google-api-python-client 2.107.0__py2.py3-none-any.whl → 2.109.0__py2.py3-none-any.whl

googleapiclient/discovery_cache/documents/aiplatform.v1.json

@@ -2620,6 +2620,158 @@
               }
             },
             "deploymentResourcePools": {
+              "methods": {
+                "create": {
+                  "description": "Create a DeploymentResourcePool.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/deploymentResourcePools",
+                  "httpMethod": "POST",
+                  "id": "aiplatform.projects.locations.deploymentResourcePools.create",
+                  "parameterOrder": [
+                    "parent"
+                  ],
+                  "parameters": {
+                    "parent": {
+                      "description": "Required. The parent location resource where this DeploymentResourcePool will be created. Format: `projects/{project}/locations/{location}`",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+parent}/deploymentResourcePools",
+                  "request": {
+                    "$ref": "GoogleCloudAiplatformV1CreateDeploymentResourcePoolRequest"
+                  },
+                  "response": {
+                    "$ref": "GoogleLongrunningOperation"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                },
+                "delete": {
+                  "description": "Delete a DeploymentResourcePool.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/deploymentResourcePools/{deploymentResourcePoolsId}",
+                  "httpMethod": "DELETE",
+                  "id": "aiplatform.projects.locations.deploymentResourcePools.delete",
+                  "parameterOrder": [
+                    "name"
+                  ],
+                  "parameters": {
+                    "name": {
+                      "description": "Required. The name of the DeploymentResourcePool to delete. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+/deploymentResourcePools/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+name}",
+                  "response": {
+                    "$ref": "GoogleLongrunningOperation"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                },
+                "get": {
+                  "description": "Get a DeploymentResourcePool.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/deploymentResourcePools/{deploymentResourcePoolsId}",
+                  "httpMethod": "GET",
+                  "id": "aiplatform.projects.locations.deploymentResourcePools.get",
+                  "parameterOrder": [
+                    "name"
+                  ],
+                  "parameters": {
+                    "name": {
+                      "description": "Required. The name of the DeploymentResourcePool to retrieve. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+/deploymentResourcePools/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+name}",
+                  "response": {
+                    "$ref": "GoogleCloudAiplatformV1DeploymentResourcePool"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                },
+                "list": {
+                  "description": "List DeploymentResourcePools in a location.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/deploymentResourcePools",
+                  "httpMethod": "GET",
+                  "id": "aiplatform.projects.locations.deploymentResourcePools.list",
+                  "parameterOrder": [
+                    "parent"
+                  ],
+                  "parameters": {
+                    "pageSize": {
+                      "description": "The maximum number of DeploymentResourcePools to return. The service may return fewer than this value.",
+                      "format": "int32",
+                      "location": "query",
+                      "type": "integer"
+                    },
+                    "pageToken": {
+                      "description": "A page token, received from a previous `ListDeploymentResourcePools` call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to `ListDeploymentResourcePools` must match the call that provided the page token.",
+                      "location": "query",
+                      "type": "string"
+                    },
+                    "parent": {
+                      "description": "Required. The parent Location which owns this collection of DeploymentResourcePools. Format: `projects/{project}/locations/{location}`",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+parent}/deploymentResourcePools",
+                  "response": {
+                    "$ref": "GoogleCloudAiplatformV1ListDeploymentResourcePoolsResponse"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                },
+                "queryDeployedModels": {
+                  "description": "List DeployedModels that have been deployed on this DeploymentResourcePool.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/deploymentResourcePools/{deploymentResourcePoolsId}:queryDeployedModels",
+                  "httpMethod": "GET",
+                  "id": "aiplatform.projects.locations.deploymentResourcePools.queryDeployedModels",
+                  "parameterOrder": [
+                    "deploymentResourcePool"
+                  ],
+                  "parameters": {
+                    "deploymentResourcePool": {
+                      "description": "Required. The name of the target DeploymentResourcePool to query. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+/deploymentResourcePools/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    },
