From 401ef21a843cd2dc126712165e812956a0c93345 Mon Sep 17 00:00:00 2001 From: Yoshi Automation Date: Tue, 9 Apr 2024 07:09:31 +0000 Subject: [PATCH] feat(aiplatform): update the api #### aiplatform:v1 The following keys were deleted: - schemas.GoogleCloudAiplatformV1GroundingMetadata.properties.retrievalQueries (Total Keys: 2) - schemas.GoogleCloudAiplatformV1PublisherModelCallToAction.properties.multiDeployVertex.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex (Total Keys: 4) - schemas.GoogleCloudAiplatformV1RayMetricSpec (Total Keys: 3) - schemas.GoogleCloudAiplatformV1RaySpec.properties.headNodeResourcePoolId.type (Total Keys: 1) - schemas.GoogleCloudAiplatformV1RaySpec.properties.imageUri.type (Total Keys: 1) - schemas.GoogleCloudAiplatformV1RaySpec.properties.rayMetricSpec.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1RaySpec.properties.resourcePoolImages (Total Keys: 2) - schemas.GoogleCloudAiplatformV1ResourceRuntime.properties.accessUris (Total Keys: 3) - schemas.GoogleCloudAiplatformV1ResourceRuntime.properties.notebookRuntimeTemplate (Total Keys: 2) The following keys were added: - resources.projects.resources.locations.resources.tuningJobs.methods.cancel (Total Keys: 12) - resources.projects.resources.locations.resources.tuningJobs.methods.create (Total Keys: 12) - resources.projects.resources.locations.resources.tuningJobs.methods.get (Total Keys: 11) - resources.projects.resources.locations.resources.tuningJobs.methods.list (Total Keys: 18) - schemas.CloudAiNlLlmProtoServiceMessageMetadata.properties.factualityDebugMetadata.$ref (Total Keys: 1) - schemas.CloudAiNlLlmProtoServiceRaiResult.properties.translationRequestInfos (Total Keys: 2) - schemas.GoogleCloudAiplatformV1CancelTuningJobRequest (Total Keys: 2) - schemas.GoogleCloudAiplatformV1GenerationConfig.properties.responseMimeType.type (Total Keys: 1) - schemas.GoogleCloudAiplatformV1ListTuningJobsResponse (Total Keys: 5) - schemas.GoogleCloudAiplatformV1SchemaModelevaluationMetricsPairwiseTextGenerationEvaluationMetrics (Total Keys: 28) - schemas.GoogleCloudAiplatformV1SupervisedHyperParameters (Total Keys: 7) - schemas.GoogleCloudAiplatformV1SupervisedTuningDataStats (Total Keys: 23) - schemas.GoogleCloudAiplatformV1SupervisedTuningDatasetDistribution (Total Keys: 37) - schemas.GoogleCloudAiplatformV1SupervisedTuningSpec (Total Keys: 5) - schemas.GoogleCloudAiplatformV1TunedModel (Total Keys: 6) - schemas.GoogleCloudAiplatformV1TuningDataStats (Total Keys: 3) - schemas.GoogleCloudAiplatformV1TuningJob (Total Keys: 31) - schemas.LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata (Total Keys: 7) - schemas.LearningGenaiRootTranslationRequestInfo (Total Keys: 6) #### aiplatform:v1beta1 The following keys were deleted: - resources.media.methods.upload (Total Keys: 16) - resources.projects.resources.locations.methods.retrieveContexts (Total Keys: 12) - resources.projects.resources.locations.resources.ragCorpora.methods.create (Total Keys: 12) - resources.projects.resources.locations.resources.ragCorpora.methods.delete (Total Keys: 13) - resources.projects.resources.locations.resources.ragCorpora.methods.get (Total Keys: 11) - resources.projects.resources.locations.resources.ragCorpora.methods.list (Total Keys: 16) - resources.projects.resources.locations.resources.ragCorpora.resources.ragFiles.methods.delete (Total Keys: 11) - resources.projects.resources.locations.resources.ragCorpora.resources.ragFiles.methods.get (Total Keys: 11) - resources.projects.resources.locations.resources.ragCorpora.resources.ragFiles.methods.import (Total Keys: 12) - resources.projects.resources.locations.resources.ragCorpora.resources.ragFiles.methods.list (Total Keys: 16) - schemas.GoogleCloudAiplatformV1beta1DirectUploadSource (Total Keys: 2) - schemas.GoogleCloudAiplatformV1beta1EvaluateInstancesRequest.properties.ragContextRecallInput.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1EvaluateInstancesRequest.properties.responseRecallInput.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1EvaluateInstancesResponse.properties.ragContextRecallResult.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1EvaluateInstancesResponse.properties.responseRecallResult.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1GoogleDriveSource (Total Keys: 8) - schemas.GoogleCloudAiplatformV1beta1ImportRagFilesConfig (Total Keys: 5) - schemas.GoogleCloudAiplatformV1beta1ImportRagFilesRequest (Total Keys: 3) - schemas.GoogleCloudAiplatformV1beta1ListRagCorporaResponse (Total Keys: 5) - schemas.GoogleCloudAiplatformV1beta1ListRagFilesResponse (Total Keys: 5) - schemas.GoogleCloudAiplatformV1beta1PublisherModelCallToAction.properties.multiDeployVertex.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployVertex (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1RagContextRecallInput (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1RagContextRecallInstance (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1RagContextRecallResult (Total Keys: 10) - schemas.GoogleCloudAiplatformV1beta1RagContextRecallSpec (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1RagContexts (Total Keys: 10) - schemas.GoogleCloudAiplatformV1beta1RagCorpus (Total Keys: 11) - schemas.GoogleCloudAiplatformV1beta1RagFile (Total Keys: 28) - schemas.GoogleCloudAiplatformV1beta1RagQuery (Total Keys: 5) - schemas.GoogleCloudAiplatformV1beta1ResponseRecallInput (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1ResponseRecallInstance (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1ResponseRecallResult (Total Keys: 10) - schemas.GoogleCloudAiplatformV1beta1ResponseRecallSpec (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1RetrieveContextsRequest (Total Keys: 8) - schemas.GoogleCloudAiplatformV1beta1RetrieveContextsResponse (Total Keys: 3) - schemas.GoogleCloudAiplatformV1beta1UploadRagFileConfig (Total Keys: 3) - schemas.GoogleCloudAiplatformV1beta1UploadRagFileRequest (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1UploadRagFileResponse (Total Keys: 4) The following keys were added: - resources.projects.methods.getCacheConfig (Total Keys: 11) - resources.projects.methods.updateCacheConfig (Total Keys: 12) - resources.projects.resources.locations.resources.endpoints.resources.chat.methods.completions (Total Keys: 12) - schemas.CloudAiNlLlmProtoServiceMessageMetadata.properties.factualityDebugMetadata.$ref (Total Keys: 1) - schemas.CloudAiNlLlmProtoServiceRaiResult.properties.translationRequestInfos (Total Keys: 2) - schemas.GoogleCloudAiplatformV1beta1CacheConfig (Total Keys: 4) - schemas.GoogleCloudAiplatformV1beta1Extension.properties.privateServiceConnectConfig.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1Extension.properties.runtimeConfig.$ref (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1ExtensionPrivateServiceConnectConfig (Total Keys: 3) - schemas.GoogleCloudAiplatformV1beta1GenerationConfig.properties.responseMimeType.type (Total Keys: 1) - schemas.GoogleCloudAiplatformV1beta1RuntimeConfig (Total Keys: 13) - schemas.GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsPairwiseTextGenerationEvaluationMetrics (Total Keys: 28) - schemas.LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata (Total Keys: 7) - schemas.LearningGenaiRootTranslationRequestInfo (Total Keys: 6) --- ...tform_v1.projects.locations.endpoints.html | 8 +- ..._v1.projects.locations.indexEndpoints.html | 2 +- ...rojects.locations.persistentResources.html | 56 +- ....projects.locations.publishers.models.html | 8 +- ...form_v1.projects.locations.tuningJobs.html | 621 +++++++++ docs/dyn/aiplatform_v1.publishers.models.html | 81 -- docs/dyn/aiplatform_v1beta1.html | 5 - docs/dyn/aiplatform_v1beta1.projects.html | 69 + ...ta1.projects.locations.endpoints.chat.html | 127 ++ ..._v1beta1.projects.locations.endpoints.html | 7 + ...v1beta1.projects.locations.extensions.html | 75 ++ ...aiplatform_v1beta1.projects.locations.html | 77 +- ...ta1.projects.locations.indexEndpoints.html | 2 +- ...rojects.locations.persistentResources.html | 8 +- ....projects.locations.publishers.models.html | 2 + ...v1beta1.projects.locations.ragCorpora.html | 164 --- ...rojects.locations.ragCorpora.ragFiles.html | 211 --- .../aiplatform_v1beta1.publishers.models.html | 162 --- .../documents/aiplatform.v1.json | 749 +++++++++-- .../documents/aiplatform.v1beta1.json | 1187 +++++------------ 20 files changed, 1931 insertions(+), 1690 deletions(-) create mode 100644 docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.chat.html diff --git a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html index 088b910955f..f5573198ea4 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html +++ b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html @@ -1098,6 +1098,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], @@ -1269,9 +1270,6 @@

Method Details

}, }, ], - "retrievalQueries": [ # Optional. Queries executed by the retrieval tools. - "A String", - ], "webSearchQueries": [ # Optional. Web search queries for the following-up web search. "A String", ], @@ -2589,6 +2587,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], @@ -2760,9 +2759,6 @@

Method Details

}, }, ], - "retrievalQueries": [ # Optional. Queries executed by the retrieval tools. - "A String", - ], "webSearchQueries": [ # Optional. Web search queries for the following-up web search. "A String", ], diff --git a/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html b/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html index 44d2d5368b8..9c9df7d2c88 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html +++ b/docs/dyn/aiplatform_v1.projects.locations.indexEndpoints.html @@ -377,7 +377,7 @@

Method Details

body: object, The request body. The object takes the form of: -{ # LINT.IfChange The request message for MatchService.FindNeighbors. +{ # The request message for MatchService.FindNeighbors. "deployedIndexId": "A String", # The ID of the DeployedIndex that will serve the request. This request is sent to a specific IndexEndpoint, as per the IndexEndpoint.network. That IndexEndpoint also has IndexEndpoint.deployed_indexes, and each such index has a DeployedIndex.id field. The value of the field below must equal one of the DeployedIndex.id fields of the IndexEndpoint that is being called for this request. "queries": [ # The list of queries. { # A query to find a number of the nearest neighbors (most similar vectors) of a vector. diff --git a/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html b/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html index 154cd5e1ccb..6af3e0a394d 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html +++ b/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html @@ -163,25 +163,13 @@

Method Details

}, ], "resourceRuntime": { # Persistent Cluster runtime information as output # Output only. Runtime information of the Persistent Resource. - "accessUris": { # Output only. URIs for user to connect to the Cluster. Example: { "RAY_HEAD_NODE_INTERNAL_IP": "head-node-IP:10001" "RAY_DASHBOARD_URI": "ray-dashboard-address:8888" } - "a_key": "A String", - }, - "notebookRuntimeTemplate": "A String", # Output only. The resource name of NotebookRuntimeTemplate for the RoV Persistent Cluster The NotebokRuntimeTemplate is created in the same VPC (if set), and with the same Ray and Python version as the Persistent Cluster. Example: "projects/1000/locations/us-central1/notebookRuntimeTemplates/abc123" }, "resourceRuntimeSpec": { # Configuration for the runtime on a PersistentResource instance, including but not limited to: * Service accounts used to run the workloads. * Whether to make it a dedicated Ray Cluster. # Optional. Persistent Resource runtime spec. For example, used for Ray cluster configuration. "raySpec": { # Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes. # Optional. Ray cluster configuration. Required when creating a dedicated RayCluster on the PersistentResource. - "headNodeResourcePoolId": "A String", # Optional. This will be used to indicate which resource pool will serve as the Ray head node(the first node within that pool). Will use the machine from the first workerpool as the head node by default if this field isn't set. - "imageUri": "A String", # Optional. Default image for user to choose a preferred ML framework (for example, TensorFlow or Pytorch) by choosing from [Vertex prebuilt images](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). Either this or the resource_pool_images is required. Use this field if you need all the resource pools to have the same Ray image. Otherwise, use the {@code resource_pool_images} field. - "rayMetricSpec": { # Configuration for the Ray metrics. # Optional. Ray metrics configurations. - "disabled": True or False, # Optional. Flag to disable the Ray metrics collection. - }, - "resourcePoolImages": { # Optional. Required if image_uri isn't set. A map of resource_pool_id to prebuild Ray image if user need to use different images for different head/worker pools. This map needs to cover all the resource pool ids. Example: { "ray_head_node_pool": "head image" "ray_worker_node_pool1": "worker image" "ray_worker_node_pool2": "another worker image" } - "a_key": "A String", - }, }, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. @@ -313,25 +301,13 @@

Method Details

}, ], "resourceRuntime": { # Persistent Cluster runtime information as output # Output only. Runtime information of the Persistent Resource. - "accessUris": { # Output only. URIs for user to connect to the Cluster. Example: { "RAY_HEAD_NODE_INTERNAL_IP": "head-node-IP:10001" "RAY_DASHBOARD_URI": "ray-dashboard-address:8888" } - "a_key": "A String", - }, - "notebookRuntimeTemplate": "A String", # Output only. The resource name of NotebookRuntimeTemplate for the RoV Persistent Cluster The NotebokRuntimeTemplate is created in the same VPC (if set), and with the same Ray and Python version as the Persistent Cluster. Example: "projects/1000/locations/us-central1/notebookRuntimeTemplates/abc123" }, "resourceRuntimeSpec": { # Configuration for the runtime on a PersistentResource instance, including but not limited to: * Service accounts used to run the workloads. * Whether to make it a dedicated Ray Cluster. # Optional. Persistent Resource runtime spec. For example, used for Ray cluster configuration. "raySpec": { # Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes. # Optional. Ray cluster configuration. Required when creating a dedicated RayCluster on the PersistentResource. - "headNodeResourcePoolId": "A String", # Optional. This will be used to indicate which resource pool will serve as the Ray head node(the first node within that pool). Will use the machine from the first workerpool as the head node by default if this field isn't set. - "imageUri": "A String", # Optional. Default image for user to choose a preferred ML framework (for example, TensorFlow or Pytorch) by choosing from [Vertex prebuilt images](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). Either this or the resource_pool_images is required. Use this field if you need all the resource pools to have the same Ray image. Otherwise, use the {@code resource_pool_images} field. - "rayMetricSpec": { # Configuration for the Ray metrics. # Optional. Ray metrics configurations. - "disabled": True or False, # Optional. Flag to disable the Ray metrics collection. - }, - "resourcePoolImages": { # Optional. Required if image_uri isn't set. A map of resource_pool_id to prebuild Ray image if user need to use different images for different head/worker pools. This map needs to cover all the resource pool ids. Example: { "ray_head_node_pool": "head image" "ray_worker_node_pool1": "worker image" "ray_worker_node_pool2": "another worker image" } - "a_key": "A String", - }, }, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. @@ -404,25 +380,13 @@

Method Details

}, ], "resourceRuntime": { # Persistent Cluster runtime information as output # Output only. Runtime information of the Persistent Resource. - "accessUris": { # Output only. URIs for user to connect to the Cluster. Example: { "RAY_HEAD_NODE_INTERNAL_IP": "head-node-IP:10001" "RAY_DASHBOARD_URI": "ray-dashboard-address:8888" } - "a_key": "A String", - }, - "notebookRuntimeTemplate": "A String", # Output only. The resource name of NotebookRuntimeTemplate for the RoV Persistent Cluster The NotebokRuntimeTemplate is created in the same VPC (if set), and with the same Ray and Python version as the Persistent Cluster. Example: "projects/1000/locations/us-central1/notebookRuntimeTemplates/abc123" }, "resourceRuntimeSpec": { # Configuration for the runtime on a PersistentResource instance, including but not limited to: * Service accounts used to run the workloads. * Whether to make it a dedicated Ray Cluster. # Optional. Persistent Resource runtime spec. For example, used for Ray cluster configuration. "raySpec": { # Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes. # Optional. Ray cluster configuration. Required when creating a dedicated RayCluster on the PersistentResource. - "headNodeResourcePoolId": "A String", # Optional. This will be used to indicate which resource pool will serve as the Ray head node(the first node within that pool). Will use the machine from the first workerpool as the head node by default if this field isn't set. - "imageUri": "A String", # Optional. Default image for user to choose a preferred ML framework (for example, TensorFlow or Pytorch) by choosing from [Vertex prebuilt images](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). Either this or the resource_pool_images is required. Use this field if you need all the resource pools to have the same Ray image. Otherwise, use the {@code resource_pool_images} field. - "rayMetricSpec": { # Configuration for the Ray metrics. # Optional. Ray metrics configurations. - "disabled": True or False, # Optional. Flag to disable the Ray metrics collection. - }, - "resourcePoolImages": { # Optional. Required if image_uri isn't set. A map of resource_pool_id to prebuild Ray image if user need to use different images for different head/worker pools. This map needs to cover all the resource pool ids. Example: { "ray_head_node_pool": "head image" "ray_worker_node_pool1": "worker image" "ray_worker_node_pool2": "another worker image" } - "a_key": "A String", - }, }, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. @@ -501,25 +465,13 @@

Method Details

}, ], "resourceRuntime": { # Persistent Cluster runtime information as output # Output only. Runtime information of the Persistent Resource. - "accessUris": { # Output only. URIs for user to connect to the Cluster. Example: { "RAY_HEAD_NODE_INTERNAL_IP": "head-node-IP:10001" "RAY_DASHBOARD_URI": "ray-dashboard-address:8888" } - "a_key": "A String", - }, - "notebookRuntimeTemplate": "A String", # Output only. The resource name of NotebookRuntimeTemplate for the RoV Persistent Cluster The NotebokRuntimeTemplate is created in the same VPC (if set), and with the same Ray and Python version as the Persistent Cluster. Example: "projects/1000/locations/us-central1/notebookRuntimeTemplates/abc123" }, "resourceRuntimeSpec": { # Configuration for the runtime on a PersistentResource instance, including but not limited to: * Service accounts used to run the workloads. * Whether to make it a dedicated Ray Cluster. # Optional. Persistent Resource runtime spec. For example, used for Ray cluster configuration. "raySpec": { # Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes. # Optional. Ray cluster configuration. Required when creating a dedicated RayCluster on the PersistentResource. - "headNodeResourcePoolId": "A String", # Optional. This will be used to indicate which resource pool will serve as the Ray head node(the first node within that pool). Will use the machine from the first workerpool as the head node by default if this field isn't set. - "imageUri": "A String", # Optional. Default image for user to choose a preferred ML framework (for example, TensorFlow or Pytorch) by choosing from [Vertex prebuilt images](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). Either this or the resource_pool_images is required. Use this field if you need all the resource pools to have the same Ray image. Otherwise, use the {@code resource_pool_images} field. - "rayMetricSpec": { # Configuration for the Ray metrics. # Optional. Ray metrics configurations. - "disabled": True or False, # Optional. Flag to disable the Ray metrics collection. - }, - "resourcePoolImages": { # Optional. Required if image_uri isn't set. A map of resource_pool_id to prebuild Ray image if user need to use different images for different head/worker pools. This map needs to cover all the resource pool ids. Example: { "ray_head_node_pool": "head image" "ray_worker_node_pool1": "worker image" "ray_worker_node_pool2": "another worker image" } - "a_key": "A String", - }, }, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. diff --git a/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html b/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html index fa69d5997a8..720ddbc3bb1 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html +++ b/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html @@ -257,6 +257,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], @@ -428,9 +429,6 @@

Method Details

}, }, ], - "retrievalQueries": [ # Optional. Queries executed by the retrieval tools. - "A String", - ], "webSearchQueries": [ # Optional. Web search queries for the following-up web search. "A String", ], @@ -783,6 +781,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], @@ -954,9 +953,6 @@

Method Details

}, }, ], - "retrievalQueries": [ # Optional. Queries executed by the retrieval tools. - "A String", - ], "webSearchQueries": [ # Optional. Web search queries for the following-up web search. "A String", ], diff --git a/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html b/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html index 481ce416f99..56c4db6bc38 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html +++ b/docs/dyn/aiplatform_v1.projects.locations.tuningJobs.html @@ -79,13 +79,634 @@

Instance Methods

Returns the operations Resource.

