chore: Update discovery artifacts (#1195)
* chore(accesscontextmanager): update the api
* chore(adexchangebuyer2): update the api
* chore(admin): update the api
* chore(alertcenter): update the api
* chore(analyticsadmin): update the api
* chore(analyticsdata): update the api
* chore(androidmanagement): update the api
* chore(apigateway): update the api
* chore(apigee): update the api
* chore(appengine): update the api
* chore(area120tables): update the api
* chore(artifactregistry): update the api
* chore(bigquery): update the api
* chore(bigqueryconnection): update the api
* chore(bigqueryreservation): update the api
* chore(billingbudgets): update the api
* chore(binaryauthorization): update the api
* chore(blogger): update the api
* chore(calendar): update the api
* chore(chat): update the api
* chore(cloudasset): update the api
* chore(cloudbuild): update the api
* chore(cloudfunctions): update the api
* chore(cloudidentity): update the api
* chore(cloudkms): update the api
* chore(cloudresourcemanager): update the api
* chore(cloudscheduler): update the api
* chore(cloudtasks): update the api
* chore(composer): update the api
* chore(compute): update the api
* chore(container): update the api
* chore(containeranalysis): update the api
* chore(content): update the api
* chore(datacatalog): update the api
* chore(dataflow): update the api
* chore(datafusion): update the api
* chore(datamigration): update the api
* chore(dataproc): update the api
* chore(deploymentmanager): update the api
* chore(dialogflow): update the api
* chore(displayvideo): update the api
* chore(dlp): update the api
* chore(dns): update the api
* chore(documentai): update the api
* chore(eventarc): update the api
* chore(file): update the api
* chore(firebaseml): update the api
* chore(games): update the api
* chore(gameservices): update the api
* chore(genomics): update the api
* chore(healthcare): update the api
* chore(homegraph): update the api
* chore(iam): update the api
* chore(iap): update the api
* chore(jobs): update the api
* chore(lifesciences): update the api
* chore(localservices): update the api
* chore(managedidentities): update the api
* chore(manufacturers): update the api
* chore(memcache): update the api
* chore(ml): update the api
* chore(monitoring): update the api
* chore(notebooks): update the api
* chore(osconfig): update the api
* chore(pagespeedonline): update the api
* chore(people): update the api
* chore(privateca): update the api
* chore(prod_tt_sasportal): update the api
* chore(pubsub): update the api
* chore(pubsublite): update the api
* chore(recommender): update the api
* chore(remotebuildexecution): update the api
* chore(reseller): update the api
* chore(run): update the api
* chore(safebrowsing): update the api
* chore(sasportal): update the api
* chore(searchconsole): update the api
* chore(secretmanager): update the api
* chore(securitycenter): update the api
* chore(serviceconsumermanagement): update the api
* chore(servicecontrol): update the api
* chore(servicenetworking): update the api
* chore(serviceusage): update the api
* chore(sheets): update the api
* chore(slides): update the api
* chore(spanner): update the api
* chore(speech): update the api
* chore(sqladmin): update the api
* chore(storage): update the api
* chore(storagetransfer): update the api
* chore(sts): update the api
* chore(tagmanager): update the api
* chore(testing): update the api
* chore(toolresults): update the api
* chore(transcoder): update the api
* chore(vectortile): update the api
* chore(videointelligence): update the api
* chore(vision): update the api
* chore(webmasters): update the api
* chore(workflowexecutions): update the api
* chore(youtube): update the api
diff --git a/docs/dyn/ml_v1.projects.models.versions.html b/docs/dyn/ml_v1.projects.models.versions.html
index 3bdc038..fc6c0e2 100644
--- a/docs/dyn/ml_v1.projects.models.versions.html
+++ b/docs/dyn/ml_v1.projects.models.versions.html
@@ -118,7 +118,7 @@
"count": "A String", # The number of accelerators to attach to each machine running the job.
"type": "A String", # The type of accelerator to use.
},
- "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use specify `manual_scaling`.
+ "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
"maxNodes": 42, # The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
"metrics": [ # MetricSpec contains the specifications to use to calculate the desired nodes count.
{ # MetricSpec contains the specifications to use to calculate the desired nodes count when autoscaling is enabled.