+                    "pageSize": {
+                      "description": "The maximum number of DeployedModels to return. The service may return fewer than this value.",
+                      "format": "int32",
+                      "location": "query",
+                      "type": "integer"
+                    },
+                    "pageToken": {
+                      "description": "A page token, received from a previous `QueryDeployedModels` call. Provide this to retrieve the subsequent page. When paginating, all other parameters provided to `QueryDeployedModels` must match the call that provided the page token.",
+                      "location": "query",
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+deploymentResourcePool}:queryDeployedModels",
+                  "response": {
+                    "$ref": "GoogleCloudAiplatformV1QueryDeployedModelsResponse"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                }
+              },
               "resources": {
                 "operations": {
                   "methods": {
@@ -2776,6 +2928,62 @@
             },
             "endpoints": {
               "methods": {
+                "computeTokens": {
+                  "description": "Return a list of tokens based on the input text.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/endpoints/{endpointsId}:computeTokens",
+                  "httpMethod": "POST",
+                  "id": "aiplatform.projects.locations.endpoints.computeTokens",
+                  "parameterOrder": [
+                    "endpoint"
+                  ],
+                  "parameters": {
+                    "endpoint": {
+                      "description": "Required. The name of the Endpoint requested to get lists of tokens and token ids.",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+/endpoints/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+endpoint}:computeTokens",
+                  "request": {
+                    "$ref": "GoogleCloudAiplatformV1ComputeTokensRequest"
+                  },
+                  "response": {
+                    "$ref": "GoogleCloudAiplatformV1ComputeTokensResponse"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                },
+                "countTokens": {
+                  "description": "Perform a token counting.",
+                  "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/endpoints/{endpointsId}:countTokens",
+                  "httpMethod": "POST",
+                  "id": "aiplatform.projects.locations.endpoints.countTokens",
+                  "parameterOrder": [
+                    "endpoint"
+                  ],
+                  "parameters": {
+                    "endpoint": {
+                      "description": "Required. The name of the Endpoint requested to perform token counting. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`",
+                      "location": "path",
+                      "pattern": "^projects/[^/]+/locations/[^/]+/endpoints/[^/]+$",
+                      "required": true,
+                      "type": "string"
+                    }
+                  },
+                  "path": "v1/{+endpoint}:countTokens",
+                  "request": {
+                    "$ref": "GoogleCloudAiplatformV1CountTokensRequest"
+                  },
+                  "response": {
+                    "$ref": "GoogleCloudAiplatformV1CountTokensResponse"
+                  },
+                  "scopes": [
+                    "https://www.googleapis.com/auth/cloud-platform"
+                  ]
+                },
                 "create": {
                   "description": "Creates an Endpoint.",
                   "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/endpoints",
@@ -10838,6 +11046,62 @@
               "resources": {
                 "models": {
                   "methods": {
+                    "computeTokens": {
+                      "description": "Return a list of tokens based on the input text.",
+                      "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/publishers/{publishersId}/models/{modelsId}:computeTokens",
+                      "httpMethod": "POST",
+                      "id": "aiplatform.projects.locations.publishers.models.computeTokens",
+                      "parameterOrder": [
+                        "endpoint"
+                      ],
+                      "parameters": {
+                        "endpoint": {
+                          "description": "Required. The name of the Endpoint requested to get lists of tokens and token ids.",
+                          "location": "path",
+                          "pattern": "^projects/[^/]+/locations/[^/]+/publishers/[^/]+/models/[^/]+$",
+                          "required": true,
+                          "type": "string"
+                        }
+                      },
+                      "path": "v1/{+endpoint}:computeTokens",
+                      "request": {
+                        "$ref": "GoogleCloudAiplatformV1ComputeTokensRequest"
+                      },
+                      "response": {
+                        "$ref": "GoogleCloudAiplatformV1ComputeTokensResponse"
+                      },
+                      "scopes": [
+                        "https://www.googleapis.com/auth/cloud-platform"
+                      ]
+                    },
+                    "countTokens": {
+                      "description": "Perform a token counting.",
