String indicating the location of the expression for error reporting, e.g. a file name and a position in the file.
"title": "A String", # Optional. Title for the expression, i.e. a short string describing its purpose. This can be used e.g. in UIs which allow to enter the expression.
},
"members": [ # Specifies the principals requesting access for a Google Cloud resource. `members` can have the following values: * `allUsers`: A special identifier that represents anyone who is on the internet; with or without a Google account. * `allAuthenticatedUsers`: A special identifier that represents anyone who is authenticated with a Google account or a service account. Does not include identities that come from external identity providers (IdPs) through identity federation. * `user:{emailid}`: An email address that represents a specific Google account. For example, `alice@example.com` . * `serviceAccount:{emailid}`: An email address that represents a Google service account. For example, `my-other-app@appspot.gserviceaccount.com`. * `serviceAccount:{projectid}.svc.id.goog[{namespace}/{kubernetes-sa}]`: An identifier for a [Kubernetes service account](https://cloud.google.com/kubernetes-engine/docs/how-to/kubernetes-service-accounts). For example, `my-project.svc.id.goog[my-namespace/my-kubernetes-sa]`. * `group:{emailid}`: An email address that represents a Google group. For example, `admins@example.com`. * `domain:{domain}`: The G Suite domain (primary) that represents all the users of that domain. For example, `google.com` or `example.com`. * `principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workforce identity pool. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/group/{group_id}`: All workforce identities in a group. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All workforce identities with a specific attribute value. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/*`: All identities in a workforce identity pool. * `principal://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workload identity pool. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/group/{group_id}`: A workload identity pool group. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All identities in a workload identity pool with a certain attribute. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/*`: All identities in a workload identity pool. * `deleted:user:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a user that has been recently deleted. For example, `alice@example.com?uid=123456789012345678901`. If the user is recovered, this value reverts to `user:{emailid}` and the recovered user retains the role in the binding. * `deleted:serviceAccount:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a service account that has been recently deleted. For example, `my-other-app@appspot.gserviceaccount.com?uid=123456789012345678901`. If the service account is undeleted, this value reverts to `serviceAccount:{emailid}` and the undeleted service account retains the role in the binding. * `deleted:group:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a Google group that has been recently deleted. For example, `admins@example.com?uid=123456789012345678901`. If the group is recovered, this value reverts to `group:{emailid}` and the recovered group retains the role in the binding. * `deleted:principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: Deleted single identity in a workforce identity pool. For example, `deleted:principal://iam.googleapis.com/locations/global/workforcePools/my-pool-id/subject/my-subject-attribute-value`.
"A String",
],
"role": "A String", # Role that is assigned to the list of `members`, or principals. For example, `roles/viewer`, `roles/editor`, or `roles/owner`. For an overview of the IAM roles and permissions, see the [IAM documentation](https://cloud.google.com/iam/docs/roles-overview). For a list of the available pre-defined roles, see [here](https://cloud.google.com/iam/docs/understanding-roles).
},
],
"etag": "A String", # `etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a policy from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform policy updates in order to avoid race conditions: An `etag` is returned in the response to `getIamPolicy`, and systems are expected to put that etag in the request to `setIamPolicy` to ensure that their change will be applied to the same version of the policy. **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost.
"version": 42, # Specifies the format of the policy. Valid values are `0`, `1`, and `3`. Requests that specify an invalid value are rejected. Any operation that affects conditional role bindings must specify version `3`. This requirement applies to the following operations: * Getting a policy that includes a conditional role binding * Adding a conditional role binding to a policy * Changing a conditional role binding in a policy * Removing any role binding, with or without a condition, from a policy that includes conditions **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost. If a policy does not include any conditions, operations on that policy may specify any valid version or leave the field unset. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
}
list(parent, filter=None, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)
Lists Models in a Location.
Args:
parent: string, Required. The resource name of the Location to list the Models from. Format: `projects/{project}/locations/{location}` (required)
filter: string, An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `model` supports = and !=. `model` represents the Model ID, i.e. the last segment of the Model's resource name. * `display_name` supports = and != * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:* or labels:key - key existence * A key including a space must be quoted. `labels."a key"`. * `base_model_name` only supports = Some examples: * `model=1234` * `displayName="myDisplayName"` * `labels.myKey="myValue"` * `baseModelName="text-bison"`
pageSize: integer, The standard list page size.
pageToken: string, The standard list page token. Typically obtained via ListModelsResponse.next_page_token of the previous ModelService.ListModels call.
readMask: string, Mask specifying which fields to read.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for ModelService.ListModels
"models": [ # List of Models in the requested page.
{ # A trained machine learning Model.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
},
],
"nextPageToken": "A String", # A token to retrieve next page of results. Pass to ListModelsRequest.page_token to obtain that page.
}
listVersions(name, filter=None, orderBy=None, pageSize=None, pageToken=None, readMask=None, x__xgafv=None)
Lists versions of the specified model.