@@ -126,7 +126,7 @@
"target": 42, # Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
},
],
- "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use ManualScaling. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
+ "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
},
"container": { # Specification of a custom container for serving predictions. This message is a subset of the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core). # Optional. Specifies a custom container to use for serving predictions. If you specify this field, then `machineType` is required. If you specify this field, then `deploymentUri` is optional. If you specify this field, then you must not specify `runtimeVersion`, `packageUris`, `framework`, `pythonVersion`, or `predictionClass`.
"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 `commmand` 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 AI Platform Prediction](/ai-platform/prediction/docs/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/v1.18/#container-v1-core).
@@ -169,8 +169,10 @@
"labels": { # Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels.
"a_key": "A String",
},
+ "lastMigrationModelId": "A String", # Output only. The [AI Platform (Unified) `Model`](https://cloud.google.com/ai-platform-unified/docs/reference/rest/v1beta1/projects.locations.models) ID for the last [model migration](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
+ "lastMigrationTime": "A String", # Output only. The last time this version was successfully [migrated to AI Platform (Unified)](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
"lastUseTime": "A String", # Output only. The time the version was last used for prediction.
- "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. If this field is not specified, it defaults to `mls1-c1-m2`. Online prediction supports the following machine types: * `mls1-c1-m2` * `mls1-c4-m2` * `n1-standard-2` * `n1-standard-4` * `n1-standard-8` * `n1-standard-16` * `n1-standard-32` * `n1-highmem-2` * `n1-highmem-4` * `n1-highmem-8` * `n1-highmem-16` * `n1-highmem-32` * `n1-highcpu-2` * `n1-highcpu-4` * `n1-highcpu-8` * `n1-highcpu-16` * `n1-highcpu-32` `mls1-c4-m2` is in beta. All other machine types are generally available. Learn more about the [differences between machine types](/ml-engine/docs/machine-types-online-prediction).
+ "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read [Choosing a machine type for online prediction](/ai-platform/prediction/docs/machine-types-online-prediction). If this field is not specified and you are using a [regional endpoint](/ai-platform/prediction/docs/regional-endpoints), then the machine type defaults to `n1-standard-2`. If this field is not specified and you are using the global endpoint (`ml.googleapis.com`), then the machine type defaults to `mls1-c1-m2`.
"manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the model. You should generally use `auto_scaling` with an appropriate `min_nodes` instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
"nodes": 42, # The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to `nodes` * number of hours since last billing cycle plus the cost for each prediction performed.
},
@@ -185,8 +187,8 @@
"samplingPercentage": 3.14, # Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter `0.1`. The sampling window is the lifetime of the model version. Defaults to 0.
},
"routes": { # Specifies HTTP paths served by a custom container. AI Platform Prediction sends requests to these paths on the container; the custom container must run an HTTP server that responds to these requests with appropriate responses. Read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements) for details on how to create your container image to meet these requirements. # Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the `container` field. If you specify the `container` field and do not specify this field, it defaults to the following: ```json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } ``` See RouteMap for more details about these default values.
- "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the following URL on the container: localhost:PORT/bar PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
- "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the following URL on the container: localhost:PORT/foo PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the `/foo` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
},
"runtimeVersion": "A String", # Required. The AI Platform runtime version to use for this deployment. For more information, see the [runtime version list](/ml-engine/docs/runtime-version-list) and [how to manage runtime versions](/ml-engine/docs/versioning).
"serviceAccount": "A String", # Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the `containerSpec` or the `predictionClass` field. Learn more about [using a custom service account](/ai-platform/prediction/docs/custom-service-account).
@@ -276,7 +278,7 @@
"count": "A String", # The number of accelerators to attach to each machine running the job.
"type": "A String", # The type of accelerator to use.
},
- "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use specify `manual_scaling`.
+ "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
"maxNodes": 42, # The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
"metrics": [ # MetricSpec contains the specifications to use to calculate the desired nodes count.
{ # MetricSpec contains the specifications to use to calculate the desired nodes count when autoscaling is enabled.