+                      "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/publishers/{publishersId}/models/{modelsId}:countTokens",
+                      "httpMethod": "POST",
+                      "id": "aiplatform.projects.locations.publishers.models.countTokens",
+                      "parameterOrder": [
+                        "endpoint"
+                      ],
+                      "parameters": {
+                        "endpoint": {
+                          "description": "Required. The name of the Endpoint requested to perform token counting. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`",
+                          "location": "path",
+                          "pattern": "^projects/[^/]+/locations/[^/]+/publishers/[^/]+/models/[^/]+$",
+                          "required": true,
+                          "type": "string"
+                        }
+                      },
+                      "path": "v1/{+endpoint}:countTokens",
+                      "request": {
+                        "$ref": "GoogleCloudAiplatformV1CountTokensRequest"
+                      },
+                      "response": {
+                        "$ref": "GoogleCloudAiplatformV1CountTokensResponse"
+                      },
+                      "scopes": [
+                        "https://www.googleapis.com/auth/cloud-platform"
+                      ]
+                    },
                     "predict": {
                       "description": "Perform an online prediction.",
                       "flatPath": "v1/projects/{projectsId}/locations/{locationsId}/publishers/{publishersId}/models/{modelsId}:predict",
@@ -14336,7 +14600,7 @@
       }
     }
   },
-  "revision": "20231101",
+  "revision": "20231121",
   "rootUrl": "https://aiplatform.googleapis.com/",
   "schemas": {
     "GoogleApiHttpBody": {
@@ -15526,6 +15790,34 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1ComputeTokensRequest": {
+      "description": "Request message for ComputeTokens RPC call.",
+      "id": "GoogleCloudAiplatformV1ComputeTokensRequest",
+      "properties": {
+        "instances": {
+          "description": "Required. The instances that are the input to token computing API call. Schema is identical to the prediction schema of the text model, even for the non-text models, like chat models, or Codey models.",
+          "items": {
+            "type": "any"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "GoogleCloudAiplatformV1ComputeTokensResponse": {
+      "description": "Response message for ComputeTokens RPC call.",
+      "id": "GoogleCloudAiplatformV1ComputeTokensResponse",
+      "properties": {
+        "tokensInfo": {
+          "description": "Lists of tokens info from the input. A ComputeTokensRequest could have multiple instances with a prompt in each instance. We also need to return lists of tokens info for the request with multiple instances.",
+          "items": {
+            "$ref": "GoogleCloudAiplatformV1TokensInfo"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1ContainerRegistryDestination": {
       "description": "The Container Registry location for the container image.",
       "id": "GoogleCloudAiplatformV1ContainerRegistryDestination",
@@ -15685,6 +15977,37 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1CountTokensRequest": {
+      "description": "Request message for PredictionService.CountTokens.",
+      "id": "GoogleCloudAiplatformV1CountTokensRequest",
+      "properties": {
+        "instances": {
+          "description": "Required. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.",
+          "items": {
+            "type": "any"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "GoogleCloudAiplatformV1CountTokensResponse": {
+      "description": "Response message for PredictionService.CountTokens.",
+      "id": "GoogleCloudAiplatformV1CountTokensResponse",
+      "properties": {
+        "totalBillableCharacters": {
+          "description": "The total number of billable characters counted across all instances from the request.",
+          "format": "int32",
+          "type": "integer"
+        },
+        "totalTokens": {
+          "description": "The total number of tokens counted across all instances from the request.",
+          "format": "int32",
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1CreateDatasetOperationMetadata": {
       "description": "Runtime operation information for DatasetService.CreateDataset.",
       "id": "GoogleCloudAiplatformV1CreateDatasetOperationMetadata",
@@ -15707,6 +16030,32 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1CreateDeploymentResourcePoolOperationMetadata": {
+      "description": "Runtime operation information for CreateDeploymentResourcePool method.",
+      "id": "GoogleCloudAiplatformV1CreateDeploymentResourcePoolOperationMetadata",
+      "properties": {
+        "genericMetadata": {
+          "$ref": "GoogleCloudAiplatformV1GenericOperationMetadata",
+          "description": "The operation generic information."
+        }
+      },
+      "type": "object"
+    },
+    "GoogleCloudAiplatformV1CreateDeploymentResourcePoolRequest": {
+      "description": "Request message for CreateDeploymentResourcePool method.",
+      "id": "GoogleCloudAiplatformV1CreateDeploymentResourcePoolRequest",
+      "properties": {
+        "deploymentResourcePool": {
+          "$ref": "GoogleCloudAiplatformV1DeploymentResourcePool",
+          "description": "Required. The DeploymentResourcePool to create."
