Uni-Parser Technical Report

TL;DR

Uni-Parser is a scalable, modular document parsing engine designed for scientific literature and patents, offering high throughput, accuracy, and extensibility for large-scale AI and data extraction applications.

Contribution

It introduces a novel multi-expert, modular architecture that enhances robustness, scalability, and cross-modal alignment in document parsing, optimized for cloud deployment.

Findings

Processes up to 20 PDF pages/sec on 8 GPUs

Supports diverse modalities including text, equations, and chemical structures

Enables large-scale scientific literature analysis and AI training data curation

Abstract

This technical report introduces Uni-Parser, an industrial-grade document parsing engine tailored for scientific literature and patents, delivering high throughput, robust accuracy, and cost efficiency. Unlike pipeline-based document parsing methods, Uni-Parser employs a modular, loosely coupled multi-expert architecture that preserves fine-grained cross-modal alignments across text, equations, tables, figures, and chemical structures, while remaining easily extensible to emerging modalities. The system incorporates adaptive GPU load balancing, distributed inference, dynamic module orchestration, and configurable modes that support either holistic or modality-specific parsing. Optimized for large-scale cloud deployment, Uni-Parser achieves a processing rate of up to 20 PDF pages per second on 8 x NVIDIA RTX 4090D GPUs, enabling cost-efficient inference across billions of pages. This level of scalability facilitates a broad spectrum of downstream applications, ranging from literature retrieval and summarization to the extraction of chemical structures, reaction schemes, and bioactivity data, as well as the curation of large-scale corpora for training next-generation large language models and AI4Science models.