+

+ cancel(name, body=None, x__xgafv=None)

+

Cancels a TuningJob. Starts asynchronous cancellation on the TuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use GenAiTuningService.GetTuningJob or other methods to check whether the cancellation succeeded or whether the job completed despite cancellation. On successful cancellation, the TuningJob is not deleted; instead it becomes a job with a TuningJob.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`, and TuningJob.state is set to `CANCELLED`.

close()

Close httplib2 connections.

+

+ create(parent, body=None, x__xgafv=None)

+

Creates a TuningJob. A created TuningJob right away will be attempted to be run.

+

+ get(name, x__xgafv=None)

+

Gets a TuningJob.

+

+ list(parent, filter=None, pageSize=None, pageToken=None, x__xgafv=None)

+

Lists TuningJobs in a Location.

+

+ list_next()

+

Retrieves the next page of results.

Method Details

+
+ cancel(name, body=None, x__xgafv=None) + 
Cancels a TuningJob. Starts asynchronous cancellation on the TuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use GenAiTuningService.GetTuningJob or other methods to check whether the cancellation succeeded or whether the job completed despite cancellation. On successful cancellation, the TuningJob is not deleted; instead it becomes a job with a TuningJob.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`, and TuningJob.state is set to `CANCELLED`.
+
+Args:
+  name: string, Required. The name of the TuningJob to cancel. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Request message for GenAiTuningService.CancelTuningJob.
+}
+
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }
+}
+
+
close() 
Close httplib2 connections.
+
+ create(parent, body=None, x__xgafv=None) + 
Creates a TuningJob. A created TuningJob right away will be attempted to be run.
+
+Args:
+  parent: string, Required. The resource name of the Location to create the TuningJob in. Format: `projects/{project}/locations/{location}` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Represents a TuningJob that runs with Google owned models.
+  "baseModel": "A String", # Model name for tuning, e.g., "gemini-1.0-pro-002".
+  "createTime": "A String", # Output only. Time when the TuningJob was created.
+  "description": "A String", # Optional. The description of the TuningJob.
+  "endTime": "A String", # Output only. Time when the TuningJob entered any of the following JobStates: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`, `JOB_STATE_EXPIRED`.
+  "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). # Output only. Only populated when job's state is `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.
+    "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.
+  },
+  "experiment": "A String", # Output only. The Experiment associated with this TuningJob.
+  "labels": { # Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. 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",
+  },
+  "name": "A String", # Output only. Identifier. Resource name of a TuningJob. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`
+  "startTime": "A String", # Output only. Time when the TuningJob for the first time entered the `JOB_STATE_RUNNING` state.
+  "state": "A String", # Output only. The detailed state of the job.
+  "supervisedTuningSpec": { # Tuning Spec for Supervised Tuning. # Tuning Spec for Supervised Fine Tuning.
+    "hyperParameters": { # Hyperparameters for SFT. # Optional. Hyperparameters for SFT.
+      "adapterSize": "A String", # Optional. Adapter size for tuning.
+      "epochCount": "A String", # Optional. Number of training epoches for this tuning job.
+      "learningRateMultiplier": 3.14, # Optional. Learning rate multiplier for tuning.
+    },
+    "trainingDatasetUri": "A String", # Required. Cloud Storage path to file containing training dataset for tuning.
+    "validationDatasetUri": "A String", # Optional. Cloud Storage path to file containing validation dataset for tuning.
+  },
+  "tunedModel": { # The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob. # Output only. The tuned model resources assiociated with this TuningJob.
+    "endpoint": "A String", # Output only. A resource name of an Endpoint. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`.
+    "model": "A String", # Output only. The resource name of the TunedModel. Format: `projects/{project}/locations/{location}/models/{model}`.
+  },
+  "tunedModelDisplayName": "A String", # Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.
+  "tuningDataStats": { # The tuning data statistic values for TuningJob. # Output only. The tuning data statistics associated with this TuningJob.
+    "supervisedTuningDataStats": { # Tuning data statistics for Supervised Tuning. # The SFT Tuning data stats.
+      "totalBillableCharacterCount": "A String", # Output only. Number of billable characters in the tuning dataset.
+      "totalTuningCharacterCount": "A String", # Output only. Number of tuning characters in the tuning dataset.
+      "tuningDatasetExampleCount": "A String", # Output only. Number of examples in the tuning dataset.
+      "tuningStepCount": "A String", # Output only. Number of tuning steps for this Tuning Job.
+      "userDatasetExamples": [ # Output only. Sample user messages in the training dataset uri.
+        { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
+          "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
+            { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+              "fileData": { # URI based data. # Optional. URI based data.
+                "fileUri": "A String", # Required. URI.
+                "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+              },
+              "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
+                "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+                  "a_key": "", # Properties of the object.
+                },
+                "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
+              },
+              "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
+                "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+                "response": { # Required. The function response in JSON object format.
+                  "a_key": "", # Properties of the object.
+                },
+              },
+              "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
+                "data": "A String", # Required. Raw bytes.
+                "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+              },
+              "text": "A String", # Optional. Text part (can be code).
+              "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
+                "endOffset": "A String", # Optional. The end offset of the video.
+                "startOffset": "A String", # Optional. The start offset of the video.
+              },
+            },
+          ],
+          "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
+        },
+      ],
+      "userInputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user input tokens.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+      "userMessagePerExampleDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the messages per example.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+      "userOutputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user output tokens.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+    },
+  },
+  "updateTime": "A String", # Output only. Time when the TuningJob was most recently updated.
+}
+
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # Represents a TuningJob that runs with Google owned models.
+  "baseModel": "A String", # Model name for tuning, e.g., "gemini-1.0-pro-002".
+  "createTime": "A String", # Output only. Time when the TuningJob was created.
+  "description": "A String", # Optional. The description of the TuningJob.
+  "endTime": "A String", # Output only. Time when the TuningJob entered any of the following JobStates: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`, `JOB_STATE_EXPIRED`.
+  "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). # Output only. Only populated when job's state is `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.
+    "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.
+  },
+  "experiment": "A String", # Output only. The Experiment associated with this TuningJob.
+  "labels": { # Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. 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",
+  },
+  "name": "A String", # Output only. Identifier. Resource name of a TuningJob. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`
+  "startTime": "A String", # Output only. Time when the TuningJob for the first time entered the `JOB_STATE_RUNNING` state.
+  "state": "A String", # Output only. The detailed state of the job.
+  "supervisedTuningSpec": { # Tuning Spec for Supervised Tuning. # Tuning Spec for Supervised Fine Tuning.
+    "hyperParameters": { # Hyperparameters for SFT. # Optional. Hyperparameters for SFT.
+      "adapterSize": "A String", # Optional. Adapter size for tuning.
+      "epochCount": "A String", # Optional. Number of training epoches for this tuning job.
+      "learningRateMultiplier": 3.14, # Optional. Learning rate multiplier for tuning.
+    },
+    "trainingDatasetUri": "A String", # Required. Cloud Storage path to file containing training dataset for tuning.
+    "validationDatasetUri": "A String", # Optional. Cloud Storage path to file containing validation dataset for tuning.
+  },
+  "tunedModel": { # The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob. # Output only. The tuned model resources assiociated with this TuningJob.
+    "endpoint": "A String", # Output only. A resource name of an Endpoint. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`.
+    "model": "A String", # Output only. The resource name of the TunedModel. Format: `projects/{project}/locations/{location}/models/{model}`.
+  },
+  "tunedModelDisplayName": "A String", # Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.
+  "tuningDataStats": { # The tuning data statistic values for TuningJob. # Output only. The tuning data statistics associated with this TuningJob.
+    "supervisedTuningDataStats": { # Tuning data statistics for Supervised Tuning. # The SFT Tuning data stats.
+      "totalBillableCharacterCount": "A String", # Output only. Number of billable characters in the tuning dataset.
+      "totalTuningCharacterCount": "A String", # Output only. Number of tuning characters in the tuning dataset.
+      "tuningDatasetExampleCount": "A String", # Output only. Number of examples in the tuning dataset.
+      "tuningStepCount": "A String", # Output only. Number of tuning steps for this Tuning Job.
+      "userDatasetExamples": [ # Output only. Sample user messages in the training dataset uri.
+        { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
+          "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
+            { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+              "fileData": { # URI based data. # Optional. URI based data.
+                "fileUri": "A String", # Required. URI.
+                "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+              },
+              "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
+                "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+                  "a_key": "", # Properties of the object.
+                },
+                "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
+              },
+              "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
+                "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+                "response": { # Required. The function response in JSON object format.
+                  "a_key": "", # Properties of the object.
+                },
+              },
+              "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
+                "data": "A String", # Required. Raw bytes.
+                "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+              },
+              "text": "A String", # Optional. Text part (can be code).
+              "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
+                "endOffset": "A String", # Optional. The end offset of the video.
+                "startOffset": "A String", # Optional. The start offset of the video.
+              },
+            },
+          ],
+          "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
+        },
+      ],
+      "userInputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user input tokens.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+      "userMessagePerExampleDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the messages per example.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+      "userOutputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user output tokens.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+    },
+  },
+  "updateTime": "A String", # Output only. Time when the TuningJob was most recently updated.
+}
+
+ +
+ get(name, x__xgafv=None) + 
Gets a TuningJob.
+
+Args:
+  name: string, Required. The name of the TuningJob resource. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}` (required)
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # Represents a TuningJob that runs with Google owned models.
+  "baseModel": "A String", # Model name for tuning, e.g., "gemini-1.0-pro-002".
+  "createTime": "A String", # Output only. Time when the TuningJob was created.
+  "description": "A String", # Optional. The description of the TuningJob.
+  "endTime": "A String", # Output only. Time when the TuningJob entered any of the following JobStates: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`, `JOB_STATE_EXPIRED`.
+  "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). # Output only. Only populated when job's state is `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.
+    "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.
+  },
+  "experiment": "A String", # Output only. The Experiment associated with this TuningJob.
+  "labels": { # Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. 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",
+  },
+  "name": "A String", # Output only. Identifier. Resource name of a TuningJob. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`
+  "startTime": "A String", # Output only. Time when the TuningJob for the first time entered the `JOB_STATE_RUNNING` state.
+  "state": "A String", # Output only. The detailed state of the job.
+  "supervisedTuningSpec": { # Tuning Spec for Supervised Tuning. # Tuning Spec for Supervised Fine Tuning.
+    "hyperParameters": { # Hyperparameters for SFT. # Optional. Hyperparameters for SFT.
+      "adapterSize": "A String", # Optional. Adapter size for tuning.
+      "epochCount": "A String", # Optional. Number of training epoches for this tuning job.
+      "learningRateMultiplier": 3.14, # Optional. Learning rate multiplier for tuning.
+    },
+    "trainingDatasetUri": "A String", # Required. Cloud Storage path to file containing training dataset for tuning.
+    "validationDatasetUri": "A String", # Optional. Cloud Storage path to file containing validation dataset for tuning.
+  },
+  "tunedModel": { # The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob. # Output only. The tuned model resources assiociated with this TuningJob.
+    "endpoint": "A String", # Output only. A resource name of an Endpoint. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`.
+    "model": "A String", # Output only. The resource name of the TunedModel. Format: `projects/{project}/locations/{location}/models/{model}`.
+  },
+  "tunedModelDisplayName": "A String", # Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.
+  "tuningDataStats": { # The tuning data statistic values for TuningJob. # Output only. The tuning data statistics associated with this TuningJob.
+    "supervisedTuningDataStats": { # Tuning data statistics for Supervised Tuning. # The SFT Tuning data stats.
+      "totalBillableCharacterCount": "A String", # Output only. Number of billable characters in the tuning dataset.
+      "totalTuningCharacterCount": "A String", # Output only. Number of tuning characters in the tuning dataset.
+      "tuningDatasetExampleCount": "A String", # Output only. Number of examples in the tuning dataset.
+      "tuningStepCount": "A String", # Output only. Number of tuning steps for this Tuning Job.
+      "userDatasetExamples": [ # Output only. Sample user messages in the training dataset uri.
+        { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
+          "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
+            { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+              "fileData": { # URI based data. # Optional. URI based data.
+                "fileUri": "A String", # Required. URI.
+                "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+              },
+              "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
+                "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+                  "a_key": "", # Properties of the object.
+                },
+                "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
+              },
+              "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
+                "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+                "response": { # Required. The function response in JSON object format.
+                  "a_key": "", # Properties of the object.
+                },
+              },
+              "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
+                "data": "A String", # Required. Raw bytes.
+                "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+              },
+              "text": "A String", # Optional. Text part (can be code).
+              "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
+                "endOffset": "A String", # Optional. The end offset of the video.
+                "startOffset": "A String", # Optional. The start offset of the video.
+              },
+            },
+          ],
+          "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
+        },
+      ],
+      "userInputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user input tokens.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+      "userMessagePerExampleDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the messages per example.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+      "userOutputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user output tokens.
+        "buckets": [ # Output only. Defines the histogram bucket.
+          { # Dataset bucket used to create a histogram for the distribution given a population of values.
+            "count": 3.14, # Output only. Number of values in the bucket.
+            "left": 3.14, # Output only. Left bound of the bucket.
+            "right": 3.14, # Output only. Right bound of the bucket.
+          },
+        ],
+        "max": 3.14, # Output only. The maximum of the population values.
+        "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+        "median": 3.14, # Output only. The median of the values in the population.
+        "min": 3.14, # Output only. The minimum of the population values.
+        "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+        "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+        "sum": "A String", # Output only. Sum of a given population of values.
+      },
+    },
+  },
+  "updateTime": "A String", # Output only. Time when the TuningJob was most recently updated.
+}
+
+ +
+ list(parent, filter=None, pageSize=None, pageToken=None, x__xgafv=None) + 
Lists TuningJobs in a Location.
+
+Args:
+  parent: string, Required. The resource name of the Location to list the TuningJobs from. Format: `projects/{project}/locations/{location}` (required)
+  filter: string, Optional. The standard list filter.
+  pageSize: integer, Optional. The standard list page size.
+  pageToken: string, Optional. The standard list page token. Typically obtained via ListTuningJob.next_page_token of the previous GenAiTuningService.ListTuningJob][] call.
+  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 GenAiTuningService.ListTuningJobs
+  "nextPageToken": "A String", # A token to retrieve the next page of results. Pass to ListTuningJobsRequest.page_token to obtain that page.
+  "tuningJobs": [ # List of TuningJobs in the requested page.
+    { # Represents a TuningJob that runs with Google owned models.
+      "baseModel": "A String", # Model name for tuning, e.g., "gemini-1.0-pro-002".
+      "createTime": "A String", # Output only. Time when the TuningJob was created.
+      "description": "A String", # Optional. The description of the TuningJob.
+      "endTime": "A String", # Output only. Time when the TuningJob entered any of the following JobStates: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`, `JOB_STATE_EXPIRED`.
+      "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). # Output only. Only populated when job's state is `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.
+        "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.
+      },
+      "experiment": "A String", # Output only. The Experiment associated with this TuningJob.
+      "labels": { # Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. 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",
+      },
+      "name": "A String", # Output only. Identifier. Resource name of a TuningJob. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`
+      "startTime": "A String", # Output only. Time when the TuningJob for the first time entered the `JOB_STATE_RUNNING` state.
+      "state": "A String", # Output only. The detailed state of the job.
+      "supervisedTuningSpec": { # Tuning Spec for Supervised Tuning. # Tuning Spec for Supervised Fine Tuning.
+        "hyperParameters": { # Hyperparameters for SFT. # Optional. Hyperparameters for SFT.
+          "adapterSize": "A String", # Optional. Adapter size for tuning.
+          "epochCount": "A String", # Optional. Number of training epoches for this tuning job.
+          "learningRateMultiplier": 3.14, # Optional. Learning rate multiplier for tuning.
+        },
+        "trainingDatasetUri": "A String", # Required. Cloud Storage path to file containing training dataset for tuning.
+        "validationDatasetUri": "A String", # Optional. Cloud Storage path to file containing validation dataset for tuning.
+      },
+      "tunedModel": { # The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob. # Output only. The tuned model resources assiociated with this TuningJob.
+        "endpoint": "A String", # Output only. A resource name of an Endpoint. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`.
+        "model": "A String", # Output only. The resource name of the TunedModel. Format: `projects/{project}/locations/{location}/models/{model}`.
+      },
+      "tunedModelDisplayName": "A String", # Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.
+      "tuningDataStats": { # The tuning data statistic values for TuningJob. # Output only. The tuning data statistics associated with this TuningJob.
+        "supervisedTuningDataStats": { # Tuning data statistics for Supervised Tuning. # The SFT Tuning data stats.
+          "totalBillableCharacterCount": "A String", # Output only. Number of billable characters in the tuning dataset.
+          "totalTuningCharacterCount": "A String", # Output only. Number of tuning characters in the tuning dataset.
+          "tuningDatasetExampleCount": "A String", # Output only. Number of examples in the tuning dataset.
+          "tuningStepCount": "A String", # Output only. Number of tuning steps for this Tuning Job.
+          "userDatasetExamples": [ # Output only. Sample user messages in the training dataset uri.
+            { # The base structured datatype containing multi-part content of a message. A `Content` includes a `role` field designating the producer of the `Content` and a `parts` field containing multi-part data that contains the content of the message turn.
+              "parts": [ # Required. Ordered `Parts` that constitute a single message. Parts may have different IANA MIME types.
+                { # A datatype containing media that is part of a multi-part `Content` message. A `Part` consists of data which has an associated datatype. A `Part` can only contain one of the accepted types in `Part.data`. A `Part` must have a fixed IANA MIME type identifying the type and subtype of the media if `inline_data` or `file_data` field is filled with raw bytes.
+                  "fileData": { # URI based data. # Optional. URI based data.
+                    "fileUri": "A String", # Required. URI.
+                    "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+                  },
+                  "functionCall": { # A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing the parameters and their values. # Optional. A predicted [FunctionCall] returned from the model that contains a string representing the [FunctionDeclaration.name] with the parameters and their values.
+                    "args": { # Optional. Required. The function parameters and values in JSON object format. See [FunctionDeclaration.parameters] for parameter details.
+                      "a_key": "", # Properties of the object.
+                    },
+                    "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name].
+                  },
+                  "functionResponse": { # The result output from a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a [FunctionCall] made based on model prediction. # Optional. The result output of a [FunctionCall] that contains a string representing the [FunctionDeclaration.name] and a structured JSON object containing any output from the function call. It is used as context to the model.
+                    "name": "A String", # Required. The name of the function to call. Matches [FunctionDeclaration.name] and [FunctionCall.name].
+                    "response": { # Required. The function response in JSON object format.
+                      "a_key": "", # Properties of the object.
+                    },
+                  },
+                  "inlineData": { # Content blob. It's preferred to send as text directly rather than raw bytes. # Optional. Inlined bytes data.
+                    "data": "A String", # Required. Raw bytes.
+                    "mimeType": "A String", # Required. The IANA standard MIME type of the source data.
+                  },
+                  "text": "A String", # Optional. Text part (can be code).
+                  "videoMetadata": { # Metadata describes the input video content. # Optional. Video metadata. The metadata should only be specified while the video data is presented in inline_data or file_data.
+                    "endOffset": "A String", # Optional. The end offset of the video.
+                    "startOffset": "A String", # Optional. The start offset of the video.
+                  },
+                },
+              ],
+              "role": "A String", # Optional. The producer of the content. Must be either 'user' or 'model'. Useful to set for multi-turn conversations, otherwise can be left blank or unset.
+            },
+          ],
+          "userInputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user input tokens.
+            "buckets": [ # Output only. Defines the histogram bucket.
+              { # Dataset bucket used to create a histogram for the distribution given a population of values.
+                "count": 3.14, # Output only. Number of values in the bucket.
+                "left": 3.14, # Output only. Left bound of the bucket.
+                "right": 3.14, # Output only. Right bound of the bucket.
+              },
+            ],
+            "max": 3.14, # Output only. The maximum of the population values.
+            "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+            "median": 3.14, # Output only. The median of the values in the population.
+            "min": 3.14, # Output only. The minimum of the population values.
+            "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+            "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+            "sum": "A String", # Output only. Sum of a given population of values.
+          },
+          "userMessagePerExampleDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the messages per example.
+            "buckets": [ # Output only. Defines the histogram bucket.
+              { # Dataset bucket used to create a histogram for the distribution given a population of values.
+                "count": 3.14, # Output only. Number of values in the bucket.
+                "left": 3.14, # Output only. Left bound of the bucket.
+                "right": 3.14, # Output only. Right bound of the bucket.
+              },
+            ],
+            "max": 3.14, # Output only. The maximum of the population values.
+            "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+            "median": 3.14, # Output only. The median of the values in the population.
+            "min": 3.14, # Output only. The minimum of the population values.
+            "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+            "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+            "sum": "A String", # Output only. Sum of a given population of values.
+          },
+          "userOutputTokenDistribution": { # Dataset distribution for Supervised Tuning. # Output only. Dataset distributions for the user output tokens.
+            "buckets": [ # Output only. Defines the histogram bucket.
+              { # Dataset bucket used to create a histogram for the distribution given a population of values.
+                "count": 3.14, # Output only. Number of values in the bucket.
+                "left": 3.14, # Output only. Left bound of the bucket.
+                "right": 3.14, # Output only. Right bound of the bucket.
+              },
+            ],
+            "max": 3.14, # Output only. The maximum of the population values.
+            "mean": 3.14, # Output only. The arithmetic mean of the values in the population.
+            "median": 3.14, # Output only. The median of the values in the population.
+            "min": 3.14, # Output only. The minimum of the population values.
+            "p5": 3.14, # Output only. The 5th percentile of the values in the population.
+            "p95": 3.14, # Output only. The 95th percentile of the values in the population.
+            "sum": "A String", # Output only. Sum of a given population of values.
+          },
+        },
+      },
+      "updateTime": "A String", # Output only. Time when the TuningJob was most recently updated.
+    },
+  ],
+}
+
+ +
+ 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.
+
+
+ \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1.publishers.models.html b/docs/dyn/aiplatform_v1.publishers.models.html index 092ffda7e9d..7727c7007ee 100644 --- a/docs/dyn/aiplatform_v1.publishers.models.html +++ b/docs/dyn/aiplatform_v1.publishers.models.html @@ -217,87 +217,6 @@

