Repolode
Enviar

huridocs/pdf-document-layout-analysis

A Docker-based microservice that analyzes PDF layout, classifies elements like titles, text, tables and pictures, and converts PDFs to Markdown or HTML.

Alternativa open source a:Adobe AcrobatABBYY FineReader

Ver en GitHub
Estrellas
1,356
Forks
0
Issues abiertos
0
Último commit
hace 13 días

Funciones clave

  • 01Classifies page regions into 11 types such as Title, Text, Table, Picture and Formula.
  • 02Offers VGT for higher accuracy and LightGBM for faster CPU-only processing.
  • 03Performs OCR with Tesseract, with support for 150+ languages.
  • 04Converts PDFs to Markdown and HTML, with optional translation via Ollama.
  • 05Extracts tables as HTML and formulas as LaTeX.
  • 06Provides a REST API and a Gradio web interface, packaged in Docker.

Casos de uso

  • Preparing scanned or digital PDFs for search, indexing or LLM ingestion by extracting structured segments.
  • Converting academic papers or reports to Markdown or HTML, optionally translated.
  • Building pipelines that need table of contents or content-type text extraction from PDFs.
  • Adding searchable text layers to scanned documents with OCR.

Temas

#pdf#document-layout-analysis#ocr#docker#computer-vision#markdown-conversion#rest-api

Preguntas frecuentes

¿Qué es pdf-document-layout-analysis?
A Docker-based microservice that analyzes PDF layout, classifies elements like titles, text, tables and pictures, and converts PDFs to Markdown or HTML.
¿pdf-document-layout-analysis es gratuito? ¿Qué licencia tiene?
pdf-document-layout-analysis es open source bajo la licencia Apache-2.0. Revisa los términos de la licencia antes de usarlo en productos comerciales.
¿pdf-document-layout-analysis sigue mantenido?
Mantenimiento activo. El último commit de pdf-document-layout-analysis fue el 6 oct 2026.
¿Para qué puedo usar pdf-document-layout-analysis?
Preparing scanned or digital PDFs for search, indexing or LLM ingestion by extracting structured segments. Converting academic papers or reports to Markdown or HTML, optionally translated. Building pipelines that need table of contents or content-type text extraction from PDFs. Adding searchable text layers to scanned documents with OCR.
¿Dónde consigo pdf-document-layout-analysis?
El código fuente y las instrucciones de instalación están en GitHub: https://github.com/huridocs/pdf-document-layout-analysis

Resumen generado por IA a partir del README del proyecto. Las estadísticas de GitHub se actualizan a diario.

Proyectos relacionados