English

Advanced ingestion process powered by LLM parsing for RAG system

Computation and Language 2024-12-23 v1 Artificial Intelligence Information Retrieval

Abstract

Retrieval Augmented Generation (RAG) systems struggle with processing multimodal documents of varying structural complexity. This paper introduces a novel multi-strategy parsing approach using LLM-powered OCR to extract content from diverse document types, including presentations and high text density files both scanned or not. The methodology employs a node-based extraction technique that creates relationships between different information types and generates context-aware metadata. By implementing a Multimodal Assembler Agent and a flexible embedding strategy, the system enhances document comprehension and retrieval capabilities. Experimental evaluations across multiple knowledge bases demonstrate the approach's effectiveness, showing improvements in answer relevancy and information faithfulness.

Keywords

Cite

@article{arxiv.2412.15262,
  title  = {Advanced ingestion process powered by LLM parsing for RAG system},
  author = {Arnau Perez and Xavier Vizcaino},
  journal= {arXiv preprint arXiv:2412.15262},
  year   = {2024}
}

Comments

12 pages, 3 figures

R2 v1 2026-06-28T20:42:53.361Z