diff --git a/docs/dyn/aiplatform_v1.projects.locations.customJobs.html b/docs/dyn/aiplatform_v1.projects.locations.customJobs.html index 4024e0394e..6144b94f67 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.customJobs.html +++ b/docs/dyn/aiplatform_v1.projects.locations.customJobs.html @@ -167,6 +167,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -280,6 +281,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -435,6 +437,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -561,6 +564,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", diff --git a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html index a35e488eed..c13c5a5bb3 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.endpoints.html +++ b/docs/dyn/aiplatform_v1.projects.locations.endpoints.html @@ -1108,40 +1108,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -1149,20 +1115,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -1173,7 +1150,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, @@ -1491,7 +1468,7 @@

Method Details

Args: parent: string, Required. The resource name of the Location from which to list the Endpoints. Format: `projects/{project}/locations/{location}` (required) - filter: string, Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports = and !=. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports = and, != * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:* or labels:key - key existence * A key including a space must be quoted. `labels."a key"`. * `base_model_name` only supports = Some examples: * `endpoint=1` * `displayName="myDisplayName"` * `labels.myKey="myValue"` * `baseModelName="text-bison"` + filter: string, Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports `=` and `!=`. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports `=` and `!=`. * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:*` or `labels:key` - key existence * A key including a space must be quoted. `labels."a key"`. * `base_model_name` only supports `=`. Some examples: * `endpoint=1` * `displayName="myDisplayName"` * `labels.myKey="myValue"` * `baseModelName="text-bison"` orderBy: string, A comma-separated list of fields to order by, sorted in ascending order. Use "desc" after a field name for descending. Supported fields: * `display_name` * `create_time` * `update_time` Example: `display_name, create_time desc`. pageSize: integer, Optional. The standard list page size. pageToken: string, Optional. The standard list page token. Typically obtained via ListEndpointsResponse.next_page_token of the previous EndpointService.ListEndpoints call. @@ -2580,40 +2557,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -2621,20 +2564,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -2645,7 +2599,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, diff --git a/docs/dyn/aiplatform_v1.projects.locations.featureOnlineStores.featureViews.html b/docs/dyn/aiplatform_v1.projects.locations.featureOnlineStores.featureViews.html index 0b1ff1ec3e..d0d692055e 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.featureOnlineStores.featureViews.html +++ b/docs/dyn/aiplatform_v1.projects.locations.featureOnlineStores.featureViews.html @@ -255,6 +255,14 @@

Method Details

An object of the form: { # Response message for FeatureOnlineStoreService.FetchFeatureValues + "dataKey": { # Lookup key for a feature view. # The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs. + "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec. + "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order. + "A String", + ], + }, + "key": "A String", # String key to use for lookup. + }, "keyValues": { # Response structure in the format of key (feature name) and (feature) value pair. # Feature values in KeyValue format. "features": [ # List of feature names and values. { # Feature name & value pair. @@ -533,6 +541,14 @@

Method Details

"distance": 3.14, # The distance between the neighbor and the query vector. "entityId": "A String", # The id of the similar entity. "entityKeyValues": { # Response message for FeatureOnlineStoreService.FetchFeatureValues # The attributes of the neighbor, e.g. filters, crowding and metadata Note that full entities are returned only when "return_full_entity" is set to true. Otherwise, only the "entity_id" and "distance" fields are populated. + "dataKey": { # Lookup key for a feature view. # The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs. + "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec. + "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order. + "A String", + ], + }, + "key": "A String", # String key to use for lookup. + }, "keyValues": { # Response structure in the format of key (feature name) and (feature) value pair. # Feature values in KeyValue format. "features": [ # List of feature names and values. { # Feature name & value pair. diff --git a/docs/dyn/aiplatform_v1.projects.locations.hyperparameterTuningJobs.html b/docs/dyn/aiplatform_v1.projects.locations.hyperparameterTuningJobs.html index 0791e580cc..db0bc1330e 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.hyperparameterTuningJobs.html +++ b/docs/dyn/aiplatform_v1.projects.locations.hyperparameterTuningJobs.html @@ -268,6 +268,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -516,6 +517,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -806,6 +808,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -1067,6 +1070,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", diff --git a/docs/dyn/aiplatform_v1.projects.locations.nasJobs.html b/docs/dyn/aiplatform_v1.projects.locations.nasJobs.html index eff4ab06c3..3b6a4c7c46 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.nasJobs.html +++ b/docs/dyn/aiplatform_v1.projects.locations.nasJobs.html @@ -223,6 +223,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -304,6 +305,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -471,6 +473,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -552,6 +555,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -761,6 +765,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -842,6 +847,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -1022,6 +1028,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", @@ -1103,6 +1110,7 @@

Method Details

"A String", ], "network": "A String", # Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network. + "persistentResourceId": "A String", # Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected. "protectedArtifactLocationId": "A String", # The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations "reservedIpRanges": [ # Optional. A list of names for the reserved ip ranges under the VPC network that can be used for this job. If set, we will deploy the job within the provided ip ranges. Otherwise, the job will be deployed to any ip ranges under the provided VPC network. Example: ['vertex-ai-ip-range']. "A String", diff --git a/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html b/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html index a04edd8375..154cd5e1cc 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html +++ b/docs/dyn/aiplatform_v1.projects.locations.persistentResources.html @@ -74,6 +74,11 @@

Vertex AI API . projects . locations . persistentResources

Instance Methods

+

+ operations() +

+

Returns the operations Resource.

+

close()

Close httplib2 connections.

@@ -95,6 +100,9 @@

Instance Methods

patch(name, body=None, updateMask=None, x__xgafv=None)

Updates a PersistentResource.

+

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

+

Reboots a PersistentResource.

Method Details

close() @@ -549,4 +557,45 @@

Method Details

}
+
+ reboot(name, body=None, x__xgafv=None) + 
Reboots a PersistentResource.
+
+Args:
+  name: string, Required. The name of the PersistentResource resource. Format: `projects/{project_id_or_number}/locations/{location_id}/persistentResources/{persistent_resource_id}` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Request message for PersistentResourceService.RebootPersistentResource.
+}
+
+  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_v1.projects.locations.persistentResources.operations.html b/docs/dyn/aiplatform_v1.projects.locations.persistentResources.operations.html new file mode 100644 index 0000000000..39c1167b1d --- /dev/null +++ b/docs/dyn/aiplatform_v1.projects.locations.persistentResources.operations.html @@ -0,0 +1,268 @@ + + + +

Vertex AI API . projects . locations . persistentResources . operations

+

Instance Methods

+

+ cancel(name, x__xgafv=None)

+

Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`.

+

+ close()

+

Close httplib2 connections.

+

+ delete(name, x__xgafv=None)

+

Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`.

+

+ get(name, x__xgafv=None)

+

Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.

+

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

+

Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.

+

+ list_next()

+

Retrieves the next page of results.

+

+ wait(name, timeout=None, x__xgafv=None)

+

Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done.

+

Method Details

+
+ cancel(name, x__xgafv=None) + 
Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`.
+
+Args:
+  name: string, The name of the operation resource to be cancelled. (required)
+  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.
+
+ +
+ delete(name, x__xgafv=None) + 
Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`.
+
+Args:
+  name: string, The name of the operation resource to be deleted. (required)
+  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); }
+}
+
+ +
+ get(name, x__xgafv=None) + 
Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
+
+Args:
+  name: string, The name of the operation resource. (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.
+  },
+}
+
+ +
+ list(name, filter=None, pageSize=None, pageToken=None, x__xgafv=None) + 
Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.
+
+Args:
+  name: string, The name of the operation's parent resource. (required)
+  filter: string, The standard list filter.
+  pageSize: integer, The standard list page size.
+  pageToken: string, The standard list page token.
+  x__xgafv: string, V1 error format.
+    Allowed values
+      1 - v1 error format
+      2 - v2 error format
+
+Returns:
+  An object of the form:
+
+    { # The response message for Operations.ListOperations.
+  "nextPageToken": "A String", # The standard List next-page token.
+  "operations": [ # A list of operations that matches the specified filter in the request.
+    { # 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_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.
+
+
+ +
+ wait(name, timeout=None, x__xgafv=None) + 
Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done.
+
+Args:
+  name: string, The name of the operation resource to wait on. (required)
+  timeout: string, The maximum duration to wait before timing out. If left blank, the wait will be at most the time permitted by the underlying HTTP/RPC protocol. If RPC context deadline is also specified, the shorter one will be used.
+  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_v1.projects.locations.publishers.models.html b/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html index 1e2a359dcc..8a9ab3fc73 100644 --- a/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html +++ b/docs/dyn/aiplatform_v1.projects.locations.publishers.models.html @@ -269,40 +269,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -310,20 +276,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -334,7 +311,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, @@ -781,40 +758,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -822,20 +765,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -846,7 +800,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, diff --git a/docs/dyn/aiplatform_v1.publishers.models.html b/docs/dyn/aiplatform_v1.publishers.models.html index 7727c7007e..092ffda7e9 100644 --- a/docs/dyn/aiplatform_v1.publishers.models.html +++ b/docs/dyn/aiplatform_v1.publishers.models.html @@ -217,6 +217,87 @@

