Try Gemini 1.5 models , the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window.

Organize documents in folders

This page gives a brief overview of folders and explains how to manage documents using folders.

What are Document AI Warehouse folders

A folder is a special type of document. It can't include inline contents or have any associated contents, but users can still add properties to the folder. A folder serves as a container to group and label documents. Users can attach a document to multiple folders and a folder can contain multiple documents. Folders can also be used in documents.search API to filter child documents under a specific folder.

Before you begin

Before you begin, make sure you have completed the Quickstart page.

Create a Document AI Warehouse folder with a schema

To create a schema for instantiating folders, do the following:

REST

Request:

 curl  
-X  
POST  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
-H  
 "Content-Type: application/json" 
  
-d  
 '{ 
 "display_name": "abc", 
 "property_definitions": [ 
 { 
 "name": "Name", 
 "display_name": "Name", 
 "is_repeatable": false, 
 "is_filterable": true, 
 "is_searchable": true, 
 "is_metadata": true, 
 "is_required": true, 
 "text_type_options": {}, 
 "schema_sources": [] 
 } 
 ], 
 "document_is_folder": true 
 }' 
  
 \ 
 "https://contentwarehouse.googleapis.com/v1/projects/406397197218/locations/us/documentSchemas"

Response:

  { 
  
 "name" 
:  
 " SCHEMA_NAME 
" 
,  
 "displayName" 
:  
 "abc" 
,  
 "documentIsFolder" 
:  
true,  
 "updateTime" 
:  
 "2022-08-31T16:10:43.111978Z" 
,  
 "createTime" 
:  
 "2022-08-31T16:10:43.111978Z" 
 }

Python

  from 
  
 google.cloud 
  
 import 
 contentwarehouse_v1 
 def 
  
 create_folder_schema 
 (): 
 # Create a client 
 client 
 = 
 contentwarehouse_v1 
 . 
 DocumentSchemaServiceClient 
 () 
 # Initialize request argument(s) 
 document_schema 
 = 
 contentwarehouse_v1 
 . 
 DocumentSchema 
 () 
 document_schema 
 . 
 display_name 
 = 
 "display_name_value" 
 document_schema 
 . 
 document_is_folder 
 = 
 True 
 request 
 = 
 contentwarehouse_v1 
 . 
 CreateDocumentSchemaRequest 
 ( 
 parent 
 = 
 "projects/533503808294/locations/us" 
 , 
 document_schema 
 = 
 document_schema 
 , 
 ) 
 # Make the request 
 return 
 client 
 . 
 create_document_schema 
 ( 
 request 
 = 
 request 
 )

Add a document to a Document AI Warehouse folder

To add a document to a folder, do the following:

REST

Request:

 curl  
-X  
POST  
 \ 
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
-H  
 "Content-Type: application/json; charset=utf-8" 
  
-d  
 '{ 
 "document_link": { 
 "source_document_reference": { 
 "document_name": "projects/ PROJECT_NUMBER 
/locations/ LOCATION 
/documents/{document_id}" 
 }, 
 "target_document_reference": { 
 "document_name": "projects/ PROJECT_NUMBER 
/locations/ LOCATION 
/documents/{document_id}" 
 } 
 }, 
 "requestMetadata": { 
 "userInfo": { 
 "id": "user: USER_EMAIL_ID 
" 
 } 
 } 
 }' 
  
 \ 
 "https://contentwarehouse.googleapis.com/v1/projects/ PROJECT_NUMBER 
/locations/ LOCATION 
/documents/{document_id}/documentLinks"

Response:

  { 
  
 "name" 
:  
 " LINK_NAME 
" 
,  
 "source_document_reference" 
:  
 { 
  
 "document_name" 
:  
 " FOLDER_NAME 
" 
  
 } 
,  
 "target_document_reference" 
:  
 { 
  
 "document_name" 
:  
 " DOCUMENT_NAME 
" 
  
 } 
 }

Python

  from 
  
 google.cloud 
  
 import 
 contentwarehouse_v1 
 def 
  
 add_to_folder 
 ( 
 folder 
 : 
 str 
 , 
 doc 
 : 
 str 
 ): 
 # Create a client 
 client 
 = 
 contentwarehouse_v1 
 . 
 DocumentLinkServiceClient 
 () 
 # Initialize request argument(s) 
 link 
 = 
 contentwarehouse_v1 
 . 
 DocumentLink 
 () 
 link 
 . 
 source_document_reference 
 = 
 contentwarehouse_v1 
 . 
 DocumentReference 
 () 
 link 
 . 
 source_document_reference 
 . 
 document_name 
 = 
 folder 
 link 
 . 
 target_document_reference 
 = 
 contentwarehouse_v1 
 . 
 DocumentReference 
 () 
 link 
 . 
 target_document_reference 
 . 
 document_name 
 = 
 doc 
 request 
 = 
 contentwarehouse_v1 
 . 
 CreateDocumentLinkRequest 
 ( 
 parent 
 = 
 folder 
 , 
 document_link 
 = 
 link 
 , 
 ) 
 # Make the request 
 return 
 client 
 . 
 create_document_link 
 ( 
 request 
 = 
 request 
 )

Create a Document AI Warehouse folder, and link a document

Python

For more information, see the Document AI Warehouse Python API reference documentation .

