Rishi Puri

Rishi Puri graduated from UC Berkeley and is a lead engineer for the Deep Learning FrameWork PyG at NVIDIA. He is also a core contributor to the open source PyG framework and community. His main focus is researching how to combine state of the art graph and language modeling techniques. He enjoys teaching about this work at Stanford, conferences, webinars, and through the PyG Slack and LinkedIn communities.
Rishi Puri NVIDIA

Posts by Rishi Puri

Decorative image.
Models / Libraries / Frameworks Mar 26, 2025

Boosting Q&A Accuracy with GraphRAG Using PyG and Graph Databases

Large language models (LLMs) often struggle with accuracy when handling domain-specific questions, especially those requiring multi-hop reasoning or access to... 9 MIN READ
PyG and Accelerated with NVIDIA logos on a white background.
Data Science Jan 17, 2024

Release: PyTorch Geometric Container for GNNs on NGC

The NVIDIA PyG container, now generally available, packages PyTorch Geometric with accelerations for GNN models, dataloading, and pre-processing using... 1 MIN READ
Image is the DGL and PyG logos with the words Accelerated by NVIDIA.
Data Science Dec 08, 2023

Available Now: NVIDIA AI Accelerated DGL and PyG Containers for GNNs

From credit card transactions, social networks, and recommendation systems to transportation networks and protein-protein interactions in biology, graphs are... 9 MIN READ