@@ -284,7 +286,7 @@
"target": 42, # Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
},
],
- "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use ManualScaling. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
+ "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
},
"container": { # Specification of a custom container for serving predictions. This message is a subset of the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core). # Optional. Specifies a custom container to use for serving predictions. If you specify this field, then `machineType` is required. If you specify this field, then `deploymentUri` is optional. If you specify this field, then you must not specify `runtimeVersion`, `packageUris`, `framework`, `pythonVersion`, or `predictionClass`.
"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 `commmand` 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 AI Platform Prediction](/ai-platform/prediction/docs/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/v1.18/#container-v1-core).
@@ -327,8 +329,10 @@
"labels": { # Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels.
"a_key": "A String",
},
+ "lastMigrationModelId": "A String", # Output only. The [AI Platform (Unified) `Model`](https://cloud.google.com/ai-platform-unified/docs/reference/rest/v1beta1/projects.locations.models) ID for the last [model migration](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
+ "lastMigrationTime": "A String", # Output only. The last time this version was successfully [migrated to AI Platform (Unified)](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
"lastUseTime": "A String", # Output only. The time the version was last used for prediction.
- "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. If this field is not specified, it defaults to `mls1-c1-m2`. Online prediction supports the following machine types: * `mls1-c1-m2` * `mls1-c4-m2` * `n1-standard-2` * `n1-standard-4` * `n1-standard-8` * `n1-standard-16` * `n1-standard-32` * `n1-highmem-2` * `n1-highmem-4` * `n1-highmem-8` * `n1-highmem-16` * `n1-highmem-32` * `n1-highcpu-2` * `n1-highcpu-4` * `n1-highcpu-8` * `n1-highcpu-16` * `n1-highcpu-32` `mls1-c4-m2` is in beta. All other machine types are generally available. Learn more about the [differences between machine types](/ml-engine/docs/machine-types-online-prediction).
+ "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read [Choosing a machine type for online prediction](/ai-platform/prediction/docs/machine-types-online-prediction). If this field is not specified and you are using a [regional endpoint](/ai-platform/prediction/docs/regional-endpoints), then the machine type defaults to `n1-standard-2`. If this field is not specified and you are using the global endpoint (`ml.googleapis.com`), then the machine type defaults to `mls1-c1-m2`.
"manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the model. You should generally use `auto_scaling` with an appropriate `min_nodes` instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
"nodes": 42, # The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to `nodes` * number of hours since last billing cycle plus the cost for each prediction performed.
},
@@ -343,8 +347,8 @@
"samplingPercentage": 3.14, # Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter `0.1`. The sampling window is the lifetime of the model version. Defaults to 0.
},
"routes": { # Specifies HTTP paths served by a custom container. AI Platform Prediction sends requests to these paths on the container; the custom container must run an HTTP server that responds to these requests with appropriate responses. Read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements) for details on how to create your container image to meet these requirements. # Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the `container` field. If you specify the `container` field and do not specify this field, it defaults to the following: ```json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } ``` See RouteMap for more details about these default values.
- "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the following URL on the container: localhost:PORT/bar PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
- "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the following URL on the container: localhost:PORT/foo PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the `/foo` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
},
"runtimeVersion": "A String", # Required. The AI Platform runtime version to use for this deployment. For more information, see the [runtime version list](/ml-engine/docs/runtime-version-list) and [how to manage runtime versions](/ml-engine/docs/versioning).
"serviceAccount": "A String", # Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the `containerSpec` or the `predictionClass` field. Learn more about [using a custom service account](/ai-platform/prediction/docs/custom-service-account).
@@ -377,7 +381,7 @@
"count": "A String", # The number of accelerators to attach to each machine running the job.
"type": "A String", # The type of accelerator to use.
},
- "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use specify `manual_scaling`.
+ "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
"maxNodes": 42, # The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
"metrics": [ # MetricSpec contains the specifications to use to calculate the desired nodes count.
{ # MetricSpec contains the specifications to use to calculate the desired nodes count when autoscaling is enabled.
@@ -385,7 +389,7 @@
"target": 42, # Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
},
],
- "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use ManualScaling. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
+ "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
},
"container": { # Specification of a custom container for serving predictions. This message is a subset of the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core). # Optional. Specifies a custom container to use for serving predictions. If you specify this field, then `machineType` is required. If you specify this field, then `deploymentUri` is optional. If you specify this field, then you must not specify `runtimeVersion`, `packageUris`, `framework`, `pythonVersion`, or `predictionClass`.
