Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

Lightweight Nearest Neighbors with Flexible Backends

⚡ A fast embedded library for approximate nearest neighbor search

HNSW tutorial

(distributed) vector database

S3 vector database for LLM Agents and RAG.

facenet recognition and retrieve by using hnswlib and flask, convert tensorflow model to caffe

A specialized implementation of the Hierarchical Navigable Small World (HNSW) data structure adapted for efficient nearest neighbor lookup of approximate matching hashes

The thesis presents the parallelisation of a state-of-the art clustering algorithm, FISHDBC. This objective has been achived by improving the main data structures and components of the algorithm: HNSW, MST and HDBSCAN. My contribution is based on a lock-free strategy, completely wrote in Python.

KNN Search Algorithm Comparison – This project compares the performance of different K-Nearest Neighbors (KNN) search algorithms across various dataset sizes and dimensions.

High-performance database management system

Optimized RAG Retrieval with Indexing, Quantization, Hybrid Search and Caching

Comparison of IVFFlat and HNSW Algorithms

This project leverages Vision Transformers (ViT) to build a scalable image retrieval system. Images are encoded into compact vectors and stored in MongoDB for efficient querying. Advanced indexing techniques like Product Quantization (PQ) and HNSW graph optimize retrieval for speed and memory. A Streamlit-based web app allows users to upload images

Local in-memory vector database

# ZeusDBZeusDB is a powerful database solution designed for ease of use and flexibility. 🌩️ With support for Python 3.10 to 3.13, it integrates smoothly into your projects. 🐙