Args:
name: string, Required. The name of the model to list versions for. (required)
filter: string, An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:* or labels:key - key existence * A key including a space must be quoted. `labels."a key"`. Some examples: * `labels.myKey="myValue"`
orderBy: string, A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * `create_time` * `update_time` Example: `update_time asc, create_time desc`.
pageSize: integer, The standard list page size.
pageToken: string, The standard list page token. Typically obtained via next_page_token of the previous ListModelVersions call.
readMask: string, Mask specifying which fields to read.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for ModelService.ListModelVersions
"models": [ # List of Model versions in the requested page. In the returned Model name field, version ID instead of regvision tag will be included.
{ # A trained machine learning Model.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
},
],
"nextPageToken": "A String", # A token to retrieve the next page of results. Pass to ListModelVersionsRequest.page_token to obtain that page.
}
listVersions_next()
Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
list_next()
Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
mergeVersionAliases(name, body=None, x__xgafv=None)
Merges a set of aliases for a Model version.
Args:
name: string, Required. The name of the model version to merge aliases, with a version ID explicitly included. Example: `projects/{project}/locations/{location}/models/{model}@1234` (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ModelService.MergeVersionAliases.
"versionAliases": [ # Required. The set of version aliases to merge. The alias should be at most 128 characters, and match `a-z{0,126}[a-z-0-9]`. Add the `-` prefix to an alias means removing that alias from the version. `-` is NOT counted in the 128 characters. Example: `-golden` means removing the `golden` alias from the version. There is NO ordering in aliases, which means 1) The aliases returned from GetModel API might not have the exactly same order from this MergeVersionAliases API. 2) Adding and deleting the same alias in the request is not recommended, and the 2 operations will be cancelled out.
"A String",
],
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A trained machine learning Model.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
}
patch(name, body=None, updateMask=None, x__xgafv=None)
Updates a Model.
Args:
name: string, The resource name of the Model. (required)
body: object, The request body.
The object takes the form of:
{ # A trained machine learning Model.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
}
updateMask: string, Required. The update mask applies to the resource. For the `FieldMask` definition, see google.protobuf.FieldMask.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A trained machine learning Model.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
}
setIamPolicy(resource, body=None, x__xgafv=None)
Sets the access control policy on the specified resource. Replaces any existing policy. Can return `NOT_FOUND`, `INVALID_ARGUMENT`, and `PERMISSION_DENIED` errors.
Args:
resource: string, REQUIRED: The resource for which the policy is being specified. See [Resource names](https://cloud.google.com/apis/design/resource_names) for the appropriate value for this field. (required)
body: object, The request body.
The object takes the form of:
{ # Request message for `SetIamPolicy` method.
"policy": { # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources. A `Policy` is a collection of `bindings`. A `binding` binds one or more `members`, or principals, to a single `role`. Principals can be user accounts, service accounts, Google groups, and domains (such as G Suite). A `role` is a named list of permissions; each `role` can be an IAM predefined role or a user-created custom role. For some types of Google Cloud resources, a `binding` can also specify a `condition`, which is a logical expression that allows access to a resource only if the expression evaluates to `true`. A condition can add constraints based on attributes of the request, the resource, or both. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies). **JSON example:** ``` { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "serviceAccount:my-project-id@appspot.gserviceaccount.com" ] }, { "role": "roles/resourcemanager.organizationViewer", "members": [ "user:eve@example.com" ], "condition": { "title": "expirable access", "description": "Does not grant access after Sep 2020", "expression": "request.time < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } ``` **YAML example:** ``` bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - serviceAccount:my-project-id@appspot.gserviceaccount.com role: roles/resourcemanager.organizationAdmin - members: - user:eve@example.com role: roles/resourcemanager.organizationViewer condition: title: expirable access description: Does not grant access after Sep 2020 expression: request.time < timestamp('2020-10-01T00:00:00.000Z') etag: BwWWja0YfJA= version: 3 ``` For a description of IAM and its features, see the [IAM documentation](https://cloud.google.com/iam/docs/). # REQUIRED: The complete policy to be applied to the `resource`. The size of the policy is limited to a few 10s of KB. An empty policy is a valid policy but certain Google Cloud services (such as Projects) might reject them.
"bindings": [ # Associates a list of `members`, or principals, with a `role`. Optionally, may specify a `condition` that determines how and when the `bindings` are applied. Each of the `bindings` must contain at least one principal. The `bindings` in a `Policy` can refer to up to 1,500 principals; up to 250 of these principals can be Google groups. Each occurrence of a principal counts towards these limits. For example, if the `bindings` grant 50 different roles to `user:alice@example.com`, and not to any other principal, then you can add another 1,450 principals to the `bindings` in the `Policy`.
{ # Associates `members`, or principals, with a `role`.