"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 `commmand` 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 AI Platform Prediction](/ai-platform/prediction/docs/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/v1.18/#container-v1-core).
@@ -428,8 +432,10 @@
"labels": { # Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels.
"a_key": "A String",
},
+ "lastMigrationModelId": "A String", # Output only. The [AI Platform (Unified) `Model`](https://cloud.google.com/ai-platform-unified/docs/reference/rest/v1beta1/projects.locations.models) ID for the last [model migration](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
+ "lastMigrationTime": "A String", # Output only. The last time this version was successfully [migrated to AI Platform (Unified)](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
"lastUseTime": "A String", # Output only. The time the version was last used for prediction.
- "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. If this field is not specified, it defaults to `mls1-c1-m2`. Online prediction supports the following machine types: * `mls1-c1-m2` * `mls1-c4-m2` * `n1-standard-2` * `n1-standard-4` * `n1-standard-8` * `n1-standard-16` * `n1-standard-32` * `n1-highmem-2` * `n1-highmem-4` * `n1-highmem-8` * `n1-highmem-16` * `n1-highmem-32` * `n1-highcpu-2` * `n1-highcpu-4` * `n1-highcpu-8` * `n1-highcpu-16` * `n1-highcpu-32` `mls1-c4-m2` is in beta. All other machine types are generally available. Learn more about the [differences between machine types](/ml-engine/docs/machine-types-online-prediction).
+ "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read [Choosing a machine type for online prediction](/ai-platform/prediction/docs/machine-types-online-prediction). If this field is not specified and you are using a [regional endpoint](/ai-platform/prediction/docs/regional-endpoints), then the machine type defaults to `n1-standard-2`. If this field is not specified and you are using the global endpoint (`ml.googleapis.com`), then the machine type defaults to `mls1-c1-m2`.
"manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the model. You should generally use `auto_scaling` with an appropriate `min_nodes` instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
"nodes": 42, # The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to `nodes` * number of hours since last billing cycle plus the cost for each prediction performed.
},
@@ -444,8 +450,8 @@
"samplingPercentage": 3.14, # Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter `0.1`. The sampling window is the lifetime of the model version. Defaults to 0.
},
"routes": { # Specifies HTTP paths served by a custom container. AI Platform Prediction sends requests to these paths on the container; the custom container must run an HTTP server that responds to these requests with appropriate responses. Read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements) for details on how to create your container image to meet these requirements. # Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the `container` field. If you specify the `container` field and do not specify this field, it defaults to the following: ```json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } ``` See RouteMap for more details about these default values.
- "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the following URL on the container: localhost:PORT/bar PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
- "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the following URL on the container: localhost:PORT/foo PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the `/foo` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
},
"runtimeVersion": "A String", # Required. The AI Platform runtime version to use for this deployment. For more information, see the [runtime version list](/ml-engine/docs/runtime-version-list) and [how to manage runtime versions](/ml-engine/docs/versioning).
"serviceAccount": "A String", # Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the `containerSpec` or the `predictionClass` field. Learn more about [using a custom service account](/ai-platform/prediction/docs/custom-service-account).
@@ -483,7 +489,7 @@
"count": "A String", # The number of accelerators to attach to each machine running the job.
"type": "A String", # The type of accelerator to use.
},
- "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use specify `manual_scaling`.
+ "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
"maxNodes": 42, # The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
"metrics": [ # MetricSpec contains the specifications to use to calculate the desired nodes count.
{ # MetricSpec contains the specifications to use to calculate the desired nodes count when autoscaling is enabled.
@@ -491,7 +497,7 @@
"target": 42, # Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
},
],
- "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use ManualScaling. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
+ "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
},
"container": { # Specification of a custom container for serving predictions. This message is a subset of the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core). # Optional. Specifies a custom container to use for serving predictions. If you specify this field, then `machineType` is required. If you specify this field, then `deploymentUri` is optional. If you specify this field, then you must not specify `runtimeVersion`, `packageUris`, `framework`, `pythonVersion`, or `predictionClass`.
"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 `commmand` 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 AI Platform Prediction](/ai-platform/prediction/docs/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/v1.18/#container-v1-core).