To authenticate to Document AI Warehouse, set up Application Default Credentials. For more information, see Set up authentication for a local development environment .

  from 
  
 google.cloud 
  
 import 
 contentwarehouse 
 # TODO(developer): Uncomment these variables before running the sample. 
 # project_number = "YOUR_PROJECT_NUMBER" 
 # location = "us" # Format is 'us' or 'eu' 
 # user_id = "user:xxxx@example.com" # Format is "user:xxxx@example.com" 
 def 
  
 create_folder 
 ( 
 project_number 
 : 
 str 
 , 
 location 
 : 
 str 
 , 
 user_id 
 : 
 str 
 ) 
 - 
> contentwarehouse 
 . 
 Document 
 : 
 # Create a Schema Service client 
 document_schema_client 
 = 
 contentwarehouse 
 . 
  DocumentSchemaServiceClient 
 
 () 
 # The full resource name of the location, e.g.: 
 # projects/{project_number}/locations/{location} 
 parent 
 = 
 document_schema_client 
 . 
  common_location_path 
 
 ( 
 project 
 = 
 project_number 
 , 
 location 
 = 
 location 
 ) 
 # Define Folder Schema Request 
 create_folder_schema_request 
 = 
 contentwarehouse 
 . 
  CreateDocumentSchemaRequest 
 
 ( 
 parent 
 = 
 parent 
 , 
 document_schema 
 = 
 contentwarehouse 
 . 
  DocumentSchema 
 
 ( 
 display_name 
 = 
 "Test Folder Schema " 
 , 
 document_is_folder 
 = 
 True 
 , 
 ), 
 ) 
 # Create a Folder Schema 
 folder_schema 
 = 
 document_schema_client 
 . 
  create_document_schema 
 
 ( 
 request 
 = 
 create_folder_schema_request 
 ) 
 # Create a Document(Folder) Service client 
 folder_client 
 = 
 contentwarehouse 
 . 
  DocumentServiceClient 
 
 () 
 # Define Folder 
 folder 
 = 
 contentwarehouse 
 . 
  Document 
 
 ( 
 display_name 
 = 
 "My Test Folder" 
 , 
 document_schema_name 
 = 
 folder_schema 
 . 
 name 
 , 
 ) 
 # Define Request to create Folder 
 create_folder_request 
 = 
 contentwarehouse 
 . 
  CreateDocumentRequest 
 
 ( 
 parent 
 = 
 parent 
 , 
 document 
 = 
 folder 
 , 
 request_metadata 
 = 
 contentwarehouse 
 . 
  RequestMetadata 
 
 ( 
 user_info 
 = 
 contentwarehouse 
 . 
  UserInfo 
 
 ( 
 id 
 = 
 user_id 
 ) 
 ), 
 ) 
 # Create a Folder for the given schema 
 folder_response 
 = 
 folder_client 
 . 
  create_document 
 
 ( 
 request 
 = 
 create_folder_request 
 ) 
 # Read the output 
 print 
 ( 
 f 
 "Rule Engine Output: 
 { 
 folder_response 
 . 
 rule_engine_output 
 } 
 " 
 ) 
 print 
 ( 
 f 
 "Folder Created: 
 { 
 folder_response 
 . 
 document 
 } 
 " 
 ) 
 return 
 folder_response 
 def 
  
 create_document 
 ( 
 project_number 
 : 
 str 
 , 
 location 
 : 
 str 
 , 
 user_id 
 : 
 str 
 ) 
 - 
> contentwarehouse 
 . 
 Document 
 : 
 # Create a Schema Service client 
 document_schema_client 
 = 
 contentwarehouse 
 . 
  DocumentSchemaServiceClient 
 
 () 
 # The full resource name of the location, e.g.: 
 # projects/{project_number}/locations/{location} 
 parent 
 = 
 document_schema_client 
 . 
  common_location_path 
 
 ( 
 project 
 = 
 project_number 
 , 
 location 
 = 
 location 
 ) 
 # Define Schema Property of Text Type 
 property_definition 
 = 
 contentwarehouse 
 . 
  PropertyDefinition 
 