+        },
+        "deploymentResourcePoolId": {
+          "description": "Required. The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are `/^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/`.",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1CreateEndpointOperationMetadata": {
       "description": "Runtime operation information for EndpointService.CreateEndpoint.",
       "id": "GoogleCloudAiplatformV1CreateEndpointOperationMetadata",
@@ -16676,7 +17025,7 @@
         },
         "dedicatedResources": {
           "$ref": "GoogleCloudAiplatformV1DedicatedResources",
-          "description": "Optional. A description of resources that are dedicated to the DeployedIndex, and that need a higher degree of manual configuration. If min_replica_count is not set, the default value is 2 (we don't provide SLA when min_replica_count=1). If max_replica_count is not set, the default value is min_replica_count. The max allowed replica count is 1000. Available machine types for SMALL shard: e2-standard-2 and all machine types available for MEDIUM and LARGE shard. Available machine types for MEDIUM shard: e2-standard-16 and all machine types available for LARGE shard. Available machine types for LARGE shard: e2-highmem-16, n2d-standard-32. n1-standard-16 and n1-standard-32 are still available, but we recommend e2-standard-16 and e2-highmem-16 for cost efficiency."
+          "description": "Optional. A description of resources that are dedicated to the DeployedIndex, and that need a higher degree of manual configuration. The field min_replica_count must be set to a value strictly greater than 0, or else validation will fail. We don't provide SLA when min_replica_count=1. If max_replica_count is not set, the default value is min_replica_count. The max allowed replica count is 1000. Available machine types for SMALL shard: e2-standard-2 and all machine types available for MEDIUM and LARGE shard. Available machine types for MEDIUM shard: e2-standard-16 and all machine types available for LARGE shard. Available machine types for LARGE shard: e2-highmem-16, n2d-standard-32. n1-standard-16 and n1-standard-32 are still available, but we recommend e2-standard-16 and e2-highmem-16 for cost efficiency."
         },
         "deployedIndexAuthConfig": {
           "$ref": "GoogleCloudAiplatformV1DeployedIndexAuthConfig",
@@ -16844,6 +17193,27 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1DeploymentResourcePool": {
+      "description": "A description of resources that can be shared by multiple DeployedModels, whose underlying specification consists of a DedicatedResources.",
+      "id": "GoogleCloudAiplatformV1DeploymentResourcePool",
+      "properties": {
+        "createTime": {
+          "description": "Output only. Timestamp when this DeploymentResourcePool was created.",
+          "format": "google-datetime",
+          "readOnly": true,
+          "type": "string"
+        },
+        "dedicatedResources": {
+          "$ref": "GoogleCloudAiplatformV1DedicatedResources",
+          "description": "Required. The underlying DedicatedResources that the DeploymentResourcePool uses."
+        },
+        "name": {
+          "description": "Immutable. The resource name of the DeploymentResourcePool. Format: `projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1DestinationFeatureSetting": {
       "id": "GoogleCloudAiplatformV1DestinationFeatureSetting",
       "properties": {
@@ -18333,14 +18703,6 @@
           "readOnly": true,
           "type": "string"
         },
-        "dedicatedServingEndpoint": {
-          "$ref": "GoogleCloudAiplatformV1FeatureOnlineStoreDedicatedServingEndpoint",
-          "description": "Optional. The dedicated serving endpoint for this FeatureOnlineStore, which is different from common Vertex service endpoint."
-        },
-        "embeddingManagement": {
-          "$ref": "GoogleCloudAiplatformV1FeatureOnlineStoreEmbeddingManagement",
-          "description": "Optional. The settings for embedding management in FeatureOnlineStore."
