OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System

TL;DR

OneKE is a dockerized, schema-guided knowledge extraction system that utilizes multiple agents and a configurable knowledge base to extract information from web sources and PDFs across various domains, demonstrating high adaptability and effectiveness.

Contribution

The paper presents a novel multi-agent, schema-guided knowledge extraction system with a configurable knowledge base, supporting diverse data sources and domains, and demonstrating improved performance.

Findings

Effective knowledge extraction from web and PDFs across domains.

Demonstrated high accuracy and adaptability in empirical evaluations.

Open-sourced implementation and demonstration videos available.

Abstract

We introduce OneKE, a dockerized schema-guided knowledge extraction system, which can extract knowledge from the Web and raw PDF Books, and support various domains (science, news, etc.). Specifically, we design OneKE with multiple agents and a configure knowledge base. Different agents perform their respective roles, enabling support for various extraction scenarios. The configure knowledge base facilitates schema configuration, error case debugging and correction, further improving the performance. Empirical evaluations on benchmark datasets demonstrate OneKE's efficacy, while case studies further elucidate its adaptability to diverse tasks across multiple domains, highlighting its potential for broad applications. We have open-sourced the Code at https://github.com/zjunlp/OneKE and released a Video at http://oneke.openkg.cn/demo.mp4.