RaBitQ Library

Compact vectors. Accurate distances. Fast ANN search.

A research-backed C++17 library with Python bindings for 1-bit and multi-bit
vector quantization, IVF, HNSW, and SymphonyQG.

PyPI Python versions C++ tests Python tests Documentation Paper DOI License

Documentation · Python package · Paper · Releases

Install

pip install rabitqlib

Prebuilt wheels support Linux x86-64 and CPython 3.11–3.14. AVX2 + FMA is the portable CPU baseline; supported AVX-512 kernels are selected at runtime.

Adopted across the vector-search ecosystem

Milvus · Faiss · NVIDIA cuVS · VSAG · VectorChord · Volcengine OpenSearch · CockroachDB · Elasticsearch · Lucene · turbopuffer · Zvec

Accuracy at a glance

RaBitQ estimation error benchmark across MSong, YouTube, OpenAI embeddings, Word2Vec, and GIST

Average and maximum relative estimation error across six datasets; lower is better. Results from the SIGMOD camera-ready paper.

Why RaBitQ?
Compact by design Choose 1-bit or multi-bit codes to match your memory and accuracy target.
Accurate estimates An asymptotically optimal theoretical error bound supports reliable ordering and reranking.
Fast on x86-64 Dedicated AVX2 and AVX-512 kernels are selected through runtime CPU dispatch.
Ready for ANN search Use the quantizer directly or build complete IVF, HNSW, and SymphonyQG indexes.

The library supports Euclidean distance and inner product. Cosine search is available by normalizing vectors before using inner product.

RaBitQ is developed by the VectorDB group at Nanyang Technological University, Singapore. A GPU implementation is also available in cuvs_rabitq.

Python quick start

The following complete example builds a small IVF index and searches it. It uses deterministic synthetic data, so no dataset download is required.

import numpy as np
from rabitqlib import IvfIndex

rng = np.random.default_rng(42)
data = rng.standard_normal((500, 64)).astype(np.float32)
queries = rng.standard_normal((5, 64)).astype(np.float32)

# Assign vectors to five clusters and calculate their centroids.
cluster_ids = (np.arange(len(data)) % 5).astype(np.uint32)
centroids = np.stack(
    [data[cluster_ids == cluster].mean(axis=0) for cluster in range(5)]
).astype(np.float32)

index = IvfIndex(
    dim=64,
    max_elements=len(data),
    num_clusters=5,
    nbits=4,
    metric="l2",
)
index.build(data, centroids, cluster_ids)

ids, distances = index.search(queries, k=10, nprobe=5)
print(ids.shape, distances.shape)  # (5, 10) (5, 10)
print(ids[0])

Python bindings are also available for HnswIndex and SymqgIndex. See the Python examples for index construction, querying, and index persistence.

Build the Python bindings from source

Source builds require a C++17 compiler, CMake 3.15 or newer, and OpenMP. On Ubuntu or Debian:

sudo apt-get update
sudo apt-get install -y build-essential cmake libomp-dev
git clone https://github.com/VectorDB-NTU/RaBitQ-Library.git
cd RaBitQ-Library
python -m pip install .

C++ quick start

Requirements

  • CMake 3.15 or newer
  • a C++17 compiler with OpenMP support
  • an x86-64 CPU supported by the selected kernels: most paths accept either AVX2 with FMA or AVX-512F/BW/DQ with FMA
CPU dispatch details

Most SIMD entry points select AVX-512 kernels when AVX-512F, AVX-512BW, and AVX-512DQ are detected; otherwise they use AVX2 when AVX2 and FMA are available. AVX-512 VPOPCNTDQ enables additional popcount kernels. The HNSW AVX-512 core path also checks for AVX2 and FMA. AVX-512 translation units are compiled with FMA enabled.

Clone and build the library and example programs:

git clone https://github.com/VectorDB-NTU/RaBitQ-Library.git
cd RaBitQ-Library

cmake -S . -B build -DCMAKE_BUILD_TYPE=Release
cmake --build build --parallel

Release builds enable native CPU tuning by default. To build a binary that can be moved between AVX2- and AVX-512-capable machines, configure with -DRABITQ_ENABLE_NATIVE_OPTIMIZATION=OFF; the ISA-specific kernels will still be selected at runtime.

The index example executables are written to bin/. Their source code shows the complete indexing and querying workflows:

A separate RaBitQ quantization example demonstrates the lower-level quantizer API; it is provided as source and is not currently a CMake target.

To build and run the C++ test suite:

cmake -S . -B build -DRABITQ_BUILD_TESTS=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build --parallel
ctest --test-dir build --output-on-failure

GoogleTest is downloaded during test configuration. For a full benchmark on the GIST dataset, see example.sh. More detailed API and algorithm guidance is available in the documentation.

