Incubator team supports Doc AI clients in providing assistance on bugs,technical guidance and solutions based on the business needs. GCP Doc AI experienced team members also suggests the best practices to get best out of the product for the given business case.

Folder contains various tools which is made for the benefit of Doc AI users.

• Best Practic Guide Tools

• Tag Child Entites under Header

• Annotate/Label Data Entities

• Migrate DocAI Processor and Dataset to Different Project

• Remove Child Entities from Parent

• Compare Line Items

• Improve Line Item via Post-processing

• Split Multi-line Address fields

• Compare Pre-trained and Custom Processor Schemas

• Find and Tag Customer Account Number field

• Compute Character and Word Error Rate

• Normalize Currency Entity Type

• Compute Document Level Accuracy

• Use Cloud Translate to Detect Languages in Documents

• Split PDF into Chunks

• Reorder Document Pages based on Unique Strings

• Test Harness Tool

• Amount Rectification in Cheque

• Custom Splitter Dataset Creator

• Clean Amount Fields

• Combine Address Lines

• Processor Output Visualizer

• Extend Bounding Boxes

• Import and Evaluator Processors

• Labeled Dataset Validation

• Split Overlapping Entities

• Rename Entity Type

• Combine Two Processors Output

• DocAI Json to Canonical Json Conversion

• Export and Import Document Schema from Processor

• Asynchronous API Reference Architecture

• Advance Table Line Enhancement

• Backmapping Entities from Parser Output Language to Original Language of the Document

• Bank Statement Post Processing Tool

• Bank Statements Line Item Improver and Missing Items Finder

• Categorizing Bank Statement Transactions by Account Number

• Comparison between Custom Document Classifier Ground Truth and Parsed Json Prediction Results

• CMEK Key Creation and Destroying Procedure

• Date Entity Normalization

• PDF Clustering Analysis Tool

• Document AI Processor Types

• Schema from Form Parser Output

• Migrating Schema Between the Processors

• Enrich the Address for Invioce Parser

• Entity Sorting using Csharp

• Entity Sorting using Python

• Formparser Table to Entity Converter Tool

• HITL Line Item Prefix Issues

• Identity Document Proofing Evaluation

• Normalize Date Entities from 19xx to 20xx

• OCR Based Document Section Splitter

• OCR Upgradation Tool

• Reprocess Old OCR Json to New OCR Engine

• Seperation of Paragraphs in a Document

• Replace PII Data with Synthetic Data

• Post Processing Negative Values

• Annotating the Entities in the Document based on the OCR Tokens

• Schema Converter Tool

• Signature Detection Technique

• Special Character Removal

• Tagging Line Items in a Specific Format

• Labeling Documents through Custom Document Splitter Parser using Synonyms List

• Tagging Entity Synonyms

• Vertex Object Detection Visualization