TurboVec is a high-performance Rust vector database and quantized search index designed for storing and retrieving high-dimensional embeddings. It functions as a pluggable vector store for large language model orchestration frameworks, providing a memory-efficient alternative to standard in-memory storage.
The project distinguishes itself through a high-dimensional vector compressor that utilizes random rotation and data-oblivious scalar quantization to reduce memory footprints. Retrieval is accelerated via SIMD kernels that process distance calculations and search operations for increased throughput.
The system covers a broad range of indexing capabilities, including real-time data ingestion and the management of stable vector identifiers to allow for deletions without rebuilding the corpus. It also implements result filtering using bitmasks to isolate specific subsets of documents during the search process.
The core engine is written in Rust and exposed to Python through foreign function interface bindings.
