gcp_discoveryengine_datastore

acl_enabled

Type: BOOLEAN
Provider name: aclEnabled
Description: Immutable. Whether data in the DataStore has ACL information. If set to true, the source data must have ACL. ACL will be ingested when data is ingested by DocumentService.ImportDocuments methods. When ACL is enabled for the DataStore, Document can’t be accessed by calling DocumentService.GetDocument or DocumentService.ListDocuments. Currently ACL is only supported in GENERIC industry vertical with non-PUBLIC_WEBSITE content config.

advanced_site_search_config

Type: STRUCT
Provider name: advancedSiteSearchConfig
Description: Optional. Configuration for advanced site search.

• disable_automatic_refresh
  Type: BOOLEAN
  Provider name: disableAutomaticRefresh
  Description: If set true, automatic refresh is disabled for the DataStore.
  
• disable_initial_index
  Type: BOOLEAN
  Provider name: disableInitialIndex
  Description: If set true, initial indexing is disabled for the DataStore.
  

ancestors

Type: UNORDERED_LIST_STRING

billing_estimation

Type: STRUCT
Provider name: billingEstimation
Description: Output only. Data size estimation for billing.

• structured_data_size
  Type: INT64
  Provider name: structuredDataSize
  Description: Data size for structured data in terms of bytes.
  
• structured_data_update_time
  Type: TIMESTAMP
  Provider name: structuredDataUpdateTime
  Description: Last updated timestamp for structured data.
  
• unstructured_data_size
  Type: INT64
  Provider name: unstructuredDataSize
  Description: Data size for unstructured data in terms of bytes.
  
• unstructured_data_update_time
  Type: TIMESTAMP
  Provider name: unstructuredDataUpdateTime
  Description: Last updated timestamp for unstructured data.
  
• website_data_size
  Type: INT64
  Provider name: websiteDataSize
  Description: Data size for websites in terms of bytes.
  
• website_data_update_time
  Type: TIMESTAMP
  Provider name: websiteDataUpdateTime
  Description: Last updated timestamp for websites.
  

cmek_config

Type: STRUCT
Provider name: cmekConfig
Description: Output only. CMEK-related information for the DataStore.

• is_default
  Type: BOOLEAN
  Provider name: isDefault
  Description: Output only. The default CmekConfig for the Customer.
  
• kms_key
  Type: STRING
  Provider name: kmsKey
  Description: Required. KMS key resource name which will be used to encrypt resources projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}.
  
• kms_key_version
  Type: STRING
  Provider name: kmsKeyVersion
  Description: Output only. KMS key version resource name which will be used to encrypt resources /cryptoKeyVersions/{keyVersion}.
  
• last_rotation_timestamp_micros
  Type: INT64
  Provider name: lastRotationTimestampMicros
  Description: Output only. The timestamp of the last key rotation.
  
• name
  Type: STRING
  Provider name: name
  Description: Required. The name of the CmekConfig of the form projects/{project}/locations/{location}/cmekConfig or projects/{project}/locations/{location}/cmekConfigs/{cmek_config}.
  
• notebooklm_state
  Type: STRING
  Provider name: notebooklmState
  Description: Output only. Whether the NotebookLM Corpus is ready to be used.
  Possible values:
  
  • NOTEBOOK_LM_STATE_UNSPECIFIED - The NotebookLM state is unknown.
    
  • NOTEBOOK_LM_NOT_READY - The NotebookLM is not ready.
    
  • NOTEBOOK_LM_READY - The NotebookLM is ready to be used.
    
  • NOTEBOOK_LM_NOT_ENABLED - The NotebookLM is not enabled.
    
• single_region_keys
  Type: UNORDERED_LIST_STRUCT
  Provider name: singleRegionKeys
  Description: Optional. Single-regional CMEKs that are required for some VAIS features.
  
  • kms_key
    Type: STRING
    Provider name: kmsKey
    Description: Required. Single-regional kms key resource name which will be used to encrypt resources projects/{project}/locations/{location}/keyRings/{keyRing}/cryptoKeys/{keyId}.
    
• state
  Type: STRING
  Provider name: state
  Description: Output only. The states of the CmekConfig.
  Possible values:
  
  • STATE_UNSPECIFIED - The CmekConfig state is unknown.
    
  • CREATING - The CmekConfig is creating.
    
  • ACTIVE - The CmekConfig can be used with DataStores.
    
  • KEY_ISSUE - The CmekConfig is unavailable, most likely due to the KMS Key being revoked.
    
  • DELETING - The CmekConfig is deleting.
    
  • DELETE_FAILED - The CmekConfig deletion process failed.
    
  • UNUSABLE - The CmekConfig is not usable, most likely due to some internal issue.
    
  • ACTIVE_ROTATING - The KMS key version is being rotated.
    
  • DELETED - The KMS key is soft deleted. Some cleanup policy will eventually be applied.
    

content_config

Type: STRING
Provider name: contentConfig
Description: Immutable. The content config of the data store. If this field is unset, the server behavior defaults to ContentConfig.NO_CONTENT.
Possible values:

• CONTENT_CONFIG_UNSPECIFIED - Default value.
  