Method Details

"A String", ], }, - "multiDeployVertex": { # Multiple setups to deploy the PublisherModel. # Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint. - "multiDeployVertex": [ # Optional. One click deployment configurations. - { # Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests. - "artifactUri": "A String", # Optional. The path to the directory containing the Model artifact and any of its supporting files. - "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. - "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number. - "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error. - }, - "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). # Optional. The specification of the container that is to be used when deploying this Model in Vertex AI. Not present for Large 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. # Exec specifies the action to take. - "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. # Exec specifies the action to take. - "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'. - }, - }, - "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. - "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`. - { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count. - "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization` - "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided. - }, - ], - "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction. - "acceleratorCount": 42, # The number of accelerators to attach to the machine. - "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count. - "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1"). - }, - "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). - "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. - }, - "largeModelReference": { # Contains information about the Large Model. # Optional. Large model reference. When this is set, model_artifact_spec is not needed. - "name": "A String", # Required. The unique name of the large Foundation or pre-built model. Like "chat-bison", "text-bison". Or model name with version ID, like "chat-bison@001", "text-bison@005", etc. - }, - "modelDisplayName": "A String", # Optional. Default model display name. - "publicArtifactUri": "A String", # Optional. The signed URI for ephemeral Cloud Storage access to model artifact. - "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}` - "title": "A String", # Required. The title of the regional resource reference. - }, - ], - }, "openEvaluationPipeline": { # The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc.. # Optional. Open evaluation pipeline of the PublisherModel. "references": { # Required. "a_key": { # Reference to a resource. diff --git a/docs/dyn/aiplatform_v1beta1.html b/docs/dyn/aiplatform_v1beta1.html index 554ada442ab..909495b3453 100644 --- a/docs/dyn/aiplatform_v1beta1.html +++ b/docs/dyn/aiplatform_v1beta1.html @@ -74,11 +74,6 @@

Vertex AI API

Instance Methods

-

- media() -

-

Returns the media Resource.

-

projects()

diff --git a/docs/dyn/aiplatform_v1beta1.projects.html b/docs/dyn/aiplatform_v1beta1.projects.html index cd9c137c0e9..1ac1a359874 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.html +++ b/docs/dyn/aiplatform_v1beta1.projects.html @@ -82,10 +82,79 @@

Instance Methods

close()

Close httplib2 connections.

+

+ getCacheConfig(name, x__xgafv=None)

+

Gets a GenAI cache config.

+

+ updateCacheConfig(name, body=None, x__xgafv=None)

+

Updates a cache config.

Method Details

close() 
Close httplib2 connections.
+
+ getCacheConfig(name, x__xgafv=None) + 
Gets a GenAI cache config.
+
+Args:
+  name: string, Required. Name of the cache config. Format: - `projects/{project}/cacheConfig`. (required)
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # Config of GenAI caching features. This is a singleton resource.
+  "disableCache": True or False, # If set to true, disables GenAI caching. Otherwise caching is enabled.
+  "name": "A String", # Identifier. Name of the cache config. Format: - `projects/{project}/cacheConfig`.
+}
+
+ +
+ updateCacheConfig(name, body=None, x__xgafv=None) + 
Updates a cache config.
+
+Args:
+  name: string, Identifier. Name of the cache config. Format: - `projects/{project}/cacheConfig`. (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Config of GenAI caching features. This is a singleton resource.
+  "disableCache": True or False, # If set to true, disables GenAI caching. Otherwise caching is enabled.
+  "name": "A String", # Identifier. Name of the cache config. Format: - `projects/{project}/cacheConfig`.
+}
+
+  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.
+  },
+}
+
+ \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.chat.html b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.chat.html new file mode 100644 index 00000000000..2eb96bc1540 --- /dev/null +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.chat.html @@ -0,0 +1,127 @@ + + + +

Vertex AI API . projects . locations . endpoints . chat

+

Instance Methods

+

+ close()

+

Close httplib2 connections.

+

+ completions(endpoint, body=None, x__xgafv=None)

+

Exposes an OpenAI-compatible endpoint for chat completions.

+

Method Details

+
+ close() + 
Close httplib2 connections.
+
+ +
+ completions(endpoint, body=None, x__xgafv=None) + 
Exposes an OpenAI-compatible endpoint for chat completions.
+
+Args:
+  endpoint: string, Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/openapi` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
+  "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
+  "data": "A String", # The HTTP request/response body as raw binary.
+  "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
+    {
+      "a_key": "", # Properties of the object. Contains field @type with type URL.
+    },
+  ],
+}
+
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # Message that represents an arbitrary HTTP body. It should only be used for payload formats that can't be represented as JSON, such as raw binary or an HTML page. This message can be used both in streaming and non-streaming API methods in the request as well as the response. It can be used as a top-level request field, which is convenient if one wants to extract parameters from either the URL or HTTP template into the request fields and also want access to the raw HTTP body. Example: message GetResourceRequest { // A unique request id. string request_id = 1; // The raw HTTP body is bound to this field. google.api.HttpBody http_body = 2; } service ResourceService { rpc GetResource(GetResourceRequest) returns (google.api.HttpBody); rpc UpdateResource(google.api.HttpBody) returns (google.protobuf.Empty); } Example with streaming methods: service CaldavService { rpc GetCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); rpc UpdateCalendar(stream google.api.HttpBody) returns (stream google.api.HttpBody); } Use of this type only changes how the request and response bodies are handled, all other features will continue to work unchanged.
+  "contentType": "A String", # The HTTP Content-Type header value specifying the content type of the body.
+  "data": "A String", # The HTTP request/response body as raw binary.
+  "extensions": [ # Application specific response metadata. Must be set in the first response for streaming APIs.
+    {
+      "a_key": "", # Properties of the object. Contains field @type with type URL.
+    },
+  ],
+}
+
+ + \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html index ba87dd36b17..1460313fe58 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html @@ -74,6 +74,11 @@

Vertex AI API . projects . locations . endpoints

Instance Methods

+

+ chat() +

+

Returns the chat Resource.

+

operations()

@@ -1242,6 +1247,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], @@ -2896,6 +2902,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html b/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html index 7a37d7958b9..c4f9f112897 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html @@ -322,6 +322,21 @@

Method Details

"name": "A String", # Required. Extension name shown to the LLM. The name can be up to 128 characters long. }, "name": "A String", # Identifier. The resource name of the Extension. + "privateServiceConnectConfig": { # PrivateExtensionConfig configuration for the extension. # Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access). If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution. + "serviceDirectory": "A String", # Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: `projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}` - The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted `servicedirectory.viewer` and `servicedirectory.pscAuthorizedService` roles on the resource. + }, + "runtimeConfig": { # Runtime configuration to run the extension. # Optional. Runtime config controlling the runtime behavior of this Extension. + "codeInterpreterRuntimeConfig": { # Code execution runtime configurations for code interpreter extension. + "fileInputGcsBucket": "A String", # Optional. The GCS bucket for file input of this Extension. If specified, support input from the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject GCS file inputs. + "fileOutputGcsBucket": "A String", # Optional. The GCS bucket for file output of this Extension. If specified, write all output files to the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body. + }, + "defaultParams": { # Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. + "a_key": "", # Properties of the object. + }, + "vertexAiSearchRuntimeConfig": { # Runtime configuration for Vertext AI Search extension. + "servingConfigName": "A String", # Required. Vertext AI Search serving config name. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}` + }, + }, "toolUseExamples": [ # Optional. Examples to illustrate the usage of the extension as a tool. { # A single example of the tool usage. "displayName": "A String", # Required. The display name for example. @@ -456,6 +471,21 @@

Method Details

"name": "A String", # Required. Extension name shown to the LLM. The name can be up to 128 characters long. }, "name": "A String", # Identifier. The resource name of the Extension. + "privateServiceConnectConfig": { # PrivateExtensionConfig configuration for the extension. # Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access). If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution. + "serviceDirectory": "A String", # Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: `projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}` - The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted `servicedirectory.viewer` and `servicedirectory.pscAuthorizedService` roles on the resource. + }, + "runtimeConfig": { # Runtime configuration to run the extension. # Optional. Runtime config controlling the runtime behavior of this Extension. + "codeInterpreterRuntimeConfig": { # Code execution runtime configurations for code interpreter extension. + "fileInputGcsBucket": "A String", # Optional. The GCS bucket for file input of this Extension. If specified, support input from the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject GCS file inputs. + "fileOutputGcsBucket": "A String", # Optional. The GCS bucket for file output of this Extension. If specified, write all output files to the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body. + }, + "defaultParams": { # Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. + "a_key": "", # Properties of the object. + }, + "vertexAiSearchRuntimeConfig": { # Runtime configuration for Vertext AI Search extension. + "servingConfigName": "A String", # Required. Vertext AI Search serving config name. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}` + }, + }, "toolUseExamples": [ # Optional. Examples to illustrate the usage of the extension as a tool. { # A single example of the tool usage. "displayName": "A String", # Required. The display name for example. @@ -629,6 +659,21 @@

Method Details

"name": "A String", # Required. Extension name shown to the LLM. The name can be up to 128 characters long. }, "name": "A String", # Identifier. The resource name of the Extension. + "privateServiceConnectConfig": { # PrivateExtensionConfig configuration for the extension. # Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access). If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution. + "serviceDirectory": "A String", # Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: `projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}` - The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted `servicedirectory.viewer` and `servicedirectory.pscAuthorizedService` roles on the resource. + }, + "runtimeConfig": { # Runtime configuration to run the extension. # Optional. Runtime config controlling the runtime behavior of this Extension. + "codeInterpreterRuntimeConfig": { # Code execution runtime configurations for code interpreter extension. + "fileInputGcsBucket": "A String", # Optional. The GCS bucket for file input of this Extension. If specified, support input from the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject GCS file inputs. + "fileOutputGcsBucket": "A String", # Optional. The GCS bucket for file output of this Extension. If specified, write all output files to the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body. + }, + "defaultParams": { # Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. + "a_key": "", # Properties of the object. + }, + "vertexAiSearchRuntimeConfig": { # Runtime configuration for Vertext AI Search extension. + "servingConfigName": "A String", # Required. Vertext AI Search serving config name. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}` + }, + }, "toolUseExamples": [ # Optional. Examples to illustrate the usage of the extension as a tool. { # A single example of the tool usage. "displayName": "A String", # Required. The display name for example. @@ -780,6 +825,21 @@

Method Details

"name": "A String", # Required. Extension name shown to the LLM. The name can be up to 128 characters long. }, "name": "A String", # Identifier. The resource name of the Extension. + "privateServiceConnectConfig": { # PrivateExtensionConfig configuration for the extension. # Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access). If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution. + "serviceDirectory": "A String", # Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: `projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}` - The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted `servicedirectory.viewer` and `servicedirectory.pscAuthorizedService` roles on the resource. + }, + "runtimeConfig": { # Runtime configuration to run the extension. # Optional. Runtime config controlling the runtime behavior of this Extension. + "codeInterpreterRuntimeConfig": { # Code execution runtime configurations for code interpreter extension. + "fileInputGcsBucket": "A String", # Optional. The GCS bucket for file input of this Extension. If specified, support input from the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject GCS file inputs. + "fileOutputGcsBucket": "A String", # Optional. The GCS bucket for file output of this Extension. If specified, write all output files to the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body. + }, + "defaultParams": { # Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. + "a_key": "", # Properties of the object. + }, + "vertexAiSearchRuntimeConfig": { # Runtime configuration for Vertext AI Search extension. + "servingConfigName": "A String", # Required. Vertext AI Search serving config name. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}` + }, + }, "toolUseExamples": [ # Optional. Examples to illustrate the usage of the extension as a tool. { # A single example of the tool usage. "displayName": "A String", # Required. The display name for example. @@ -913,6 +973,21 @@

Method Details

"name": "A String", # Required. Extension name shown to the LLM. The name can be up to 128 characters long. }, "name": "A String", # Identifier. The resource name of the Extension. + "privateServiceConnectConfig": { # PrivateExtensionConfig configuration for the extension. # Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access). If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution. + "serviceDirectory": "A String", # Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: `projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}` - The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted `servicedirectory.viewer` and `servicedirectory.pscAuthorizedService` roles on the resource. + }, + "runtimeConfig": { # Runtime configuration to run the extension. # Optional. Runtime config controlling the runtime behavior of this Extension. + "codeInterpreterRuntimeConfig": { # Code execution runtime configurations for code interpreter extension. + "fileInputGcsBucket": "A String", # Optional. The GCS bucket for file input of this Extension. If specified, support input from the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject GCS file inputs. + "fileOutputGcsBucket": "A String", # Optional. The GCS bucket for file output of this Extension. If specified, write all output files to the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body. + }, + "defaultParams": { # Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param "name" to be set to "abc". you can set this to something like {"name": "abc"}. + "a_key": "", # Properties of the object. + }, + "vertexAiSearchRuntimeConfig": { # Runtime configuration for Vertext AI Search extension. + "servingConfigName": "A String", # Required. Vertext AI Search serving config name. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}` + }, + }, "toolUseExamples": [ # Optional. Examples to illustrate the usage of the extension as a tool. { # A single example of the tool usage. "displayName": "A String", # Required. The display name for example. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.html b/docs/dyn/aiplatform_v1beta1.projects.locations.html index 44de52670c1..339ce7aa5e8 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.html @@ -279,9 +279,6 @@

Instance Methods

list_next()

Retrieves the next page of results.