"condition": { # Represents a textual expression in the Common Expression Language (CEL) syntax. CEL is a C-like expression language. The syntax and semantics of CEL are documented at https://github.com/google/cel-spec. Example (Comparison): title: "Summary size limit" description: "Determines if a summary is less than 100 chars" expression: "document.summary.size() < 100" Example (Equality): title: "Requestor is owner" description: "Determines if requestor is the document owner" expression: "document.owner == request.auth.claims.email" Example (Logic): title: "Public documents" description: "Determine whether the document should be publicly visible" expression: "document.type != 'private' && document.type != 'internal'" Example (Data Manipulation): title: "Notification string" description: "Create a notification string with a timestamp." expression: "'New message received at ' + string(document.create_time)" The exact variables and functions that may be referenced within an expression are determined by the service that evaluates it. See the service documentation for additional information. # The condition that is associated with this binding. If the condition evaluates to `true`, then this binding applies to the current request. If the condition evaluates to `false`, then this binding does not apply to the current request. However, a different role binding might grant the same role to one or more of the principals in this binding. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
"location": "A String", # Optional. String indicating the location of the expression for error reporting, e.g. a file name and a position in the file.
"title": "A String", # Optional. Title for the expression, i.e. a short string describing its purpose. This can be used e.g. in UIs which allow to enter the expression.
},
"members": [ # Specifies the principals requesting access for a Google Cloud resource. `members` can have the following values: * `allUsers`: A special identifier that represents anyone who is on the internet; with or without a Google account. * `allAuthenticatedUsers`: A special identifier that represents anyone who is authenticated with a Google account or a service account. Does not include identities that come from external identity providers (IdPs) through identity federation. * `user:{emailid}`: An email address that represents a specific Google account. For example, `alice@example.com` . * `serviceAccount:{emailid}`: An email address that represents a Google service account. For example, `my-other-app@appspot.gserviceaccount.com`. * `serviceAccount:{projectid}.svc.id.goog[{namespace}/{kubernetes-sa}]`: An identifier for a [Kubernetes service account](https://cloud.google.com/kubernetes-engine/docs/how-to/kubernetes-service-accounts). For example, `my-project.svc.id.goog[my-namespace/my-kubernetes-sa]`. * `group:{emailid}`: An email address that represents a Google group. For example, `admins@example.com`. * `domain:{domain}`: The G Suite domain (primary) that represents all the users of that domain. For example, `google.com` or `example.com`. * `principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workforce identity pool. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/group/{group_id}`: All workforce identities in a group. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All workforce identities with a specific attribute value. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/*`: All identities in a workforce identity pool. * `principal://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workload identity pool. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/group/{group_id}`: A workload identity pool group. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All identities in a workload identity pool with a certain attribute. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/*`: All identities in a workload identity pool. * `deleted:user:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a user that has been recently deleted. For example, `alice@example.com?uid=123456789012345678901`. If the user is recovered, this value reverts to `user:{emailid}` and the recovered user retains the role in the binding. * `deleted:serviceAccount:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a service account that has been recently deleted. For example, `my-other-app@appspot.gserviceaccount.com?uid=123456789012345678901`. If the service account is undeleted, this value reverts to `serviceAccount:{emailid}` and the undeleted service account retains the role in the binding. * `deleted:group:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a Google group that has been recently deleted. For example, `admins@example.com?uid=123456789012345678901`. If the group is recovered, this value reverts to `group:{emailid}` and the recovered group retains the role in the binding. * `deleted:principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: Deleted single identity in a workforce identity pool. For example, `deleted:principal://iam.googleapis.com/locations/global/workforcePools/my-pool-id/subject/my-subject-attribute-value`.
"A String",
],
"role": "A String", # Role that is assigned to the list of `members`, or principals. For example, `roles/viewer`, `roles/editor`, or `roles/owner`. For an overview of the IAM roles and permissions, see the [IAM documentation](https://cloud.google.com/iam/docs/roles-overview). For a list of the available pre-defined roles, see [here](https://cloud.google.com/iam/docs/understanding-roles).
},
],
"etag": "A String", # `etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a policy from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform policy updates in order to avoid race conditions: An `etag` is returned in the response to `getIamPolicy`, and systems are expected to put that etag in the request to `setIamPolicy` to ensure that their change will be applied to the same version of the policy. **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost.
"version": 42, # Specifies the format of the policy. Valid values are `0`, `1`, and `3`. Requests that specify an invalid value are rejected. Any operation that affects conditional role bindings must specify version `3`. This requirement applies to the following operations: * Getting a policy that includes a conditional role binding * Adding a conditional role binding to a policy * Changing a conditional role binding in a policy * Removing any role binding, with or without a condition, from a policy that includes conditions **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost. If a policy does not include any conditions, operations on that policy may specify any valid version or leave the field unset. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
},
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # An Identity and Access Management (IAM) policy, which specifies access controls for Google Cloud resources. A `Policy` is a collection of `bindings`. A `binding` binds one or more `members`, or principals, to a single `role`. Principals can be user accounts, service accounts, Google groups, and domains (such as G Suite). A `role` is a named list of permissions; each `role` can be an IAM predefined role or a user-created custom role. For some types of Google Cloud resources, a `binding` can also specify a `condition`, which is a logical expression that allows access to a resource only if the expression evaluates to `true`. A condition can add constraints based on attributes of the request, the resource, or both. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies). **JSON example:** ``` { "bindings": [ { "role": "roles/resourcemanager.organizationAdmin", "members": [ "user:mike@example.com", "group:admins@example.com", "domain:google.com", "serviceAccount:my-project-id@appspot.gserviceaccount.com" ] }, { "role": "roles/resourcemanager.organizationViewer", "members": [ "user:eve@example.com" ], "condition": { "title": "expirable access", "description": "Does not grant access after Sep 2020", "expression": "request.time < timestamp('2020-10-01T00:00:00.000Z')", } } ], "etag": "BwWWja0YfJA=", "version": 3 } ``` **YAML example:** ``` bindings: - members: - user:mike@example.com - group:admins@example.com - domain:google.com - serviceAccount:my-project-id@appspot.gserviceaccount.com role: roles/resourcemanager.organizationAdmin - members: - user:eve@example.com role: roles/resourcemanager.organizationViewer condition: title: expirable access description: Does not grant access after Sep 2020 expression: request.time < timestamp('2020-10-01T00:00:00.000Z') etag: BwWWja0YfJA= version: 3 ``` For a description of IAM and its features, see the [IAM documentation](https://cloud.google.com/iam/docs/).