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.projects.locations.endpoints.html b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html index a209ceabce..484b65d6ef 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.endpoints.html @@ -1254,40 +1254,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -1295,20 +1261,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -1319,7 +1296,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, @@ -1678,7 +1655,7 @@

Method Details

Args: parent: string, Required. The resource name of the Location from which to list the Endpoints. Format: `projects/{project}/locations/{location}` (required) - filter: string, Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports = and !=. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports = and, != * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:* or labels:key - key existence * A key including a space must be quoted. `labels."a key"`. * `base_model_name` only supports = Some examples: * `endpoint=1` * `displayName="myDisplayName"` * `labels.myKey="myValue"` * `baseModelName="text-bison"` + filter: string, Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports `=` and `!=`. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports `=` and `!=`. * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:*` or `labels:key` - key existence * A key including a space must be quoted. `labels."a key"`. * `base_model_name` only supports `=`. Some examples: * `endpoint=1` * `displayName="myDisplayName"` * `labels.myKey="myValue"` * `baseModelName="text-bison"` pageSize: integer, Optional. The standard list page size. pageToken: string, Optional. The standard list page token. Typically obtained via ListEndpointsResponse.next_page_token of the previous EndpointService.ListEndpoints call. readMask: string, Optional. Mask specifying which fields to read. @@ -2848,40 +2825,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -2889,20 +2832,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -2913,7 +2867,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html b/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html index e6c65f92b8..d2b9d90d72 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.extensions.html @@ -108,6 +108,9 @@

Instance Methods

patch(name, body=None, updateMask=None, x__xgafv=None)

Updates an Extension.

+

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

+

Queries an extension with a default controller.

Method Details

close() @@ -159,31 +162,32 @@

Method Details

The object takes the form of: { # Request message for ExtensionExecutionService.ExecuteExtension. - "operationId": "A String", # Required. The operation to be executed in this extension as defined in ExtensionOperation.operation_id. + "operationId": "A String", # Required. The desired ID of the operation to be executed in this extension as defined in ExtensionOperation.operation_id. "operationParams": { # Optional. Request parameters that will be used for executing this operation. 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. }, "runtimeAuthConfig": { # Auth configuration to run the extension. # Optional. Auth config provided at runtime to override the default value in Extension.manifest.auth_config. The AuthConfig.auth_type should match the value in Extension.manifest.auth_config. "apiKeyConfig": { # Config for authentication with API key. # Config for API key auth. - "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. "httpElementLocation": "A String", # Required. The location of the API key. "name": "A String", # Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. }, "authType": "A String", # Type of auth scheme. "googleServiceAccountConfig": { # Config for Google Service Account Authentication. # Config for Google Service Account auth. - "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission. + "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. }, "httpBasicAuthConfig": { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth. - "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. }, "noAuth": { # Empty message, used to indicate no authentication for an endpoint. # Config for no auth. }, "oauthConfig": { # Config for user oauth. # Config for user oauth. - "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. - "serviceAccount": "A String", # The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission. + "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. }, "oidcConfig": { # Config for user OIDC auth. # Config for user OIDC auth. - "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. + "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). }, }, } @@ -198,9 +202,6 @@

Method Details

{ # Response message for ExtensionExecutionService.ExecuteExtension. "content": "A String", # Response content from the extension. The content should be conformant to the response.content schema in the extension's manifest/OpenAPI spec. - "output": { # Output from the extension. The output should be conformant to the extension's manifest/OpenAPI spec. The output can contain values for keys like "content", "headers", etc. This field is deprecated, please use content field below for the extension execution result. - "a_key": "", # Properties of the object. - }, }
@@ -229,20 +230,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -256,25 +268,26 @@

Method Details

}, "authConfig": { # Auth configuration to run the extension. # Required. Immutable. Type of auth supported by this extension. "apiKeyConfig": { # Config for authentication with API key. # Config for API key auth. - "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. "httpElementLocation": "A String", # Required. The location of the API key. "name": "A String", # Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. }, "authType": "A String", # Type of auth scheme. "googleServiceAccountConfig": { # Config for Google Service Account Authentication. # Config for Google Service Account auth. - "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission. + "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. }, "httpBasicAuthConfig": { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth. - "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. }, "noAuth": { # Empty message, used to indicate no authentication for an endpoint. # Config for no auth. }, "oauthConfig": { # Config for user oauth. # Config for user oauth. - "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. - "serviceAccount": "A String", # The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission. + "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. }, "oidcConfig": { # Config for user OIDC auth. # Config for user OIDC auth. - "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. + "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). }, }, "description": "A String", # Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. @@ -323,20 +336,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -350,25 +374,26 @@

Method Details

}, "authConfig": { # Auth configuration to run the extension. # Required. Immutable. Type of auth supported by this extension. "apiKeyConfig": { # Config for authentication with API key. # Config for API key auth. - "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. "httpElementLocation": "A String", # Required. The location of the API key. "name": "A String", # Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. }, "authType": "A String", # Type of auth scheme. "googleServiceAccountConfig": { # Config for Google Service Account Authentication. # Config for Google Service Account auth. - "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission. + "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. }, "httpBasicAuthConfig": { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth. - "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. }, "noAuth": { # Empty message, used to indicate no authentication for an endpoint. # Config for no auth. }, "oauthConfig": { # Config for user oauth. # Config for user oauth. - "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. - "serviceAccount": "A String", # The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission. + "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. }, "oidcConfig": { # Config for user OIDC auth. # Config for user OIDC auth. - "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. + "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). }, }, "description": "A String", # Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. @@ -456,20 +481,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -483,25 +519,26 @@

Method Details

}, "authConfig": { # Auth configuration to run the extension. # Required. Immutable. Type of auth supported by this extension. "apiKeyConfig": { # Config for authentication with API key. # Config for API key auth. - "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. "httpElementLocation": "A String", # Required. The location of the API key. "name": "A String", # Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. }, "authType": "A String", # Type of auth scheme. "googleServiceAccountConfig": { # Config for Google Service Account Authentication. # Config for Google Service Account auth. - "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission. + "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. }, "httpBasicAuthConfig": { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth. - "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. }, "noAuth": { # Empty message, used to indicate no authentication for an endpoint. # Config for no auth. }, "oauthConfig": { # Config for user oauth. # Config for user oauth. - "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. - "serviceAccount": "A String", # The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission. + "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. }, "oidcConfig": { # Config for user OIDC auth. # Config for user OIDC auth. - "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. + "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). }, }, "description": "A String", # Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. @@ -567,20 +604,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -594,25 +642,26 @@

Method Details

}, "authConfig": { # Auth configuration to run the extension. # Required. Immutable. Type of auth supported by this extension. "apiKeyConfig": { # Config for authentication with API key. # Config for API key auth. - "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. "httpElementLocation": "A String", # Required. The location of the API key. "name": "A String", # Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. }, "authType": "A String", # Type of auth scheme. "googleServiceAccountConfig": { # Config for Google Service Account Authentication. # Config for Google Service Account auth. - "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission. + "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. }, "httpBasicAuthConfig": { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth. - "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. }, "noAuth": { # Empty message, used to indicate no authentication for an endpoint. # Config for no auth. }, "oauthConfig": { # Config for user oauth. # Config for user oauth. - "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. - "serviceAccount": "A String", # The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission. + "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. }, "oidcConfig": { # Config for user OIDC auth. # Config for user OIDC auth. - "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. + "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). }, }, "description": "A String", # Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. @@ -640,7 +689,7 @@

Method Details

"updateTime": "A String", # Output only. Timestamp when this Extension was most recently updated. } - updateMask: string, Required. Mask specifying which fields to update. Supported fields: * `display_name` * `description` + updateMask: string, Required. Mask specifying which fields to update. Supported fields: * `display_name` * `description` * `tool_use_examples` x__xgafv: string, V1 error format. Allowed values 1 - v1 error format @@ -660,20 +709,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -687,25 +747,26 @@

Method Details

}, "authConfig": { # Auth configuration to run the extension. # Required. Immutable. Type of auth supported by this extension. "apiKeyConfig": { # Config for authentication with API key. # Config for API key auth. - "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "apiKeySecret": "A String", # Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. "httpElementLocation": "A String", # Required. The location of the API key. "name": "A String", # Required. The parameter name of the API key. E.g. If the API request is "https://example.com/act?api_key=", "api_key" would be the parameter name. }, "authType": "A String", # Type of auth scheme. "googleServiceAccountConfig": { # Config for Google Service Account Authentication. # Config for Google Service Account auth. - "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission. + "serviceAccount": "A String", # Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension. }, "httpBasicAuthConfig": { # Config for HTTP Basic Authentication. # Config for HTTP Basic auth. - "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` + "credentialSecret": "A String", # Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource. }, "noAuth": { # Empty message, used to indicate no authentication for an endpoint. # Config for no auth. }, "oauthConfig": { # Config for user oauth. # Config for user oauth. - "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. - "serviceAccount": "A String", # The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission. + "accessToken": "A String", # Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account. }, "oidcConfig": { # Config for user OIDC auth. # Config for user OIDC auth. - "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time. + "idToken": "A String", # OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time. + "serviceAccount": "A String", # The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents). }, }, "description": "A String", # Required. The natural language description shown to the LLM. It should describe the usage of the extension, and is essential for the LLM to perform reasoning. @@ -734,4 +795,135 @@

