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.
Choose the Cloud Storage bucket or folder that contains the documents you want to upload.
Optional: Select a Document AI Warehouse folder as destination.
Click Continue.
After following these steps, follow those for the task you want to achieve:
Upload documents with Document AI Warehouse text extractor
Select Extract with DocAI Warehouse Text Extractor, then click Continue.
Select a schema and add a processor if applicable, then click Continue.
Optional: Add permissions on the documents you want to upload.
You can specify the users or groups that have access to the documents,
then click Upload.
On the Jobs page, you can find the uploading progress.
Upload with extracted entities, document summaries
In addition to CDE and specialized Document AI processors, you can use the generative AI extractor and summarizer in the Bulk Ingest Pipeline.
Select Extract using Document AI, then click Continue.
Select a document schema, add a processor that is used for extraction, add a Cloud Storage bucket or folder to store extracted documents. Then click Continue.
Optional: Select Summarize Processor.
Optional: Add permissions on the documents you want to upload.
You can specify the users or groups that have access to the documents,
then click Upload.
On the Jobs page, you can find the uploading progress.
Upload documents with classification and extraction
Select Extract using Document AI, then click Continue.
Add a classifier, which is used for classification. Specify each classify document type's handler processor and mapping schema. Add a Cloud Storage bucket or folder to store extracted documents.
Optional: Select Summarize Processor.
Optional: Add permissions on the documents you want to upload.
You can specify the users or groups that have access to the documents,
then click Upload.
On the Jobs page, you can find the uploading progress.
Upload one document
You can upload a document by following these steps:
[[["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 2025-03-25 UTC."],[[["Document AI Warehouse is being deprecated and will be unavailable after January 16, 2025, requiring users to migrate their data to an alternative like Cloud Storage."],["The bulk upload feature allows you to import multiple documents simultaneously from a Cloud Storage bucket or folder into Document AI Warehouse."],["You can extract data using the Document AI Warehouse text extractor, which also lets you select a schema and add a processor, as well as setting up permissions to control document access."],["The bulk ingest pipeline supports the use of generative AI extractors and summarizers, enabling the extraction of entities and summaries from documents during bulk uploads."],["Individual documents can be uploaded through the \"Document Upload\" feature, with options to select from Cloud Storage or a local file, also allowing you to set a display name, a destination folder, a processor, and a document schema."]]],[]]