@@ -534,8 +540,10 @@
"labels": { # Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels.
"a_key": "A String",
},
+ "lastMigrationModelId": "A String", # Output only. The [AI Platform (Unified) `Model`](https://cloud.google.com/ai-platform-unified/docs/reference/rest/v1beta1/projects.locations.models) ID for the last [model migration](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
+ "lastMigrationTime": "A String", # Output only. The last time this version was successfully [migrated to AI Platform (Unified)](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
"lastUseTime": "A String", # Output only. The time the version was last used for prediction.
- "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. If this field is not specified, it defaults to `mls1-c1-m2`. Online prediction supports the following machine types: * `mls1-c1-m2` * `mls1-c4-m2` * `n1-standard-2` * `n1-standard-4` * `n1-standard-8` * `n1-standard-16` * `n1-standard-32` * `n1-highmem-2` * `n1-highmem-4` * `n1-highmem-8` * `n1-highmem-16` * `n1-highmem-32` * `n1-highcpu-2` * `n1-highcpu-4` * `n1-highcpu-8` * `n1-highcpu-16` * `n1-highcpu-32` `mls1-c4-m2` is in beta. All other machine types are generally available. Learn more about the [differences between machine types](/ml-engine/docs/machine-types-online-prediction).
+ "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read [Choosing a machine type for online prediction](/ai-platform/prediction/docs/machine-types-online-prediction). If this field is not specified and you are using a [regional endpoint](/ai-platform/prediction/docs/regional-endpoints), then the machine type defaults to `n1-standard-2`. If this field is not specified and you are using the global endpoint (`ml.googleapis.com`), then the machine type defaults to `mls1-c1-m2`.
"manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the model. You should generally use `auto_scaling` with an appropriate `min_nodes` instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
"nodes": 42, # The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to `nodes` * number of hours since last billing cycle plus the cost for each prediction performed.
},
@@ -550,8 +558,8 @@
"samplingPercentage": 3.14, # Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter `0.1`. The sampling window is the lifetime of the model version. Defaults to 0.
},
"routes": { # Specifies HTTP paths served by a custom container. AI Platform Prediction sends requests to these paths on the container; the custom container must run an HTTP server that responds to these requests with appropriate responses. Read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements) for details on how to create your container image to meet these requirements. # Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the `container` field. If you specify the `container` field and do not specify this field, it defaults to the following: ```json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } ``` See RouteMap for more details about these default values.
- "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the following URL on the container: localhost:PORT/bar PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
- "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the following URL on the container: localhost:PORT/foo PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the `/foo` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
},
"runtimeVersion": "A String", # Required. The AI Platform runtime version to use for this deployment. For more information, see the [runtime version list](/ml-engine/docs/runtime-version-list) and [how to manage runtime versions](/ml-engine/docs/versioning).
"serviceAccount": "A String", # Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the `containerSpec` or the `predictionClass` field. Learn more about [using a custom service account](/ai-platform/prediction/docs/custom-service-account).
@@ -613,7 +621,7 @@
"count": "A String", # The number of accelerators to attach to each machine running the job.
"type": "A String", # The type of accelerator to use.
},
- "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use specify `manual_scaling`.
+ "autoScaling": { # Options for automatically scaling a model. # Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
"maxNodes": 42, # The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
"metrics": [ # MetricSpec contains the specifications to use to calculate the desired nodes count.
{ # MetricSpec contains the specifications to use to calculate the desired nodes count when autoscaling is enabled.
@@ -621,7 +629,7 @@
"target": 42, # Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
},
],
- "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. Note that you cannot use AutoScaling if your version uses [GPUs](#Version.FIELDS.accelerator_config). Instead, you must use ManualScaling. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
+ "minNodes": 42, # Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least `rate` * `min_nodes` * number of hours since last billing cycle, where `rate` is the cost per node-hour as documented in the [pricing guide](/ml-engine/docs/pricing), even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least `min_nodes`. You will be charged for the time in which additional nodes are used. If `min_nodes` is not specified and AutoScaling is used with a [legacy (MLS1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If `min_nodes` is not specified and AutoScaling is used with a [Compute Engine (N1) machine type](/ml-engine/docs/machine-types-online-prediction), `min_nodes` defaults to 1. `min_nodes` must be at least 1 for use with a Compute Engine machine type. You can set `min_nodes` when creating the model version, and you can also update `min_nodes` for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects/*/models/*/versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
},
"container": { # Specification of a custom container for serving predictions. This message is a subset of the [Kubernetes Container v1 core specification](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core). # Optional. Specifies a custom container to use for serving predictions. If you specify this field, then `machineType` is required. If you specify this field, then `deploymentUri` is optional. If you specify this field, then you must not specify `runtimeVersion`, `packageUris`, `framework`, `pythonVersion`, or `predictionClass`.
