Repository navigation

#

layout-parsing

Filimoa/open-parse
Python
3105
1 年前

A lightweight Python library for metadata-rich document chunking in Retrieval-Augmented Generation (RAG) workflows. It leverages Azure AI Document Intelligence to enhance chunking by retaining hierarchical structure, page numbers, and bounding boxes for seamless integration with PDF viewers.

Python
2
9 个月前

--UNDER CONSTRUCTION-- (Undergrad Research) Exploring layout parsing capabilities in Python

Jupyter Notebook
0
1 年前