• NO_CONTENT - Only contains documents without any Document.content.
  
• CONTENT_REQUIRED - Only contains documents with Document.content.
  
• PUBLIC_WEBSITE - The data store is used for public website search.
  
• GOOGLE_WORKSPACE - The data store is used for workspace search. Details of workspace data store are specified in the WorkspaceConfig.
  

create_time

Type: TIMESTAMP
Provider name: createTime
Description: Output only. Timestamp the DataStore was created at.

default_schema_id

Type: STRING
Provider name: defaultSchemaId
Description: Output only. The id of the default Schema associated to this data store.

document_processing_config

Type: STRUCT
Provider name: documentProcessingConfig
Description: Configuration for Document understanding and enrichment.

• chunking_config
  Type: STRUCT
  Provider name: chunkingConfig
  Description: Whether chunking mode is enabled.
  
  • layout_based_chunking_config
    Type: STRUCT
    Provider name: layoutBasedChunkingConfig
    Description: Configuration for the layout based chunking.
    
    • chunk_size
      Type: INT32
      Provider name: chunkSize
      Description: The token size limit for each chunk. Supported values: 100-500 (inclusive). Default value: 500.
      
    • include_ancestor_headings
      Type: BOOLEAN
      Provider name: includeAncestorHeadings
      Description: Whether to include appending different levels of headings to chunks from the middle of the document to prevent context loss. Default value: False.
      
• default_parsing_config
  Type: STRUCT
  Provider name: defaultParsingConfig
  Description: Configurations for default Document parser. If not specified, we will configure it as default DigitalParsingConfig, and the default parsing config will be applied to all file types for Document parsing.
  

  • digital_parsing_config
    Type: STRUCT
    Provider name: digitalParsingConfig
    Description: Configurations applied to digital parser.
    

  • layout_parsing_config
    Type: STRUCT
    Provider name: layoutParsingConfig
    Description: Configurations applied to layout parser.
    

    • enable_get_processed_document
      Type: BOOLEAN
      Provider name: enableGetProcessedDocument
      Description: Optional. If true, the processed document will be made available for the GetProcessedDocument API.
      
    • enable_image_annotation
      Type: BOOLEAN
      Provider name: enableImageAnnotation
      Description: Optional. If true, the LLM based annotation is added to the image during parsing.
      
    • enable_table_annotation
      Type: BOOLEAN
      Provider name: enableTableAnnotation
      Description: Optional. If true, the LLM based annotation is added to the table during parsing.
      
    • exclude_html_classes
      Type: UNORDERED_LIST_STRING
      Provider name: excludeHtmlClasses
      Description: Optional. List of HTML classes to exclude from the parsed content.
      
    • exclude_html_elements
      Type: UNORDERED_LIST_STRING
      Provider name: excludeHtmlElements
      Description: Optional. List of HTML elements to exclude from the parsed content.
      
    • exclude_html_ids
      Type: UNORDERED_LIST_STRING
      Provider name: excludeHtmlIds
      Description: Optional. List of HTML ids to exclude from the parsed content.
      
    • structured_content_types
      Type: UNORDERED_LIST_STRING
      Provider name: structuredContentTypes
      Description: Optional. Contains the required structure types to extract from the document. Supported values: * shareholder-structure
      

  • ocr_parsing_config
    Type: STRUCT
    Provider name: ocrParsingConfig
    Description: Configurations applied to OCR parser. Currently it only applies to PDFs.
    

    • enhanced_document_elements
      Type: UNORDERED_LIST_STRING
      Provider name: enhancedDocumentElements
      Description: [DEPRECATED] This field is deprecated. To use the additional enhanced document elements processing, please switch to layout_parsing_config.
      
    • use_native_text
      Type: BOOLEAN
      Provider name: useNativeText
      Description: If true, will use native text instead of OCR text on pages containing native text.
      
• name
  Type: STRING
  Provider name: name
  Description: The full resource name of the Document Processing Config. Format: projects/*/locations/*/collections/*/dataStores/*/documentProcessingConfig.
  

gcp_display_name

Type: STRING
Provider name: displayName
Description: Required. The data store display name. This field must be a UTF-8 encoded string with a length limit of 128 characters. Otherwise, an INVALID_ARGUMENT error is returned.

healthcare_fhir_config

Type: STRUCT
Provider name: healthcareFhirConfig
Description: Optional. Configuration for HEALTHCARE_FHIR vertical.

• enable_configurable_schema
  Type: BOOLEAN
  Provider name: enableConfigurableSchema
  Description: Whether to enable configurable schema for HEALTHCARE_FHIR vertical. If set to true, the predefined healthcare fhir schema can be extended for more customized searching and filtering.
  