-

- retrieveContexts(parent, body=None, x__xgafv=None)

-

Retrieves relevant contexts for a query.

Method Details

close() @@ -355,7 +352,7 @@

Method Details

"pairwiseQuestionAnsweringQualityInput": { # Input for pairwise question answering quality metric. # Input for pairwise question answering quality metric. "instance": { # Spec for pairwise question answering quality instance. # Required. Pairwise question answering quality instance. "baselinePrediction": "A String", # Required. Output of the baseline model. - "context": "A String", # Optional. Text to answer the question. + "context": "A String", # Required. Text to answer the question. "instruction": "A String", # Required. Question Answering prompt for LLM. "prediction": "A String", # Required. Output of the candidate model. "reference": "A String", # Optional. Ground truth used to compare against the prediction. @@ -404,7 +401,7 @@

Method Details

}, "questionAnsweringQualityInput": { # Input for question answering quality metric. # Input for question answering quality metric. "instance": { # Spec for question answering quality instance. # Required. Question answering quality instance. - "context": "A String", # Optional. Text to answer the question. + "context": "A String", # Required. Text to answer the question. "instruction": "A String", # Required. Question Answering prompt for LLM. "prediction": "A String", # Required. Output of the evaluated model. "reference": "A String", # Optional. Ground truth used to compare against the prediction. @@ -426,24 +423,6 @@

Method Details

"version": 42, # Optional. Which version to use for evaluation. }, }, - "ragContextRecallInput": { # Input for rag context recall metric. # Input for rag context recall metric. - "instance": { # Spec for rag context recall instance. # Required. Rag context recall instance. - "context": "A String", # Required. Retrieved facts from RAG pipeline as context to be evaluated. - "reference": "A String", # Required. Ground truth used to compare against the context. - }, - "metricSpec": { # Spec for rag context recall metric. # Required. Spec for rag context recall metric. - "version": 42, # Optional. Which version to use for evaluation. - }, - }, - "responseRecallInput": { # Input for response recall metric. # Input for response recall metric. - "instance": { # Spec for response recall instance. # Required. Response recall instance. - "prediction": "A String", # Required. Output of the evaluated model. - "reference": "A String", # Required. Ground truth used to compare against the prediction. - }, - "metricSpec": { # Spec for response recall metric. # Required. Spec for response recall score metric. - "version": 42, # Optional. Which version to use for evaluation. - }, - }, "rougeInput": { # Input for rouge metric. # Instances and metric spec for rouge metric. "instances": [ # Required. Repeated rouge instances. { # Spec for rouge instance. @@ -617,16 +596,6 @@

Method Details

"explanation": "A String", # Output only. Explanation for question answering relevance score. "score": 3.14, # Output only. Question Answering Relevance score. }, - "ragContextRecallResult": { # Spec for rag context recall result. # RAG only metrics. Result for context recall metric. - "confidence": 3.14, # Output only. Confidence for rag context recall score. - "explanation": "A String", # Output only. Explanation for rag context recall score. - "score": 3.14, # Output only. RagContextRecall score. - }, - "responseRecallResult": { # Spec for response recall result. # Result for response recall metric. - "confidence": 3.14, # Output only. Confidence for fulfillment score. - "explanation": "A String", # Output only. Explanation for response recall score. - "score": 3.14, # Output only. ResponseRecall score. - }, "rougeResults": { # Results for rouge metric. # Results for rouge metric. "rougeMetricValues": [ # Output only. Rouge metric values. { # Rouge metric value for an instance. @@ -761,46 +730,4 @@

Method Details

-
- retrieveContexts(parent, body=None, x__xgafv=None) - 
Retrieves relevant contexts for a query.
-
-Args:
-  parent: string, Required. The resource name of the Location from which to retrieve RagContexts. The users must have permission to make a call in the project. Format: `projects/{project}/locations/{location}`. (required)
-  body: object, The request body.
-    The object takes the form of:
-
-{ # Request message for VertexRagService.RetrieveContexts.
-  "query": { # A query to retrieve relevant contexts. # Required. Single RAG retrieve query.
-    "similarityTopK": 42, # Optional. The number of contexts to retrieve.
-    "text": "A String", # Optional. The query in text format to get relevant contexts.
-  },
-  "vertexRagStore": { # The data source for Vertex RagStore. # The data source for Vertex RagStore.
-    "ragCorpora": [ # Required. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` Currently only one corpus is allowed. In the future we may open up multiple corpora support. However, they should be from the same project and location.
-      "A String",
-    ],
-  },
-}
-
-  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 VertexRagService.RetrieveContexts.
-  "contexts": { # Relevant contexts for one query. # The contexts of the query.
-    "contexts": [ # All its contexts.
-      { # A context of the query.
-        "distance": 3.14, # The distance between the query vector and the context text vector.
-        "sourceUri": "A String", # For vertex RagStore, if the file is imported from Cloud Storage or Google Drive, source_uri will be original file URI in Cloud Storage or Google Drive; if file is uploaded, source_uri will be file display name.
-        "text": "A String", # The text chunk.
-      },
-    ],
-  },
-}
-
- \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.indexEndpoints.html b/docs/dyn/aiplatform_v1beta1.projects.locations.indexEndpoints.html index b6a4a3a883a..0dbb1c6d114 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.indexEndpoints.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.indexEndpoints.html @@ -377,7 +377,7 @@

Method Details

body: object, The request body. The object takes the form of: -{ # LINT.IfChange The request message for MatchService.FindNeighbors. +{ # The request message for MatchService.FindNeighbors. "deployedIndexId": "A String", # The ID of the DeployedIndex that will serve the request. This request is sent to a specific IndexEndpoint, as per the IndexEndpoint.network. That IndexEndpoint also has IndexEndpoint.deployed_indexes, and each such index has a DeployedIndex.id field. The value of the field below must equal one of the DeployedIndex.id fields of the IndexEndpoint that is being called for this request. "queries": [ # The list of queries. { # A query to find a number of the nearest neighbors (most similar vectors) of a vector. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html b/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html index 3238f16a9d5..7ac213a260b 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html @@ -181,7 +181,7 @@

Method Details

}, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. @@ -331,7 +331,7 @@

Method Details

}, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. @@ -422,7 +422,7 @@

Method Details

}, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. @@ -519,7 +519,7 @@

Method Details

}, "serviceAccountSpec": { # Configuration for the use of custom service account to run the workloads. # Optional. Configure the use of workload identity on the PersistentResource "enableCustomServiceAccount": True or False, # Required. If true, custom user-managed service account is enforced to run any workloads (for example, Vertex Jobs) on the resource. Otherwise, uses the [Vertex AI Custom Code Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). - "serviceAccount": "A String", # Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`. + "serviceAccount": "A String", # Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job. }, }, "startTime": "A String", # Output only. Time when the PersistentResource for the first time entered the `RUNNING` state. diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html b/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html index a938dde9603..bae4b626300 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html @@ -257,6 +257,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], @@ -864,6 +865,7 @@

Method Details

"frequencyPenalty": 3.14, # Optional. Frequency penalties. "maxOutputTokens": 42, # Optional. The maximum number of output tokens to generate per message. "presencePenalty": 3.14, # Optional. Positive penalties. + "responseMimeType": "A String", # Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature. "stopSequences": [ # Optional. Stop sequences. "A String", ], diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.html b/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.html index e255cbab287..98616af8adc 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.html @@ -87,174 +87,10 @@

Instance Methods

close()

Close httplib2 connections.

-

- create(parent, body=None, x__xgafv=None)

-

Creates a RagCorpus.

-

- delete(name, force=None, x__xgafv=None)

-

Deletes a RagCorpus.

-

- get(name, x__xgafv=None)

-

Gets a RagCorpus.

-

- list(parent, pageSize=None, pageToken=None, x__xgafv=None)

-

Lists RagCorpora in a Location.

-

- list_next()

-

Retrieves the next page of results.

Method Details

close() 
Close httplib2 connections.
-
- create(parent, body=None, x__xgafv=None) - 
Creates a RagCorpus.
-
-Args:
-  parent: string, Required. The resource name of the Location to create the RagCorpus in. Format: `projects/{project}/locations/{location}` (required)
-  body: object, The request body.
-    The object takes the form of:
-
-{ # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
-  "createTime": "A String", # Output only. Timestamp when this RagCorpus was created.
-  "description": "A String", # Optional. The description of the RagCorpus.
-  "displayName": "A String", # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
-  "name": "A String", # Output only. The resource name of the RagCorpus.
-  "updateTime": "A String", # Output only. Timestamp when this RagCorpus was last updated.
-}
-
-  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, force=None, x__xgafv=None) - 
Deletes a RagCorpus.
-
-Args:
-  name: string, Required. The name of the RagCorpus resource to be deleted. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` (required)
-  force: boolean, Optional. If set to true, any RagFiles in this RagCorpus will also be deleted. Otherwise, the request will only work if the RagCorpus has no RagFiles.
-  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 RagCorpus.
-
-Args:
-  name: string, Required. The name of the RagCorpus resource. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` (required)
-  x__xgafv: string, V1 error format.
-    Allowed values
-      1 - v1 error format
-      2 - v2 error format
-
-Returns:
-  An object of the form:
-
-    { # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
-  "createTime": "A String", # Output only. Timestamp when this RagCorpus was created.
-  "description": "A String", # Optional. The description of the RagCorpus.
-  "displayName": "A String", # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
-  "name": "A String", # Output only. The resource name of the RagCorpus.
-  "updateTime": "A String", # Output only. Timestamp when this RagCorpus was last updated.
-}
-
- -
- list(parent, pageSize=None, pageToken=None, x__xgafv=None) - 
Lists RagCorpora in a Location.
-
-Args:
-  parent: string, Required. The resource name of the Location from which to list the RagCorpora. Format: `projects/{project}/locations/{location}` (required)
-  pageSize: integer, Optional. The standard list page size.
-  pageToken: string, Optional. The standard list page token. Typically obtained via ListRagCorporaResponse.next_page_token of the previous VertexRagDataService.ListRagCorpora call.
-  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 VertexRagDataService.ListRagCorpora.
-  "nextPageToken": "A String", # A token to retrieve the next page of results. Pass to ListRagCorporaRequest.page_token to obtain that page.
-  "ragCorpora": [ # List of RagCorpora in the requested page.
-    { # A RagCorpus is a RagFile container and a project can have multiple RagCorpora.
-      "createTime": "A String", # Output only. Timestamp when this RagCorpus was created.
-      "description": "A String", # Optional. The description of the RagCorpus.
-      "displayName": "A String", # Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.
-      "name": "A String", # Output only. The resource name of the RagCorpus.
-      "updateTime": "A String", # Output only. Timestamp when this RagCorpus was last updated.
-    },
-  ],
-}
-
- -
- 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.
-
-
- \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.ragFiles.html b/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.ragFiles.html index ff8322bde4c..91817d8cb9e 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.ragFiles.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.ragCorpora.ragFiles.html @@ -82,221 +82,10 @@

Instance Methods

close()

Close httplib2 connections.

-

- delete(name, x__xgafv=None)

-

Deletes a RagFile.

-

- get(name, x__xgafv=None)

-

Gets a RagFile.

-

- import_(parent, body=None, x__xgafv=None)

-

Import files from Google Cloud Storage or Google Drive into a RagCorpus.

-

- list(parent, pageSize=None, pageToken=None, x__xgafv=None)

-

Lists RagFiles in a RagCorpus.

-

- list_next()

-

Retrieves the next page of results.

Method Details

close() 
Close httplib2 connections.
-
- delete(name, x__xgafv=None) - 
Deletes a RagFile.
-
-Args:
-  name: string, Required. The name of the RagFile resource to be deleted. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}` (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.
-  },
-}
-
- -
- get(name, x__xgafv=None) - 
Gets a RagFile.
-
-Args:
-  name: string, Required. The name of the RagFile resource. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}` (required)
-  x__xgafv: string, V1 error format.
-    Allowed values
-      1 - v1 error format
-      2 - v2 error format
-
-Returns:
-  An object of the form:
-
-    { # A RagFile contains user data for chunking, embedding and indexing.
-  "createTime": "A String", # Output only. Timestamp when this RagFile was created.
-  "description": "A String", # Optional. The description of the RagFile.
-  "directUploadSource": { # The input content is encapsulated and uploaded in the request. # Output only. The RagFile is encapsulated and uploaded in the UploadRagFile request.
-  },
-  "displayName": "A String", # Required. The display name of the RagFile. The name can be up to 128 characters long and can consist of any UTF-8 characters.
-  "gcsSource": { # The Google Cloud Storage location for the input content. # Output only. Google Cloud Storage location of the RagFile. It does not support wildcards in the GCS uri for now.
-    "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",
-    ],
-  },
-  "googleDriveSource": { # The Google Drive location for the input content. # Output only. Google Drive location. Supports importing individual files as well as Google Drive folders.
-    "resourceIds": [ # Required. Google Drive resource IDs.
-      { # The type and ID of the Google Drive resource.
-        "resourceId": "A String", # Required. The ID of the Google Drive resource.
-        "resourceType": "A String", # Required. The type of the Google Drive resource.
-      },
-    ],
-  },
-  "name": "A String", # Output only. The resource name of the RagFile.
-  "ragFileType": "A String", # Output only. The type of the RagFile.
-  "sizeBytes": "A String", # Output only. The size of the RagFile in bytes.
-  "updateTime": "A String", # Output only. Timestamp when this RagFile was last updated.
-}
-
- -
- import_(parent, body=None, x__xgafv=None) - 
Import files from Google Cloud Storage or Google Drive into a RagCorpus.
-
-Args:
-  parent: string, Required. The name of the RagCorpus resource into which to import files. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` (required)
-  body: object, The request body.
-    The object takes the form of:
-
-{ # Request message for VertexRagDataService.ImportRagFiles.
-  "importRagFilesConfig": { # Config for importing RagFiles. # Required. The config for the RagFiles to be synced and imported into the RagCorpus. VertexRagDataService.ImportRagFiles.
-    "gcsSource": { # The Google Cloud Storage location for the input content. # Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats: * "gs://bucket_name/my_directory/object_name/my_file.txt". * "gs://bucket_name/my_directory"
-      "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",
-      ],
-    },
-    "googleDriveSource": { # The Google Drive location for the input content. # Google Drive location. Supports importing individual files as well as Google Drive folders.
-      "resourceIds": [ # Required. Google Drive resource IDs.
-        { # The type and ID of the Google Drive resource.
-          "resourceId": "A String", # Required. The ID of the Google Drive resource.
-          "resourceType": "A String", # Required. The type of the Google Drive resource.
-        },
-      ],
-    },
-    "ragFileChunkingConfig": { # Specifies the size and overlap of chunks for RagFiles. # Specifies the size and overlap of chunks after importing RagFiles.
-      "chunkOverlap": 42, # The overlap between chunks.
-      "chunkSize": 42, # The size of the chunks.
-    },
-  },
-}
-
-  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.
-  },
-}
-
- -
- list(parent, pageSize=None, pageToken=None, x__xgafv=None) - 
Lists RagFiles in a RagCorpus.
-
-Args:
-  parent: string, Required. The resource name of the RagCorpus from which to list the RagFiles. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` (required)
-  pageSize: integer, Optional. The standard list page size.
-  pageToken: string, Optional. The standard list page token. Typically obtained via ListRagFilesResponse.next_page_token of the previous VertexRagDataService.ListRagFiles call.
-  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 VertexRagDataService.ListRagFiles.
-  "nextPageToken": "A String", # A token to retrieve the next page of results. Pass to ListRagFilesRequest.page_token to obtain that page.
-  "ragFiles": [ # List of RagFiles in the requested page.
-    { # A RagFile contains user data for chunking, embedding and indexing.
-      "createTime": "A String", # Output only. Timestamp when this RagFile was created.
-      "description": "A String", # Optional. The description of the RagFile.
-      "directUploadSource": { # The input content is encapsulated and uploaded in the request. # Output only. The RagFile is encapsulated and uploaded in the UploadRagFile request.
-      },
-      "displayName": "A String", # Required. The display name of the RagFile. The name can be up to 128 characters long and can consist of any UTF-8 characters.
-      "gcsSource": { # The Google Cloud Storage location for the input content. # Output only. Google Cloud Storage location of the RagFile. It does not support wildcards in the GCS uri for now.
-        "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",
-        ],
-      },
-      "googleDriveSource": { # The Google Drive location for the input content. # Output only. Google Drive location. Supports importing individual files as well as Google Drive folders.
-        "resourceIds": [ # Required. Google Drive resource IDs.
-          { # The type and ID of the Google Drive resource.
-            "resourceId": "A String", # Required. The ID of the Google Drive resource.
-            "resourceType": "A String", # Required. The type of the Google Drive resource.
-          },
-        ],
-      },
-      "name": "A String", # Output only. The resource name of the RagFile.
-      "ragFileType": "A String", # Output only. The type of the RagFile.
-      "sizeBytes": "A String", # Output only. The size of the RagFile in bytes.
-      "updateTime": "A String", # Output only. Timestamp when this RagFile was last updated.
-    },
-  ],
-}
-
- -
- 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.
-
-
- \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.publishers.models.html b/docs/dyn/aiplatform_v1beta1.publishers.models.html index 85e0c78bd1d..a5233c4bd2e 100644 --- a/docs/dyn/aiplatform_v1beta1.publishers.models.html +++ b/docs/dyn/aiplatform_v1beta1.publishers.models.html @@ -232,87 +232,6 @@