Method Details

} +
+ query(name, body=None, x__xgafv=None) + 
Queries an extension with a default controller.
+
+Args:
+  name: string, Required. Name (identifier) of the extension; Format: `projects/{project}/locations/{location}/extensions/{extension}` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Request message for ExtensionExecutionService.QueryExtension.
+  "contents": [ # Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.
+    { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data.
+            "data": "A String", # Required. Raw bytes for media formats.
+            "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.
+    },
+  ],
+  "query": { # User provided query message. # Required. User provided input query message.
+    "query": "A String", # Required. The query from user.
+  },
+  "useFunctionCall": True or False, # Optional. Experiment control on whether to use function 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 ExtensionExecutionService.QueryExtension.
+  "failureMessage": "A String", # Failure message if any.
+  "metadata": { # Metadata for response # Metadata related to the query execution.
+    "checkpoint": { # Placeholder for all checkpoint related data. Any data needed to restore a request and more go/vertex-extension-query-operation # Optional. Checkpoint to restore a request
+      "content": "A String", # Required. encoded checkpoint
+    },
+    "executionPlan": { # Execution plan for a request. # Optional. Execution plan for the request.
+      "steps": [ # Required. Sequence of steps to execute a request.
+        { # Single step in query execution plan.
+          "extensionExecution": { # Extension execution step. # Extension execution step.
+            "extension": "A String", # Required. extension resource name
+            "operationId": "A String", # Required. the operation id
+          },
+          "respondToUser": { # Respond to user step. # Respond to user step.
+          },
+        },
+      ],
+    },
+    "flowOutputs": { # To surface the v2 flow output.
+      "a_key": "", # Properties of the object.
+    },
+  },
+  "queryResponseMetadata": {
+    "steps": [ # ReAgent execution steps.
+      { # ReAgent execution steps.
+        "error": "A String", # Error messages from the extension or during response parsing.
+        "extensionInstruction": "A String", # Planner's instruction to the extension.
+        "extensionInvoked": "A String", # Planner's choice of extension to invoke.
+        "response": "A String", # Response of the extension.
+        "success": True or False, # When set to False, either the extension fails to execute or the response cannot be summarized.
+        "thought": "A String", # Planner's thought.
+      },
+    ],
+    "useCreativity": True or False, # Whether the reasoning agent used creativity (instead of extensions provided) to build the response.
+  },
+  "response": "A String", # Response to the user's query.
+  "steps": [ # Steps of extension or LLM interaction, can contain function call, function response, or text response. The last step contains the final response to the query.
+    { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data.
+            "data": "A String", # Required. Raw bytes for media formats.
+            "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.
+    },
+  ],
+}
+
+ \ No newline at end of file diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.featureOnlineStores.featureViews.html b/docs/dyn/aiplatform_v1beta1.projects.locations.featureOnlineStores.featureViews.html index 4ecfdf2fda..9f525353a9 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.featureOnlineStores.featureViews.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.featureOnlineStores.featureViews.html @@ -117,6 +117,9 @@

Instance Methods

setIamPolicy(resource, body=None, x__xgafv=None)

Sets the access control policy on the specified resource. Replaces any existing policy. Can return `NOT_FOUND`, `INVALID_ARGUMENT`, and `PERMISSION_DENIED` errors.

+

+ streamingFetchFeatureValues(featureView, body=None, x__xgafv=None)

+

Bidirectional streaming RPC to fetch feature values under a FeatureView. Requests may not have a one-to-one mapping to responses and responses may be returned out-of-order to reduce latency.

sync(featureView, body=None, x__xgafv=None)

Triggers on-demand sync for the FeatureView.

@@ -282,6 +285,14 @@

Method Details

An object of the form: { # Response message for FeatureOnlineStoreService.FetchFeatureValues + "dataKey": { # Lookup key for a feature view. # The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs. + "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec. + "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order. + "A String", + ], + }, + "key": "A String", # String key to use for lookup. + }, "keyValues": { # Response structure in the format of key (feature name) and (feature) value pair. # Feature values in KeyValue format. "features": [ # List of feature names and values. { # Feature name & value pair. @@ -643,6 +654,14 @@

Method Details

"distance": 3.14, # The distance between the neighbor and the query vector. "entityId": "A String", # The id of the similar entity. "entityKeyValues": { # Response message for FeatureOnlineStoreService.FetchFeatureValues # The attributes of the neighbor, e.g. filters, crowding and metadata Note that full entities are returned only when "return_full_entity" is set to true. Otherwise, only the "entity_id" and "distance" fields are populated. + "dataKey": { # Lookup key for a feature view. # The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs. + "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec. + "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order. + "A String", + ], + }, + "key": "A String", # String key to use for lookup. + }, "keyValues": { # Response structure in the format of key (feature name) and (feature) value pair. # Feature values in KeyValue format. "features": [ # List of feature names and values. { # Feature name & value pair. @@ -748,6 +767,112 @@

Method Details

} +
+ streamingFetchFeatureValues(featureView, body=None, x__xgafv=None) + 
Bidirectional streaming RPC to fetch feature values under a FeatureView. Requests may not have a one-to-one mapping to responses and responses may be returned out-of-order to reduce latency.
+
+Args:
+  featureView: string, Required. FeatureView resource format `projects/{project}/locations/{location}/featureOnlineStores/{featureOnlineStore}/featureViews/{featureView}` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Request message for FeatureOnlineStoreService.StreamingFetchFeatureValues. For the entities requested, all features under the requested feature view will be returned.
+  "dataFormat": "A String", # Specify response data format. If not set, KeyValue format will be used.
+  "dataKeys": [
+    { # Lookup key for a feature view.
+      "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec.
+        "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order.
+          "A String",
+        ],
+      },
+      "key": "A String", # String key to use for lookup.
+    },
+  ],
+}
+
+  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 FeatureOnlineStoreService.StreamingFetchFeatureValues.
+  "data": [
+    { # Response message for FeatureOnlineStoreService.FetchFeatureValues
+      "dataKey": { # Lookup key for a feature view. # The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs.
+        "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec.
+          "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order.
+            "A String",
+          ],
+        },
+        "key": "A String", # String key to use for lookup.
+      },
+      "keyValues": { # Response structure in the format of key (feature name) and (feature) value pair. # Feature values in KeyValue format.
+        "features": [ # List of feature names and values.
+          { # Feature name & value pair.
+            "name": "A String", # Feature short name.
+            "value": { # Value for a feature. # Feature value.
+              "boolArrayValue": { # A list of boolean values. # A list of bool type feature value.
+                "values": [ # A list of bool values.
+                  True or False,
+                ],
+              },
+              "boolValue": True or False, # Bool type feature value.
+              "bytesValue": "A String", # Bytes feature value.
+              "doubleArrayValue": { # A list of double values. # A list of double type feature value.
+                "values": [ # A list of double values.
+                  3.14,
+                ],
+              },
+              "doubleValue": 3.14, # Double type feature value.
+              "int64ArrayValue": { # A list of int64 values. # A list of int64 type feature value.
+                "values": [ # A list of int64 values.
+                  "A String",
+                ],
+              },
+              "int64Value": "A String", # Int64 feature value.
+              "metadata": { # Metadata of feature value. # Metadata of feature value.
+                "generateTime": "A String", # Feature generation timestamp. Typically, it is provided by user at feature ingestion time. If not, feature store will use the system timestamp when the data is ingested into feature store. For streaming ingestion, the time, aligned by days, must be no older than five years (1825 days) and no later than one year (366 days) in the future.
+              },
+              "stringArrayValue": { # A list of string values. # A list of string type feature value.
+                "values": [ # A list of string values.
+                  "A String",
+                ],
+              },
+              "stringValue": "A String", # String feature value.
+            },
+          },
+        ],
+      },
+      "protoStruct": { # Feature values in proto Struct format.
+        "a_key": "", # Properties of the object.
+      },
+    },
+  ],
+  "dataKeysWithError": [
+    { # Lookup key for a feature view.
+      "compositeKey": { # ID that is comprised from several parts (columns). # The actual Entity ID will be composed from this struct. This should match with the way ID is defined in the FeatureView spec.
+        "parts": [ # Parts to construct Entity ID. Should match with the same ID columns as defined in FeatureView in the same order.
+          "A String",
+        ],
+      },
+      "key": "A String", # String key to use for lookup.
+    },
+  ],
+  "status": { # 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). # Response status. If OK, then StreamingFetchFeatureValuesResponse.data will be populated. Otherwise StreamingFetchFeatureValuesResponse.data_keys_with_error will be populated with the appropriate data keys. The error only applies to the listed data keys - the stream will remain open for further FeatureOnlineStoreService.StreamingFetchFeatureValuesRequest requests.
+    "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.
+  },
+}
+
+
sync(featureView, body=None, x__xgafv=None) 
Triggers on-demand sync for the FeatureView.
diff --git a/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html b/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html
index 9632e09bb8..3238f16a9d 100644
--- a/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html
+++ b/docs/dyn/aiplatform_v1beta1.projects.locations.persistentResources.html
@@ -100,6 +100,9 @@ 
Instance Methods

 

   patch(name, body=None, updateMask=None, x__xgafv=None)

 
Updates a PersistentResource.