 ( 
 name 
 = 
 "stock_symbol" 
 , 
 # Must be unique within a document schema (case insensitive) 
 display_name 
 = 
 "Searchable text" 
 , 
 is_searchable 
 = 
 True 
 , 
 text_type_options 
 = 
 contentwarehouse 
 . 
  TextTypeOptions 
 
 (), 
 ) 
 # Define Document Schema Request 
 create_document_schema_request 
 = 
 contentwarehouse 
 . 
  CreateDocumentSchemaRequest 
 
 ( 
 parent 
 = 
 parent 
 , 
 document_schema 
 = 
 contentwarehouse 
 . 
  DocumentSchema 
 
 ( 
 display_name 
 = 
 "My Test Schema" 
 , 
 property_definitions 
 = 
 [ 
 property_definition 
 ], 
 ), 
 ) 
 # Create a Document schema 
 document_schema 
 = 
 document_schema_client 
 . 
  create_document_schema 
 
 ( 
 request 
 = 
 create_document_schema_request 
 ) 
 # Create a Document Service client 
 document_client 
 = 
 contentwarehouse 
 . 
  DocumentServiceClient 
 
 () 
 # The full resource name of the location, e.g.: 
 # projects/{project_number}/locations/{location} 
 parent 
 = 
 document_client 
 . 
  common_location_path 
 
 ( 
 project 
 = 
 project_number 
 , 
 location 
 = 
 location 
 ) 
 # Define Document Property Value 
 document_property 
 = 
 contentwarehouse 
 . 
  Property 
 
 ( 
 name 
 = 
 document_schema 
 . 
 property_definitions 
 [ 
 0 
 ] 
 . 
 name 
 , 
 text_values 
 = 
 contentwarehouse 
 . 
  TextArray 
 
 ( 
 values 
 = 
 [ 
 "GOOG" 
 ]), 
 ) 
 # Define Document 
 document 
 = 
 contentwarehouse 
 . 
  Document 
 
 ( 
 display_name 
 = 
 "My Test Document" 
 , 
 document_schema_name 
 = 
 document_schema 
 . 
 name 
 , 
 plain_text 
 = 
 "This is a sample of a document's text." 
 , 
 properties 
 = 
 [ 
 document_property 
 ], 
 ) 
 # Define Request 
 create_document_request 
 = 
 contentwarehouse 
 . 
  CreateDocumentRequest 
 
 ( 
 parent 
 = 
 parent 
 , 
 document 
 = 
 document 
 , 
 request_metadata 
 = 
 contentwarehouse 
 . 
  RequestMetadata 
 
 ( 
 user_info 
 = 
 contentwarehouse 
 . 
  UserInfo 
 
 ( 
 id 
 = 
 user_id 
 ) 
 ), 
 ) 
 # Create a Document for the given schema 
 document_response 
 = 
 document_client 
 . 
  create_document 
 
 ( 
 request 
 = 
 create_document_request 
 ) 
 # Read the output 
 print 
 ( 
 f 
 "Rule Engine Output: 
 { 
 document_response 
 . 
 rule_engine_output 
 } 
 " 
 ) 
 print 
 ( 
 f 
 "Document Created: 
 { 
 document_response 
 . 
 document 
 } 
 " 
 ) 
 return 
 document_response 
 def 
  
 create_folder_link_document 
 ( 
 project_number 
 : 
 str 
 , 
 location 
 : 
 str 
 , 
 user_id 
 : 
 str 
 ) 
 - 
> None 
 : 
 # Function call to create a folder 
 folder 
 = 
 create_folder 
 ( 
 project_number 
 , 
 location 
 , 
 user_id 
 ) 
 # Function call to create a Document 
 document 
 = 
 create_document 
 ( 
 project_number 
 , 
 location 
 , 
 user_id 
 ) 
 # Create a Link Service client 
 link_client 
 = 
 contentwarehouse 
 . 
  DocumentLinkServiceClient 
 
 () 
 # Initialize request argument(s) 
 link 
 = 
 contentwarehouse 
 . 
  DocumentLink 
 
 ( 
 source_document_reference 
 = 
 contentwarehouse 
 . 
  DocumentReference 
 
 ( 
 document_name 
 = 
 folder 
 . 
 document 
 . 
 name 
 , 
 ), 
 target_document_reference 
 = 
 contentwarehouse 
 . 
  DocumentReference 
 
 ( 
 document_name 
 = 
 document 
 . 
 document 
 . 
 name 
 , 
 ), 
 ) 
 # Initialize document link request 
 create_document_link_request 
 = 
 contentwarehouse 
 . 
  CreateDocumentLinkRequest 
 
 ( 
 parent 
 = 
 folder 
 . 
 document 
 . 
 name 
 , 
 document_link 
 = 
 link 
 , 
 request_metadata 
 = 
 contentwarehouse 
 . 
  RequestMetadata 
 