-        },
         "etag": {
           "description": "Optional. Used to perform consistent read-modify-write updates. If not set, a blind \"overwrite\" update happens.",
           "type": "string"
@@ -18412,38 +18774,6 @@
       },
       "type": "object"
     },
-    "GoogleCloudAiplatformV1FeatureOnlineStoreDedicatedServingEndpoint": {
-      "description": "The dedicated serving endpoint for this FeatureOnlineStore. Only need to set when you choose Optimized storage type or enable EmbeddingManagement. Will use public endpoint by default.",
-      "id": "GoogleCloudAiplatformV1FeatureOnlineStoreDedicatedServingEndpoint",
-      "properties": {
-        "privateServiceConnectConfig": {
-          "$ref": "GoogleCloudAiplatformV1PrivateServiceConnectConfig",
-          "description": "Optional. Private service connect config. If PrivateServiceConnectConfig.enable_private_service_connect set to true, customers will use private service connection to send request. Otherwise, the connection will set to public endpoint."
-        },
-        "publicEndpointDomainName": {
-          "description": "Output only. This field will be populated with the domain name to use for this FeatureOnlineStore",
-          "readOnly": true,
-          "type": "string"
-        },
-        "serviceAttachment": {
-          "description": "Output only. The name of the service attachment resource. Populated if private service connect is enabled and after FeatureViewSync is created.",
-          "readOnly": true,
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    "GoogleCloudAiplatformV1FeatureOnlineStoreEmbeddingManagement": {
-      "description": "Contains settings for embedding management.",
-      "id": "GoogleCloudAiplatformV1FeatureOnlineStoreEmbeddingManagement",
-      "properties": {
-        "enabled": {
-          "description": "Optional. Immutable. Whether to enable embedding management in this FeatureOnlineStore. It's immutable after creation to ensure the FeatureOnlineStore availability.",
-          "type": "boolean"
-        }
-      },
-      "type": "object"
-    },
     "GoogleCloudAiplatformV1FeatureSelector": {
       "description": "Selector for Features of an EntityType.",
       "id": "GoogleCloudAiplatformV1FeatureSelector",
@@ -18633,10 +18963,6 @@
           "format": "google-datetime",
           "readOnly": true,
           "type": "string"
-        },
-        "vectorSearchConfig": {
-          "$ref": "GoogleCloudAiplatformV1FeatureViewVectorSearchConfig",
-          "description": "Optional. Configuration for vector search. It contains the required configurations to create an index from source data, so that approximate nearest neighbor (a.k.a ANN) algorithms search can be performed during online serving."
         }
       },
       "type": "object"
@@ -18658,6 +18984,17 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1FeatureViewDataKey": {
+      "description": "Lookup key for a feature view.",
+      "id": "GoogleCloudAiplatformV1FeatureViewDataKey",
+      "properties": {
+        "key": {
+          "description": "String key to use for lookup.",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1FeatureViewFeatureRegistrySource": {
       "description": "A Feature Registry source for features that need to be synced to Online Store.",
       "id": "GoogleCloudAiplatformV1FeatureViewFeatureRegistrySource",
@@ -18728,73 +19065,6 @@
       },
       "type": "object"
     },
-    "GoogleCloudAiplatformV1FeatureViewVectorSearchConfig": {
-      "description": "Configuration for vector search.",
-      "id": "GoogleCloudAiplatformV1FeatureViewVectorSearchConfig",
-      "properties": {
-        "bruteForceConfig": {
-          "$ref": "GoogleCloudAiplatformV1FeatureViewVectorSearchConfigBruteForceConfig",
-          "description": "Optional. Configuration options for using brute force search, which simply implements the standard linear search in the database for each query. It is primarily meant for benchmarking and to generate the ground truth for approximate search."
-        },
-        "crowdingColumn": {
-          "description": "Optional. Column of crowding. This column contains crowding attribute which is a constraint on a neighbor list produced by nearest neighbor search requiring that no more than some value k' of the k neighbors returned have the same value of crowding_attribute.",
-          "type": "string"
-        },
-        "distanceMeasureType": {
-          "description": "Optional. The distance measure used in nearest neighbor search.",
-          "enum": [
-            "DISTANCE_MEASURE_TYPE_UNSPECIFIED",
-            "SQUARED_L2_DISTANCE",
-            "COSINE_DISTANCE",
-            "DOT_PRODUCT_DISTANCE"
-          ],
-          "enumDescriptions": [
-            "Should not be set.",
-            "Euclidean (L_2) Distance.",
-            "Cosine Distance. Defined as 1 - cosine similarity. We strongly suggest using DOT_PRODUCT_DISTANCE + UNIT_L2_NORM instead of COSINE distance. Our algorithms have been more optimized for DOT_PRODUCT distance which, when combined with UNIT_L2_NORM, is mathematically equivalent to COSINE distance and results in the same ranking.",
-            "Dot Product Distance. Defined as a negative of the dot product."
