Stars
A collection of curated RAG (Retrieval Augmented Generation) resources.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
State-of-the-Art Text Embeddings
Solve puzzles. Improve your pytorch.
Fast Differentiable Sorting and Ranking
Fast, differentiable sorting and ranking in PyTorch
KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows
Graph Neural Network Library for PyTorch
Approximate Nearest Neighbor Search for Sparse Data in Python!
PyTorch Extension Library of Optimized Scatter Operations
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
GitHub Mirror of RecPack: Experimentation Toolkit for Top-N Recommendation (see https://gitlab.com/recpack-maintainers/recpack)
Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
Notebooks for the O'Reilly book "Learning Ray"
nanobind: tiny and efficient C++/Python bindings
A new implementation of WiSARD using Bloom filter as Neuron. WiSARD is the most popular weightless neural network model that is very efficient specially in real-time applications.
Automatically update function definitions in a running Julia session