Method Details

"A String", ], }, - "multiDeployVertex": { # Multiple setups to deploy the PublisherModel. # Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint. - "multiDeployVertex": [ # Optional. One click deployment configurations. - { # Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests. - "artifactUri": "A String", # Optional. The path to the directory containing the Model artifact and any of its supporting files. - "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. - "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number. - "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error. - }, - "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). # Optional. The specification of the container that is to be used when deploying this Model in Vertex AI. Not present for Large 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. # Exec specifies the action to take. - "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. # Exec specifies the action to take. - "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'. - }, - }, - "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. - "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`. - { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count. - "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization` - "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided. - }, - ], - "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction. - "acceleratorCount": 42, # The number of accelerators to attach to the machine. - "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count. - "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1"). - }, - "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). - "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. - }, - "largeModelReference": { # Contains information about the Large Model. # Optional. Large model reference. When this is set, model_artifact_spec is not needed. - "name": "A String", # Required. The unique name of the large Foundation or pre-built model. Like "chat-bison", "text-bison". Or model name with version ID, like "chat-bison@001", "text-bison@005", etc. - }, - "modelDisplayName": "A String", # Optional. Default model display name. - "publicArtifactUri": "A String", # Optional. The signed URI for ephemeral Cloud Storage access to model artifact. - "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}` - "title": "A String", # Required. The title of the regional resource reference. - }, - ], - }, "openEvaluationPipeline": { # The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc.. # Optional. Open evaluation pipeline of the PublisherModel. "references": { # Required. "a_key": { # Reference to a resource. @@ -609,87 +528,6 @@

