Lightweight Nearest Neighbors with Flexible Backends

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

RAG Application with Optimizations on HNSW Index, Quantization, Hybrid Search and Semantic Caching

Seekvec - A lightning-fast similarity search engine for embedding vectors.

Comparison of IVFFlat and HNSW Algorithms

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

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

(distributed) vector database

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

HNSW tutorial

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.

S3 vector database for LLM Agents and RAG.

⚡ A fast embedded library for approximate nearest neighbor search

Local in-memory vector database

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