- Overview
- Introduction
- Language Support
- AI Center Relation to Document Understanding
- Document Understanding Process
- Document Understanding Process: Studio Template
- Quickstart Tutorials
- Extracting Data From Receipts
- Invoices Retrained With One Additional Field
- Extracting Data From Forms
- Framework Components
- Taxonomy
- Taxonomy Overview
- Taxonomy Manager
- Taxonomy Related Activities
- Digitization
- Digitization Overview
- OCR Engines
- Digitization Related Activities
- Document Classification
- Document Classification Overview
- Configure Classifiers Wizard of Classify Document Scope
- Keyword Based Classifier
- Special Requirements
- Intelligent Keyword Classifier
- Special Requirements
- FlexiCapture Classifier
- Machine Learning Classifier
- Document Classification Related Activities
- Document Classification Validation
- Document Classification Validation Overview
- Classification Station
- Document Classification Validation Related Activities
- Document Classification Training
- Document Classification Training Overview
- Configure Classifiers Wizard of Train Classifiers Scope
- Machine Learning Classifier Trainer
- Document Classification Training Related Activities
- Data Extraction
- Data Extraction Overview
- Configure Extractors Wizard of Data Extraction Scope
- RegEx Based Extractor
- Special Requirements
- Form Extractor
- Special Requirements
- Intelligent Form Extractor
- Special Requirements
- Machine Learning Extractor
- FlexiCapture Extractor
- Data Extraction Related Activities
- Data Extraction Validation
- Data Extraction Validation Overview
- Validation Station
- Data Extraction Validation Related Activities
- Data Extraction Training
- Data Extraction Training Overview
- Configure Extractors Wizard of Train Extractors Scope
- Machine Learning Extractor Trainer
- Data Extraction Training Related Activities
- Data Consumption
- Data Consumption Overview
- Data Consumption Related Activities
- ML Packages
- About ML Packages
- Hardware Requirements
- Supported languages
- OCR
- ML Packages
- Other services
- OCR Configuration
- Pipelines
- About Pipelines
- Training Pipelines
- Evaluation Pipelines
- Full Pipelines
- Fine-tuning
- The Auto-Fine-tuning Loop (Public Preview)
- Document Manager
- About Document Manager
- Access Document Manager
- Use a Predefined Schema
- Create and Configure Fields
- Import Documents
- Label Documents
- Search Documents
- Export Documents
- Checkboxes and Signatures
- OCR Services
- OCR Services
- Document Understanding deployed in Automation Suite
- Install and Use
- First Run Experience
- Deploy UiPathDocumentOCR
- Deploy an Out-of-the-box ML Package
- ML Packages Offline Installation
- Offline bundles 2022.4.15
- Offline Bundles 2022.4.14
- Offline Bundles 2022.4.13
- Offline Bundles 2022.4.12
- Offline Bundles 2022.4.11
- Offline Bundles 2022.4.9
- Offline Bundles 2022.4.7
- Offline Bundles 2022.4.5
- Offline Bundles 2022.4.0
- Use Document Manager
- Use the Framework
- Document Understanding deployed in AI Center standalone
- Install and Use
- Hardware Requirements
- SQL Server Requirements
- First Run Experience
- Activate the License
- Create a Project on AI Center
- Upload the Document Understanding ML Packages
- Create a Data Labeling Session
- Launch the Data Labeling Session
- Deploy UiPathDocumentOCR
- Deploy an Out-of-the-box ML Package
- Create an Invoices ML Package
- Deploy the Invoices ML Package as an ML Skill
- ML Packages Offline Installation
- Use Document Manager
- Use the Framework
- Use Document Understanding Models (including UiPathDocumentOCR)
- Deep Learning
- Training High Performing Models
- Data Extraction Components
- Licensing
- Public Endpoints
- API Key
- Cloud and On-Prem Usage
- Machine Learning Extractor
- Metering & Charging Logic
- Legal Information
- References
- Activities Packages
- UiPath.Abbyy.Activities
- UiPath.AbbyyEmbedded.Activities
- UiPath.DocumentUnderstanding.ML.Activities
- UiPath.DocumentUnderstanding.OCR.LocalServer.Activities
- UiPath.IntelligentOCR.Activities
- UiPath.OCR.Activities
- UiPath.OCR.Contracts
- UiPath.DocumentProcessing.Contracts
- UiPath.OmniPage.Activities
- UiPath.PDF.Activities
Document Understanding User Guide
Create a UiPathDocumentOCR ML package in AI Center.
For online installation, the UiPathDocumentOCR model is already included in the Out of the box packages section. Go to ML Packages > Out of the box packages > UiPath Document Understanding > UiPathDocumentOCR, and click Submit.
For offline installation, go to the ML Packages tab from the left sidebar of AI Center and create a new package. Name the package and upload the package that you have downloaded from this page. Choose JSON input type, and the corresponding Python language. Create package.
Go to ML Skills and create a new ML Skill for the UiPathDocumentOCR package you created.
Please use Advanced Infra Settings to update the deployment to update the replica (the number of replica should ideally be equal to the number of nodes) and maximize the CPU (at least 4) and RAM requests if you are not using GPU machines, or the UiPathDocumentOCR processing will be slow and may fail.
The OCR engine needs GPU for optimal performance, and it is recommended for production workloads. However, if GPU is not available, it can still run on CPU, but it requires higher resources than the default. Advanced infra settings should be adjusted as such:
- Replicas: increase if there is concurrent usage of UiPathDocumentOCR. If you are using UiPathDocumentOCR to do imports on a single Data Labeling session at a time and the UiPathDocumentOCR is not used in other UiPath workflows then 1 replica suffices. Otherwise, the number of replicas needs to be increased. There is no "magic" number here, you need some trial and error. Do not use more than 2 replicas on a single node installation. Ideally, replica count should equal the number of nodes in the cluster (1 replica/node). If more parallelism is needed, increasing the CPU helps
-
CPU: it should be at least 4 (for each replica). Make sure you have appropriate resources. There is no "magic" number, but more CPU means faster processing time. You need to test under your specific scenarios what is enough.
It can take up to 30 minutes for the ML Skill to be ready. You may need to refresh the AI Center page to see the status change.
Congrats! You have successfully deployed UiPathDocumentOCR on AI Center.
You can directly select the ML Skill as your private skill in the Studio workflow. Or, if you have installed the online version of AI Center standalone and you want to use the public ML Skill, please follow the below instruction to get the public ML Skill endpoint (optional).
Once the ML Skill is available, double-click the ML Skill and go to Modify current deployment.
Switch the toggle on to make the ML Skill public. You may need to wait for a few minutes and refresh the page.
Double-click the ML Skill and copy the URL, which is the endpoint of the UiPathDocumentOCR for later use.