Layout Analysis Python Packages

mineru

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

layoutparser

A Unified Toolkit for Deep Learning Based Document Image Analysis

magic-pdf

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

asset-aware-mcp

Asset-Aware MCP Server — AI Agent precisely accesses tables, figures, sections from PDFs + .docx round-trip editing (DFM) with 46 tools / 13 resources, segmentation export, layout overlay, OCR preprocessing, knowledge graph (LightRAG)

pix2text

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

mineru-selfhosted-mcp

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

rapid-layout

Analysis of Chinese and English layouts 中英文版面分析

preocr

A fast, layout-aware OCR decision engine for document processing pipelines. Detects whether files truly require OCR before expensive processing, reducing unnecessary OCR calls while preserving extraction reliability.

pdf-layout-scanner

A more complete example of programming with PDFMiner, which continues where the default documentation stops

mindocr

A toolbox of ocr models and algorithms based on MindSpore

pdf2struct

`pdf2struct` extracts structured JSON from PDF documents.

quanta-pdf

Advanced PDF layout analysis engine for extracting figures, tables, and structured content from complex engineering documents using computer vision and machine learning.

xh-pdf-parser

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

pdfsegmenter

This library builds a graph-representation of the content of PDFs. The graph is then clustered, resulting page segments are classified and returned. Tables are retrieved formatted as a CSV.

ocrd-gbn

OCR-D compliant toolset for optical layout recognition on historical german-language documents published in Brazil

opensourcedot-mindocr

A toolbox of OCR models and algorithms based on MindSpore.

filestruct

A python package to structure files using visual and style informations

lazyllm-magic-pdf

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

text2design

A new package that enables users to input textual descriptions of visual design, layout, or interface concepts and returns structured representations or annotations derived from the description. It le