ChunkNorris: A High-Performance and Low-Energy Approach to PDF Parsing and Chunking

TL;DR

ChunkNorris is a heuristic-based PDF parsing and chunking method that offers high performance and low energy consumption, improving retrieval accuracy in resource-constrained retrieval-augmented generation applications.

Contribution

This paper introduces ChunkNorris, a novel heuristic approach for PDF parsing and chunking that does not rely on machine learning, emphasizing efficiency and practicality.

Findings

Outperforms existing parsing and chunking methods in speed and energy efficiency.

Enhances retrieval accuracy in RAG applications.

Provides an open-access dataset for benchmarking.

Abstract

In Retrieval-Augmented Generation applications, the Information Retrieval part is central as it provides the contextual information that enables a Large Language Model to generate an appropriate and truthful response. High quality parsing and chunking are critical as efficient data segmentation directly impacts downstream tasks, i.e. Information Retrieval and answer generation. In this paper, we introduce ChunkNorris, a novel heuristic-based technique designed to optimise the parsing and chunking of PDF documents. Our approach does not rely on machine learning and employs a suite of simple yet effective heuristics to achieve high performance with minimal computational overhead. We demonstrate the efficiency of ChunkNorris through a comprehensive benchmark against existing parsing and chunking methods, evaluating criteria such as execution time, energy consumption, and retrieval accuracy. We propose an open-access dataset to produce our results. ChunkNorris outperforms baseline and more advanced techniques, offering a practical and efficient alternative for Information Retrieval tasks. Therefore, this research highlights the potential of heuristic-based methods for real-world, resource-constrained RAG use cases.