• enable_static_indexing_for_batch_ingestion
  Type: BOOLEAN
  Provider name: enableStaticIndexingForBatchIngestion
  Description: Whether to enable static indexing for HEALTHCARE_FHIR batch ingestion. If set to true, the batch ingestion will be processed in a static indexing mode which is slower but more capable of handling larger volume.
  

identity_mapping_store

Type: STRING
Provider name: identityMappingStore
Description: Immutable. The fully qualified resource name of the associated IdentityMappingStore. This field can only be set for acl_enabled DataStores with THIRD_PARTY or GSUITE IdP. Format: projects/{project}/locations/{location}/identityMappingStores/{identity_mapping_store}.

industry_vertical

Type: STRING
Provider name: industryVertical
Description: Immutable. The industry vertical that the data store registers.
Possible values:

• INDUSTRY_VERTICAL_UNSPECIFIED - Value used when unset.
  
• GENERIC - The generic vertical for documents that are not specific to any industry vertical.
  
• MEDIA - The media industry vertical.
  
• HEALTHCARE_FHIR - The healthcare FHIR vertical.
  

is_infobot_faq_data_store

Type: BOOLEAN
Provider name: isInfobotFaqDataStore
Description: Optional. If set, this DataStore is an Infobot FAQ DataStore.

kms_key_name

Type: STRING
Provider name: kmsKeyName
Description: Input only. The KMS key to be used to protect this DataStore at creation time. Must be set for requests that need to comply with CMEK Org Policy protections. If this field is set and processed successfully, the DataStore will be protected by the KMS key, as indicated in the cmek_config field.

labels

Type: UNORDERED_LIST_STRING

name

Type: STRING
Provider name: name
Description: Immutable. Identifier. The full resource name of the data store. Format: projects/{project}/locations/{location}/collections/{collection_id}/dataStores/{data_store_id}. This field must be a UTF-8 encoded string with a length limit of 1024 characters.

organization_id

Type: STRING

parent

Type: STRING

project_id

Type: STRING

project_number

Type: STRING

resource_name

Type: STRING

serving_config_data_store

Type: STRUCT
Provider name: servingConfigDataStore
Description: Optional. Stores serving config at DataStore level.

• disabled_for_serving
  Type: BOOLEAN
  Provider name: disabledForServing
  Description: Optional. If set true, the DataStore will not be available for serving search requests.
  

solution_types

Type: UNORDERED_LIST_STRING
Provider name: solutionTypes
Description: The solutions that the data store enrolls. Available solutions for each industry_vertical: * MEDIA: SOLUTION_TYPE_RECOMMENDATION and SOLUTION_TYPE_SEARCH. * SITE_SEARCH: SOLUTION_TYPE_SEARCH is automatically enrolled. Other solutions cannot be enrolled.

starting_schema

Type: STRUCT
Provider name: startingSchema
Description: The start schema to use for this DataStore when provisioning it. If unset, a default vertical specialized schema will be used. This field is only used by CreateDataStore API, and will be ignored if used in other APIs. This field will be omitted from all API responses including CreateDataStore API. To retrieve a schema of a DataStore, use SchemaService.GetSchema API instead. The provided schema will be validated against certain rules on schema. Learn more from this doc.

• json_schema
  Type: STRING
  Provider name: jsonSchema
  Description: The JSON representation of the schema.
  
• name
  Type: STRING
  Provider name: name
  Description: Immutable. The full resource name of the schema, in the format of projects/{project}/locations/{location}/collections/{collection}/dataStores/{data_store}/schemas/{schema}. This field must be a UTF-8 encoded string with a length limit of 1024 characters.
  

tags

Type: UNORDERED_LIST_STRING

workspace_config

Type: STRUCT
Provider name: workspaceConfig
Description: Config to store data store type configuration for workspace data. This must be set when DataStore.content_config is set as DataStore.ContentConfig.GOOGLE_WORKSPACE.

• dasher_customer_id
  Type: STRING
  Provider name: dasherCustomerId
  Description: Obfuscated Dasher customer ID.
  
• super_admin_email_address
  Type: STRING
  Provider name: superAdminEmailAddress
  Description: Optional. The super admin email address for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
  
• super_admin_service_account
  Type: STRING
  Provider name: superAdminServiceAccount
  Description: Optional. The super admin service account for the workspace that will be used for access token generation. For now we only use it for Native Google Drive connector data ingestion.
  
• type
  Type: STRING
  Provider name: type
  Description: The Google Workspace data source.
  Possible values:
  
  • TYPE_UNSPECIFIED - Defaults to an unspecified Workspace type.
    
  • GOOGLE_DRIVE - Workspace Data Store contains Drive data
    
  • GOOGLE_MAIL - Workspace Data Store contains Mail data
    
  • GOOGLE_SITES - Workspace Data Store contains Sites data
    
  • GOOGLE_CALENDAR - Workspace Data Store contains Calendar data
    
  • GOOGLE_CHAT - Workspace Data Store contains Chat data
    
  • GOOGLE_GROUPS - Workspace Data Store contains Groups data
    
  • GOOGLE_KEEP - Workspace Data Store contains Keep data
    
  • GOOGLE_PEOPLE - Workspace Data Store contains People data