+

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

+
Reboots a PersistentResource.

 
Method Details

 

     close()
@@ -554,4 +557,45 @@ 
Method Details

 }
+
+ reboot(name, body=None, x__xgafv=None) + 
Reboots a PersistentResource.
+
+Args:
+  name: string, Required. The name of the PersistentResource resource. Format: `projects/{project_id_or_number}/locations/{location_id}/persistentResources/{persistent_resource_id}` (required)
+  body: object, The request body.
+    The object takes the form of:
+
+{ # Request message for PersistentResourceService.RebootPersistentResource.
+}
+
+  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.publishers.models.html b/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html index d923bb8e7b..eaf2899f93 100644 --- a/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html +++ b/docs/dyn/aiplatform_v1beta1.projects.locations.publishers.models.html @@ -269,40 +269,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -310,20 +276,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -334,7 +311,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, @@ -816,40 +793,6 @@

Method Details

"threshold": "A String", # Required. The harm block threshold. }, ], - "systemInstructions": [ # Optional. The user provided system instructions for the model. - { # 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": { # Raw media bytes. Text should not be sent as raw bytes, use the 'text' field. # Optional. Inlined bytes data. - "data": "A String", # Required. Raw bytes for media formats. - "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. - }, - ], "tools": [ # Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. { # Tool details that the model may use to generate response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model. A Tool object should contain exactly one type of Tool (e.g FunctionDeclaration, Retrieval or GoogleSearchRetrieval). "functionDeclarations": [ # Optional. Function tool type. One or more function declarations to be passed to the model along with the current user query. Model may decide to call a subset of these functions by populating FunctionCall in the response. User should provide a FunctionResponse for each function call in the next turn. Based on the function responses, Model will generate the final response back to the user. Maximum 64 function declarations can be provided. @@ -857,20 +800,31 @@

Method Details

"description": "A String", # Optional. Description and purpose of the function. Model uses it to decide how and whether to call the function. "name": "A String", # Required. The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contain underscores, dots and dashes, with a maximum length of 64. "parameters": { # Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed. # Optional. Describes the parameters to this function in JSON Schema Object format. Reflects the Open API 3.03 Parameter Object. string Key: the name of the parameter. Parameter names are case sensitive. Schema Value: the Schema defining the type used for the parameter. For function with no parameters, this can be left unset. Parameter names must start with a letter or an underscore and must only contain chars a-z, A-Z, 0-9, or underscores with a maximum length of 64. Example with 1 required and 1 optional parameter: type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1 + "default": "", # Optional. Default value of the data. "description": "A String", # Optional. The description of the data. "enum": [ # Optional. Possible values of the element of Type.STRING with enum format. For example we can define an Enum Direction as : {type:STRING, format:enum, enum:["EAST", NORTH", "SOUTH", "WEST"]} "A String", ], "example": "", # Optional. Example of the object. Will only populated when the object is the root. - "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64 - "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. Schema of the elements of Type.ARRAY. + "format": "A String", # Optional. The format of the data. Supported formats: for NUMBER type: "float", "double" for INTEGER type: "int32", "int64" for STRING type: "email", "byte", etc + "items": # Object with schema name: GoogleCloudAiplatformV1beta1Schema # Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY. + "maxItems": "A String", # Optional. Maximum number of the elements for Type.ARRAY. + "maxLength": "A String", # Optional. Maximum length of the Type.STRING + "maxProperties": "A String", # Optional. Maximum number of the properties for Type.OBJECT. + "maximum": 3.14, # Optional. Maximum value of the Type.INTEGER and Type.NUMBER + "minItems": "A String", # Optional. Minimum number of the elements for Type.ARRAY. + "minLength": "A String", # Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING + "minProperties": "A String", # Optional. Minimum number of the properties for Type.OBJECT. + "minimum": 3.14, # Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER "nullable": True or False, # Optional. Indicates if the value may be null. - "properties": { # Optional. Properties of Type.OBJECT. + "pattern": "A String", # Optional. Pattern of the Type.STRING to restrict a string to a regular expression. + "properties": { # Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT. "a_key": # Object with schema name: GoogleCloudAiplatformV1beta1Schema }, "required": [ # Optional. Required properties of Type.OBJECT. "A String", ], + "title": "A String", # Optional. The title of the Schema. "type": "A String", # Optional. The type of the data. }, }, @@ -881,7 +835,7 @@

Method Details

"retrieval": { # Defines a retrieval tool that model can call to access external knowledge. # Optional. Retrieval tool type. System will always execute the provided retrieval tool(s) to get external knowledge to answer the prompt. Retrieval results are presented to the model for generation. "disableAttribution": True or False, # Optional. Disable using the result from this tool in detecting grounding attribution. This does not affect how the result is given to the model for generation. "vertexAiSearch": { # Retrieve from Vertex AI Search datastore for grounding. See https://cloud.google.com/vertex-ai-search-and-conversation # Set to use data source powered by Vertex AI Search. - "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<> + "datastore": "A String", # Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore} }, }, }, diff --git a/docs/dyn/aiplatform_v1beta1.publishers.models.html b/docs/dyn/aiplatform_v1beta1.publishers.models.html index a5233c4bd2..85e0c78bd1 100644 --- a/docs/dyn/aiplatform_v1beta1.publishers.models.html +++ b/docs/dyn/aiplatform_v1beta1.publishers.models.html @@ -232,6 +232,87 @@