"bindings": [ # Associates a list of `members`, or principals, with a `role`. Optionally, may specify a `condition` that determines how and when the `bindings` are applied. Each of the `bindings` must contain at least one principal. The `bindings` in a `Policy` can refer to up to 1,500 principals; up to 250 of these principals can be Google groups. Each occurrence of a principal counts towards these limits. For example, if the `bindings` grant 50 different roles to `user:alice@example.com`, and not to any other principal, then you can add another 1,450 principals to the `bindings` in the `Policy`.
{ # Associates `members`, or principals, with a `role`.
"condition": { # Represents a textual expression in the Common Expression Language (CEL) syntax. CEL is a C-like expression language. The syntax and semantics of CEL are documented at https://github.com/google/cel-spec. Example (Comparison): title: "Summary size limit" description: "Determines if a summary is less than 100 chars" expression: "document.summary.size() < 100" Example (Equality): title: "Requestor is owner" description: "Determines if requestor is the document owner" expression: "document.owner == request.auth.claims.email" Example (Logic): title: "Public documents" description: "Determine whether the document should be publicly visible" expression: "document.type != 'private' && document.type != 'internal'" Example (Data Manipulation): title: "Notification string" description: "Create a notification string with a timestamp." expression: "'New message received at ' + string(document.create_time)" The exact variables and functions that may be referenced within an expression are determined by the service that evaluates it. See the service documentation for additional information. # The condition that is associated with this binding. If the condition evaluates to `true`, then this binding applies to the current request. If the condition evaluates to `false`, then this binding does not apply to the current request. However, a different role binding might grant the same role to one or more of the principals in this binding. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
"description": "A String", # Optional. Description of the expression. This is a longer text which describes the expression, e.g. when hovered over it in a UI.
"expression": "A String", # Textual representation of an expression in Common Expression Language syntax.
"location": "A String", # Optional. String indicating the location of the expression for error reporting, e.g. a file name and a position in the file.
"title": "A String", # Optional. Title for the expression, i.e. a short string describing its purpose. This can be used e.g. in UIs which allow to enter the expression.
},
"members": [ # Specifies the principals requesting access for a Google Cloud resource. `members` can have the following values: * `allUsers`: A special identifier that represents anyone who is on the internet; with or without a Google account. * `allAuthenticatedUsers`: A special identifier that represents anyone who is authenticated with a Google account or a service account. Does not include identities that come from external identity providers (IdPs) through identity federation. * `user:{emailid}`: An email address that represents a specific Google account. For example, `alice@example.com` . * `serviceAccount:{emailid}`: An email address that represents a Google service account. For example, `my-other-app@appspot.gserviceaccount.com`. * `serviceAccount:{projectid}.svc.id.goog[{namespace}/{kubernetes-sa}]`: An identifier for a [Kubernetes service account](https://cloud.google.com/kubernetes-engine/docs/how-to/kubernetes-service-accounts). For example, `my-project.svc.id.goog[my-namespace/my-kubernetes-sa]`. * `group:{emailid}`: An email address that represents a Google group. For example, `admins@example.com`. * `domain:{domain}`: The G Suite domain (primary) that represents all the users of that domain. For example, `google.com` or `example.com`. * `principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workforce identity pool. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/group/{group_id}`: All workforce identities in a group. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All workforce identities with a specific attribute value. * `principalSet://iam.googleapis.com/locations/global/workforcePools/{pool_id}/*`: All identities in a workforce identity pool. * `principal://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/subject/{subject_attribute_value}`: A single identity in a workload identity pool. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/group/{group_id}`: A workload identity pool group. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/attribute.{attribute_name}/{attribute_value}`: All identities in a workload identity pool with a certain attribute. * `principalSet://iam.googleapis.com/projects/{project_number}/locations/global/workloadIdentityPools/{pool_id}/*`: All identities in a workload identity pool. * `deleted:user:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a user that has been recently deleted. For example, `alice@example.com?uid=123456789012345678901`. If the user is recovered, this value reverts to `user:{emailid}` and the recovered user retains the role in the binding. * `deleted:serviceAccount:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a service account that has been recently deleted. For example, `my-other-app@appspot.gserviceaccount.com?uid=123456789012345678901`. If the service account is undeleted, this value reverts to `serviceAccount:{emailid}` and the undeleted service account retains the role in the binding. * `deleted:group:{emailid}?uid={uniqueid}`: An email address (plus unique identifier) representing a Google group that has been recently deleted. For example, `admins@example.com?uid=123456789012345678901`. If the group is recovered, this value reverts to `group:{emailid}` and the recovered group retains the role in the binding. * `deleted:principal://iam.googleapis.com/locations/global/workforcePools/{pool_id}/subject/{subject_attribute_value}`: Deleted single identity in a workforce identity pool. For example, `deleted:principal://iam.googleapis.com/locations/global/workforcePools/my-pool-id/subject/my-subject-attribute-value`.
