RyanCodrai/turbovec

Project overview

TurboVec is a Rust vector index with Python bindings that compresses Float32 embeddings to 2-bit or 4-bit using TurboQuant, achieving up to 16x compression without a training phase. It executes search via hand-written SIMD kernels that deliver faster speeds than FAISS IndexPQFastScan on ARM and operate fully locally without requiring GPU resources.

Project type

RAG · Vector Database

Use cases

Knowledge Q&A

Deployment

Refer to project documentation

License

MIT

Best for

• Developers, AI engineers, and data teams who need local-only execution, have Float32 embeddings, and require high compression ratios without a training phase.

Key capabilities

• Add vectors to the index continuously without requiring a separate training step, parameter tuning, or rebuilding as the corpus grows.
• Utilizes hand-written NEON and AVX-512BW SIMD kernels to provide search speeds faster than FAISS.
• Allows passing an id allowlist or bitmask to the search function to filter results within the SIMD kernel without over-fetching.
• Compresses vectors using a random rotation and Lloyd-Max scalar quantization to achieve up to 16x compression.
• Computes and stores a scalar per vector at encode time to correct systematic underestimation of inner products during scoring.
• Provides an IdMapIndex for mapping internal ids to stable external uint64 ids that survive deletes.
• Provides Python bindings installable via pip for interacting with the underlying Rust index.
• Provides a native Rust library installable via cargo.

Limitations and risks

• The TurboQuant asymptotic Beta assumption is looser in low-dimensional vector regimes like GloVe d=200, which may impact compression quality or recall in those configurations.
• Telemetry practices are not documented in the available facts.

Getting started

• Install using standard package managers via pip or cargo, then instantiate TurboQuantIndex to begin indexing.

Evidence and sources

• README: **A 10 million document corpus takes 31 GB of RAM as float32. turbovec fits it in 4 GB - and searches it faster than FAISS.** turbovec is a Rust vector index with Python bindings,…
• README: turbovec is a Rust vector index with Python bindings, built on Google Research's [**TurboQuant**](https://arxiv.org/abs/2504.19874) algorithm
• README: Restrict results to a candidate set produced by another system (SQL, BM25, ACL, time window, …):
• README: The calibration is frozen after the first add and reused by subsequent adds — no retraining, no rebuilds, no separate train phase. Recall gain: up to +1.4pp at @1 on the cells tha…
• README: Need stable ids that survive deletes? Use `IdMapIndex`: ```python import numpy as np from turbovec import IdMapIndex index = IdMapIndex(dim=1536, bit_width=4) index.add_with_ids(v…

Reviewed at: 2026-07-18T00:13:23Z