# Structured information extraction

PP-DocLayout-L is a high-precision document layout region localization model based on the RT-DETR-L architecture, supporting the detection of 23 common document layout categories.

PP-DocLayout_plus-L is a high-precision document layout area positioning model, trained based on the RT-DETR-L architecture, and supports the detection of 20 common document elements.

NuExtract 2.0 is a series of multimodal models specifically trained for structured information extraction tasks. It supports text and image inputs and has multilingual processing capabilities.

Phi-3-mini-4k-instruct-graph is a fine-tuned version of Microsoft's Phi-3-mini-4k-instruct, specifically designed for entity relationship extraction from general text data, aiming to achieve comparable quality and accuracy to GPT-4 in generating entity relationship graphs.

A compact language model specialized in Portuguese text compression and structured processing, trained on 330,000 Portuguese texts.

A model based on the Donut architecture for extracting structured information from medical handwritten prescriptions