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. @@ -528,6 +609,87 @@

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 91e3eece34..51dfb4ce9d 100644 --- a/googleapiclient/discovery_cache/documents/aiplatform.v1.json +++ b/googleapiclient/discovery_cache/documents/aiplatform.v1.json @@ -3242,7 +3242,7 @@ ], "parameters": { "filter": { -"description": "Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports = and !=. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports = and, != * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:* or labels:key - key existence * A key including a space must be quoted. `labels.\"a key\"`. * `base_model_name` only supports = Some examples: * `endpoint=1` * `displayName=\"myDisplayName\"` * `labels.myKey=\"myValue\"` * `baseModelName=\"text-bison\"`", +"description": "Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports `=` and `!=`. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports `=` and `!=`. * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:*` or `labels:key` - key existence * A key including a space must be quoted. `labels.\"a key\"`. * `base_model_name` only supports `=`. Some examples: * `endpoint=1` * `displayName=\"myDisplayName\"` * `labels.myKey=\"myValue\"` * `baseModelName=\"text-bison\"`", "location": "query", "type": "string" }, @@ -11797,6 +11797,187 @@ "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ] +}, +"reboot": { +"description": "Reboots a PersistentResource.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}:reboot", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.persistentResources.reboot", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "Required. The name of the PersistentResource resource. Format: `projects/{project_id_or_number}/locations/{location_id}/persistentResources/{persistent_resource_id}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+name}:reboot", +"request": { +"$ref": "GoogleCloudAiplatformV1RebootPersistentResourceRequest" +}, +"response": { +"$ref": "GoogleLongrunningOperation" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +} +}, +"resources": { +"operations": { +"methods": { +"cancel": { +"description": "Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Clients can use Operations.GetOperation or other methods to check whether the cancellation succeeded or whether the operation completed despite cancellation. On successful cancellation, the operation is not deleted; instead, it becomes an operation with an Operation.error value with a google.rpc.Status.code of 1, corresponding to `Code.CANCELLED`.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}/operations/{operationsId}:cancel", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.persistentResources.operations.cancel", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "The name of the operation resource to be cancelled.", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+/operations/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+name}:cancel", +"response": { +"$ref": "GoogleProtobufEmpty" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"delete": { +"description": "Deletes a long-running operation. This method indicates that the client is no longer interested in the operation result. It does not cancel the operation. If the server doesn't support this method, it returns `google.rpc.Code.UNIMPLEMENTED`.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}/operations/{operationsId}", +"httpMethod": "DELETE", +"id": "aiplatform.projects.locations.persistentResources.operations.delete", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "The name of the operation resource to be deleted.", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+/operations/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+name}", +"response": { +"$ref": "GoogleProtobufEmpty" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"get": { +"description": "Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}/operations/{operationsId}", +"httpMethod": "GET", +"id": "aiplatform.projects.locations.persistentResources.operations.get", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "The name of the operation resource.", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+/operations/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1/{+name}", +"response": { +"$ref": "GoogleLongrunningOperation" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"list": { +"description": "Lists operations that match the specified filter in the request. If the server doesn't support this method, it returns `UNIMPLEMENTED`.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}/operations", +"httpMethod": "GET", +"id": "aiplatform.projects.locations.persistentResources.operations.list", +"parameterOrder": [ +"name" +], +"parameters": { +"filter": { +"description": "The standard list filter.", +"location": "query", +"type": "string" +}, +"name": { +"description": "The name of the operation's parent resource.", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+$", +"required": true, +"type": "string" +}, +"pageSize": { +"description": "The standard list page size.", +"format": "int32", +"location": "query", +"type": "integer" +}, +"pageToken": { +"description": "The standard list page token.", +"location": "query", +"type": "string" +} +}, +"path": "v1/{+name}/operations", +"response": { +"$ref": "GoogleLongrunningListOperationsResponse" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, +"wait": { +"description": "Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state. If the operation is already done, the latest state is immediately returned. If the timeout specified is greater than the default HTTP/RPC timeout, the HTTP/RPC timeout is used. If the server does not support this method, it returns `google.rpc.Code.UNIMPLEMENTED`. Note that this method is on a best-effort basis. It may return the latest state before the specified timeout (including immediately), meaning even an immediate response is no guarantee that the operation is done.", +"flatPath": "v1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}/operations/{operationsId}:wait", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.persistentResources.operations.wait", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "The name of the operation resource to wait on.", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+/operations/[^/]+$", +"required": true, +"type": "string" +}, +"timeout": { +"description": "The maximum duration to wait before timing out. If left blank, the wait will be at most the time permitted by the underlying HTTP/RPC protocol. If RPC context deadline is also specified, the shorter one will be used.", +"format": "google-duration", +"location": "query", +"type": "string" +} +}, +"path": "v1/{+name}:wait", +"response": { +"$ref": "GoogleLongrunningOperation" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +} +} } } }, @@ -15858,7 +16039,7 @@ } } }, -"revision": "20240313", +"revision": "20240320", "rootUrl": "https://aiplatform.googleapis.com/", "schemas": { "CloudAiLargeModelsVisionEmbedVideoResponse": { @@ -19012,6 +19193,10 @@ "description": "Optional. The full name of the Compute Engine [network](/compute/docs/networks-and-firewalls#networks) to which the Job should be peered. For example, `projects/12345/global/networks/myVPC`. [Format](/compute/docs/reference/rest/v1/networks/insert) is of the form `projects/{project}/global/networks/{network}`. Where {project} is a project number, as in `12345`, and {network} is a network name. To specify this field, you must have already [configured VPC Network Peering for Vertex AI](https://cloud.google.com/vertex-ai/docs/general/vpc-peering). If this field is left unspecified, the job is not peered with any network.", "type": "string" }, +"persistentResourceId": { +"description": "Optional. The ID of the PersistentResource in the same Project and Location which to run If this is specified, the job will be run on existing machines held by the PersistentResource instead of on-demand short-live machines. The network and CMEK configs on the job should be consistent with those on the PersistentResource, otherwise, the job will be rejected.", +"type": "string" +}, "protectedArtifactLocationId": { "description": "The ID of the location to store protected artifacts. e.g. us-central1. Populate only when the location is different than CustomJob location. List of supported locations: https://cloud.google.com/vertex-ai/docs/general/locations", "type": "string" @@ -22038,6 +22223,10 @@ "description": "Response message for FeatureOnlineStoreService.FetchFeatureValues", "id": "GoogleCloudAiplatformV1FetchFeatureValuesResponse", "properties": { +"dataKey": { +"$ref": "GoogleCloudAiplatformV1FeatureViewDataKey", +"description": "The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs." +}, "keyValues": { "$ref": "GoogleCloudAiplatformV1FetchFeatureValuesResponseFeatureNameValuePairList", "description": "Feature values in KeyValue format." @@ -22343,13 +22532,6 @@ }, "type": "array" }, -"systemInstructions": { -"description": "Optional. The user provided system instructions for the model.", -"items": { -"$ref": "GoogleCloudAiplatformV1Content" -}, -"type": "array" -}, "tools": { "description": "Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.", "items": { @@ -27789,6 +27971,10 @@ "$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionDeployGke", "description": "Optional. Deploy PublisherModel to Google Kubernetes Engine." }, +"multiDeployVertex": { +"$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex", +"description": "Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint." +}, "openEvaluationPipeline": { "$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionRegionalResourceReferences", "description": "Optional. Open evaluation pipeline of the PublisherModel." @@ -27889,6 +28075,20 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex": { +"description": "Multiple setups to deploy the PublisherModel.", +"id": "GoogleCloudAiplatformV1PublisherModelCallToActionDeployVertex", +"properties": { +"multiDeployVertex": { +"description": "Optional. One click deployment configurations.", +"items": { +"$ref": "GoogleCloudAiplatformV1PublisherModelCallToActionDeploy" +}, +"type": "array" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1PublisherModelCallToActionOpenFineTuningPipelines": { "description": "Open fine tuning pipelines.", "id": "GoogleCloudAiplatformV1PublisherModelCallToActionOpenFineTuningPipelines", @@ -28480,6 +28680,12 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1RebootPersistentResourceRequest": { +"description": "Request message