kANNolo is a research-oriented library for Approximate Nearest Neighbors (ANN) search written in Rust 🦀. It is explicitly designed to combine usability with performance effectively. Designed with modularity and researchers in mind, kANNolo makes prototyping new ANN search algorithms and data structures easy. kANNolo supports both dense and sparse embeddings seamlessly. It implements the HNSW graph index and Product Quantization.
For most users, this is the easiest option:
pip install kannoloIf a compatible wheel exists for your platform, pip will download and install it directly without compilation.
If no compatible wheel exists, pip will automatically compile from source.
For maximum performance optimized to your CPU, build from source. Choose one of the two approaches below:
Both building approaches require Rust and nightly:
- Install Rust (via
rustup):
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh- Activate nightly:
rustup install nightly
rustup default nightlyCompile and install directly from PyPI with CPU optimization:
RUSTFLAGS="-C target-cpu=native" pip install --no-binary :all: kannoloThis installs the package in your system/virtual environment site-packages.
Clone the repository and build for development/modification:
- Clone and prepare:
git clone https://github.com/TusKANNy/kannolo.git
cd kannolo- Create a virtual environment (recommended):
python3 -m venv ./venv
source ./venv/bin/activate # On Windows: venv\Scripts\activateAlternatively, use conda:
conda create -n kannolo python=3.11
conda activate kannolo- Install maturin:
pip install maturin- Build and install in editable mode:
RUSTFLAGS="-C target-cpu=native" maturin develop --releaseWhy use editable mode? Changes to Python code take effect immediately without reinstalling. Perfect for development and prototyping.
- Verify installation:
python -c "import kannolo; print('Successfully installed kannolo!')"This command allows you to compile all the Rust binaries contained in src/bin
RUSTFLAGS="-C target-cpu=native" cargo build --releaseDetails on how to use kANNolo's core engine in Rust 🦀 can be found in docs/RustUsage.md.
Details on how to use kANNolo's Python interface can be found in docs/PythonUsage.md.
Check out our docs folder for a more detailed guide on how to use kANNolo directly in Rust, replicate the results of our paper, or use kANNolo with your custom collection.
Leonardo Delfino, Domenico Erriquez, Silvio Martinico, Franco Maria Nardini, Cosimo Rulli and Rossano Venturini. "kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search." Proc. ECIR. 2025.
The source code in this repository is subject to the following citation license:
By downloading and using this software, you agree to cite the under-noted paper in any kind of material you produce where it was used to conduct a search or experimentation, whether be it a research paper, dissertation, article, poster, presentation, or documentation. By using this software, you have agreed to the citation license.
ECIR 2025
@InProceedings{10.1007/978-3-031-88717-8_29,
author = "Leonardo Delfino and
Domenico Erriquez and
Silvio Martinico and
Franco Maria Nardini and
Cosimo Rulli and
Rossano Venturini",
title = "kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search",
booktitle = "Advances in Information Retrieval",
year = "2025",
publisher = "Springer Nature Switzerland",
pages = "400--406",
isbn = "978-3-031-88717-8"
}