Full processor and detail list

This page contains detailed information on all processors offered by Document AI. You can see a list of all processors by solution type.

General processors


Processors Details

Document OCR (Optical Character Recognition)

Solution type General
Type in UI General
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Public
Description

Identify and extract text in different types of documents.

This processor allows you to identify and extract text from documents in over 200 languages for printed text and 50 languages for handwritten text.

Quotas and limits
Files types supported:PDF, TIFF, GIF, JPEG, PNG, BMP, WEBP
Maximum pages (synchronous/online requests): 10
Maximum pages (asynchronous/offine/batch requests): 500
Maximum file size: 20Mb
Pricing Pricing

Document Splitter

Solution type General
Type in UI General
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Programmatically split documents on logical boundaries.

Document Splitter uses machine learning to separate documents on logical boundaries. For example, if you have one PDF document with multiple scanned files, the Document AI API will suggest the page location of a new file.

Notes
  • Maximum image size: 65500 x 65500 pixels
Quotas and limits
Files types supported:PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 15
Maximum pages (asynchronous/offine/batch requests): 2000
Maximum file size: 1024Mb (1Gb)
Pricing Pricing
More information Document splitters behavior

Form Parser

Solution type General
Type in UI General
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Public
Description

Extract form elements such as text and checkboxes.

Quotas and limits
Files types supported:PDF, TIFF, GIF, JPEG, PNG, BMP, WEBP
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 100
Maximum file size: 1Gb
Pricing Pricing

Intelligent Document Quality Processor

Solution type General
Type in UI General
Release stage

Preview

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Perform quality assessment of a document based on its readability and get a quality score.

Intelligent Document Quality processor uses machine learning to perform quality assessment of a document based on the readability of its content. This quality assessment is returned as a quality score [0, 1], where 1 means perfect quality. If the quality score detected is lower than 0.5, a list of negative quality reasons (sorted by the likelihood) is also returned.

Notes
  • Quality score is returned in the confidence field of the entity with type="quality_score".
  • The quality/defect_* properties are sorted in descending order by its confidence value.
  • Supported property types: quality/defect_blurry, quality/defect_dark, quality/defect_faint, quality/defect_noisy, quality/defect_text_too_small
Pricing Pricing

Lending processors


Processors Details

1003 Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract over 50 fields from Fannie Mae Form 1003 (URLA).

The 1003 Form is Fannie Mae's form number for the Uniform Residential Loan Application (URLA), a borrower’s application for a mortgage. Freddie Mac's form number is Form 65; both refer to the same form.

Notes
  • Batch processing currently not available for this processor.
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • Legacy Form 1003 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1040 Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1040, including name, filing status, amounts, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • 2019 (standard version only)
  • 2018 (standard version only)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1040 Schedule C Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1040 Schedule C, including name, wages, etc.

Supported form/versions
  • 2020 (standard and customized version)
  • 2019 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1040 Schedule E Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1040 Schedule E, including name, expenses, etc.

Supported form/versions
  • 2020 (standard and customized version)
  • 2019 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1099-DIV Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1099-DIV, including account number, qualified dividends, federal income tax withheld, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • 2020 (standard and customized version)
  • 2019 (standard and customized version)
  • 2018 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1099-G Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1099-G, including payer, recipient, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • 2020 (standard and customized version)
  • 2019 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1099-INT Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1099-INT, including payer, recipient, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • 2020 (standard and customized version)
  • 2019 (standard and customized version)
  • 2018 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

1099-MISC Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form 1099-MISC, including payer, recipient, amounts, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • 2019 (standard and customized version)
  • 2018 (standard and customized version)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

Bank Statement Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from bank statements including name, account, transactions, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 10
Maximum pages (asynchronous/offine/batch requests): 10
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

Lending Document Splitter & Classifier

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Identify documents in a large file and classify known lending document types.

Mortgage application packages and other lending documents often contain multiple documents (such as 1040 tax forms, W2, bank statements, etc.) in a single file. Lending document splitter allows you to programmatically split these combined lending documents on logical boundaries. The split files are then classified based on the document type, so that the appropriate extraction model can be applied to each file.