Method Details

"A String", ], }, - "multiDeployVertex": { # Multiple setups to deploy the PublisherModel. # Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint. - "multiDeployVertex": [ # Optional. One click deployment configurations. - { # Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests. - "artifactUri": "A String", # Optional. The path to the directory containing the Model artifact and any of its supporting files. - "automaticResources": { # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Each Model supporting these resources documents its specific guidelines. # A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. - "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number. - "minReplicaCount": 42, # Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error. - }, - "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). # Optional. The specification of the container that is to be used when deploying this Model in Vertex AI. Not present for Large 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. # Exec specifies the action to take. - "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. # Exec specifies the action to take. - "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'. - }, - }, - "dedicatedResources": { # A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration. # A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. - "autoscalingMetricSpecs": [ # Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and autoscaling_metric_specs.target to `80`. - { # The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count. - "metricName": "A String", # Required. The resource metric name. Supported metrics: * For Online Prediction: * `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle` * `aiplatform.googleapis.com/prediction/online/cpu/utilization` - "target": 42, # The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided. - }, - ], - "machineSpec": { # Specification of a single machine. # Required. Immutable. The specification of a single machine used by the prediction. - "acceleratorCount": 42, # The number of accelerators to attach to the machine. - "acceleratorType": "A String", # Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count. - "machineType": "A String", # Immutable. The type of the machine. See the [list of machine types supported for prediction](https://cloud.google.com/vertex-ai/docs/predictions/configure-compute#machine-types) See the [list of machine types supported for custom training](https://cloud.google.com/vertex-ai/docs/training/configure-compute#machine-types). For DeployedModel this field is optional, and the default value is `n1-standard-2`. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - "tpuTopology": "A String", # Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1"). - }, - "maxReplicaCount": 42, # Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type). - "minReplicaCount": 42, # Required. Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed. - }, - "largeModelReference": { # Contains information about the Large Model. # Optional. Large model reference. When this is set, model_artifact_spec is not needed. - "name": "A String", # Required. The unique name of the large Foundation or pre-built model. Like "chat-bison", "text-bison". Or model name with version ID, like "chat-bison@001", "text-bison@005", etc. - }, - "modelDisplayName": "A String", # Optional. Default model display name. - "publicArtifactUri": "A String", # Optional. The signed URI for ephemeral Cloud Storage access to model artifact. - "sharedResources": "A String", # The resource name of the shared DeploymentResourcePool to deploy on. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}` - "title": "A String", # Required. The title of the regional resource reference. - }, - ], - }, "openEvaluationPipeline": { # The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc.. # Optional. Open evaluation pipeline of the PublisherModel. "references": { # Required. "a_key": { # Reference to a resource. diff --git a/googleapiclient/discovery_cache/documents/aiplatform.v1.json b/googleapiclient/discovery_cache/documents/aiplatform.v1.json index 45bf9add9bb..b7ace75f09f 100644 --- a/googleapiclient/discovery_cache/documents/aiplatform.v1.json +++ b/googleapiclient/discovery_cache/documents/aiplatform.v1.json @@ -15922,6 +15922,130 @@ } }, "tuningJobs": { +"methods": { +"cancel": { +"description": "Cancels a TuningJob. Starts asynchronous cancellation on the TuningJob. The server makes a best effort to cancel the job, but success is not guaranteed. Clients can use GenAiTuningService.GetTuningJob or other methods to check whether the cancellation succeeded or whether the job completed despite cancellation. On successful cancellation, the TuningJob is not deleted; instead it becomes a job with a TuningJob.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`, and TuningJob.state is set to `CANCELLED`.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/tuningJobs/{tuningJobsId}:cancel", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.tuningJobs.cancel", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "Required. The name of the TuningJob to cancel. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/tuningJobs/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+name}:cancel", +"request": { +"$ref": "GoogleCloudAiplatformV1CancelTuningJobRequest" +}, +"response": { +"$ref": "GoogleProtobufEmpty" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"create": { +"description": "Creates a TuningJob. A created TuningJob right away will be attempted to be run.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/tuningJobs", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.tuningJobs.create", +"parameterOrder": [ +"parent" +], +"parameters": { +"parent": { +"description": "Required. The resource name of the Location to create the TuningJob in. Format: `projects/{project}/locations/{location}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+parent}/tuningJobs", +"request": { +"$ref": "GoogleCloudAiplatformV1TuningJob" +}, +"response": { +"$ref": "GoogleCloudAiplatformV1TuningJob" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"get": { +"description": "Gets a TuningJob.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/tuningJobs/{tuningJobsId}", +"httpMethod": "GET", +"id": "aiplatform.projects.locations.tuningJobs.get", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "Required. The name of the TuningJob resource. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/tuningJobs/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+name}", +"response": { +"$ref": "GoogleCloudAiplatformV1TuningJob" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"list": { +"description": "Lists TuningJobs in a Location.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/tuningJobs", +"httpMethod": "GET", +"id": "aiplatform.projects.locations.tuningJobs.list", +"parameterOrder": [ +"parent" +], +"parameters": { +"filter": { +"description": "Optional. The standard list filter.", +"location": "query", +"type": "string" +}, +"pageSize": { +"description": "Optional. The standard list page size.", +"format": "int32", +"location": "query", +"type": "integer" +}, +"pageToken": { +"description": "Optional. The standard list page token. Typically obtained via ListTuningJob.next_page_token of the previous GenAiTuningService.ListTuningJob][] call.", +"location": "query", +"type": "string" +}, +"parent": { +"description": "Required. The resource name of the Location to list the TuningJobs from. Format: `projects/{project}/locations/{location}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+parent}/tuningJobs", +"response": { +"$ref": "GoogleCloudAiplatformV1ListTuningJobsResponse" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +} +}, "resources": { "operations": { "methods": { @@ -16080,7 +16204,7 @@ } } }, -"revision": "20240328", +"revision": "20240404", "rootUrl": "https://aiplatform.googleapis.com/", "schemas": { "CloudAiLargeModelsVisionEmbedVideoResponse": { @@ -16677,6 +16801,10 @@ "CloudAiNlLlmProtoServiceMessageMetadata": { "id": "CloudAiNlLlmProtoServiceMessageMetadata", "properties": { +"factualityDebugMetadata": { +"$ref": "LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata", +"description": "Factuality-related debug metadata." +}, "inputFilterInfo": { "$ref": "LearningServingLlmMessageMetadata", "description": "Filter metadata of the input messages." @@ -16885,6 +17013,13 @@ }, "type": "array" }, +"translationRequestInfos": { +"description": "Translation request info during RAI for debugging purpose. Each TranslationRequestInfo corresponds to a request sent to the translation server.", +"items": { +"$ref": "LearningGenaiRootTranslationRequestInfo" +}, +"type": "array" +}, "triggeredBlocklist": { "description": "Whether the text triggered the blocklist.", "type": "boolean" @@ -18339,6 +18474,12 @@ "properties": {}, "type": "object" }, +"GoogleCloudAiplatformV1CancelTuningJobRequest": { +"description": "Request message for GenAiTuningService.CancelTuningJob.", +"id": "GoogleCloudAiplatformV1CancelTuningJobRequest", +"properties": {}, +"type": "object" +}, "GoogleCloudAiplatformV1Candidate": { "description": "A response candidate generated from the model.", "id": "GoogleCloudAiplatformV1Candidate", @@ -22465,7 +22606,7 @@ "type": "object" }, "GoogleCloudAiplatformV1FindNeighborsRequest": { -"description": "LINT.IfChange The request message for MatchService.FindNeighbors.", +"description": "The request message for MatchService.FindNeighbors.", "id": "GoogleCloudAiplatformV1FindNeighborsRequest", "properties": { "deployedIndexId": { @@ -22813,6 +22954,10 @@ "format": "float", "type": "number" }, +"responseMimeType": { +"description": "Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.", +"type": "string" +}, "stopSequences": { "description": "Optional. Stop sequences.", "items": { @@ -22937,13 +23082,6 @@ }, "type": "array" }, -"retrievalQueries": { -"description": "Optional. Queries executed by the retrieval tools.", -"items": { -"type": "string" -}, -"type": "array" -}, "webSearchQueries": { "description": "Optional. Web search queries for the following-up web search.", "items": { @@ -24578,6 +24716,24 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1ListTuningJobsResponse": { +"description": "Response message for GenAiTuningService.ListTuningJobs", +"id": "GoogleCloudAiplatformV1ListTuningJobsResponse", +"properties": { +"nextPageToken": { +"description": "A token to retrieve the next page of results. Pass to ListTuningJobsRequest.page_token to obtain that page.", +"type": "string" +}, +"tuningJobs": { +"description": "List of TuningJobs in the requested page.", +"items": { +"$ref": "GoogleCloudAiplatformV1TuningJob" +}, +"type": "array" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1LookupStudyRequest": { "description": "Request message for VizierService.LookupStudy.", "id": "GoogleCloudAiplatformV1LookupStudyRequest", @@ -26733,7 +26889,8 @@ "OP_IN_DATAPOINT", "MULTIPLE_VALUES", "INVALID_NUMERIC_VALUE", -"INVALID_ENCODING" +"INVALID_ENCODING", +"INVALID_SPARSE_DIMENSIONS" ], "enumDescriptions": [ "Default, shall not be used.", @@ -26749,7 +26906,8 @@ "Numeric restrict has operator specified in datapoint.", "Numeric restrict has multiple values specified.", "Numeric restrict has invalid numeric value specified.", -"File is not in UTF_8 format." +"File is not in UTF_8 format.", +"Error parsing sparse dimensions field." ], "type": "string" }, @@ -28153,10 +28311,6 @@ "$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionDeployGke", "description": "Optional. Deploy PublisherModel to Google Kubernetes Engine." }, -"multiDeployVertex": { -"$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex", -"description": "Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint." -}, "openEvaluationPipeline": { "$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionRegionalResourceReferences", "description": "Optional. Open evaluation pipeline of the PublisherModel." @@ -28257,20 +28411,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex": { -"description": "Multiple setups to deploy the PublisherModel.", -"id": "GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex", -"properties": { -"multiDeployVertex": { -"description": "Optional. One click deployment configurations.", -"items": { -"$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionDeploy" -}, -"type": "array" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1PublisherModelCallToActionOpenFineTuningPipelines": { "description": "Open fine tuning pipelines.", "id": "GoogleCloudAiplatformV1PublisherModelCallToActionOpenFineTuningPipelines", @@ -28605,41 +28745,10 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1RayMetricSpec": { -"description": "Configuration for the Ray metrics.", -"id": "GoogleCloudAiplatformV1RayMetricSpec", -"properties": { -"disabled": { -"description": "Optional. Flag to disable the Ray metrics collection.", -"type": "boolean" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1RaySpec": { "description": "Configuration information for the Ray cluster. For experimental launch, Ray cluster creation and Persistent cluster creation are 1:1 mapping: We will provision all the nodes within the Persistent cluster as Ray nodes.", "id": "GoogleCloudAiplatformV1RaySpec", -"properties": { -"headNodeResourcePoolId": { -"description": "Optional. This will be used to indicate which resource pool will serve as the Ray head node(the first node within that pool). Will use the machine from the first workerpool as the head node by default if this field isn't set.", -"type": "string" -}, -"imageUri": { -"description": "Optional. Default image for user to choose a preferred ML framework (for example, TensorFlow or Pytorch) by choosing from [Vertex prebuilt images](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers). Either this or the resource_pool_images is required. Use this field if you need all the resource pools to have the same Ray image. Otherwise, use the {@code resource_pool_images} field.", -"type": "string" -}, -"rayMetricSpec": { -"$ref": "GoogleCloudAiplatformV1RayMetricSpec", -"description": "Optional. Ray metrics configurations." -}, -"resourcePoolImages": { -"additionalProperties": { -"type": "string" -}, -"description": "Optional. Required if image_uri isn't set. A map of resource_pool_id to prebuild Ray image if user need to use different images for different head/worker pools. This map needs to cover all the resource pool ids. Example: { \"ray_head_node_pool\": \"head image\" \"ray_worker_node_pool1\": \"worker image\" \"ray_worker_node_pool2\": \"another worker image\" }", -"type": "object" -} -}, +"properties": {}, "type": "object" }, "GoogleCloudAiplatformV1ReadFeatureValuesRequest": { @@ -28962,21 +29071,7 @@ "GoogleCloudAiplatformV1ResourceRuntime": { "description": "Persistent Cluster runtime information as output", "id": "GoogleCloudAiplatformV1ResourceRuntime", -"properties": { -"accessUris": { -"additionalProperties": { -"type": "string" -}, -"description": "Output only. URIs for user to connect to the Cluster. Example: { \"RAY_HEAD_NODE_INTERNAL_IP\": \"head-node-IP:10001\" \"RAY_DASHBOARD_URI\": \"ray-dashboard-address:8888\" }", -"readOnly": true, -"type": "object" -}, -"notebookRuntimeTemplate": { -"description": "Output only. The resource name of NotebookRuntimeTemplate for the RoV Persistent Cluster The NotebokRuntimeTemplate is created in the same VPC (if set), and with the same Ray and Python version as the Persistent Cluster. Example: \"projects/1000/locations/us-central1/notebookRuntimeTemplates/abc123\"", -"readOnly": true, -"type": "string" -} -}, +"properties": {}, "type": "object" }, "GoogleCloudAiplatformV1ResourceRuntimeSpec": { @@ -30140,6 +30235,78 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1SchemaModelevaluationMetricsPairwiseTextGenerationEvaluationMetrics": { +"description": "Metrics for general pairwise text generation evaluation results.", +"id": "GoogleCloudAiplatformV1SchemaModelevaluationMetricsPairwiseTextGenerationEvaluationMetrics", +"properties": { +"accuracy": { +"description": "Fraction of cases where the autorater agreed with the human raters.", +"format": "float", +"type": "number" +}, +"baselineModelWinRate": { +"description": "Percentage of time the autorater decided the baseline model had the better response.", +"format": "float", +"type": "number" +}, +"cohensKappa": { +"description": "A measurement of agreement between the autorater and human raters that takes the likelihood of random agreement into account.", +"format": "float", +"type": "number" +}, +"f1Score": { +"description": "Harmonic mean of precision and recall.", +"format": "float", +"type": "number" +}, +"falseNegativeCount": { +"description": "Number of examples where the autorater chose the baseline model, but humans preferred the model.", +"format": "int64", +"type": "string" +}, +"falsePositiveCount": { +"description": "Number of examples where the autorater chose the model, but humans preferred the baseline model.", +"format": "int64", +"type": "string" +}, +"humanPreferenceBaselineModelWinRate": { +"description": "Percentage of time humans decided the baseline model had the better response.", +"format": "float", +"type": "number" +}, +"humanPreferenceModelWinRate": { +"description": "Percentage of time humans decided the model had the better response.", +"format": "float", +"type": "number" +}, +"modelWinRate": { +"description": "Percentage of time the autorater decided the model had the better response.", +"format": "float", +"type": "number" +}, +"precision": { +"description": "Fraction of cases where the autorater and humans thought the model had a better response out of all cases where the autorater thought the model had a better response. True positive divided by all positive.", +"format": "float", +"type": "number" +}, +"recall": { +"description": "Fraction of cases where the autorater and humans thought the model had a better response out of all cases where the humans thought the model had a better response.", +"format": "float", +"type": "number" +}, +"trueNegativeCount": { +"description": "Number of examples where both the autorater and humans decided that the model had the worse response.", +"format": "int64", +"type": "string" +}, +"truePositiveCount": { +"description": "Number of examples where both the autorater and humans decided that the model had the better response.", +"format": "int64", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1SchemaModelevaluationMetricsQuestionAnsweringEvaluationMetrics": { "id": "GoogleCloudAiplatformV1SchemaModelevaluationMetricsQuestionAnsweringEvaluationMetrics", "properties": { @@ -33501,7 +33668,7 @@ false "type": "boolean" }, "serviceAccount": { -"description": "Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`.", +"description": "Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job.", "type": "string" } }, @@ -34276,6 +34443,196 @@ false }, "type": "object" }, +"GoogleCloudAiplatformV1SupervisedHyperParameters": { +"description": "Hyperparameters for SFT.", +"id": "GoogleCloudAiplatformV1SupervisedHyperParameters", +"properties": { +"adapterSize": { +"description": "Optional. Adapter size for tuning.", +"enum": [ +"ADAPTER_SIZE_UNSPECIFIED", +"ADAPTER_SIZE_ONE", +"ADAPTER_SIZE_FOUR", +"ADAPTER_SIZE_EIGHT", +"ADAPTER_SIZE_SIXTEEN" +], +"enumDescriptions": [ +"Adapter size is unspecified.", +"Adapter size 1.", +"Adapter size 4.", +"Adapter size 8.", +"Adapter size 16." +], +"type": "string" +}, +"epochCount": { +"description": "Optional. Number of training epoches for this tuning job.", +"format": "int64", +"type": "string" +}, +"learningRateMultiplier": { +"description": "Optional. Learning rate multiplier for tuning.", +"format": "double", +"type": "number" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1SupervisedTuningDataStats": { +"description": "Tuning data statistics for Supervised Tuning.", +"id": "GoogleCloudAiplatformV1SupervisedTuningDataStats", +"properties": { +"totalBillableCharacterCount": { +"description": "Output only. Number of billable characters in the tuning dataset.", +"format": "int64", +"readOnly": true, +"type": "string" +}, +"totalTuningCharacterCount": { +"description": "Output only. Number of tuning characters in the tuning dataset.", +"format": "int64", +"readOnly": true, +"type": "string" +}, +"tuningDatasetExampleCount": { +"description": "Output only. Number of examples in the tuning dataset.", +"format": "int64", +"readOnly": true, +"type": "string" +}, +"tuningStepCount": { +"description": "Output only. Number of tuning steps for this Tuning Job.", +"format": "int64", +"readOnly": true, +"type": "string" +}, +"userDatasetExamples": { +"description": "Output only. Sample user messages in the training dataset uri.", +"items": { +"$ref": "GoogleCloudAiplatformV1Content" +}, +"readOnly": true, +"type": "array" +}, +"userInputTokenDistribution": { +"$ref": "GoogleCloudAiplatformV1SupervisedTuningDatasetDistribution", +"description": "Output only. Dataset distributions for the user input tokens.", +"readOnly": true +}, +"userMessagePerExampleDistribution": { +"$ref": "GoogleCloudAiplatformV1SupervisedTuningDatasetDistribution", +"description": "Output only. Dataset distributions for the messages per example.", +"readOnly": true +}, +"userOutputTokenDistribution": { +"$ref": "GoogleCloudAiplatformV1SupervisedTuningDatasetDistribution", +"description": "Output only. Dataset distributions for the user output tokens.", +"readOnly": true +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1SupervisedTuningDatasetDistribution": { +"description": "Dataset distribution for Supervised Tuning.", +"id": "GoogleCloudAiplatformV1SupervisedTuningDatasetDistribution", +"properties": { +"buckets": { +"description": "Output only. Defines the histogram bucket.", +"items": { +"$ref": "GoogleCloudAiplatformV1SupervisedTuningDatasetDistributionDatasetBucket" +}, +"readOnly": true, +"type": "array" +}, +"max": { +"description": "Output only. The maximum of the population values.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"mean": { +"description": "Output only. The arithmetic mean of the values in the population.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"median": { +"description": "Output only. The median of the values in the population.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"min": { +"description": "Output only. The minimum of the population values.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"p5": { +"description": "Output only. The 5th percentile of the values in the population.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"p95": { +"description": "Output only. The 95th percentile of the values in the population.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"sum": { +"description": "Output only. Sum of a given population of values.", +"format": "int64", +"readOnly": true, +"type": "string" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1SupervisedTuningDatasetDistributionDatasetBucket": { +"description": "Dataset bucket used to create a histogram for the distribution given a population of values.", +"id": "GoogleCloudAiplatformV1SupervisedTuningDatasetDistributionDatasetBucket", +"properties": { +"count": { +"description": "Output only. Number of values in the bucket.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"left": { +"description": "Output only. Left bound of the bucket.", +"format": "double", +"readOnly": true, +"type": "number" +}, +"right": { +"description": "Output only. Right bound of the bucket.", +"format": "double", +"readOnly": true, +"type": "number" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1SupervisedTuningSpec": { +"description": "Tuning Spec for Supervised Tuning.", +"id": "GoogleCloudAiplatformV1SupervisedTuningSpec", +"properties": { +"hyperParameters": { +"$ref": "GoogleCloudAiplatformV1SupervisedHyperParameters", +"description": "Optional. Hyperparameters for SFT." +}, +"trainingDatasetUri": { +"description": "Required. Cloud Storage path to file containing training dataset for tuning.", +"type": "string" +}, +"validationDatasetUri": { +"description": "Optional. Cloud Storage path to file containing validation dataset for tuning.", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1SyncFeatureViewRequest": { "description": "Request message for FeatureOnlineStoreAdminService.SyncFeatureView.", "id": "GoogleCloudAiplatformV1SyncFeatureViewRequest", @@ -35132,6 +35489,146 @@ false }, "type": "object" }, +"GoogleCloudAiplatformV1TunedModel": { +"description": "The Model Registry Model and Online Prediction Endpoint assiociated with this TuningJob.", +"id": "GoogleCloudAiplatformV1TunedModel", +"properties": { +"endpoint": { +"description": "Output only. A resource name of an Endpoint. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`.", +"readOnly": true, +"type": "string" +}, +"model": { +"description": "Output only. The resource name of the TunedModel. Format: `projects/{project}/locations/{location}/models/{model}`.", +"readOnly": true, +"type": "string" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1TuningDataStats": { +"description": "The tuning data statistic values for TuningJob.", +"id": "GoogleCloudAiplatformV1TuningDataStats", +"properties": { +"supervisedTuningDataStats": { +"$ref": "GoogleCloudAiplatformV1SupervisedTuningDataStats", +"description": "The SFT Tuning data stats." +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1TuningJob": { +"description": "Represents a TuningJob that runs with Google owned models.", +"id": "GoogleCloudAiplatformV1TuningJob", +"properties": { +"baseModel": { +"description": "Model name for tuning, e.g., \"gemini-1.0-pro-002\".", +"type": "string" +}, +"createTime": { +"description": "Output only. Time when the TuningJob was created.", +"format": "google-datetime", +"readOnly": true, +"type": "string" +}, +"description": { +"description": "Optional. The description of the TuningJob.", +"type": "string" +}, +"endTime": { +"description": "Output only. Time when the TuningJob entered any of the following JobStates: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`, `JOB_STATE_EXPIRED`.", +"format": "google-datetime", +"readOnly": true, +"type": "string" +}, +"error": { +"$ref": "GoogleRpcStatus", +"description": "Output only. Only populated when job's state is `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.", +"readOnly": true +}, +"experiment": { +"description": "Output only. The Experiment associated with this TuningJob.", +"readOnly": true, +"type": "string" +}, +"labels": { +"additionalProperties": { +"type": "string" +}, +"description": "Optional. The labels with user-defined metadata to organize TuningJob and generated resources such as Model and Endpoint. 