for PersistentResourceService.RebootPersistentResource.", +"id": "GoogleCloudAiplatformV1RebootPersistentResourceRequest", +"properties": {}, +"type": "object" +}, "GoogleCloudAiplatformV1RemoveContextChildrenRequest": { "description": "Request message for MetadataService.DeleteContextChildrenRequest.", "id": "GoogleCloudAiplatformV1RemoveContextChildrenRequest", @@ -29082,6 +29288,10 @@ "description": "Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed.", "id": "GoogleCloudAiplatformV1Schema", "properties": { +"default": { +"description": "Optional. Default value of the data.", +"type": "any" +}, "description": { "description": "Optional. The description of the data.", "type": "string" @@ -29098,22 +29308,66 @@ "type": "any" }, "format": { -"description": "Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64", +"description": "Optional. The format of the data. Supported formats: for NUMBER type: \"float\", \"double\" for INTEGER type: \"int32\", \"int64\" for STRING type: \"email\", \"byte\", etc", "type": "string" }, "items": { "$ref": "GoogleCloudAiplatformV1Schema", -"description": "Optional. Schema of the elements of Type.ARRAY." +"description": "Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY." +}, +"maxItems": { +"description": "Optional. Maximum number of the elements for Type.ARRAY.", +"format": "int64", +"type": "string" +}, +"maxLength": { +"description": "Optional. Maximum length of the Type.STRING", +"format": "int64", +"type": "string" +}, +"maxProperties": { +"description": "Optional. Maximum number of the properties for Type.OBJECT.", +"format": "int64", +"type": "string" +}, +"maximum": { +"description": "Optional. Maximum value of the Type.INTEGER and Type.NUMBER", +"format": "double", +"type": "number" +}, +"minItems": { +"description": "Optional. Minimum number of the elements for Type.ARRAY.", +"format": "int64", +"type": "string" +}, +"minLength": { +"description": "Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING", +"format": "int64", +"type": "string" +}, +"minProperties": { +"description": "Optional. Minimum number of the properties for Type.OBJECT.", +"format": "int64", +"type": "string" +}, +"minimum": { +"description": "Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER", +"format": "double", +"type": "number" }, "nullable": { "description": "Optional. Indicates if the value may be null.", "type": "boolean" }, +"pattern": { +"description": "Optional. Pattern of the Type.STRING to restrict a string to a regular expression.", +"type": "string" +}, "properties": { "additionalProperties": { "$ref": "GoogleCloudAiplatformV1Schema" }, -"description": "Optional. Properties of Type.OBJECT.", +"description": "Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.", "type": "object" }, "required": { @@ -29123,6 +29377,10 @@ }, "type": "array" }, +"title": { +"description": "Optional. The title of the Schema.", +"type": "string" +}, "type": { "description": "Optional. The type of the data.", "enum": [ @@ -35078,7 +35336,7 @@ false "id": "GoogleCloudAiplatformV1VertexAISearch", "properties": { "datastore": { -"description": "Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<>", +"description": "Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}", "type": "string" } }, @@ -35830,6 +36088,8 @@ false "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -36155,6 +36415,8 @@ false "", "", "", +"", +"", "Bard ARCADE finetune dataset.", "Mobile assistant finetune datasets.", "", @@ -36594,6 +36856,8 @@ false "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -36919,6 +37183,8 @@ false "", "", "", +"", +"", "Bard ARCADE finetune dataset.", "Mobile assistant finetune datasets.", "", @@ -37369,6 +37635,8 @@ false "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -37694,6 +37962,8 @@ false "", "", "", +"", +"", "Bard ARCADE finetune dataset", "Mobile assistant finetune datasets.", "", @@ -38133,6 +38403,8 @@ false "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -38458,6 +38730,8 @@ false "", "", "", +"", +"", "Bard ARCADE finetune dataset", "Mobile assistant finetune datasets.", "", @@ -39150,7 +39424,7 @@ false "id": "LearningGenaiRootGroundingMetadataCitation", "properties": { "endIndex": { -"description": "Index in the prediction output where the citation ends (exclusive). Must be > start_index and < len(output).", +"description": "Index in the prediction output where the citation ends (exclusive). Must be > start_index and <= len(output).", "format": "int32", "type": "integer" }, @@ -39940,14 +40214,16 @@ false "RETURN", "STOP", "MAX_TOKENS", -"FILTER" +"FILTER", +"TOP_N_FILTERED" ], "enumDescriptions": [ "", "Return all the tokens back. This typically implies no filtering or stop sequence was triggered.", "Finished due to provided stop sequence.", "Model has emitted the maximum number of tokens as specified by max_decoding_steps.", -"Finished due to triggering some post-processing filter." +"Finished due to triggering some post-processing filter.", +"Filtered out due to Top_N < Response_Candidates.Size()" ], "type": "string" }, diff --git a/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json b/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json index 1722305cb2..c1f9316330 100644 --- a/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json +++ b/googleapiclient/discovery_cache/documents/aiplatform.v1beta1.json @@ -3428,7 +3428,7 @@ ], "parameters": { "filter": { -"description": "Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports = and !=. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports = and, != * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:* or labels:key - key existence * A key including a space must be quoted. `labels.\"a key\"`. * `base_model_name` only supports = Some examples: * `endpoint=1` * `displayName=\"myDisplayName\"` * `labels.myKey=\"myValue\"` * `baseModelName=\"text-bison\"`", +"description": "Optional. An expression for filtering the results of the request. For field names both snake_case and camelCase are supported. * `endpoint` supports `=` and `!=`. `endpoint` represents the Endpoint ID, i.e. the last segment of the Endpoint's resource name. * `display_name` supports `=` and `!=`. * `labels` supports general map functions that is: * `labels.key=value` - key:value equality * `labels.key:*` or `labels:key` - key existence * A key including a space must be quoted. `labels.\"a key\"`. * `base_model_name` only supports `=`. Some examples: * `endpoint=1` * `displayName=\"myDisplayName\"` * `labels.myKey=\"myValue\"` * `baseModelName=\"text-bison\"`", "location": "query", "type": "string" }, @@ -4492,7 +4492,7 @@ "type": "string" }, "updateMask": { -"description": "Required. Mask specifying which fields to update. Supported fields: * `display_name` * `description`", +"description": "Required. Mask specifying which fields to update. Supported fields: * `display_name` * `description` * `tool_use_examples`", "format": "google-fieldmask", "location": "query", "type": "string" @@ -4508,6 +4508,34 @@ "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ] +}, +"query": { +"description": "Queries an extension with a default controller.", +"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/extensions/{extensionsId}:query", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.extensions.query", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "Required. Name (identifier) of the extension; Format: `projects/{project}/locations/{location}/extensions/{extension}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/extensions/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1beta1/{+name}:query", +"request": { +"$ref": "GoogleCloudAiplatformV1beta1QueryExtensionRequest" +}, +"response": { +"$ref": "GoogleCloudAiplatformV1beta1QueryExtensionResponse" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] } }, "resources": { @@ -5973,6 +6001,34 @@ "https://www.googleapis.com/auth/cloud-platform" ] }, +"streamingFetchFeatureValues": { +"description": "Bidirectional streaming RPC to fetch feature values under a FeatureView. Requests may not have a one-to-one mapping to responses and responses may be returned out-of-order to reduce latency.", +"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/featureOnlineStores/{featureOnlineStoresId}/featureViews/{featureViewsId}:streamingFetchFeatureValues", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.featureOnlineStores.featureViews.streamingFetchFeatureValues", +"parameterOrder": [ +"featureView" +], +"parameters": { +"featureView": { +"description": "Required. FeatureView resource format `projects/{project}/locations/{location}/featureOnlineStores/{featureOnlineStore}/featureViews/{featureView}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/featureOnlineStores/[^/]+/featureViews/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1beta1/{+featureView}:streamingFetchFeatureValues", +"request": { +"$ref": "GoogleCloudAiplatformV1beta1StreamingFetchFeatureValuesRequest" +}, +"response": { +"$ref": "GoogleCloudAiplatformV1beta1StreamingFetchFeatureValuesResponse" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] +}, "sync": { "description": "Triggers on-demand sync for the FeatureView.", "flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/featureOnlineStores/{featureOnlineStoresId}/featureViews/{featureViewsId}:sync", @@ -13387,6 +13443,34 @@ "scopes": [ "https://www.googleapis.com/auth/cloud-platform" ] +}, +"reboot": { +"description": "Reboots a PersistentResource.", +"flatPath": "v1beta1/projects/{projectsId}/locations/{locationsId}/persistentResources/{persistentResourcesId}:reboot", +"httpMethod": "POST", +"id": "aiplatform.projects.locations.persistentResources.reboot", +"parameterOrder": [ +"name" +], +"parameters": { +"name": { +"description": "Required. The name of the PersistentResource resource. Format: `projects/{project_id_or_number}/locations/{location_id}/persistentResources/{persistent_resource_id}`", +"location": "path", +"pattern": "^projects/[^/]+/locations/[^/]+/persistentResources/[^/]+$", +"required": true, +"type": "string" +} +}, +"path": "v1beta1/{+name}:reboot", +"request": { +"$ref": "GoogleCloudAiplatformV1beta1RebootPersistentResourceRequest" +}, +"response": { +"$ref": "GoogleLongrunningOperation" +}, +"scopes": [ +"https://www.googleapis.com/auth/cloud-platform" +] } }, "resources": { @@ -18168,7 +18252,7 @@ } } }, -"revision": "20240313", +"revision": "20240320", "rootUrl": "https://aiplatform.googleapis.com/", "schemas": { "CloudAiLargeModelsVisionEmbedVideoResponse": { @@ -19696,7 +19780,7 @@ "id": "GoogleCloudAiplatformV1beta1AuthConfigApiKeyConfig", "properties": { "apiKeySecret": { -"description": "Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}`", +"description": "Required. The name of the SecretManager secret version resource storing the API key. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.", "type": "string" }, "httpElementLocation": { @@ -19731,7 +19815,7 @@ "id": "GoogleCloudAiplatformV1beta1AuthConfigGoogleServiceAccountConfig", "properties": { "serviceAccount": { -"description": "Optional. The service account that the extension execution service runs as. - If it is not specified, the Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) will be used. - If the service account is provided, the service account should grant Vertex AI Extension Service Agent `iam.serviceAccounts.getAccessToken` permission.", +"description": "Optional. The service account that the extension execution service runs as. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified service account. - If not specified, the Vertex AI Extension Service Agent will be used to execute the Extension.", "type": "string" } }, @@ -19742,7 +19826,7 @@ "id": "GoogleCloudAiplatformV1beta1AuthConfigHttpBasicAuthConfig", "properties": { "credentialSecret": { -"description": "Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}`", +"description": "Required. The name of the SecretManager secret version resource storing the base64 encoded credentials. Format: `projects/{project}/secrets/{secrete}/versions/{version}` - If specified, the `secretmanager.versions.access` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the specified resource.", "type": "string" } }, @@ -19759,11 +19843,11 @@ "id": "GoogleCloudAiplatformV1beta1AuthConfigOauthConfig", "properties": { "accessToken": { -"description": "Access token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time.", +"description": "Access token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.", "type": "string" }, "serviceAccount": { -"description": "The service account that the extension execution service will use to query extension. Used for generating OAuth token on behalf of provided service account. - If the service account is provided, the service account should grant Vertex AI Service Agent `iam.serviceAccounts.getAccessToken` permission.", +"description": "The service account used to generate access tokens for executing the Extension. - If the service account is specified, the `iam.serviceAccounts.getAccessToken` permission should be granted to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents) on the provided service account.", "type": "string" } }, @@ -19774,7 +19858,11 @@ "id": "GoogleCloudAiplatformV1beta1AuthConfigOidcConfig", "properties": { "idToken": { -"description": "OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from ExecuteExtensionRequest.runtime_auth_config at request time.", +"description": "OpenID Connect formatted ID token for extension endpoint. Only used to propagate token from [[ExecuteExtensionRequest.runtime_auth_config]] at request time.", +"type": "string" +}, +"serviceAccount": { +"description": "The service account used to generate an OpenID Connect (OIDC)-compatible JWT token signed by the Google OIDC Provider (accounts.google.com) for extension endpoint (https://cloud.google.com/iam/docs/create-short-lived-credentials-direct#sa-credentials-oidc). - The audience for the token will be set to the URL in the server url defined in the OpenApi spec. - If the service account is provided, the service account should grant `iam.serviceAccounts.getOpenIdToken` permission to Vertex AI Extension Service Agent (https://cloud.google.com/vertex-ai/docs/general/access-control#service-agents).", "type": "string" } }, @@ -20667,6 +20755,17 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1CheckPoint": { +"description": "Placeholder for all checkpoint related data. Any data needed to restore a request and more go/vertex-extension-query-operation", +"id": "GoogleCloudAiplatformV1beta1CheckPoint", +"properties": { +"content": { +"description": "Required. encoded checkpoint", +"type": "string" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1CheckTrialEarlyStoppingStateMetatdata": { "description": "This message will be placed in the metadata field of a google.longrunning.Operation associated with a CheckTrialEarlyStoppingState request.", "id": "GoogleCloudAiplatformV1beta1CheckTrialEarlyStoppingStateMetatdata", @@ -22920,7 +23019,7 @@ "id": "GoogleCloudAiplatformV1beta1ExecuteExtensionRequest", "properties": { "operationId": { -"description": "Required. The operation to be executed in this extension as defined in ExtensionOperation.operation_id.", +"description": "Required. The desired ID of the operation to be executed in this extension as defined in ExtensionOperation.operation_id.", "type": "string" }, "operationParams": { @@ -22945,15 +23044,6 @@ "content": { "description": "Response content from the extension. The content should be conformant to the response.content schema in the extension's manifest/OpenAPI spec.", "type": "string" -}, -"output": { -"additionalProperties": { -"description": "Properties of the object.", -"type": "any" -}, -"deprecated": true, -"description": "Output from the extension. The output should be conformant to the extension's manifest/OpenAPI spec. The output can contain values for keys like \"content\", \"headers\", etc. This field is deprecated, please use content field below for the extension execution result.", -"type": "object" } }, "type": "object" @@ -23039,6 +23129,56 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1ExecutionPlan": { +"description": "Execution plan for a request.", +"id": "GoogleCloudAiplatformV1beta1ExecutionPlan", +"properties": { +"steps": { +"description": "Required. Sequence of steps to execute a request.", +"items": { +"$ref": "GoogleCloudAiplatformV1beta1ExecutionPlanStep" +}, +"type": "array" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1ExecutionPlanStep": { +"description": "Single step in query execution plan.", +"id": "GoogleCloudAiplatformV1beta1ExecutionPlanStep", +"properties": { +"extensionExecution": { +"$ref": "GoogleCloudAiplatformV1beta1ExecutionPlanStepExtensionExecution", +"description": "Extension execution step." +}, +"respondToUser": { +"$ref": "GoogleCloudAiplatformV1beta1ExecutionPlanStepRespondToUser", +"description": "Respond to user step." +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1ExecutionPlanStepExtensionExecution": { +"description": "Extension execution step.", +"id": "GoogleCloudAiplatformV1beta1ExecutionPlanStepExtensionExecution", +"properties": { +"extension": { +"description": "Required. extension resource name", +"type": "string" +}, +"operationId": { +"description": "Required. the operation id", +"type": "string" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1ExecutionPlanStepRespondToUser": { +"description": "Respond to user step.", +"id": "GoogleCloudAiplatformV1beta1ExecutionPlanStepRespondToUser", +"properties": {}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1ExplainRequest": { "description": "Request message for PredictionService.Explain.", "id": "GoogleCloudAiplatformV1beta1ExplainRequest", @@ -24893,6 +25033,10 @@ "description": "Response message for FeatureOnlineStoreService.FetchFeatureValues", "id": "GoogleCloudAiplatformV1beta1FetchFeatureValuesResponse", "properties": { +"dataKey": { +"$ref": "GoogleCloudAiplatformV1beta1FeatureViewDataKey", +"description": "The data key associated with this response. Will only be populated for FeatureOnlineStoreService.StreamingFetchFeatureValues RPCs." +}, "keyValues": { "$ref": "GoogleCloudAiplatformV1beta1FetchFeatureValuesResponseFeatureNameValuePairList", "description": "Feature values in KeyValue format." @@ -25233,13 +25377,6 @@ }, "type": "array" }, -"systemInstructions": { -"description": "Optional. The user provided system instructions for the model.", -"items": { -"$ref": "GoogleCloudAiplatformV1beta1Content" -}, -"type": "array" -}, "tools": { "description": "Optional. A list of `Tools` the model may use to generate the next response. A `Tool` is a piece of code that enables the system to interact with external systems to perform an action, or set of actions, outside of knowledge and scope of the model.", "items": { @@ -30780,6 +30917,10 @@ "$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." @@ -30880,6 +31021,20 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployVertex": { +"description": "Multiple setups to deploy the PublisherModel.", +"id": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeployVertex", +"properties": { +"multiDeployVertex": { +"description": "Optional. One click deployment configurations.", +"items": { +"$ref": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionDeploy" +}, +"type": "array" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1PublisherModelCallToActionOpenFineTuningPipelines": { "description": "Open fine tuning pipelines.", "id": "GoogleCloudAiplatformV1beta1PublisherModelCallToActionOpenFineTuningPipelines", @@ -31218,6 +31373,143 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1QueryExtensionRequest": { +"description": "Request message for ExtensionExecutionService.QueryExtension.", +"id": "GoogleCloudAiplatformV1beta1QueryExtensionRequest", +"properties": { +"contents": { +"description": "Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries, this is a repeated field that contains conversation history + latest request.", +"items": { +"$ref": "GoogleCloudAiplatformV1beta1Content" +}, +"type": "array" +}, +"query": { +"$ref": "GoogleCloudAiplatformV1beta1QueryRequestQuery", +"deprecated": true, +"description": "Required. User provided input query message." +}, +"useFunctionCall": { +"description": "Optional. Experiment control on whether to use function call.", +"type": "boolean" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1QueryExtensionResponse": { +"description": "Response message for ExtensionExecutionService.QueryExtension.", +"id": "GoogleCloudAiplatformV1beta1QueryExtensionResponse", +"properties": { +"failureMessage": { +"description": "Failure message if any.", +"type": "string" +}, +"metadata": { +"$ref": "GoogleCloudAiplatformV1beta1QueryResponseResponseMetadata", +"deprecated": true, +"description": "Metadata related to the query execution." +}, +"queryResponseMetadata": { +"$ref": "GoogleCloudAiplatformV1beta1QueryResponseQueryResponseMetadata", +"deprecated": true +}, +"response": { +"deprecated": true, +"description": "Response to the user's query.", +"type": "string" +}, +"steps": { +"description": "Steps of extension or LLM interaction, can contain function call, function response, or text response. The