Databases / prototype

VortexDB

A Rust vector database engine with RocksDB and in-memory storage backends, custom embedding modules, KD-Tree indexing, KNN search, and ANN benchmark preparation.

Architecture Overview

VortexDB stores embeddings and metadata through pluggable storage engines, including RocksDB-backed persistence and an in-memory backend, then exposes vector search through custom indexing and retrieval components.

The project explores a compact database architecture: storage engine boundaries, embedding generation hooks, indexing structures, and terminal-first interaction.

Technical Challenges

storage layout for vectors and metadata
storage engine abstraction across RocksDB and in-memory backends
KD-Tree construction and query performance
KNN search implementation tradeoffs
module boundaries for custom embedding generation
terminal UI ergonomics for inspecting database state

Benchmarks

The key measurements are index build time, query latency, recall quality, memory overhead, and RocksDB storage overhead as vector counts grow. The project is being prepared for ANN benchmark submission.

Lessons Learned

Vector search systems are database systems first: storage layout, indexing strategy, and observability matter as much as the embedding model.

Tools

Rust, Ratatui, RocksDB