Notes
  • Lending processors run split and classification for the input document and validate if the first page's document type is supported by the processors or not. If not, an error is returned.
Quotas and limits
Files types supported:PDF, TIFF
Maximum pages (synchronous/online requests): 15
Maximum pages (asynchronous/offine/batch requests): 1250
Maximum file size: 1024Mb (1Gb)
More information Document splitters behavior

Pay Slip Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from pay slips, including name, business, amounts, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

W2 Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form W2, including employee, employer, wages, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • 2020 (standard and customized versions)
  • 2019 (standard and customized versions)
  • 2018 (standard and customized versions)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

W9 Parser

Solution type Lending
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract from Form W9 including name, address, TIN, etc.

Notes
  • If a page of a multi-page input file is the correct document type and one of the supported versions, the processor performs entity extraction on the first supported document. If the processor doesn't find any applicable documents in the input file, the processor returns an error message.
Supported form/versions
  • Form (Rev. 10-2018, Rev. 11-2017)
Quotas and limits
Files types supported:JPEG, PNG, WEBP, PDF, TIFF, GIF
Maximum pages (synchronous/online requests): 5
Maximum pages (asynchronous/offine/batch requests): 50
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

Procurement processors


Processors Details

Expense Parser

Solution type Procurement
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract text and values from expense documents such as expense date, supplier name, total amount, and currency.

Notes
  • Formerly referred to as "Receipt Parser".
  • Fields enriched by Google Knowledge Graph: supplier_address, supplier_name.
  • Languages supported: Dutch, English, French, German, Spanish.
Quotas and limits
Files types supported:PDF, TIFF, GIF, JPEG, PNG, BMP, WEBP
Maximum pages (synchronous/online requests): 10
Maximum pages (asynchronous/offine/batch requests): 10
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

Invoice Parser

Solution type Procurement
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract text and values from invoices such as invoice number, supplier name, invoice amount, tax amount, invoice date, due date.

The invoice Parser extracts both header and line item fields, such as invoice number, supplier name, invoice amount, tax amount, invoice date, due date, and line item amounts.

Notes
  • Fields enhanced by Google Knowledge Graph: supplier_address, supplier_name.
  • Languages supported: Dutch, English, French, German, Spanish.
Quotas and limits
Files types supported:PDF, TIFF, GIF, JPEG, PNG, BMP, WEBP
Maximum pages (synchronous/online requests): 10
Maximum pages (asynchronous/offine/batch requests): 200
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

Procurement Document Splitter

Solution type Procurement
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Allows you to programmatically split these combined procurement documents on logical boundaries.

Procurement document splitter allows you to take different procurement documents grouped in a single file and programmatically split the documents on logical boundaries. The split files are then classified based on the document type, so that the appropriate extraction model can be applied to each file.

Notes

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.

Quotas and limits
Files types supported:PDF, TIFF
Maximum pages (synchronous/online requests): 15
Maximum pages (asynchronous/offine/batch requests): 1250
Maximum file size: 1024Mb (1Gb)
More information Document splitters behavior

Utility Parser

Solution type Procurement
Type in UI Specialized
Release stage

General availability

For more information, see see the launch stage descriptions.

Access status Limited

To request API access, please fill out and submit the Document AI limited access customer request form. The form requests information about you, your company, and your use case. Please note that a Google Cloud Project ID is required for access. To create a new Google Cloud project, or identify your existing project's Project ID see the following instructions.

After you submit the form, the Document AI team will review your request to ensure you meet the criteria for access. If approved, you will receive an email with instructions on how to access and use this feature.

Description

Extract text and values from utility bills such as supplier name and previous paid amount.

Notes
  • Fields enhanced by Google Knowledge Graph: supplier_address, supplier_name, supplier_phone
Quotas and limits
Files types supported:PDF, TIFF, GIF, JPEG, PNG, BMP, WEBP
Maximum pages (synchronous/online requests): 10
Maximum pages (asynchronous/offine/batch requests): 200
Maximum file size: 20Mb
Fields detected

This content is available to approved customers. You can view this content after you have been approved and added to the appropriate allowlist.