"A String",
],
"role": "A String", # Role that is assigned to the list of `members`, or principals. For example, `roles/viewer`, `roles/editor`, or `roles/owner`. For an overview of the IAM roles and permissions, see the [IAM documentation](https://cloud.google.com/iam/docs/roles-overview). For a list of the available pre-defined roles, see [here](https://cloud.google.com/iam/docs/understanding-roles).
},
],
"etag": "A String", # `etag` is used for optimistic concurrency control as a way to help prevent simultaneous updates of a policy from overwriting each other. It is strongly suggested that systems make use of the `etag` in the read-modify-write cycle to perform policy updates in order to avoid race conditions: An `etag` is returned in the response to `getIamPolicy`, and systems are expected to put that etag in the request to `setIamPolicy` to ensure that their change will be applied to the same version of the policy. **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost.
"version": 42, # Specifies the format of the policy. Valid values are `0`, `1`, and `3`. Requests that specify an invalid value are rejected. Any operation that affects conditional role bindings must specify version `3`. This requirement applies to the following operations: * Getting a policy that includes a conditional role binding * Adding a conditional role binding to a policy * Changing a conditional role binding in a policy * Removing any role binding, with or without a condition, from a policy that includes conditions **Important:** If you use IAM Conditions, you must include the `etag` field whenever you call `setIamPolicy`. If you omit this field, then IAM allows you to overwrite a version `3` policy with a version `1` policy, and all of the conditions in the version `3` policy are lost. If a policy does not include any conditions, operations on that policy may specify any valid version or leave the field unset. To learn which resources support conditions in their IAM policies, see the [IAM documentation](https://cloud.google.com/iam/help/conditions/resource-policies).
}
testIamPermissions(resource, permissions=None, x__xgafv=None)
Returns permissions that a caller has on the specified resource. If the resource does not exist, this will return an empty set of permissions, not a `NOT_FOUND` error. Note: This operation is designed to be used for building permission-aware UIs and command-line tools, not for authorization checking. This operation may "fail open" without warning.
Args:
resource: string, REQUIRED: The resource for which the policy detail is being requested. See [Resource names](https://cloud.google.com/apis/design/resource_names) for the appropriate value for this field. (required)
permissions: string, The set of permissions to check for the `resource`. Permissions with wildcards (such as `*` or `storage.*`) are not allowed. For more information see [IAM Overview](https://cloud.google.com/iam/docs/overview#permissions). (repeated)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response message for `TestIamPermissions` method.
"permissions": [ # A subset of `TestPermissionsRequest.permissions` that the caller is allowed.
"A String",
],
}
updateExplanationDataset(model, body=None, x__xgafv=None)
Incrementally update the dataset used for an examples model.
Args:
model: string, Required. The resource name of the Model to update. Format: `projects/{project}/locations/{location}/models/{model}` (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ModelService.UpdateExplanationDataset.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # The example config containing the location of the dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}
upload(parent, body=None, x__xgafv=None)
Uploads a Model artifact into Vertex AI.
Args:
parent: string, Required. The resource name of the Location into which to upload the Model. Format: `projects/{project}/locations/{location}` (required)
body: object, The request body.
The object takes the form of:
{ # Request message for ModelService.UploadModel.
"model": { # A trained machine learning Model. # Required. The Model to create.
"artifactUri": "A String", # Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not required for AutoML Models.
"baseModelSource": { # User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models. # Optional. User input field to specify the base model source. Currently it only supports specifing the Model Garden models and Genie models.
"genieSource": { # Contains information about the source of the models generated from Generative AI Studio. # Information about the base model of Genie models.
"baseModelUri": "A String", # Required. The public base model URI.
},
"modelGardenSource": { # Contains information about the source of the models generated from Model Garden. # Source information of Model Garden models.
"publicModelName": "A String", # Required. The model garden source model resource name.
},
},
"containerSpec": { # Specification of a container for serving predictions. Some fields in this message correspond to fields in the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core). # Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not required for AutoML Models.
