# ryancodrai/turbovec

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/ryancodrai-turbovec).**

11,738 stars · 1,018 forks · Python · MIT

## Links

- GitHub: https://github.com/RyanCodrai/turbovec
- Homepage: https://pypi.org/project/turbovec/
- awesome-repositories: https://awesome-repositories.com/repository/ryancodrai-turbovec.md

## Topics

`ann` `avx512` `embedding` `embeddings` `faiss` `nearest-neighbor` `neon` `python` `quant` `quantization` `rag` `rust` `simd` `turboquant` `vector-search`

## Description

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.

## Tags

### Data & Databases

- [Vector Embedding Indexes](https://awesome-repositories.com/f/data-databases/vector-search/vector-embedding-indexes.md) — Provides a high-performance index for storing and retrieving high-dimensional embeddings via similarity search.
- [Random Rotation Compression](https://awesome-repositories.com/f/data-databases/random-rotation-compression.md) — Uses random orthogonal matrices to distribute variance and improve the accuracy of quantized vector searches.
- [Vector Search Indexes](https://awesome-repositories.com/f/data-databases/search-indexing-technologies/search-indexing/search-and-indexing/vector-search-indexes.md) — Provides a quantized vector index for high-performance similarity search using SIMD kernels.
- [Vector Databases](https://awesome-repositories.com/f/data-databases/vector-databases.md) — A memory-efficient vector database written in Rust with Python bindings for embedding storage and retrieval.
- [Memory-Optimized Storage](https://awesome-repositories.com/f/data-databases/vector-memory-stores/memory-optimized-storage.md) — Reduces the memory footprint of vector indices by using low-bit representations of embeddings.
- [Vector Quantization](https://awesome-repositories.com/f/data-databases/vector-quantization.md) — Implements vector quantization using random rotation and scalar quantization to reduce memory footprints. ([source](https://github.com/ryancodrai/turbovec#readme))
- [Coordinate-Specific Scalar Quantization](https://awesome-repositories.com/f/data-databases/vector-quantization/coordinate-specific-scalar-quantization.md) — Compresses high-dimensional embeddings using coordinate-specific shift and scale values for memory efficiency.
- [Data-Oblivious Quantization](https://awesome-repositories.com/f/data-databases/vector-quantization/data-oblivious-quantization.md) — Reduces memory footprint by converting floating-point vectors into integers using data-oblivious quantization.
- [High-Dimensional Vector Compressors](https://awesome-repositories.com/f/data-databases/vector-quantization/high-dimensional-vector-compressors.md) — Implements a vector compressor that uses random rotation and data-oblivious quantization to reduce memory usage.
- [Vector Search](https://awesome-repositories.com/f/data-databases/vector-search.md) — Provides a high-performance implementation of vector similarity search for high-dimensional embeddings. ([source](https://github.com/ryancodrai/turbovec#readme))
- [SIMD-Accelerated Arithmetic](https://awesome-repositories.com/f/data-databases/vectorized-arithmetic/simd-accelerated-arithmetic.md) — Accelerates nearest neighbor retrieval using SIMD-accelerated kernels for maximum throughput.
- [Stable Index Mappings](https://awesome-repositories.com/f/data-databases/identifier-configurations/identifier-mappings/stable-index-mappings.md) — Maintains stable mappings between vector IDs and physical locations to support deletions without rebuilding the corpus.
- [Real-Time Vector Ingestion](https://awesome-repositories.com/f/data-databases/real-time-vector-ingestion.md) — Enables adding new vectors to the index in real-time without requiring full corpus rebuilding. ([source](https://github.com/ryancodrai/turbovec#readme))
- [Bitmask Filtering](https://awesome-repositories.com/f/data-databases/search-result-filtering/bitmask-filtering.md) — Implements high-performance result filtering using bitmasks to isolate document subsets during retrieval.
- [Persistent Identifier Management](https://awesome-repositories.com/f/data-databases/vector-indexing/persistent-identifier-management.md) — Assigns persistent IDs to vectors to maintain index consistency after entries are deleted. ([source](https://github.com/ryancodrai/turbovec#readme))
- [Filtered Similarity Searches](https://awesome-repositories.com/f/data-databases/vector-similarity-search/filtered-similarity-searches.md) — Restricts vector similarity search results to specific document subsets using bitmask filtering. ([source](https://github.com/ryancodrai/turbovec#readme))
- [Kernel-Level Filter Optimizations](https://awesome-repositories.com/f/data-databases/vector-similarity-search/filtered-similarity-searches/kernel-level-filter-optimizations.md) — Optimizes search performance by short-circuiting blocks of disallowed vectors within the processing kernel. ([source](https://github.com/ryancodrai/turbovec#readme))

### Artificial Intelligence & ML

- [Vector Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-memory-systems/vector-memory-stores.md) — Functions as a pluggable vector store designed to replace in-memory storage in LLM orchestration frameworks.
- [Orchestration Store Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-integration-frameworks/orchestration-store-integrations.md) — Provides a pluggable vector store implementation that integrates directly into LLM orchestration frameworks. ([source](https://github.com/ryancodrai/turbovec#readme))
- [Calibration Parameters](https://awesome-repositories.com/f/artificial-intelligence-ml/precision-quantization/online-quantization/calibration-parameters.md) — Fits empirical data distributions to coordinate-specific shift and scale values during data ingestion. ([source](https://github.com/ryancodrai/turbovec#readme))

### Web Development

- [SIMD Accelerated Searchers](https://awesome-repositories.com/f/web-development/performance-optimizations/computational-parallelization/simd-accelerated-searchers.md) — Utilizes SIMD-accelerated kernels to perform high-throughput distance calculations and memory scanning.