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.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.
Stay organized with collections
Save and categorize content based on your preferences.
This feature is built on the same technology as enterprise search. Document AI Warehouse is for document management. It should be used when some of the following document management features are also useful:
Integrated Document AI pipelines. Extract or classify documents using OCR, which includes scan images in TIFF or PDF format, specialized, or custom parsers.
Document processing workflows. Document AI Warehouse supports conditional notifications by pub/sub to various document processing workflows.
Retention policies. Support records management, legal holds, and archives.
Fine grained access control (ACL):
IAM roles: viewer, editor, admin, creator.
Simplified administration at the project level or document- or folder-level inheritance
Select-document analysis and summaries.
If your use case requires search of other data types, for example, websites, image searches, or retail catalogs, these are better supported by enterprise search.
Types of filter and search
There are multiple ways to filter and search in Document AI Warehouse:
Search using semantic search
On the documents page, enter the words you want to search in the filter bar above the table:
You can add multiple filter chips to search for documents that match any of the search queries.
Filter on Document AI Warehouse schemas
On the documents page, you can use the schema picker dropdown (left of the filter bar) to constrain the entire browser to a set of Document AI Warehouse schemas. (By default, all are enabled.)
Open the dropdown and select only the schemas you want to see and click Ok.
Now, you only see documents that were parsed with the selected schemas. Also, only properties belonging to the selected schemas are visible in the filter suggestions and table columns.
Filter under a Document AI Warehouse folder
On the documents page,
you can click the folder branched on the left to constrain the entire browser
to a Document AI Warehouse folder.
See documents or folders under the selected folder.
Filter using document creation or last update time
On the documents page, the filter bar provides multiple suggestions for filtering the documents by created or updated on a particular date. You can apply a filter as follows:
You can also add multiple filters to filter within a range of dates.
Filter the browser using property values
On the documents page, click the filter to see suggestions for properties, or start entering a property name to filter the suggestions.
Enter a value for the property to filter the list of documents to only the ones that have a property with that value:
You can add multiple filters to refine the search results and hide or show any columns using the column picker to the right of the filter bar.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-04-10 UTC."],[[["Document AI Warehouse is being deprecated and will be unavailable after January 16, 2025, requiring users to migrate their data to an alternative storage solution like Cloud Storage before this date to prevent data loss."],["Document AI Warehouse is designed for document management, offering features like integrated Document AI pipelines, document type support (scanned images, TIFFs, PDFs, TXT files), processing workflows, retention policies, and fine-grained access control."],["The service can be used to filter and search using semantic search, Document AI Warehouse schemas, specific folders, creation or update times, and property values."],["The service is currently in a pre-GA (General Availability) stage, meaning it's available \"as is\" with potentially limited support and is subject to specific service terms, including data processing and security terms."],["There is a form available for reporting suspected abuse of the service, or generated content that contains inaccurate or inappropriate information."]]],[]]