"args": [ # Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's [`CMD`](https://docs.docker.com/engine/reference/builder/#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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). If you don't specify this field and don't specify the `command` field, then the container's [`ENTRYPOINT`](https://docs.docker.com/engine/reference/builder/#cmd) and `CMD` determine what runs based on their default behavior. See the Docker documentation about [how `CMD` and `ENTRYPOINT` interact](https://docs.docker.com/engine/reference/builder/#understand-how-cmd-and-entrypoint-interact). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"command": [ # Immutable. Specifies the command that runs when the container starts. This overrides the container's [ENTRYPOINT](https://docs.docker.com/engine/reference/builder/#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`](https://docs.docker.com/engine/reference/builder/#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](https://docs.docker.com/engine/reference/builder/#understand-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`](https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#notes). In this field, you can reference [environment variables set by Vertex AI](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables) 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](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
"A String",
],
"deploymentTimeout": "A String", # Immutable. Deployment timeout. Limit for deployment timeout is 2 hours.
"env": [ # Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable `VAR_2` to have the value `foo bar`: ```json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents an environment variable present in a Container or Python Module.
"name": "A String", # Required. Name of the environment variable. Must be a valid C identifier.
"value": "A String", # Required. Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
},
],
"grpcPorts": [ # Immutable. List of ports to expose from the container. Vertex AI sends gRPC prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, gRPC requests to the container will be disabled. Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers v1 core API.
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"healthProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes readiness probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
"healthRoute": "A String", # Immutable. HTTP path on the container to send health checks to. Vertex AI 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](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#health). For example, if you set this field to `/bar`, then Vertex AI intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"imageUri": "A String", # Required. Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the [container publishing requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#publishing), including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see [Custom container requirements](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#). You can use the URI to one of Vertex AI's [pre-built container images for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers) in this field.
"ports": [ # Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends [liveness and health checks](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#liveness) to this port. If you do not specify this field, it defaults to following value: ```json [ { "containerPort": 8080 } ] ``` Vertex AI does not use ports other than the first one listed. This field corresponds to the `ports` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).
{ # Represents a network port in a container.
"containerPort": 42, # The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
},
],
"predictRoute": "A String", # Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to `/foo`, then when Vertex AI 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 this `ModelContainerSpec`'s ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (following `endpoints/`)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as the [`AIP_ENDPOINT_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).) * DEPLOYED_MODEL: DeployedModel.id of the `DeployedModel`. (Vertex AI makes this value available to your container code as the [`AIP_DEPLOYED_MODEL_ID` environment variable](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#aip-variables).)
"sharedMemorySizeMb": "A String", # Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes.
"startupProbe": { # Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic. # Immutable. Specification for Kubernetes startup probe.
"exec": { # ExecAction specifies a command to execute. # ExecAction probes the health of a container by executing a command.
"command": [ # Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
"A String",
],
},
"periodSeconds": 42, # How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
"timeoutSeconds": 42, # Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
},
},
"createTime": "A String", # Output only. Timestamp when this Model was uploaded into Vertex AI.
"deployedModels": [ # Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
{ # Points to a DeployedModel.
"deployedModelId": "A String", # Immutable. An ID of a DeployedModel in the above Endpoint.
"endpoint": "A String", # Immutable. A resource name of an Endpoint.
},
],
"description": "A String", # The description of the Model.
"displayName": "A String", # Required. The display name of the Model. The name can be up to 128 characters long and can consist of any UTF-8 characters.
"encryptionSpec": { # Represents a customer-managed encryption key spec that can be applied to a top-level resource. # Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
"kmsKeyName": "A String", # Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: `projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key`. The key needs to be in the same region as where the compute resource is created.
},
"etag": "A String", # Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
"explanationSpec": { # Specification of Model explanation. # The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
"metadata": { # Metadata describing the Model's input and output for explanation. # Optional. Metadata describing the Model's input and output for explanation.
"featureAttributionsSchemaUri": "A String", # Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"inputs": { # Required. Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
"a_key": { # Metadata of the input of a feature. Fields other than InputMetadata.input_baselines are applicable only for Models that are using Vertex AI-provided images for Tensorflow.
"denseShapeTensorName": "A String", # Specifies the shape of the values of the input if the input is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"encodedBaselines": [ # A list of baselines for the encoded tensor. The shape of each baseline should match the shape of the encoded tensor. If a scalar is provided, Vertex AI broadcasts to the same shape as the encoded tensor.
"",
],
"encodedTensorName": "A String", # Encoded tensor is a transformation of the input tensor. Must be provided if choosing Integrated Gradients attribution or XRAI attribution and the input tensor is not differentiable. An encoded tensor is generated if the input tensor is encoded by a lookup table.
"encoding": "A String", # Defines how the feature is encoded into the input tensor. Defaults to IDENTITY.
"featureValueDomain": { # Domain details of the input feature value. Provides numeric information about the feature, such as its range (min, max). If the feature has been pre-processed, for example with z-scoring, then it provides information about how to recover the original feature. For example, if the input feature is an image and it has been pre-processed to obtain 0-mean and stddev = 1 values, then original_mean, and original_stddev refer to the mean and stddev of the original feature (e.g. image tensor) from which input feature (with mean = 0 and stddev = 1) was obtained. # The domain details of the input feature value. Like min/max, original mean or standard deviation if normalized.