Choose the right building block

Component Best fit Storage and search profile
Quantizer Integrating RaBitQ into an existing system Low-level 1-bit or multi-bit encoding and distance estimation.
IVF Memory-efficient partitioned search Stores quantized codes without retaining the raw dataset.
HNSW Graph search with compact vectors Adds graph links and searches directly from quantized codes.
SymphonyQG Query speed when more memory is available Retains raw vectors and stores per-neighborhood quantization data.

IVF and SymphonyQG use FastScan for batched estimates, while HNSW uses single-code AVX2 or AVX-512 kernels.

In typical workloads, 4-bit, 5-bit, and 7-bit quantization can achieve roughly 90%, 95%, and 99% recall, respectively, without reranking. Actual results depend on the dataset, index configuration, and search parameters.

Citation

If RaBitQ helps your research or system, please cite:

Jianyang Gao, Yutong Gou, Yuexuan Xu, Yongyi Yang, Cheng Long, and Raymond Chi-Wing Wong. “Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search.” Proceedings of the ACM on Management of Data 3, 3, Article 202 (June 2025), 26 pages. https://doi.org/10.1145/3725413.

Contributing

Contributions are welcome. See the contributing guide for the build, formatting, pre-commit, and static-analysis workflows.

Acknowledgements

RaBitQ Library is developed by Yutong Gou, Jianyang Gao, Yuexuan Xu, Jifan Shi, and Zhonghao Yang. We thank Alexandr Guzhva, Li Liu, Chao Gao, Silu Huang, Jiabao Jin, Xiaoyao Zhong, and Jinjing Zhou for their valuable feedback.

License

RaBitQ Library is available under the Apache License 2.0.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.3.2)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for TamimEhsan from gravatar.com TamimEhsan

Requires

Python >=3.11

Provides Extra

test

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

rabitqlib-0.2.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (590.5 kB view details)

Uploaded CPython 3.14manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

rabitqlib-0.2.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (590.2 kB view details)

Uploaded CPython 3.13manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

rabitqlib-0.2.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (590.1 kB view details)

Uploaded CPython 3.12manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

rabitqlib-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (589.8 kB view details)

Uploaded CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

File details

Details for the file rabitqlib-0.2.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for rabitqlib-0.2.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 97926289b73e3cf28df58e8bee325c70a85cabef9a6f9fa21532d1d66d031d0c
MD5 b3bc0cd19575bbaa0a786cf320b9d796
BLAKE2b-256 424b7647e8501d4348ee47bd28cf600bfcecc3c6023e93777f495a6bddc9cef5

See more details on using hashes here.

Provenance

The following attestation bundles were made for rabitqlib-0.2.1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: release.yml on VectorDB-NTU/RaBitQ-Library

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file rabitqlib-0.2.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for rabitqlib-0.2.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 8218b7248f7858b3a9a347d23374e08ec5153fd07228a6f093675c4fe4a9709b
MD5 179627c881dd7d5883535223873a4c8c
BLAKE2b-256 546051c33163294b8506e0d2e4edfcaff610a0df75cfaf9b2ef6c76d27b9e44c

See more details on using hashes here.

Provenance

The following attestation bundles were made for rabitqlib-0.2.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: release.yml on VectorDB-NTU/RaBitQ-Library

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file rabitqlib-0.2.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for rabitqlib-0.2.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 c19af180028d610b45812eecc28a264729f5764b0651cc06d0a9690d953550cc
MD5 3cafca5cf309e2546fe82b55b48d1550
BLAKE2b-256 1adb4dac160fc5779f7334032568e6700d2bd3c81d88294313fb8e26347df6b0

See more details on using hashes here.

Provenance

The following attestation bundles were made for rabitqlib-0.2.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: release.yml on VectorDB-NTU/RaBitQ-Library

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file rabitqlib-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for rabitqlib-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 af83b980aa63849020f689327045a5e65a18588959f2b3c7846d045ba8f7c5cf
MD5 629aed83d77b1b5d3e86d04db4fb98e2
BLAKE2b-256 a9c28bb4c1e76a487bcff27c5cc31f2e5b3c060d68d68e4c31c0027e0dd94be5

See more details on using hashes here.

Provenance

The following attestation bundles were made for rabitqlib-0.2.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl:

Publisher: release.yml on VectorDB-NTU/RaBitQ-Library

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.3.2

4 files

0.3.1

4 files

0.3.0

4 files

0.2.2

4 files

This release

0.2.1 This release

4 files

0.2.0

6 files

0.1.0

1 file

0.0.1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page