document-understanding
2022.10
false
UiPath logo, featuring letters U and I in white

Document Understanding User Guide

Automation CloudAutomation Cloud Public SectorAutomation SuiteStandalone
Last updated Nov 11, 2024

ML Packages Offline Installation

Getting started

Depending on the models you want to use, you need the following:

  • For models 2022.10 and newer:
    • Download the needed Document Understanding bundle. Here are the links for all the available bundles. The du bundle contains information about all models included into a specific version. For example, the dusemistructured-2022.10.0.tar.gz contains information about all out-of-the-box pre-trained ML Packages included in the 2023.4.0 version.
  • For models 2022.4 and older (python37duv3 and python37duv4):
    • All ML Packages are provided as a .zip file which is uploaded directly as a Custom Package in AI Center. To download the models, contact your Account Manager, CSM, or Support to receive a download link per package.
    • Download the needed Document Understanding bundle. Here are the links for all the available bundles.

Install the Offline Bundle

Offline installations are requiring that the downloaded du bundle to be renamed in the command line into du-ondemand.tar.gz. For instance, if you downloaded the du bundle named dusemistructured-2023.4.0.tar.gz, at installation time you need to rename it as du-ondemand.tar.gz.
  1. For Windows machines, directly download through the bundle link and rename the file to du-ondemand.tar.gz
  2. For Linux machines, from the machine having access to the internet, download the needed bundle following the below command:

    wget -O ~/<bundle-name.tar.gz> 'bundle-link'wget -O ~/<bundle-name.tar.gz> 'bundle-link'

    Here's an example of how to download the needed bundle for Linux:

    wget -O ~/du-ondemand.tar.gz 'https://download.uipath.com/automation-suite/2023.4.0/dusemistructured-2023.4.0.tar.gz'wget -O ~/du-ondemand.tar.gz 'https://download.uipath.com/automation-suite/2023.4.0/dusemistructured-2023.4.0.tar.gz'
  3. Copy the following bundle to the /uipath/tmp folder on the main machine of the cluster (where the install took place):
    scp ~/<bundle-name.tar.gz> <username>@<node dns>:/uipath/tmp/scp ~/<bundle-name.tar.gz> <username>@<node dns>:/uipath/tmp/
  4. Connect to this main machine and load the bundle:

    ./configureUiPathAS.sh registry upload --optional-offline-bundle "/uipath/tmp/du.tar.gz" --offline-tmp-folder "/uipath/tmp"./configureUiPathAS.sh registry upload --optional-offline-bundle "/uipath/tmp/du.tar.gz" --offline-tmp-folder "/uipath/tmp"

Upload the Model to AI Center

After downloading and installing the models, follow the steps described here to upload them to AI Center.

Offline Bundles 2022.10.8

Each offline bundle contains base images used by multiple ML Packages. To make sure which bundle to download for a certain model version, check their compatibility.

Important: To ensure the compatibility of the model you want to install, check the table below.
Model versionPlatform version
2024.102023.102023.42022.102022.4
2024.10availablenot availablenot availablenot availablenot available
2023.10availableavailablenot availablenot availablenot available
2023.4not availableavailableavailablenot availablenot available
2022.10not available* not available* availableavailablenot available
2022.4not available* not available* not available* not available* available
* - Models still work if you upgrade the platform, but they are not actively maintained in this platform version and security issues are no longer fixed. We recommend updating to a newer model to maintain a safe security posture in your environments.

Offline bundle for UiPath Document OCR

The UiPath Document OCR offline bundle needs to be installed only for the UiPathDocumentOCR ML Package 22.10.8.

ML Package

Model version

Metadata

UiPathDocumentOCR

Only for DU installed in the AI Center standalone environment

22.10.8

Offline Bundle for UiPath Document OCR_CPU

The UiPathDocumentOCR_CPU offline bundle needs to be installed for the ML Packages in the table below.

ML Packages

Model version

Metadata

UiPathDocumentOCR_CPU

22.10.8

Offline bundle for OCR for Chinese, Japanese, Korean

The OCR for Chinese, Japanese, Korean offline bundle needs to be installed for the ML Packages in the table below. This bundle can be used only on a CPU VM.

If you want to enable Chinese, Japanese, Korean OCR in an offline environment, you also need to follow these steps.

ML Packages

Model version

Metadata

OCR for Chinese, Japanese, Korean

22.10.8

N/A

Offline bundle for Out-of-the-box Pre-trained ML Packages

The Out-of-the-box Pre-trained ML Packages offline bundle needs to be installed for the ML Packages in the table below.

ML Packages

Model version

Metadata

DocumentUnderstanding

22.10.8

Invoices

22.10.8

InvoicesAustralia

22.10.8

InvoicesIndia

22.10.8

InvoicesJapan

22.10.8

InvoicesChina

22.10.8

Receipts

22.10.8

PurchaseOrders

22.10.8

UtilityBills

22.10.8

IDCards

22.10.8

Passports

22.10.8

RemittanceAdvices

22.10.8

BillsOfLading

22.10.8

W2

22.10.8

W9

22.10.8

ACORD125

22.10.8

I9

22.10.8

990

22.10.8 Preview

4506T

22.10.8

FM1003

22.10.8Preview

ACORD25

22.10.8

ACORD131

22.10.8

ACORD126

22.10.8

ACORD140

22.10.8

1040

22.10.8

Checks

22.10.8

Bank Statements

22.10.8

Financial statements

22.10.8

Packing Lists

22.10.8

Vehicle Titles

22.10.8

Offline bundle for Document Classifier

The Document Classifier offline bundle needs to be installed only for the UiPathDocumentOCR ML Package 22.10.8.

ML Package

Model version

Metadata

Document Classifier

Only for DU installed in the AI Center standalone environment

22.10.8

Offline bundle dulv4

The dulv4 offline bundle needs to be installed only if you want to use ML Packages from the 2022.10.8 enterprise release with AI Center version 2022.4.

ML Packages

Model version

Metadata

DocumentUnderstanding

22.10.8

Invoices

22.10.8

InvoicesAustralia

22.10.8

InvoicesIndia

22.10.8

InvoicesJapan

22.10.8 Preview

InvocesChina

22.10.8 Preview

Receipts

22.10.8

PurchaseOrders

22.10.8

UtilityBills

22.10.8

IDCards

22.10.8

Passports

22.10.8

RemittanceAdvices

22.10.8

BillsOfLading

22.10.8

W2

22.10.8

W9

22.10.8

ACORD125

22.10.8

I9

22.10.8

990

22.10.8 Preview

4506T

22.10.8

FM1003

22.10.8 Preview

ACORD25

22.10.8

ACORD131

22.10.8

ACORD126

22.10.8

ACORD140

22.10.8

1040

22.10.8

Checks

22.10.8

Bank Statements

22.10.8

Financial statements

22.10.8

Packing Lists

22.10.8

Vehicle Titles

22.10.8

Offline bundle dulv3

The dulv3 offline bundle needs to be installed only if you want to use ML Packages from the 2021.10 enterprise release with AI Center version 2022.10.

For the metadata links, check out the tables in the 2021.10 Document Understanding User Guide.

Offline bundle dulv2

The dulv2 offline bundle needs to be installed only if you want to use ML Packages from the 2021.10 enterprise release with AI Center version 2022.10.8.

For the metadata links, check out the tables in the 2021.10 Document Understanding User Guide.

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2024 UiPath. All rights reserved.