Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents
For enterprises dealing with complex, hierarchical documents (e.g., legal regulations), this method significantly improves retrieval accuracy over existing RAG approaches.
This paper tackles retrieval inaccuracies in enterprise document search by proposing Agentic Knowledge Graphs with Recursive Crawling, achieving a 70% accuracy improvement over standard vector-based RAG on the Code of Federal Regulations benchmark.
This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We propose Agentic Knowledge Graphs featuring Recursive Crawling as a robust solution for navigating superseding logic and multi-hop references. Our benchmark evaluation using the Code of Federal Regulations (CFR) demonstrates that this Knowledge Graph-enhanced approach achieves a 70% accuracy improvement over standard vector-based RAG systems, providing exhaustive and precise answers for complex regulatory queries.