-          ],
-          "type": "string"
-        },
-        "embeddingColumn": {
-          "description": "Optional. Column of embedding. This column contains the source data to create index for vector search. embedding_column must be set when using vector search.",
-          "type": "string"
-        },
-        "embeddingDimension": {
-          "description": "Optional. The number of dimensions of the input embedding.",
-          "format": "int32",
-          "type": "integer"
-        },
-        "filterColumns": {
-          "description": "Optional. Columns of features that're used to filter vector search results.",
-          "items": {
-            "type": "string"
-          },
-          "type": "array"
-        },
-        "treeAhConfig": {
-          "$ref": "GoogleCloudAiplatformV1FeatureViewVectorSearchConfigTreeAHConfig",
-          "description": "Optional. Configuration options for the tree-AH algorithm (Shallow tree + Asymmetric Hashing). Please refer to this paper for more details: https://arxiv.org/abs/1908.10396"
-        }
-      },
-      "type": "object"
-    },
-    "GoogleCloudAiplatformV1FeatureViewVectorSearchConfigBruteForceConfig": {
-      "id": "GoogleCloudAiplatformV1FeatureViewVectorSearchConfigBruteForceConfig",
-      "properties": {},
-      "type": "object"
-    },
-    "GoogleCloudAiplatformV1FeatureViewVectorSearchConfigTreeAHConfig": {
-      "id": "GoogleCloudAiplatformV1FeatureViewVectorSearchConfigTreeAHConfig",
-      "properties": {
-        "leafNodeEmbeddingCount": {
-          "description": "Optional. Number of embeddings on each leaf node. The default value is 1000 if not set.",
-          "format": "int64",
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
     "GoogleCloudAiplatformV1Featurestore": {
       "description": "Vertex AI Feature Store provides a centralized repository for organizing, storing, and serving ML features. The Featurestore is a top-level container for your features and their values.",
       "id": "GoogleCloudAiplatformV1Featurestore",
@@ -18995,10 +19265,10 @@
       "description": "Request message for FeatureOnlineStoreService.FetchFeatureValues. All the features under the requested feature view will be returned.",
       "id": "GoogleCloudAiplatformV1FetchFeatureValuesRequest",
       "properties": {
-        "format": {
-          "description": "Specify response data format. If not set, KeyValue format will be used.",
+        "dataFormat": {
+          "description": "Optional. Response data format. If not set, FeatureViewDataFormat.KEY_VALUE will be used.",
           "enum": [
-            "FORMAT_UNSPECIFIED",
+            "FEATURE_VIEW_DATA_FORMAT_UNSPECIFIED",
             "KEY_VALUE",
             "PROTO_STRUCT"
           ],
@@ -19009,9 +19279,9 @@
           ],
           "type": "string"
         },
-        "id": {
-          "description": "Simple ID. The whole string will be used as is to identify Entity to fetch feature values for.",
-          "type": "string"
+        "dataKey": {
+          "$ref": "GoogleCloudAiplatformV1FeatureViewDataKey",
+          "description": "Optional. The request key to fetch feature values for."
