Improved file parsing for LLM’s
-
Updated
May 17, 2026 - Python
#
layout-parsing
Here are 5 public repositories matching this topic...
Visual Scene Graph for PowerPoint. Extracts structured layout data from PPTX files, enabling AI agents to parse element positions, understand spatial relationships, and detect layout patterns. Exposes bounding boxes, z-order, and spatial relations that humans see but machines couldn’t access. Built on python-pptx. MIT licensed.
-
Updated
May 30, 2026 - Python
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.
react python agent azure chunking agents unstructured-data rag production-grade react-pdf-viewer layout-parser llm langchain retrieval-augmented-generation azure-ai-search azure-ai-document-intelligence layout-parsing document-chunking
-
Updated
Jan 11, 2025 - Python
A Flask microservice for extracting structured data from PDFs and images using PaddleOCR layout parsing API.
-
Updated
Dec 21, 2025 - Python
--UNDER CONSTRUCTION-- (Undergrad Research) Exploring layout parsing capabilities in Python
-
Updated
Nov 11, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the layout-parsing topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the layout-parsing topic, visit your repo's landing page and select "manage topics."