"maxValue": 3.14, # The maximum permissible value for this feature.
"minValue": 3.14, # The minimum permissible value for this feature.
"originalMean": 3.14, # If this input feature has been normalized to a mean value of 0, the original_mean specifies the mean value of the domain prior to normalization.
"originalStddev": 3.14, # If this input feature has been normalized to a standard deviation of 1.0, the original_stddev specifies the standard deviation of the domain prior to normalization.
},
"groupName": "A String", # Name of the group that the input belongs to. Features with the same group name will be treated as one feature when computing attributions. Features grouped together can have different shapes in value. If provided, there will be one single attribution generated in Attribution.feature_attributions, keyed by the group name.
"indexFeatureMapping": [ # A list of feature names for each index in the input tensor. Required when the input InputMetadata.encoding is BAG_OF_FEATURES, BAG_OF_FEATURES_SPARSE, INDICATOR.
"A String",
],
"indicesTensorName": "A String", # Specifies the index of the values of the input tensor. Required when the input tensor is a sparse representation. Refer to Tensorflow documentation for more details: https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor.
"inputBaselines": [ # Baseline inputs for this feature. If no baseline is specified, Vertex AI chooses the baseline for this feature. If multiple baselines are specified, Vertex AI returns the average attributions across them in Attribution.feature_attributions. For Vertex AI-provided Tensorflow images (both 1.x and 2.x), the shape of each baseline must match the shape of the input tensor. If a scalar is provided, we broadcast to the same shape as the input tensor. For custom images, the element of the baselines must be in the same format as the feature's input in the instance[]. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
"",
],
"inputTensorName": "A String", # Name of the input tensor for this feature. Required and is only applicable to Vertex AI-provided images for Tensorflow.
"modality": "A String", # Modality of the feature. Valid values are: numeric, image. Defaults to numeric.
"visualization": { # Visualization configurations for image explanation. # Visualization configurations for image explanation.
"clipPercentLowerbound": 3.14, # Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
"clipPercentUpperbound": 3.14, # Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
"colorMap": "A String", # The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
"overlayType": "A String", # How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
"polarity": "A String", # Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
"type": "A String", # Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
},
},
},
"latentSpaceSource": "A String", # Name of the source to generate embeddings for example based explanations.
"outputs": { # Required. Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
"a_key": { # Metadata of the prediction output to be explained.
"displayNameMappingKey": "A String", # Specify a field name in the prediction to look for the display name. Use this if the prediction contains the display names for the outputs. The display names in the prediction must have the same shape of the outputs, so that it can be located by Attribution.output_index for a specific output.
"indexDisplayNameMapping": "", # Static mapping between the index and display name. Use this if the outputs are a deterministic n-dimensional array, e.g. a list of scores of all the classes in a pre-defined order for a multi-classification Model. It's not feasible if the outputs are non-deterministic, e.g. the Model produces top-k classes or sort the outputs by their values. The shape of the value must be an n-dimensional array of strings. The number of dimensions must match that of the outputs to be explained. The Attribution.output_display_name is populated by locating in the mapping with Attribution.output_index.
"outputTensorName": "A String", # Name of the output tensor. Required and is only applicable to Vertex AI provided images for Tensorflow.
},
},
},
"parameters": { # Parameters to configure explaining for Model's predictions. # Required. Parameters that configure explaining of the Model's predictions.
"examples": { # Example-based explainability that returns the nearest neighbors from the provided dataset. # Example-based explanations that returns the nearest neighbors from the provided dataset.
"exampleGcsSource": { # The Cloud Storage input instances. # The Cloud Storage input instances.
"dataFormat": "A String", # The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage location for the input instances.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
},
"gcsSource": { # The Google Cloud Storage location for the input content. # The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.
"uris": [ # Required. Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
"A String",
],
},
"nearestNeighborSearchConfig": "", # The full configuration for the generated index, the semantics are the same as metadata and should match [NearestNeighborSearchConfig](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations-example-based#nearest-neighbor-search-config).
"neighborCount": 42, # The number of neighbors to return when querying for examples.
"presets": { # Preset configuration for example-based explanations # Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
"modality": "A String", # The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
"query": "A String", # Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to `PRECISE`.
},
},
"integratedGradientsAttribution": { # An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365 # An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
},
"outputIndices": [ # If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
"",
],
"sampledShapleyAttribution": { # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. # An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
"pathCount": 42, # Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
},
"topK": 42, # If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
"xraiAttribution": { # An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Supported only by image Models. # An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
"blurBaselineConfig": { # Config for blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383 # Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
"maxBlurSigma": 3.14, # The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
},
"smoothGradConfig": { # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf # Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
"featureNoiseSigma": { # Noise sigma by features. Noise sigma represents the standard deviation of the gaussian kernel that will be used to add noise to interpolated inputs prior to computing gradients. # This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
"noiseSigma": [ # Noise sigma per feature. No noise is added to features that are not set.
{ # Noise sigma for a single feature.