         }
       },
       "type": "object"
@@ -20205,6 +20475,24 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1ListDeploymentResourcePoolsResponse": {
+      "description": "Response message for ListDeploymentResourcePools method.",
+      "id": "GoogleCloudAiplatformV1ListDeploymentResourcePoolsResponse",
+      "properties": {
+        "deploymentResourcePools": {
+          "description": "The DeploymentResourcePools from the specified location.",
+          "items": {
+            "$ref": "GoogleCloudAiplatformV1DeploymentResourcePool"
+          },
+          "type": "array"
+        },
+        "nextPageToken": {
+          "description": "A token, which can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1ListEndpointsResponse": {
       "description": "Response message for EndpointService.ListEndpoints.",
       "id": "GoogleCloudAiplatformV1ListEndpointsResponse",
@@ -21503,6 +21791,11 @@
           },
           "type": "array"
         },
+        "deploymentTimeout": {
+          "description": "Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.",
+          "format": "google-duration",
+          "type": "string"
+        },
         "env": {
           "description": "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\": \"$(VAR_1) bar\" } ] ``` If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the `env` field of the Kubernetes Containers [v1 core API](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core).",
           "items": {
@@ -21510,6 +21803,10 @@
           },
           "type": "array"
         },
+        "healthProbe": {
+          "$ref": "GoogleCloudAiplatformV1Probe",
+          "description": "Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing."
+        },
         "healthRoute": {
           "description": "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).)",
           "type": "string"
@@ -21528,6 +21825,15 @@
         "predictRoute": {
           "description": "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).)",
           "type": "string"
+        },
+        "sharedMemorySizeMb": {
+          "description": "Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.",
+          "format": "int64",
+          "type": "string"
+        },
+        "startupProbe": {
+          "$ref": "GoogleCloudAiplatformV1Probe",
+          "description": "Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing."
         }
       },
       "type": "object"
@@ -23806,6 +24112,41 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1Probe": {
+      "description": "Probe describes a health check to be performed against a container to determine whether it is alive or ready to receive traffic.",
+      "id": "GoogleCloudAiplatformV1Probe",
+      "properties": {
+        "exec": {
+          "$ref": "GoogleCloudAiplatformV1ProbeExecAction",
+          "description": "Exec specifies the action to take."
+        },
+        "periodSeconds": {
+          "description": "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'.",
+          "format": "int32",
+          "type": "integer"
+        },
+        "timeoutSeconds": {
+          "description": "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'.",
+          "format": "int32",
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
+    "GoogleCloudAiplatformV1ProbeExecAction": {
+      "description": "ExecAction specifies a command to execute.",
+      "id": "GoogleCloudAiplatformV1ProbeExecAction",
+      "properties": {
+        "command": {
+          "description": "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.",
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1PublisherModel": {
       "description": "A Model Garden Publisher Model.",
       "id": "GoogleCloudAiplatformV1PublisherModel",
@@ -24204,6 +24545,42 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1QueryDeployedModelsResponse": {
+      "description": "Response message for QueryDeployedModels method.",
+      "id": "GoogleCloudAiplatformV1QueryDeployedModelsResponse",
+      "properties": {
+        "deployedModelRefs": {
+          "description": "References to the DeployedModels that share the specified deploymentResourcePool.",
+          "items": {
+            "$ref": "GoogleCloudAiplatformV1DeployedModelRef"
+          },
+          "type": "array"
+        },
+        "deployedModels": {
+          "deprecated": true,
+          "description": "DEPRECATED Use deployed_model_refs instead.",
+          "items": {
+            "$ref": "GoogleCloudAiplatformV1DeployedModel"
+          },
+          "type": "array"
+        },
+        "nextPageToken": {
+          "description": "A token, which can be sent as `page_token` to retrieve the next page. If this field is omitted, there are no subsequent pages.",
+          "type": "string"
+        },
+        "totalDeployedModelCount": {
+          "description": "The total number of DeployedModels on this DeploymentResourcePool.",
+          "format": "int32",
+          "type": "integer"
+        },
+        "totalEndpointCount": {
+          "description": "The total number of Endpoints that have DeployedModels on this DeploymentResourcePool.",
+          "format": "int32",
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1RawPredictRequest": {
       "description": "Request message for PredictionService.RawPredict.",
       "id": "GoogleCloudAiplatformV1RawPredictRequest",
@@ -25834,6 +26211,10 @@
       "description": "The configuration for grounding checking.",
       "id": "GoogleCloudAiplatformV1SchemaPredictParamsGroundingConfig",
       "properties": {
+        "disableAttribution": {
+          "description": "If set, skip finding claim attributions (i.e not generate grounding citation).",
+          "type": "boolean"
+        },
         "sources": {
           "description": "The sources for the grounding checking.",
           "items": {
@@ -25849,7 +26230,8 @@
       "id": "GoogleCloudAiplatformV1SchemaPredictParamsGroundingConfigSourceEntry",
       "properties": {
         "enterpriseDatastore": {
-          "description": "The uri of the Enterprise Search data source.",
+          "deprecated": true,
+          "description": "The uri of the Vertex AI Search data source. Deprecated. Use vertex_ai_search_datastore instead.",
           "type": "string"
         },
         "type": {
@@ -25857,14 +26239,26 @@
           "enum": [
             "UNSPECIFIED",
             "WEB",
-            "ENTERPRISE"
+            "ENTERPRISE",
+            "VERTEX_AI_SEARCH"
+          ],
+          "enumDeprecated": [
+            false,
+            false,
+            true,
+            false
           ],
           "enumDescriptions": [
             "",
             "Uses Web Search to check the grounding.",
-            "Uses Enterprise Search to check the grounding."
