Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

DocILE: Document Information Localization and Extraction Benchmark

A curated list of papers about key information extraction.

Key information extraction from invoice document with Graph Convolution Network

Compute Kinetic Isotope Effects using the Bigeleisen-Mayer equation

利用llm大语言模型提取卡证票据关键信息。Key Information Extraction from Image with LLM(large language model).Basically, it can extract key information from all bills and documents.

Expert System Shell implemented in Java

drools example, drools示例：电商产品价格计算

Moqui tool component for KIE for Drools, jBPM, etc

Business driven testing of Drools 6.5 components using Cucumber-java test framework

Deployment of kjar into the KIE-Server

BRMS [Drools] :: BRMS Decision Tables Lessons Learned

Opinionated statistical inference engine with fluent api to make it easier for conducting statistical inference with little or no knowledge of statistical inference principles involved

Drools 7.23 runtime and test support APIs

BRMS (Drools) Rules Example application to deploy as KJar into Kie-Server

RHPAM project with service task usage

jBPM machine learning prediction service API demo project

Apache KIE Website

Awesome template

Sample project on process automation that utilizes RedHat Process Automation Manager and SpringBoot

drools official examples, drools官方示例附中文说明、注释

Prepare the Kleister NDA dataset for LLM inference. Validates labels against a Pydantic schema and delivers partitioned Parquet with co-located PDFs

Agentic and single-pass Key Information Extraction (KIE) from documents using LLMs

Capture all the rules that didn't fire

Example Automating the extraction and generation of executable business rules from natural language documents using AI.

Kogito Blog WordPress Theme

Sample for Spring Boot integration with Drools.

Turn your Android device into a low-latency Bluetooth HID gamepad recognized as a native controller by Windows and other systems without extra software.

An example of how to use a BPMN process defined within another KJAR within a different KJAR process.