How to Extract Data from Complex PDFs: Landing AI’s DPT-2 Complete Guide
Last Updated on October 4, 2025 by Editorial Team
Author(s): GenAI Lab
Originally published on Towards AI.
Andrew Ng’s Landing AI just changed document processing: Extract structured data from any PDF, no matter how complex
Landing AI has unveiled Document Pre-trained Transformer-2 (DPT-2), a groundbreaking advancement in their Agentic Document Extraction (ADE) system. This next-generation model represents a paradigm shift in how enterprises handle complex, unstructured documents — delivering unprecedented accuracy in extracting structured insights from even the messiest, most compliance-heavy files.
DPT-2 represents a significant advancement in document processing by decomposing extraction tasks into specialized steps, handling complex layouts and ensuring traceability for compliance. The system’s innovations, such as agentic table handling, refined figure captioning, and smarter layout detection, enhance accuracy and streamline workflows in various industries including finance and healthcare. Overall, DPT-2 sets a new standard for document intelligence, solving real-world challenges through improved processing capabilities.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