"name": "A String", # The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
"sigma": 3.14, # This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
},
],
},
"noiseSigma": 3.14, # This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about [normalization](https://developers.google.com/machine-learning/data-prep/transform/normalization). For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
"noisySampleCount": 42, # The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
},
"stepCount": 42, # Required. The 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. Valid range of its value is [1, 100], inclusively.
},
},
},
"labels": { # The labels with user-defined metadata to organize your Models. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
"a_key": "A String",
},
"metadata": "", # Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
"metadataArtifact": "A String", # Output only. The resource name of the Artifact that was created in MetadataStore when creating the Model. The Artifact resource name pattern is `projects/{project}/locations/{location}/metadataStores/{metadata_store}/artifacts/{artifact}`.
"metadataSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"modelSourceInfo": { # Detail description of the source information of the model. # Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or saved and tuned from Genie or Model Garden.
"copy": True or False, # If this Model is copy of another Model. If true then source_type pertains to the original.
"sourceType": "A String", # Type of the model source.
},
"name": "A String", # The resource name of the Model.
"originalModelInfo": { # Contains information about the original Model if this Model is a copy. # Output only. If this Model is a copy of another Model, this contains info about the original.
"model": "A String", # Output only. The resource name of the Model this Model is a copy of, including the revision. Format: `projects/{project}/locations/{location}/models/{model_id}@{version_id}`
},
"predictSchemata": { # Contains the schemata used in Model's predictions and explanations via PredictionService.Predict, PredictionService.Explain and BatchPredictionJob. # The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
"instanceSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"parametersSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
"predictionSchemaUri": "A String", # Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 [Schema Object](https://github.com/OAI/OpenAPI-Specification/blob/main/versions/3.0.2.md#schemaObject). AutoML Models always have this field populated by Vertex AI. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
},
"satisfiesPzi": True or False, # Output only. Reserved for future use.
"satisfiesPzs": True or False, # Output only. Reserved for future use.
"supportedDeploymentResourcesTypes": [ # Output only. When this Model is deployed, its prediction resources are described by the `prediction_resources` field of the Endpoint.deployed_models object. Because not all Models support all resource configuration types, the configuration types this Model supports are listed here. If no configuration types are listed, the Model cannot be deployed to an Endpoint and does not support online predictions (PredictionService.Predict or PredictionService.Explain). Such a Model can serve predictions by using a BatchPredictionJob, if it has at least one entry each in supported_input_storage_formats and supported_output_storage_formats.
"A String",
],
"supportedExportFormats": [ # Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
{ # Represents export format supported by the Model. All formats export to Google Cloud Storage.
"exportableContents": [ # Output only. The content of this Model that may be exported.
"A String",
],
"id": "A String", # Output only. The ID of the export format. The possible format IDs are: * `tflite` Used for Android mobile devices. * `edgetpu-tflite` Used for [Edge TPU](https://cloud.google.com/edge-tpu/) devices. * `tf-saved-model` A tensorflow model in SavedModel format. * `tf-js` A [TensorFlow.js](https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript. * `core-ml` Used for iOS mobile devices. * `custom-trained` A Model that was uploaded or trained by custom code.
},
],
"supportedInputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are: * `jsonl` The JSON Lines format, where each instance is a single line. Uses GcsSource. * `csv` The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource. * `tf-record` The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource. * `tf-record-gzip` Similar to `tf-record`, but the file is gzipped. Uses GcsSource. * `bigquery` Each instance is a single row in BigQuery. Uses BigQuerySource. * `file-list` Each line of the file is the location of an instance to process, uses `gcs_source` field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"supportedOutputStorageFormats": [ # Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are: * `jsonl` The JSON Lines format, where each prediction is a single line. Uses GcsDestination. * `csv` The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination. * `bigquery` Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
"A String",
],
"trainingPipeline": "A String", # Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
"updateTime": "A String", # Output only. Timestamp when this Model was most recently updated.
"versionAliases": [ # User provided version aliases so that a model version can be referenced via alias (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_alias}` instead of auto-generated version id (i.e. `projects/{project}/locations/{location}/models/{model_id}@{version_id})`. The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
"A String",
],
"versionCreateTime": "A String", # Output only. Timestamp when this version was created.
"versionDescription": "A String", # The description of this version.
"versionId": "A String", # Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
"versionUpdateTime": "A String", # Output only. Timestamp when this version was most recently updated.
},
"modelId": "A String", # Optional. The ID to use for the uploaded Model, which will become the final component of the model resource name. This value may be up to 63 characters, and valid characters are `[a-z0-9_-]`. The first character cannot be a number or hyphen.
"parentModel": "A String", # Optional. The resource name of the model into which to upload the version. Only specify this field when uploading a new version.
"serviceAccount": "A String", # Optional. The user-provided custom service account to use to do the model upload. If empty, [Vertex AI Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used to access resources needed to upload the model. This account must belong to the target project where the model is uploaded to, i.e., the project specified in the `parent` field of this request and have necessary read permissions (to Google Cloud Storage, Artifact Registry, etc.).
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}