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.", +"type": "object" +}, +"name": { +"description": "Output only. Identifier. Resource name of a TuningJob. Format: `projects/{project}/locations/{location}/tuningJobs/{tuning_job}`", +"readOnly": true, +"type": "string" +}, +"startTime": { +"description": "Output only. Time when the TuningJob for the first time entered the `JOB_STATE_RUNNING` state.", +"format": "google-datetime", +"readOnly": true, +"type": "string" +}, +"state": { +"description": "Output only. The detailed state of the job.", +"enum": [ +"JOB_STATE_UNSPECIFIED", +"JOB_STATE_QUEUED", +"JOB_STATE_PENDING", +"JOB_STATE_RUNNING", +"JOB_STATE_SUCCEEDED", +"JOB_STATE_FAILED", +"JOB_STATE_CANCELLING", +"JOB_STATE_CANCELLED", +"JOB_STATE_PAUSED", +"JOB_STATE_EXPIRED", +"JOB_STATE_UPDATING", +"JOB_STATE_PARTIALLY_SUCCEEDED" +], +"enumDescriptions": [ +"The job state is unspecified.", +"The job has been just created or resumed and processing has not yet begun.", +"The service is preparing to run the job.", +"The job is in progress.", +"The job completed successfully.", +"The job failed.", +"The job is being cancelled. From this state the job may only go to either `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED` or `JOB_STATE_CANCELLED`.", +"The job has been cancelled.", +"The job has been stopped, and can be resumed.", +"The job has expired.", +"The job is being updated. Only jobs in the `RUNNING` state can be updated. After updating, the job goes back to the `RUNNING` state.", +"The job is partially succeeded, some results may be missing due to errors." +], +"readOnly": true, +"type": "string" +}, +"supervisedTuningSpec": { +"$ref": "GoogleCloudAiplatformV1SupervisedTuningSpec", +"description": "Tuning Spec for Supervised Fine Tuning." +}, +"tunedModel": { +"$ref": "GoogleCloudAiplatformV1TunedModel", +"description": "Output only. The tuned model resources assiociated with this TuningJob.", +"readOnly": true +}, +"tunedModelDisplayName": { +"description": "Optional. The display name of the TunedModel. The name can be up to 128 characters long and can consist of any UTF-8 characters.", +"type": "string" +}, +"tuningDataStats": { +"$ref": "GoogleCloudAiplatformV1TuningDataStats", +"description": "Output only. The tuning data statistics associated with this TuningJob.", +"readOnly": true +}, +"updateTime": { +"description": "Output only. Time when the TuningJob was most recently updated.", +"format": "google-datetime", +"readOnly": true, +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1UndeployIndexOperationMetadata": { "description": "Runtime operation information for IndexEndpointService.UndeployIndex.", "id": "GoogleCloudAiplatformV1UndeployIndexOperationMetadata", @@ -36434,7 +36931,13 @@ false "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -36761,6 +37264,12 @@ false "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -37202,7 +37711,13 @@ false "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -37529,6 +38044,12 @@ false "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -37981,7 +38502,13 @@ false "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -38101,7 +38628,7 @@ false "", "", "", -"Github Github dataset with license info. We prefer this to help cite proper licenses for code recitation.", +"GitHub dataset with license info. We prefer this to help cite proper licenses for code recitation.", "", "", "", @@ -38308,6 +38835,12 @@ false "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -38749,7 +39282,13 @@ false "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -38869,7 +39408,7 @@ false "", "", "", -"Github Github dataset with license info. We prefer this to help cite proper licenses for code recitation.", +"GitHub dataset with license info. We prefer this to help cite proper licenses for code recitation.", "", "", "", @@ -39076,6 +39615,12 @@ false "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -39920,6 +40465,25 @@ false }, "type": "object" }, +"LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata": { +"id": "LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata", +"properties": { +"factRetrievalMillisecondsByProvider": { +"additionalProperties": { +"format": "int64", +"type": "string" +}, +"description": "Latency spent on fact retrievals. There might be multiple retrievals from different fact providers.", +"type": "object" +}, +"prompt2queryMilliseconds": { +"description": "Latency spent on prompt2query. The procedure generates a search-friendly query given the original prompt.", +"format": "int64", +"type": "string" +} +}, +"type": "object" +}, "LearningGenaiRootRAIOutput": { "description": "This is per harm.", "id": "LearningGenaiRootRAIOutput", @@ -40381,6 +40945,25 @@ false }, "type": "object" }, +"LearningGenaiRootTranslationRequestInfo": { +"description": "Each TranslationRequestInfo corresponds to a request sent to the translation server.", +"id": "LearningGenaiRootTranslationRequestInfo", +"properties": { +"detectedLanguageCodes": { +"description": "The ISO-639 language code of source text in the initial request, detected automatically, if no source language was passed within the initial request. If the source language was passed, auto-detection of the language does not occur and this field is empty.", +"items": { +"type": "string" +}, +"type": "array" +}, +"totalContentSize": { +"description": "The sum of the size of all the contents in the request.", +"format": "int64", +"type": "string" +} +}, +"type": "object" +}, "LearningServingLlmMessageMetadata": { "description": "LINT.IfChange This metadata contains additional information required for debugging.", "id": "LearningServingLlmMessageMetadata", diff --git a/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json b/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json index 94dceeecaa7..702075c9c62 100644 --- a/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json +++ b/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json @@ -305,51 +305,62 @@ }, "protocol": "rest", "resources": { -"media": { +"projects": { "methods": { -"upload": { -"description": "Upload a file into a RagCorpus.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}/ragFiles:upload", -"httpMethod": "POST", -"id": "aiplatform.media.upload", -"mediaUpload": { -"accept": [ -"*/*" +"getCacheConfig": { +"description": "Gets a GenAI cache config.", +"flatPath": "v1beta1/projects/{projectsId}/cacheConfig", +"httpMethod": "GET", +"id": "aiplatform.projects.getCacheConfig", +"parameterOrder": [ +"name" ], -"protocols": { -"simple": { -"multipart": true, -"path": "/upload/v1beta1/{+parent}/ragFiles:upload" -} +"parameters": { +"name": { +"description": "Required. Name of the cache config. Format: - `projects/{project}/cacheConfig`.", +"location": "path", +"pattern": "^projects/[^/]+/cacheConfig$", +"required": true, +"type": "string" } }, +"path": "v1beta1/{+name}", +"response": { +"$ref": "GoogleCloudAiplatformV1beta1CacheConfig" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"updateCacheConfig": { +"description": "Updates a cache config.", +"flatPath": "v1beta1/projects/{projectsId}/cacheConfig", +"httpMethod": "PATCH", +"id": "aiplatform.projects.updateCacheConfig", "parameterOrder": [ -"parent" +"name" ], "parameters": { -"parent": { -"description": "Required. The name of the RagCorpus resource into which to upload the file. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`", +"name": { +"description": "Identifier. Name of the cache config. Format: - `projects/{project}/cacheConfig`.", "location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+$", +"pattern": "^projects/[^/]+/cacheConfig$", "required": true, "type": "string" } }, -"path": "v1beta1/{+parent}/ragFiles:upload", +"path": "v1beta1/{+name}", "request": { -"$ref": "GoogleCloudAiplatformV1beta1UploadRagFileRequest" +"$ref": "GoogleCloudAiplatformV1beta1CacheConfig" }, "response": { -"$ref": "GoogleCloudAiplatformV1beta1UploadRagFileResponse" +"$ref": "GoogleLongrunningOperation" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform" -], -"supportsMediaUpload": true -} +] } }, -"projects": { "resources": { "locations": { "methods": { @@ -446,34 +457,6 @@ "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ] -}, -"retrieveContexts": { -"description": "Retrieves relevant contexts for a query.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}:retrieveContexts", -"httpMethod": "POST", -"id": "aiplatform.projects.locations.retrieveContexts", -"parameterOrder": [ -"parent" -], -"parameters": { -"parent": { -"description": "Required. The resource name of the Location from which to retrieve RagContexts. The users must have permission to make a call in the project. Format: `projects/{project}/locations/{location}`.", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+parent}:retrieveContexts", -"request": { -"$ref": "GoogleCloudAiplatformV1beta1RetrieveContextsRequest" -}, -"response": { -"$ref": "GoogleCloudAiplatformV1beta1RetrieveContextsResponse" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] } }, "resources": { @@ -3828,6 +3811,38 @@ } }, "resources": { +"chat": { +"methods": { +"completions": { +"description": "Exposes an OpenAI-compatible endpoint for chat completions.", +"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/endpoints/{endpointsId}/chat/completions", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.endpoints.chat.completions", +"parameterOrder": [ +"endpoint" +], +"parameters": { +"endpoint": { +"description": "Required. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/openapi`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/endpoints/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1beta1/{+endpoint}/chat/completions", +"request": { +"$ref": "GoogleApiHttpBody" +}, +"response": { +"$ref": "GoogleApiHttpBody" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +} +} +}, "operations": { "methods": { "cancel": { @@ -14339,127 +14354,6 @@ } }, "ragCorpora": { -"methods": { -"create": { -"description": "Creates a RagCorpus.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora", -"httpMethod": "POST", -"id": "aiplatform.projects.locations.ragCorpora.create", -"parameterOrder": [ -"parent" -], -"parameters": { -"parent": { -"description": "Required. The resource name of the Location to create the RagCorpus in. Format: `projects/{project}/locations/{location}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+parent}/ragCorpora", -"request": { -"$ref": "GoogleCloudAiplatformV1beta1RagCorpus" -}, -"response": { -"$ref": "GoogleLongrunningOperation" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -}, -"delete": { -"description": "Deletes a RagCorpus.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}", -"httpMethod": "DELETE", -"id": "aiplatform.projects.locations.ragCorpora.delete", -"parameterOrder": [ -"name" -], -"parameters": { -"force": { -"description": "Optional. If set to true, any RagFiles in this RagCorpus will also be deleted. Otherwise, the request will only work if the RagCorpus has no RagFiles.", -"location": "query", -"type": "boolean" -}, -"name": { -"description": "Required. The name of the RagCorpus resource to be deleted. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+name}", -"response": { -"$ref": "GoogleLongrunningOperation" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -}, -"get": { -"description": "Gets a RagCorpus.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}", -"httpMethod": "GET", -"id": "aiplatform.projects.locations.ragCorpora.get", -"parameterOrder": [ -"name" -], -"parameters": { -"name": { -"description": "Required. The name of the RagCorpus resource. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+name}", -"response": { -"$ref": "GoogleCloudAiplatformV1beta1RagCorpus" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -}, -"list": { -"description": "Lists RagCorpora in a Location.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora", -"httpMethod": "GET", -"id": "aiplatform.projects.locations.ragCorpora.list", -"parameterOrder": [ -"parent" -], -"parameters": { -"pageSize": { -"description": "Optional. The standard list page size.", -"format": "int32", -"location": "query", -"type": "integer" -}, -"pageToken": { -"description": "Optional. The standard list page token. Typically obtained via ListRagCorporaResponse.next_page_token of the previous VertexRagDataService.ListRagCorpora call.", -"location": "query", -"type": "string" -}, -"parent": { -"description": "Required. The resource name of the Location from which to list the RagCorpora. Format: `projects/{project}/locations/{location}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+parent}/ragCorpora", -"response": { -"$ref": "GoogleCloudAiplatformV1beta1ListRagCorporaResponse" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -} -}, "resources": { "operations": { "methods": { @@ -14613,122 +14507,6 @@ } }, "ragFiles": { -"methods": { -"delete": { -"description": "Deletes a RagFile.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}/ragFiles/{ragFilesId}", -"httpMethod": "DELETE", -"id": "aiplatform.projects.locations.ragCorpora.ragFiles.delete", -"parameterOrder": [ -"name" -], -"parameters": { -"name": { -"description": "Required. The name of the RagFile resource to be deleted. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+/ragFiles/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+name}", -"response": { -"$ref": "GoogleLongrunningOperation" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -}, -"get": { -"description": "Gets a RagFile.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}/ragFiles/{ragFilesId}", -"httpMethod": "GET", -"id": "aiplatform.projects.locations.ragCorpora.ragFiles.get", -"parameterOrder": [ -"name" -], -"parameters": { -"name": { -"description": "Required. The name of the RagFile resource. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}/ragFiles/{rag_file}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+/ragFiles/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+name}", -"response": { -"$ref": "GoogleCloudAiplatformV1beta1RagFile" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -}, -"import": { -"description": "Import files from Google Cloud Storage or Google Drive into a RagCorpus.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}/ragFiles:import", -"httpMethod": "POST", -"id": "aiplatform.projects.locations.ragCorpora.ragFiles.import", -"parameterOrder": [ -"parent" -], -"parameters": { -"parent": { -"description": "Required. The name of the RagCorpus resource into which to import files. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+parent}/ragFiles:import", -"request": { -"$ref": "GoogleCloudAiplatformV1beta1ImportRagFilesRequest" -}, -"response": { -"$ref": "GoogleLongrunningOperation" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -}, -"list": { -"description": "Lists RagFiles in a RagCorpus.", -"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/ragCorpora/{ragCorporaId}/ragFiles", -"httpMethod": "GET", -"id": "aiplatform.projects.locations.ragCorpora.ragFiles.list", -"parameterOrder": [ -"parent" -], -"parameters": { -"pageSize": { -"description": "Optional. The standard list page size.", -"format": "int32", -"location": "query", -"type": "integer" -}, -"pageToken": { -"description": "Optional. The standard list page token. Typically obtained via ListRagFilesResponse.next_page_token of the previous VertexRagDataService.ListRagFiles call.", -"location": "query", -"type": "string" -}, -"parent": { -"description": "Required. The resource name of the RagCorpus from which to list the RagFiles. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}`", -"location": "path", -"pattern": "^projects/[^/]+/locations/[^/]+/ragCorpora/[^/]+$", -"required": true, -"type": "string" -} -}, -"path": "v1beta1/{+parent}/ragFiles", -"response": { -"$ref": "GoogleCloudAiplatformV1beta1ListRagFilesResponse" -}, -"scopes": [ -"https://www.googleapis.com/auth/cloud-platform" -] -} -}, "resources": { "operations": { "methods": { @@ -18738,7 +18516,7 @@ } } }, -"revision": "20240328", +"revision": "20240404", "rootUrl": "https://aiplatform.googleapis.com/", "schemas": { "CloudAiLargeModelsVisionEmbedVideoResponse": { @@ -19335,6 +19113,10 @@ "CloudAiNlLlmProtoServiceMessageMetadata": { "id": "CloudAiNlLlmProtoServiceMessageMetadata", "properties": { +"factualityDebugMetadata": { +"$ref": "LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata", +"description": "Factuality-related debug metadata." +}, "inputFilterInfo": { "$ref": "LearningServingLlmMessageMetadata", "description": "Filter metadata of the input messages." @@ -19543,6 +19325,13 @@ }, "type": "array" }, +"translationRequestInfos": { +"description": "Translation request info during RAI for debugging purpose. Each TranslationRequestInfo corresponds to a request sent to the translation server.", +"items": { +"$ref": "LearningGenaiRootTranslationRequestInfo" +}, +"type": "array" +}, "triggeredBlocklist": { "description": "Whether the text triggered the blocklist.", "type": "boolean" @@ -20243,12 +20032,12 @@ ], "enumDescriptions": [ "", -"", -"", -"", -"", -"", -"" +"No Auth.", +"API Key Auth.", +"HTTP Basic Auth.", +"Google Service Account Auth.", +"OAuth auth.", +"OpenID Connect (OIDC) Auth." ], "type": "string" }, @@ -20296,11 +20085,11 @@ ], "enumDescriptions": [ "", -"", -"", -"", -"", -"" +"Element is in the HTTP request query.", +"Element is in the HTTP request header.", +"Element is in the HTTP request path.", +"Element is in the HTTP request body.", +"Element is in the HTTP request cookie." ], "type": "string" }, @@ -21213,6 +21002,21 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1CacheConfig": { +"description": "Config of GenAI caching features. This is a singleton resource.", +"id": "GoogleCloudAiplatformV1beta1CacheConfig", +"properties": { +"disableCache": { +"description": "If set to true, disables GenAI caching. Otherwise caching is enabled.", +"type": "boolean" +}, +"name": { +"description": "Identifier. Name of the cache config. Format: - `projects/{project}/cacheConfig`.", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1CancelBatchPredictionJobRequest": { "description": "Request message for JobService.CancelBatchPredictionJob.", "id": "GoogleCloudAiplatformV1beta1CancelBatchPredictionJobRequest", @@ -23137,12 +22941,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1DirectUploadSource": { -"description": "The input content is encapsulated and uploaded in the request.", -"id": "GoogleCloudAiplatformV1beta1DirectUploadSource", -"properties": {}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1DiskSpec": { "description": "Represents the spec of disk options.", "id": "GoogleCloudAiplatformV1beta1DiskSpec", @@ -23451,14 +23249,6 @@ "$ref": "GoogleCloudAiplatformV1beta1QuestionAnsweringRelevanceInput", "description": "Input for question answering relevance metric." }, -"ragContextRecallInput": { -"$ref": "GoogleCloudAiplatformV1beta1RagContextRecallInput", -"description": "Input for rag context recall metric." -}, -"responseRecallInput": { -"$ref": "GoogleCloudAiplatformV1beta1ResponseRecallInput", -"description": "Input for response recall metric." -}, "rougeInput": { "$ref": "GoogleCloudAiplatformV1beta1RougeInput", "description": "Instances and metric spec for rouge metric." @@ -23550,14 +23340,6 @@ "$ref": "GoogleCloudAiplatformV1beta1QuestionAnsweringRelevanceResult", "description": "Result for question answering relevance metric." }, -"ragContextRecallResult": { -"$ref": "GoogleCloudAiplatformV1beta1RagContextRecallResult", -"description": "RAG only metrics. Result for context recall metric." -}, -"responseRecallResult": { -"$ref": "GoogleCloudAiplatformV1beta1ResponseRecallResult", -"description": "Result for response recall metric." -}, "rougeResults": { "$ref": "GoogleCloudAiplatformV1beta1RougeResults", "description": "Results for rouge metric." @@ -24773,6 +24555,14 @@ "description": "Identifier. The resource name of the Extension.", "type": "string" }, +"privateServiceConnectConfig": { +"$ref": "GoogleCloudAiplatformV1beta1ExtensionPrivateServiceConnectConfig", +"description": "Optional. The PrivateServiceConnect config for the extension. If specified, the service endpoints associated with the Extension should be registered with private network access in the provided Service Directory (https://cloud.google.com/service-directory/docs/configuring-private-network-access). If the service contains more than one endpoint with a network, the service will arbitrarilty choose one of the endpoints to use for extension execution." +}, +"runtimeConfig": { +"$ref": "GoogleCloudAiplatformV1beta1RuntimeConfig", +"description": "Optional. Runtime config controlling the runtime behavior of this Extension." +}, "toolUseExamples": { "description": "Optional. Examples to illustrate the usage of the extension as a tool.", "items": { @@ -24843,6 +24633,17 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1ExtensionPrivateServiceConnectConfig": { +"description": "PrivateExtensionConfig configuration for the extension.", +"id": "GoogleCloudAiplatformV1beta1ExtensionPrivateServiceConnectConfig", +"properties": { +"serviceDirectory": { +"description": "Required. The Service Directory resource name in which the service endpoints associated to the extension are registered. Format: `projects/{project_id}/locations/{location_id}/namespaces/{namespace_id}/services/{service_id}` - The Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) should be granted `servicedirectory.viewer` and `servicedirectory.pscAuthorizedService` roles on the resource.", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1Feature": { "description": "Feature Metadata information. For example, color is a feature that describes an apple.", "id": "GoogleCloudAiplatformV1beta1Feature", @@ -26031,7 +25832,7 @@ "type": "object" }, "GoogleCloudAiplatformV1beta1FindNeighborsRequest": { -"description": "LINT.IfChange The request message for MatchService.FindNeighbors.", +"description": "The request message for MatchService.FindNeighbors.", "id": "GoogleCloudAiplatformV1beta1FindNeighborsRequest", "properties": { "deployedIndexId": { @@ -26580,6 +26381,10 @@ "format": "float", "type": "number" }, +"responseMimeType": { +"description": "Optional. Output response mimetype of the generated candidate text. Supported mimetype: `text/plain`: (default) Text output. `application/json`: JSON response in the candidates. The model needs to be prompted to output the appropriate response type, otherwise the behavior is undefined. This is a preview feature.", +"type": "string" +}, "stopSequences": { "description": "Optional. Stop sequences.", "items": { @@ -26643,45 +26448,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1GoogleDriveSource": { -"description": "The Google Drive location for the input content.", -"id": "GoogleCloudAiplatformV1beta1GoogleDriveSource", -"properties": { -"resourceIds": { -"description": "Required. Google Drive resource IDs.", -"items": { -"$ref": "GoogleCloudAiplatformV1beta1GoogleDriveSourceResourceId" -}, -"type": "array" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1GoogleDriveSourceResourceId": { -"description": "The type and ID of the Google Drive resource.", -"id": "GoogleCloudAiplatformV1beta1GoogleDriveSourceResourceId", -"properties": { -"resourceId": { -"description": "Required. The ID of the Google Drive resource.", -"type": "string" -}, -"resourceType": { -"description": "Required. The type of the Google Drive resource.", -"enum": [ -"RESOURCE_TYPE_UNSPECIFIED", -"RESOURCE_TYPE_FILE", -"RESOURCE_TYPE_FOLDER" -], -"enumDescriptions": [ -"Unspecified resource type.", -"File resource type.", -"Folder resource type." -], -"type": "string" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1GoogleSearchRetrieval": { "description": "Tool to retrieve public web data for grounding, powered by Google.", "id": "GoogleCloudAiplatformV1beta1GoogleSearchRetrieval", @@ -27200,36 +26966,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1ImportRagFilesConfig": { -"description": "Config for importing RagFiles.", -"id": "GoogleCloudAiplatformV1beta1ImportRagFilesConfig", -"properties": { -"gcsSource": { -"$ref": "GoogleCloudAiplatformV1beta1GcsSource", -"description": "Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats: * \"gs://bucket_name/my_directory/object_name/my_file.txt\". * \"gs://bucket_name/my_directory\"" -}, -"googleDriveSource": { -"$ref": "GoogleCloudAiplatformV1beta1GoogleDriveSource", -"description": "Google Drive location. Supports importing individual files as well as Google Drive folders." -}, -"ragFileChunkingConfig": { -"$ref": "GoogleCloudAiplatformV1beta1RagFileChunkingConfig", -"description": "Specifies the size and overlap of chunks after importing RagFiles." -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1ImportRagFilesRequest": { -"description": "Request message for VertexRagDataService.ImportRagFiles.", -"id": "GoogleCloudAiplatformV1beta1ImportRagFilesRequest", -"properties": { -"importRagFilesConfig": { -"$ref": "GoogleCloudAiplatformV1beta1ImportRagFilesConfig", -"description": "Required. The config for the RagFiles to be synced and imported into the RagCorpus. VertexRagDataService.ImportRagFiles." -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1Index": { "description": "A representation of a collection of database items organized in a way that allows for approximate nearest neighbor (a.k.a ANN) algorithms search.", "id": "GoogleCloudAiplatformV1beta1Index", @@ -28417,42 +28153,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1ListRagCorporaResponse": { -"description": "Response message for VertexRagDataService.ListRagCorpora.", -"id": "GoogleCloudAiplatformV1beta1ListRagCorporaResponse", -"properties": { -"nextPageToken": { -"description": "A token to retrieve the next page of results. Pass to ListRagCorporaRequest.page_token to obtain that page.", -"type": "string" -}, -"ragCorpora": { -"description": "List of RagCorpora in the requested page.", -"items": { -"$ref": "GoogleCloudAiplatformV1beta1RagCorpus" -}, -"type": "array" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1ListRagFilesResponse": { -"description": "Response message for VertexRagDataService.ListRagFiles.", -"id": "GoogleCloudAiplatformV1beta1ListRagFilesResponse", -"properties": { -"nextPageToken": { -"description": "A token to retrieve the next page of results. Pass to ListRagFilesRequest.page_token to obtain that page.", -"type": "string" -}, -"ragFiles": { -"description": "List of RagFiles in the requested page.", -"items": { -"$ref": "GoogleCloudAiplatformV1beta1RagFile" -}, -"type": "array" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1ListReasoningEnginesResponse": { "description": "Response message for ReasoningEngineService.ListReasoningEngines", "id": "GoogleCloudAiplatformV1beta1ListReasoningEnginesResponse", @@ -30803,7 +30503,8 @@ "OP_IN_DATAPOINT", "MULTIPLE_VALUES", "INVALID_NUMERIC_VALUE", -"INVALID_ENCODING" +"INVALID_ENCODING", +"INVALID_SPARSE_DIMENSIONS" ], "enumDescriptions": [ "Default, shall not be used.", @@ -30819,7 +30520,8 @@ "Numeric restrict has operator specified in datapoint.", "Numeric restrict has multiple values specified.", "Numeric restrict has invalid numeric value specified.", -"File is not in UTF_8 format." +"File is not in UTF_8 format.", +"Error parsing sparse dimensions field." ], "type": "string" }, @@ -31267,7 +30969,7 @@ "type": "string" }, "context": { -"description": "Optional. Text to answer the question.", +"description": "Required. Text to answer the question.", "type": "string" }, "instruction": { @@ -32417,10 +32119,6 @@ "$ref": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployGke", "description": "Optional. Deploy PublisherModel to Google Kubernetes Engine." }, -"multiDeployVertex": { -"$ref": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployVertex", -"description": "Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint." -}, "openEvaluationPipeline": { "$ref": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionRegionalResourceReferences", "description": "Optional. Open evaluation pipeline of the PublisherModel." @@ -32521,20 +32219,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployVertex": { -"description": "Multiple setups to deploy the PublisherModel.", -"id": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployVertex", -"properties": { -"multiDeployVertex": { -"description": "Optional. One click deployment configurations.", -"items": { -"$ref": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeploy" -}, -"type": "array" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1PublisherModelCallToActionOpenFineTuningPipelines": { "description": "Open fine tuning pipelines.", "id": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionOpenFineTuningPipelines", @@ -33107,7 +32791,7 @@ "id": "GoogleCloudAiplatformV1beta1QuestionAnsweringQualityInstance", "properties": { "context": { -"description": "Optional. Text to answer the question.", +"description": "Required. Text to answer the question.", "type": "string" }, "instruction": { @@ -33243,239 +32927,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1RagContextRecallInput": { -"description": "Input for rag context recall metric.", -"id": "GoogleCloudAiplatformV1beta1RagContextRecallInput", -"properties": { -"instance": { -"$ref": "GoogleCloudAiplatformV1beta1RagContextRecallInstance", -"description": "Required. Rag context recall instance." -}, -"metricSpec": { -"$ref": "GoogleCloudAiplatformV1beta1RagContextRecallSpec", -"description": "Required. Spec for rag context recall metric." -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagContextRecallInstance": { -"description": "Spec for rag context recall instance.", -"id": "GoogleCloudAiplatformV1beta1RagContextRecallInstance", -"properties": { -"context": { -"description": "Required. Retrieved facts from RAG pipeline as context to be evaluated.", -"type": "string" -}, -"reference": { -"description": "Required. Ground truth used to compare against the context.", -"type": "string" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagContextRecallResult": { -"description": "Spec for rag context recall result.", -"id": "GoogleCloudAiplatformV1beta1RagContextRecallResult", -"properties": { -"confidence": { -"description": "Output only. Confidence for rag context recall score.", -"format": "float", -"readOnly": true, -"type": "number" -}, -"explanation": { -"description": "Output only. Explanation for rag context recall score.", -"readOnly": true, -"type": "string" -}, -"score": { -"description": "Output only. RagContextRecall score.", -"format": "float", -"readOnly": true, -"type": "number" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagContextRecallSpec": { -"description": "Spec for rag context recall metric.", -"id": "GoogleCloudAiplatformV1beta1RagContextRecallSpec", -"properties": { -"version": { -"description": "Optional. Which version to use for evaluation.", -"format": "int32", -"type": "integer" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagContexts": { -"description": "Relevant contexts for one query.", -"id": "GoogleCloudAiplatformV1beta1RagContexts", -"properties": { -"contexts": { -"description": "All its contexts.", -"items": { -"$ref": "GoogleCloudAiplatformV1beta1RagContextsContext" -}, -"type": "array" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagContextsContext": { -"description": "A context of the query.", -"id": "GoogleCloudAiplatformV1beta1RagContextsContext", -"properties": { -"distance": { -"description": "The distance between the query vector and the context text vector.", -"format": "double", -"type": "number" -}, -"sourceUri": { -"description": "For vertex RagStore, if the file is imported from Cloud Storage or Google Drive, source_uri will be original file URI in Cloud Storage or Google Drive; if file is uploaded, source_uri will be file display name.", -"type": "string" -}, -"text": { -"description": "The text chunk.", -"type": "string" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagCorpus": { -"description": "A RagCorpus is a RagFile container and a project can have multiple RagCorpora.", -"id": "GoogleCloudAiplatformV1beta1RagCorpus", -"properties": { -"createTime": { -"description": "Output only. Timestamp when this RagCorpus was created.", -"format": "google-datetime", -"readOnly": true, -"type": "string" -}, -"description": { -"description": "Optional. The description of the RagCorpus.", -"type": "string" -}, -"displayName": { -"description": "Required. The display name of the RagCorpus. The name can be up to 128 characters long and can consist of any UTF-8 characters.", -"type": "string" -}, -"name": { -"description": "Output only. The resource name of the RagCorpus.", -"readOnly": true, -"type": "string" -}, -"updateTime": { -"description": "Output only. Timestamp when this RagCorpus was last updated.", -"format": "google-datetime", -"readOnly": true, -"type": "string" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagFile": { -"description": "A RagFile contains user data for chunking, embedding and indexing.", -"id": "GoogleCloudAiplatformV1beta1RagFile", -"properties": { -"createTime": { -"description": "Output only. Timestamp when this RagFile was created.", -"format": "google-datetime", -"readOnly": true, -"type": "string" -}, -"description": { -"description": "Optional. The description of the RagFile.", -"type": "string" -}, -"directUploadSource": { -"$ref": "GoogleCloudAiplatformV1beta1DirectUploadSource", -"description": "Output only. The RagFile is encapsulated and uploaded in the UploadRagFile request.", -"readOnly": true -}, -"displayName": { -"description": "Required. The display name of the RagFile. The name can be up to 128 characters long and can consist of any UTF-8 characters.", -"type": "string" -}, -"gcsSource": { -"$ref": "GoogleCloudAiplatformV1beta1GcsSource", -"description": "Output only. Google Cloud Storage location of the RagFile. It does not support wildcards in the GCS uri for now.", -"readOnly": true -}, -"googleDriveSource": { -"$ref": "GoogleCloudAiplatformV1beta1GoogleDriveSource", -"description": "Output only. Google Drive location. Supports importing individual files as well as Google Drive folders.", -"readOnly": true -}, -"name": { -"description": "Output only. The resource name of the RagFile.", -"readOnly": true, -"type": "string" -}, -"ragFileType": { -"description": "Output only. The type of the RagFile.", -"enum": [ -"RAG_FILE_TYPE_UNSPECIFIED", -"RAG_FILE_TYPE_TXT", -"RAG_FILE_TYPE_PDF" -], -"enumDescriptions": [ -"RagFile type is unspecified.", -"RagFile type is TXT.", -"RagFile type is PDF." -], -"readOnly": true, -"type": "string" -}, -"sizeBytes": { -"description": "Output only. The size of the RagFile in bytes.", -"format": "int64", -"readOnly": true, -"type": "string" -}, -"updateTime": { -"description": "Output only. Timestamp when this RagFile was last updated.", -"format": "google-datetime", -"readOnly": true, -"type": "string" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagFileChunkingConfig": { -"description": "Specifies the size and overlap of chunks for RagFiles.", -"id": "GoogleCloudAiplatformV1beta1RagFileChunkingConfig", -"properties": { -"chunkOverlap": { -"description": "The overlap between chunks.", -"format": "int32", -"type": "integer" -}, -"chunkSize": { -"description": "The size of the chunks.", -"format": "int32", -"type": "integer" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RagQuery": { -"description": "A query to retrieve relevant contexts.", -"id": "GoogleCloudAiplatformV1beta1RagQuery", -"properties": { -"similarityTopK": { -"description": "Optional. The number of contexts to retrieve.", -"format": "int32", -"type": "integer" -}, -"text": { -"description": "Optional. The query in text format to get relevant contexts.", -"type": "string" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1RawPredictRequest": { "description": "Request message for PredictionService.RawPredict.", "id": "GoogleCloudAiplatformV1beta1RawPredictRequest", @@ -34068,72 +33519,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1ResponseRecallInput": { -"description": "Input for response recall metric.", -"id": "GoogleCloudAiplatformV1beta1ResponseRecallInput", -"properties": { -"instance": { -"$ref": "GoogleCloudAiplatformV1beta1ResponseRecallInstance", -"description": "Required. Response recall instance." -}, -"metricSpec": { -"$ref": "GoogleCloudAiplatformV1beta1ResponseRecallSpec", -"description": "Required. Spec for response recall score metric." -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1ResponseRecallInstance": { -"description": "Spec for response recall instance.", -"id": "GoogleCloudAiplatformV1beta1ResponseRecallInstance", -"properties": { -"prediction": { -"description": "Required. Output of the evaluated model.", -"type": "string" -}, -"reference": { -"description": "Required. Ground truth used to compare against the prediction.", -"type": "string" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1ResponseRecallResult": { -"description": "Spec for response recall result.", -"id": "GoogleCloudAiplatformV1beta1ResponseRecallResult", -"properties": { -"confidence": { -"description": "Output only. Confidence for fulfillment score.", -"format": "float", -"readOnly": true, -"type": "number" -}, -"explanation": { -"description": "Output only. Explanation for response recall score.", -"readOnly": true, -"type": "string" -}, -"score": { -"description": "Output only. ResponseRecall score.", -"format": "float", -"readOnly": true, -"type": "number" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1ResponseRecallSpec": { -"description": "Spec for response recall metric.", -"id": "GoogleCloudAiplatformV1beta1ResponseRecallSpec", -"properties": { -"version": { -"description": "Optional. Which version to use for evaluation.", -"format": "int32", -"type": "integer" -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1RestoreDatasetVersionOperationMetadata": { "description": "Runtime operation information for DatasetService.RestoreDatasetVersion.", "id": "GoogleCloudAiplatformV1beta1RestoreDatasetVersionOperationMetadata", @@ -34181,46 +33566,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1RetrieveContextsRequest": { -"description": "Request message for VertexRagService.RetrieveContexts.", -"id": "GoogleCloudAiplatformV1beta1RetrieveContextsRequest", -"properties": { -"query": { -"$ref": "GoogleCloudAiplatformV1beta1RagQuery", -"description": "Required. Single RAG retrieve query." -}, -"vertexRagStore": { -"$ref": "GoogleCloudAiplatformV1beta1RetrieveContextsRequestVertexRagStore", -"description": "The data source for Vertex RagStore." -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RetrieveContextsRequestVertexRagStore": { -"description": "The data source for Vertex RagStore.", -"id": "GoogleCloudAiplatformV1beta1RetrieveContextsRequestVertexRagStore", -"properties": { -"ragCorpora": { -"description": "Required. RagCorpora resource name. Format: `projects/{project}/locations/{location}/ragCorpora/{rag_corpus}` Currently only one corpus is allowed. In the future we may open up multiple corpora support. However, they should be from the same project and location.", -"items": { -"type": "string" -}, -"type": "array" -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1RetrieveContextsResponse": { -"description": "Response message for VertexRagService.RetrieveContexts.", -"id": "GoogleCloudAiplatformV1beta1RetrieveContextsResponse", -"properties": { -"contexts": { -"$ref": "GoogleCloudAiplatformV1beta1RagContexts", -"description": "The contexts of the query." -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1RougeInput": { "description": "Input for rouge metric.", "id": "GoogleCloudAiplatformV1beta1RougeInput", @@ -34301,6 +33646,53 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1RuntimeConfig": { +"description": "Runtime configuration to run the extension.", +"id": "GoogleCloudAiplatformV1beta1RuntimeConfig", +"properties": { +"codeInterpreterRuntimeConfig": { +"$ref": "GoogleCloudAiplatformV1beta1RuntimeConfigCodeInterpreterRuntimeConfig", +"description": "Code execution runtime configurations for code interpreter extension." +}, +"defaultParams": { +"additionalProperties": { +"description": "Properties of the object.", +"type": "any" +}, +"description": "Optional. Default parameters that will be set for all the execution of this extension. If specified, the parameter values can be overridden by values in [[ExecuteExtensionRequest.operation_params]] at request time. The struct should be in a form of map with param name as the key and actual param value as the value. E.g. If this operation requires a param \"name\" to be set to \"abc\". you can set this to something like {\"name\": \"abc\"}.", +"type": "object" +}, +"vertexAiSearchRuntimeConfig": { +"$ref": "GoogleCloudAiplatformV1beta1RuntimeConfigVertexAISearchRuntimeConfig", +"description": "Runtime configuration for Vertext AI Search extension." +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1RuntimeConfigCodeInterpreterRuntimeConfig": { +"id": "GoogleCloudAiplatformV1beta1RuntimeConfigCodeInterpreterRuntimeConfig", +"properties": { +"fileInputGcsBucket": { +"description": "Optional. The GCS bucket for file input of this Extension. If specified, support input from the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file reader to this bucket. If not specified, the extension will only accept file contents from request body and reject GCS file inputs.", +"type": "string" +}, +"fileOutputGcsBucket": { +"description": "Optional. The GCS bucket for file output of this Extension. If specified, write all output files to the GCS bucket. Vertex Extension Custom Code Service Agent should be granted file writer to this bucket. If not specified, the file content will be output in response body.", +"type": "string" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1RuntimeConfigVertexAISearchRuntimeConfig": { +"id": "GoogleCloudAiplatformV1beta1RuntimeConfigVertexAISearchRuntimeConfig", +"properties": { +"servingConfigName": { +"description": "Required. Vertext AI Search serving config name. Format: `projects/{project}/locations/{location}/collections/{collection}/engines/{engine}/servingConfigs/{serving_config}` or `projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/servingConfigs/{serving_config}`", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1SafetyInput": { "description": "Input for safety metric.", "id": "GoogleCloudAiplatformV1beta1SafetyInput", @@ -35453,6 +34845,78 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsPairwiseTextGenerationEvaluationMetrics": { +"description": "Metrics for general pairwise text generation evaluation results.", +"id": "GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsPairwiseTextGenerationEvaluationMetrics", +"properties": { +"accuracy": { +"description": "Fraction of cases where the autorater agreed with the human raters.", +"format": "float", +"type": "number" +}, +"baselineModelWinRate": { +"description": "Percentage of time the autorater decided the baseline model had the better response.", +"format": "float", +"type": "number" +}, +"cohensKappa": { +"description": "A measurement of agreement between the autorater and human raters that takes the likelihood of random agreement into account.", +"format": "float", +"type": "number" +}, +"f1Score": { +"description": "Harmonic mean of precision and recall.", +"format": "float", +"type": "number" +}, +"falseNegativeCount": { +"description": "Number of examples where the autorater chose the baseline model, but humans preferred the model.", +"format": "int64", +"type": "string" +}, +"falsePositiveCount": { +"description": "Number of examples where the autorater chose the model, but humans preferred the baseline model.", +"format": "int64", +"type": "string" +}, +"humanPreferenceBaselineModelWinRate": { +"description": "Percentage of time humans decided the baseline model had the better response.", +"format": "float", +"type": "number" +}, +"humanPreferenceModelWinRate": { +"description": "Percentage of time humans decided the model had the better response.", +"format": "float", +"type": "number" +}, +"modelWinRate": { +"description": "Percentage of time the autorater decided the model had the better response.", +"format": "float", +"type": "number" +}, +"precision": { +"description": "Fraction of cases where the autorater and humans thought the model had a better response out of all cases where the autorater thought the model had a better response. True positive divided by all positive.", +"format": "float", +"type": "number" +}, +"recall": { +"description": "Fraction of cases where the autorater and humans thought the model had a better response out of all cases where the humans thought the model had a better response.", +"format": "float", +"type": "number" +}, +"trueNegativeCount": { +"description": "Number of examples where both the autorater and humans decided that the model had the worse response.", +"format": "int64", +"type": "string" +}, +"truePositiveCount": { +"description": "Number of examples where both the autorater and humans decided that the model had the better response.", +"format": "int64", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsQuestionAnsweringEvaluationMetrics": { "id": "GoogleCloudAiplatformV1beta1SchemaModelevaluationMetricsQuestionAnsweringEvaluationMetrics", "properties": { @@ -38692,7 +38156,7 @@ "type": "boolean" }, "serviceAccount": { -"description": "Optional. Default service account that this PersistentResource's workloads run as. The workloads include: * Any runtime specified via `ResourceRuntimeSpec` on creation time, for example, Ray. * Jobs submitted to PersistentResource, if no other service account specified in the job specs. Only works when custom service account is enabled and users have the `iam.serviceAccounts.actAs` permission on this service account. Required if any containers are specified in `ResourceRuntimeSpec`.", +"description": "Optional. Required when all below conditions are met * `enable_custom_service_account` is true; * any runtime is specified via `ResourceRuntimeSpec` on creation time, for example, Ray The users must have `iam.serviceAccounts.actAs` permission on this service account and then the specified runtime containers will run as it. Do not set this field if you want to submit jobs using custom service account to this PersistentResource after creation, but only specify the `service_account` inside the job.", "type": "string" } }, @@ -41324,47 +40788,6 @@ }, "type": "object" }, -"GoogleCloudAiplatformV1beta1UploadRagFileConfig": { -"description": "Config for uploading RagFile.", -"id": "GoogleCloudAiplatformV1beta1UploadRagFileConfig", -"properties": { -"ragFileChunkingConfig": { -"$ref": "GoogleCloudAiplatformV1beta1RagFileChunkingConfig", -"description": "Specifies the size and overlap of chunks after uploading RagFile." -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1UploadRagFileRequest": { -"description": "Request message for VertexRagDataService.UploadRagFile.", -"id": "GoogleCloudAiplatformV1beta1UploadRagFileRequest", -"properties": { -"ragFile": { -"$ref": "GoogleCloudAiplatformV1beta1RagFile", -"description": "Required. The RagFile to upload." -}, -"uploadRagFileConfig": { -"$ref": "GoogleCloudAiplatformV1beta1UploadRagFileConfig", -"description": "Required. The config for the RagFiles to be uploaded into the RagCorpus. VertexRagDataService.UploadRagFile." -} -}, -"type": "object" -}, -"GoogleCloudAiplatformV1beta1UploadRagFileResponse": { -"description": "Response message for VertexRagDataService.UploadRagFile.", -"id": "GoogleCloudAiplatformV1beta1UploadRagFileResponse", -"properties": { -"error": { -"$ref": "GoogleRpcStatus", -"description": "The error that occurred while processing the RagFile." -}, -"ragFile": { -"$ref": "GoogleCloudAiplatformV1beta1RagFile", -"description": "The RagFile that had been uploaded into the RagCorpus." -} -}, -"type": "object" -}, "GoogleCloudAiplatformV1beta1UpsertDatapointsRequest": { "description": "Request message for IndexService.UpsertDatapoints", "id": "GoogleCloudAiplatformV1beta1UpsertDatapointsRequest", @@ -42407,7 +41830,13 @@ "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -42734,6 +42163,12 @@ "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -43175,7 +42610,13 @@ "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -43502,6 +42943,12 @@ "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -43954,7 +43401,13 @@ "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -44074,7 +43527,7 @@ "", "", "", -"Github Github dataset with license info. We prefer this to help cite proper licenses for code recitation.", +"GitHub dataset with license info. We prefer this to help cite proper licenses for code recitation.", "", "", "", @@ -44281,6 +43734,12 @@ "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -44722,7 +44181,13 @@ "CLOUD_GEMIT_AMPS", "CLOUD_GEMIT_AQUA", "CLOUD_GEMIT_COMMON_SENSE_REASONING_SCHEMA", -"CLOUD_GEMIT_GSM8K_SCHEMA" +"CLOUD_GEMIT_GSM8K_SCHEMA", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_UN", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_EUROPARL", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_WMT_NEWSCOMMENTARY", +"GEMINI_V1_TAIL_PATCH_TRANSLATION_2021_INCR", +"GEMINI_V1_TAIL_PATCH_GOALDMINE", +"GEMINI_V1_TAIL_PATCH_PHOTOMATH_IM2SOL_PROBLEM_AND_SOLUTION" ], "enumDescriptions": [ "", @@ -44842,7 +44307,7 @@ "", "", "", -"Github Github dataset with license info. We prefer this to help cite proper licenses for code recitation.", +"GitHub dataset with license info. We prefer this to help cite proper licenses for code recitation.", "", "", "", @@ -45049,6 +44514,12 @@ "", "", "", +"", +"Gemini V1 tail patch translation.", +"", +"", +"", +"Gemini V1 tail patch others.", "" ], "type": "string" @@ -45893,6 +45364,25 @@ false }, "type": "object" }, +"LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata": { +"id": "LearningGenaiRootPerRequestProcessorDebugMetadataFactualityDebugMetadata", +"properties": { +"factRetrievalMillisecondsByProvider": { +"additionalProperties": { +"format": "int64", +"type": "string" +}, +"description": "Latency spent on fact retrievals. There might be multiple retrievals from different fact providers.", +"type": "object" +}, +"prompt2queryMilliseconds": { +"description": "Latency spent on prompt2query. The procedure generates a search-friendly query given the original prompt.", +"format": "int64", +"type": "string" +} +}, +"type": "object" +}, "LearningGenaiRootRAIOutput": { "description": "This is per harm.", "id": "LearningGenaiRootRAIOutput", @@ -46354,6 +45844,25 @@ false }, "type": "object" }, +"LearningGenaiRootTranslationRequestInfo": { +"description": "Each TranslationRequestInfo corresponds to a request sent to the translation server.", +"id": "LearningGenaiRootTranslationRequestInfo", +"properties": { +"detectedLanguageCodes": { +"description": "The ISO-639 language code of source text in the initial request, detected automatically, if no source language was passed within the initial request. If the source language was passed, auto-detection of the language does not occur and this field is empty.", +"items": { +"type": "string" +}, +"type": "array" +}, +"totalContentSize": { +"description": "The sum of the size of all the contents in the request.", +"format": "int64", +"type": "string" +} +}, +"type": "object" +}, "LearningServingLlmMessageMetadata": { "description": "LINT.IfChange This metadata contains additional information required for debugging.", "id": "LearningServingLlmMessageMetadata",