A lightweight, lightning-fast, in-process vector database

Embeddable, in-memory, document-oriented database with a high-level Query builder interface.

PomaiDB Vector Database for low performance devices

Optimizing multi-attribute filtering for Approximate Nearest Neighbor (ANN) search using HNSW. This project integrates bitsets and Roaring Bitmaps into HNSWLib to accelerate query performance by reducing evaluation costs for large attribute datasets.

3-Lane retrieval for lifelong LLM agent memory: parallel recent safety-net, temporal date-range, and vector ANN search with Neo4j knowledge-graph persistence. Features importance-floor landmark bypass, dynamic candidate scaling, and state supersession chains.

Accelerate vector similarity search and embedding management for efficient AI applications with zvec.

Building a Custom Vector Search Engine with Weaviate : The project discusses the architecture of Weaviate, an open-source vector database and provides a tutorial implementation of a custom vector search engine using Weaviate Cloud Service(WCS).

Production-ready multimodal retrieval system built with OpenCLIP, Qdrant, FastAPI and Streamlit. Includes full evaluation pipeline (Recall@K, mAP, nDCG) and Docker-based deployment.

A framework for the implementation of candidate generation/retrieval algorithms for recommender systems.

RAG pipeline prototype MVP project

Approximate shortest path between the nodes in a (knowledge or any other) graph

A basic RAG pipeline which uses gpt-oss-20b model to answer the user query with the external knowledge stored in a vector database.

App Store Search example using ReactiveSearch pipelines and aNN

Transform-domain representation enabling 3–4× storage reduction with direct ANN search and novel multi-resolution signals. UK patent application under accelerated examination (Green Channel).