+            "Uses Vertex AI Search to check the grounding. Deprecated. Use VERTEX_AI_SEARCH instead.",
+            "Uses Vertex AI Search to check the grounding"
           ],
           "type": "string"
+        },
+        "vertexAiSearchDatastore": {
+          "description": "The uri of the Vertex AI Search data source.",
+          "type": "string"
         }
       },
       "type": "object"
@@ -28790,7 +29184,7 @@
       "type": "object"
     },
     "GoogleCloudAiplatformV1Study": {
-      "description": "A message representing a Study. Next id: 12",
+      "description": "A message representing a Study.",
       "id": "GoogleCloudAiplatformV1Study",
       "properties": {
         "createTime": {
@@ -29909,6 +30303,29 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1TokensInfo": {
+      "description": "Tokens info with a list of tokens and the corresponding list of token ids.",
+      "id": "GoogleCloudAiplatformV1TokensInfo",
+      "properties": {
+        "tokenIds": {
+          "description": "A list of token ids from the input.",
+          "items": {
+            "format": "int64",
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "tokens": {
+          "description": "A list of tokens from the input.",
+          "items": {
+            "format": "byte",
+            "type": "string"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1TrainingConfig": {
       "description": "CMLE training config. For every active learning labeling iteration, system will train a machine learning model on CMLE. The trained model will be used by data sampling algorithm to select DataItems.",
       "id": "GoogleCloudAiplatformV1TrainingConfig",
@@ -30245,6 +30662,17 @@
       },
       "type": "object"
     },
+    "GoogleCloudAiplatformV1UpdateDeploymentResourcePoolOperationMetadata": {
+      "description": "Runtime operation information for UpdateDeploymentResourcePool method.",
+      "id": "GoogleCloudAiplatformV1UpdateDeploymentResourcePoolOperationMetadata",
+      "properties": {
+        "genericMetadata": {
+          "$ref": "GoogleCloudAiplatformV1GenericOperationMetadata",
+          "description": "The operation generic information."
+        }
+      },
+      "type": "object"
+    },
     "GoogleCloudAiplatformV1UpdateExplanationDatasetOperationMetadata": {
       "description": "Runtime operation information for ModelService.UpdateExplanationDataset.",
       "id": "GoogleCloudAiplatformV1UpdateExplanationDatasetOperationMetadata",
@@ -30409,7 +30837,7 @@
           "type": "string"
         },
         "serviceAccount": {
-          "description": "Optional. The user-provided custom service account to use to do the model upload. If empty, [Vertex AI Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. Users uploading the Model must have the `iam.serviceAccounts.actAs` permission on this service account. Also, this account must belong to the project specified in the `parent` field and have all necessary read permissions.",
+          "description": "Optional. The user-provided custom service account to use to do the model upload. If empty, [Vertex AI Service Agent](https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used to access resources needed to upload the model. This account must belong to the target project where the model is uploaded to, i.e., the project specified in the `parent` field of this request and have necessary read permissions (to Google Cloud Storage, Artifact Registry, etc.).",
           "type": "string"
         }
       },