 ( 
 user_info 
 = 
 contentwarehouse 
 . 
  UserInfo 
 
 ( 
 id 
 = 
 user_id 
 ) 
 ), 
 ) 
 # Make the Document Link request 
 create_link_response 
 = 
 link_client 
 . 
  create_document_link 
 
 ( 
 request 
 = 
 create_document_link_request 
 ) 
 print 
 ( 
 f 
 "Link Created: 
 { 
 create_link_response 
 } 
 " 
 ) 
 # Initialize list linked targets request 
 linked_targets_request 
 = 
 contentwarehouse 
 . 
  ListLinkedTargetsRequest 
 
 ( 
 parent 
 = 
 folder 
 . 
 document 
 . 
 name 
 , 
 request_metadata 
 = 
 contentwarehouse 
 . 
  RequestMetadata 
 
 ( 
 user_info 
 = 
 contentwarehouse 
 . 
  UserInfo 
 
 ( 
 id 
 = 
 user_id 
 ) 
 ), 
 ) 
 # Make the request 
 linked_targets_response 
 = 
 link_client 
 . 
  list_linked_targets 
 
 ( 
 request 
 = 
 linked_targets_request 
 ) 
 print 
 ( 
 f 
 "Validate Link Created: 
 { 
 linked_targets_response 
 } 
 " 
 )

List child documents under a Document AI Warehouse folder

To list immediate child documents under a folder, do the following:

REST

Request:

 curl  
-X  
POST  
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
https://contentwarehouse.googleapis.com/v1/projects/ PROJECT_NUMBER 
/locations/ LOCATION 
/documents/ FOLDER 
/linkedTargets

Response:

  { 
  
 "documentLinks" 
:  
 [ 
  
 { 
  
 "name" 
:  
 " LINK_NAME1 
" 
  
 "source_document_reference" 
:  
 { 
  
 "document_name" 
:  
 " FOLDER_NAME 
" 
  
 } 
,  
 "target_document_reference" 
:  
 { 
  
 "document_name" 
:  
 " DOCUMENT_NAME1 
" 
  
 } 
  
 } 
,  
 { 
  
 "name" 
:  
 " LINK_NAME2 
" 
  
 "source_document_reference" 
:  
 { 
  
 "document_name" 
:  
 " FOLDER_NAME 
" 
  
 } 
,  
 "target_document_reference" 
:  
 { 
  
 "document_name" 
:  
 " DOCUMENT_NAME2 
" 
  
 } 
  
 } 
  
...  
 ] 
 }

Python

  from 
  
 google.cloud 
  
 import 
 contentwarehouse_v1 
 def 
  
 list_sub_docs 
 ( 
 folder 
 : 
 str 
 ): 
 # Create a client 
 client 
 = 
 contentwarehouse_v1 
 . 
 DocumentLinkServiceClient 
 () 
 # Initialize request argument(s) 
 request 
 = 
 contentwarehouse_v1 
 . 
 ListLinkedTargetsRequest 
 ( 
 parent 
 = 
 folder 
 , 
 ) 
 # Make the request 
 return 
 client 
 . 
 list_linked_targets 
 ( 
 request 
 = 
 request 
 )

Remove a document from a Document AI Warehouse folder

To remove a document from a folder, you need the link name. You can retrieve the link name using the documents.linkedTargets method in the preceding step.

REST

Request:

 curl  
-X  
POST  
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
https://contentwarehouse.googleapis.com/v1/projects/ PROJECT_NUMBER 
/locations/ LOCATION 
/documents/ FOLDER 
/documentLinks/ LINK 
:delete

Python

  from 
  
 google.cloud 
  
 import 
 contentwarehouse_v1 
 def 
  
 remove_doc_from_folder 
 ( 
 link 
 : 
 str 
 ): 
 # Create a client 
 client 
 = 
 contentwarehouse_v1 
 . 
 DocumentLinkServiceClient 
 () 
 # Initialize request argument(s) 
 request 
 = 
 contentwarehouse_v1 
 . 
 DeleteDocumentLinkRequest 
 ( 
 name 
 = 
 link 
 , 
 ) 
 # Make the request 
 return 
 client 
 . 
 delete_document_link 
 ( 
 request 
 = 
 request 
 )

Organize documents in folders Stay organized with collections Save and categorize content based on your preferences.

What are Document AI Warehouse folders

Before you begin

Create a Document AI Warehouse folder with a schema

REST

Python

Add a document to a Document AI Warehouse folder

REST

Python

Create a Document AI Warehouse folder, and link a document

Python

List child documents under a Document AI Warehouse folder

REST

Python

Remove a document from a Document AI Warehouse folder

REST

Python

Organize documents in folders