Top 8 nearest-neighbor Open-Source Projects

ann-benchmarks

51 4,588 8.1 Python

Benchmarks of approximate nearest neighbor libraries in Python

Project mention: Using Your Vector Database as a JSON (Or Relational) Datastore | news.ycombinator.com | 2024-04-23

On top of my head, pgvector only supports 2 indexes, those are running in memory only. They don't support GPU indexing, nor Disk based indexing, they also don't have separation of query and insertions.
Also with different people I've talked to, they struggle with scale past 100K-1M vector.
You can also have a look yourself from a performance perspective: https://ann-benchmarks.com/

similarity

7 994 6.5 Python

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.
InfluxDB

www.influxdata.com sponsored

Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
raft

3 612 9.5 Cuda

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications. (by rapidsai)

Project mention: Raft: Fundamental widely-used algorithms and primitives for machine learning | news.ycombinator.com | 2024-02-22

NearestNeighbors.jl

1 400 6.1 Julia

High performance nearest neighbor data structures (KDTree and BallTree) and algorithms for Julia.
pgANN

2 289 0.0 Python

Fast Approximate Nearest Neighbor (ANN) searches with a PostgreSQL database.
MachineLearningWithPython

1 144 0.0 Jupyter Notebook

Get started with Machine Learning with Python - An introduction with Python programming examples
Iris

1 30 3.7 PHP

The original lightweight introduction to machine learning in Rubix ML using the famous Iris dataset and the K Nearest Neighbors classifier. (by RubixML)
WorkOS

workos.com sponsored

The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
CSGO-Pro-Gear-Performance-and-EDA

5 1 0.0 Jupyter Notebook

Modeling Professional (CS:GO) Gamer's Accuracy Performance Based on Gear and Settings, and Exploratory Data Analysis.

NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020).