last step contains the final response to the query.", +"items": { +"$ref": "GoogleCloudAiplatformV1beta1Content" +}, +"type": "array" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1QueryRequestQuery": { +"description": "User provided query message.", +"id": "GoogleCloudAiplatformV1beta1QueryRequestQuery", +"properties": { +"query": { +"description": "Required. The query from user.", +"type": "string" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1QueryResponseQueryResponseMetadata": { +"id": "GoogleCloudAiplatformV1beta1QueryResponseQueryResponseMetadata", +"properties": { +"steps": { +"description": "ReAgent execution steps.", +"items": { +"$ref": "GoogleCloudAiplatformV1beta1QueryResponseQueryResponseMetadataReAgentSteps" +}, +"type": "array" +}, +"useCreativity": { +"description": "Whether the reasoning agent used creativity (instead of extensions provided) to build the response.", +"type": "boolean" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1QueryResponseQueryResponseMetadataReAgentSteps": { +"description": "ReAgent execution steps.", +"id": "GoogleCloudAiplatformV1beta1QueryResponseQueryResponseMetadataReAgentSteps", +"properties": { +"error": { +"description": "Error messages from the extension or during response parsing.", +"type": "string" +}, +"extensionInstruction": { +"description": "Planner's instruction to the extension.", +"type": "string" +}, +"extensionInvoked": { +"description": "Planner's choice of extension to invoke.", +"type": "string" +}, +"response": { +"description": "Response of the extension.", +"type": "string" +}, +"success": { +"description": "When set to False, either the extension fails to execute or the response cannot be summarized.", +"type": "boolean" +}, +"thought": { +"description": "Planner's thought.", +"type": "string" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1QueryResponseResponseMetadata": { +"description": "Metadata for response", +"id": "GoogleCloudAiplatformV1beta1QueryResponseResponseMetadata", +"properties": { +"checkpoint": { +"$ref": "GoogleCloudAiplatformV1beta1CheckPoint", +"description": "Optional. Checkpoint to restore a request" +}, +"executionPlan": { +"$ref": "GoogleCloudAiplatformV1beta1ExecutionPlan", +"description": "Optional. Execution plan for the request." +}, +"flowOutputs": { +"additionalProperties": { +"description": "Properties of the object.", +"type": "any" +}, +"description": "To surface the v2 flow output.", +"type": "object" +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1RawPredictRequest": { "description": "Request message for PredictionService.RawPredict.", "id": "GoogleCloudAiplatformV1beta1RawPredictRequest", @@ -31486,6 +31778,12 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1RebootPersistentResourceRequest": { +"description": "Request message for PersistentResourceService.RebootPersistentResource.", +"id": "GoogleCloudAiplatformV1beta1RebootPersistentResourceRequest", +"properties": {}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1RemoveContextChildrenRequest": { "description": "Request message for MetadataService.DeleteContextChildrenRequest.", "id": "GoogleCloudAiplatformV1beta1RemoveContextChildrenRequest", @@ -32183,6 +32481,10 @@ "description": "Schema is used to define the format of input/output data. Represents a select subset of an [OpenAPI 3.0 schema object](https://spec.openapis.org/oas/v3.0.3#schema). More fields may be added in the future as needed.", "id": "GoogleCloudAiplatformV1beta1Schema", "properties": { +"default": { +"description": "Optional. Default value of the data.", +"type": "any" +}, "description": { "description": "Optional. The description of the data.", "type": "string" @@ -32199,22 +32501,66 @@ "type": "any" }, "format": { -"description": "Optional. The format of the data. Supported formats: for NUMBER type: float, double for INTEGER type: int32, int64", +"description": "Optional. The format of the data. Supported formats: for NUMBER type: \"float\", \"double\" for INTEGER type: \"int32\", \"int64\" for STRING type: \"email\", \"byte\", etc", "type": "string" }, "items": { "$ref": "GoogleCloudAiplatformV1beta1Schema", -"description": "Optional. Schema of the elements of Type.ARRAY." +"description": "Optional. SCHEMA FIELDS FOR TYPE ARRAY Schema of the elements of Type.ARRAY." +}, +"maxItems": { +"description": "Optional. Maximum number of the elements for Type.ARRAY.", +"format": "int64", +"type": "string" +}, +"maxLength": { +"description": "Optional. Maximum length of the Type.STRING", +"format": "int64", +"type": "string" +}, +"maxProperties": { +"description": "Optional. Maximum number of the properties for Type.OBJECT.", +"format": "int64", +"type": "string" +}, +"maximum": { +"description": "Optional. Maximum value of the Type.INTEGER and Type.NUMBER", +"format": "double", +"type": "number" +}, +"minItems": { +"description": "Optional. Minimum number of the elements for Type.ARRAY.", +"format": "int64", +"type": "string" +}, +"minLength": { +"description": "Optional. SCHEMA FIELDS FOR TYPE STRING Minimum length of the Type.STRING", +"format": "int64", +"type": "string" +}, +"minProperties": { +"description": "Optional. Minimum number of the properties for Type.OBJECT.", +"format": "int64", +"type": "string" +}, +"minimum": { +"description": "Optional. SCHEMA FIELDS FOR TYPE INTEGER and NUMBER Minimum value of the Type.INTEGER and Type.NUMBER", +"format": "double", +"type": "number" }, "nullable": { "description": "Optional. Indicates if the value may be null.", "type": "boolean" }, +"pattern": { +"description": "Optional. Pattern of the Type.STRING to restrict a string to a regular expression.", +"type": "string" +}, "properties": { "additionalProperties": { "$ref": "GoogleCloudAiplatformV1beta1Schema" }, -"description": "Optional. Properties of Type.OBJECT.", +"description": "Optional. SCHEMA FIELDS FOR TYPE OBJECT Properties of Type.OBJECT.", "type": "object" }, "required": { @@ -32224,6 +32570,10 @@ }, "type": "array" }, +"title": { +"description": "Optional. The title of the Schema.", +"type": "string" +}, "type": { "description": "Optional. The type of the data.", "enum": [ @@ -36174,6 +36524,56 @@ }, "type": "object" }, +"GoogleCloudAiplatformV1beta1StreamingFetchFeatureValuesRequest": { +"description": "Request message for FeatureOnlineStoreService.StreamingFetchFeatureValues. For the entities requested, all features under the requested feature view will be returned.", +"id": "GoogleCloudAiplatformV1beta1StreamingFetchFeatureValuesRequest", +"properties": { +"dataFormat": { +"description": "Specify response data format. If not set, KeyValue format will be used.", +"enum": [ +"FEATURE_VIEW_DATA_FORMAT_UNSPECIFIED", +"KEY_VALUE", +"PROTO_STRUCT" +], +"enumDescriptions": [ +"Not set. Will be treated as the KeyValue format.", +"Return response data in key-value format.", +"Return response data in proto Struct format." +], +"type": "string" +}, +"dataKeys": { +"items": { +"$ref": "GoogleCloudAiplatformV1beta1FeatureViewDataKey" +}, +"type": "array" +} +}, +"type": "object" +}, +"GoogleCloudAiplatformV1beta1StreamingFetchFeatureValuesResponse": { +"description": "Response message for FeatureOnlineStoreService.StreamingFetchFeatureValues.", +"id": "GoogleCloudAiplatformV1beta1StreamingFetchFeatureValuesResponse", +"properties": { +"data": { +"items": { +"$ref": "GoogleCloudAiplatformV1beta1FetchFeatureValuesResponse" +}, +"type": "array" +}, +"dataKeysWithError": { +"items": { +"$ref": "GoogleCloudAiplatformV1beta1FeatureViewDataKey" +}, +"type": "array" +}, +"status": { +"$ref": "GoogleRpcStatus", +"description": "Response status. If OK, then StreamingFetchFeatureValuesResponse.data will be populated. Otherwise StreamingFetchFeatureValuesResponse.data_keys_with_error will be populated with the appropriate data keys. The error only applies to the listed data keys - the stream will remain open for further FeatureOnlineStoreService.StreamingFetchFeatureValuesRequest requests." +} +}, +"type": "object" +}, "GoogleCloudAiplatformV1beta1StreamingPredictRequest": { "description": "Request message for PredictionService.StreamingPredict. The first message must contain endpoint field and optionally input. The subsequent messages must contain input.", "id": "GoogleCloudAiplatformV1beta1StreamingPredictRequest", @@ -38174,7 +38574,7 @@ "id": "GoogleCloudAiplatformV1beta1VertexAISearch", "properties": { "datastore": { -"description": "Required. Fully-qualified Vertex AI Search's datastore resource ID. projects/<>/locations/<>/collections/<>/dataStores/<>", +"description": "Required. Fully-qualified Vertex AI Search's datastore resource ID. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStore}", "type": "string" } }, @@ -38963,6 +39363,8 @@ "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -39288,6 +39690,8 @@ "", "", "", +"", +"", "Bard ARCADE finetune dataset.", "Mobile assistant finetune datasets.", "", @@ -39727,6 +40131,8 @@ "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -40052,6 +40458,8 @@ "", "", "", +"", +"", "Bard ARCADE finetune dataset.", "Mobile assistant finetune datasets.", "", @@ -40502,6 +40910,8 @@ "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -40827,6 +41237,8 @@ "", "", "", +"", +"", "Bard ARCADE finetune dataset", "Mobile assistant finetune datasets.", "", @@ -41266,6 +41678,8 @@ "DUET_GOOGLESQL_GENERATION", "DUET_CLOUD_IX_PROMPTS", "DUET_RAD", +"DUET_STACKOVERFLOW_ISSUES", +"DUET_STACKOVERFLOW_ANSWERS", "BARD_ARCADE_GITHUB", "MOBILE_ASSISTANT_MAGI_FILTERED_0825_373K", "MOBILE_ASSISTANT_PALM24B_FILTERED_400K", @@ -41591,6 +42005,8 @@ "", "", "", +"", +"", "Bard ARCADE finetune dataset", "Mobile assistant finetune datasets.", "", @@ -42283,7 +42699,7 @@ false "id": "LearningGenaiRootGroundingMetadataCitation", "properties": { "endIndex": { -"description": "Index in the prediction output where the citation ends (exclusive). Must be > start_index and < len(output).", +"description": "Index in the prediction output where the citation ends (exclusive). Must be > start_index and <= len(output).", "format": "int32", "type": "integer" }, @@ -43073,14 +43489,16 @@ false "RETURN", "STOP", "MAX_TOKENS", -"FILTER" +"FILTER", +"TOP_N_FILTERED" ], "enumDescriptions": [ "", "Return all the tokens back. This typically implies no filtering or stop sequence was triggered.", "Finished due to provided stop sequence.", "Model has emitted the maximum number of tokens as specified by max_decoding_steps.", -"Finished due to triggering some post-processing filter." +"Finished due to triggering some post-processing filter.", +"Filtered out due to Top_N < Response_Candidates.Size()" ], "type": "string" },