AI Data Extraction Demand Surges! E-Papyrus PermuPDF Pro Downloads Up 5x.

ePapyrus's document AI specialized solution 'PIMYU PDF Pro' has recorded explosive growth, surpassing 220 million downloads this year (January~November). This is an increase of more than 5 times compared to the previous year, with 120 million concentrated in just two months of the second half (October~November), proving the market's enthusiastic response. The rapid expansion of the AI service market is behind this remarkable growth. ePapyrus explained that PIMYU PDF Pro supports the creation of 'chunks' including metadata within documents and can output data in JSON, Markdown, and LlamaIndex Reader formats optimized for LLM (Large Language Model) and RAG (Retrieval Augmented Generation), thus accurately targeting the demand for AI training data extraction and conversational service development. Its technical differentiation also stands out. By applying its self-developed machine learning-based layout analyzer, it can operate with just a CPU, unlike the VLM (Vision Language Model) methods on the market that require GPU resources. This provides approximately 10 times faster data processing speed and higher cost-efficiency compared to VLM methods, contributing to lowering the barrier for companies to adopt AI. Furthermore, PIMYU PDF Pro maintains data extraction accuracy even under challenging conditions such as complex tables without borders or with merged cells, and documents containing a mix of scanned images and digital data. It also boasts versatility, supporting various document formats including PDF, MS Office, Hangul (HWP), and images, thereby establishing itself as a core infrastructure in the document AI market.