"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 `commmand` 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 AI Platform Prediction](/ai-platform/prediction/docs/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/v1.18/#container-v1-core).
@@ -664,8 +672,10 @@
"labels": { # Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels.
"a_key": "A String",
},
+ "lastMigrationModelId": "A String", # Output only. The [AI Platform (Unified) `Model`](https://cloud.google.com/ai-platform-unified/docs/reference/rest/v1beta1/projects.locations.models) ID for the last [model migration](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
+ "lastMigrationTime": "A String", # Output only. The last time this version was successfully [migrated to AI Platform (Unified)](https://cloud.google.com/ai-platform-unified/docs/start/migrating-to-ai-platform-unified).
"lastUseTime": "A String", # Output only. The time the version was last used for prediction.
- "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. If this field is not specified, it defaults to `mls1-c1-m2`. Online prediction supports the following machine types: * `mls1-c1-m2` * `mls1-c4-m2` * `n1-standard-2` * `n1-standard-4` * `n1-standard-8` * `n1-standard-16` * `n1-standard-32` * `n1-highmem-2` * `n1-highmem-4` * `n1-highmem-8` * `n1-highmem-16` * `n1-highmem-32` * `n1-highcpu-2` * `n1-highcpu-4` * `n1-highcpu-8` * `n1-highcpu-16` * `n1-highcpu-32` `mls1-c4-m2` is in beta. All other machine types are generally available. Learn more about the [differences between machine types](/ml-engine/docs/machine-types-online-prediction).
+ "machineType": "A String", # Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read [Choosing a machine type for online prediction](/ai-platform/prediction/docs/machine-types-online-prediction). If this field is not specified and you are using a [regional endpoint](/ai-platform/prediction/docs/regional-endpoints), then the machine type defaults to `n1-standard-2`. If this field is not specified and you are using the global endpoint (`ml.googleapis.com`), then the machine type defaults to `mls1-c1-m2`.
"manualScaling": { # Options for manually scaling a model. # Manually select the number of nodes to use for serving the model. You should generally use `auto_scaling` with an appropriate `min_nodes` instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
"nodes": 42, # The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to `nodes` * number of hours since last billing cycle plus the cost for each prediction performed.
},
@@ -680,8 +690,8 @@
"samplingPercentage": 3.14, # Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter `0.1`. The sampling window is the lifetime of the model version. Defaults to 0.
},
"routes": { # Specifies HTTP paths served by a custom container. AI Platform Prediction sends requests to these paths on the container; the custom container must run an HTTP server that responds to these requests with appropriate responses. Read [Custom container requirements](/ai-platform/prediction/docs/custom-container-requirements) for details on how to create your container image to meet these requirements. # Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the `container` field. If you specify the `container` field and do not specify this field, it defaults to the following: ```json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } ``` See RouteMap for more details about these default values.
- "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the following URL on the container: localhost:PORT/bar PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
- "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the following URL on the container: localhost:PORT/foo PORT refers to the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "health": "A String", # HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about [health checks](/ai-platform/prediction/docs/custom-container-requirements#checks). For example, if you set this field to `/bar`, then AI Platform Prediction intermittently sends a GET request to the `/bar` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
+ "predict": "A String", # HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to `/foo`, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the `/foo` path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
},
"runtimeVersion": "A String", # Required. The AI Platform runtime version to use for this deployment. For more information, see the [runtime version list](/ml-engine/docs/runtime-version-list) and [how to manage runtime versions](/ml-engine/docs/versioning).
"serviceAccount": "A String", # Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the `containerSpec` or the `predictionClass` field. Learn more about [using a custom service account](/ai-platform/prediction/docs/custom-service-account).