andreagemelli/doc2graph
Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.
This project helps people who need to extract specific information from various documents like forms, invoices, or scanned papers. It takes an image of a document as input and identifies key information, such as spotting key-value relationships in forms or detecting tables, outputting the extracted data in a structured format (like a JSON file). This is useful for data entry specialists, administrative staff, or anyone processing large volumes of documents.
137 stars.
Use this if you need to automatically extract structured data from scanned documents or images, such as identifying key fields on a form or detecting tables in an invoice.
Not ideal if you need to train the system on your own specific, private datasets without a developer's help, as this feature is still under development.
Stars
137
Forks
25
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/andreagemelli/doc2graph"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.