Efficient Approximate Nearest Neighbor Search on a Raspberry Pi

This repository contains the experimental setup for our SIGIR 2025 paper:

Efficient Approximate Nearest Neighbor Search on a Raspberry Pi
Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini
Presented at SIGIR 2025 (Low-Resource Environments Track), Padua, Italy.

---

📦 Datasets

The datasets used in this work are available on Hugging Face.

---

🧪 Reproducing the Experiments

Experiments were run on a Raspberry Pi 3 Model B+.

Refer to kANNolo's guide and Seismic's guide to reproduce the experiments.

Below you can find the .toml configuration files to reproduce the experiments:

• kANNolo:
  File to appear
  Version: commit 77f1890

• Seismic:
  File to appear
  Version: commit 1234567

---

For questions or issues, please open an issue or contact the authors.

Citation License

To cite this work, please use the following BibTeX entry:

SIGIR 2025

@inproceedings{10.1145/3726302.3730268,
author = {Martinico, Silvio and Nardini, Franco Maria and Rulli, Cosimo and Venturini, Rossano},
title = {Efficient Approximate Nearest Neighbor Search on a Raspberry Pi},
year = {2025},
isbn = {9798400715921},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3726302.3730268},
doi = {10.1145/3726302.3730268},
booktitle = {Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {3116–3118},
numpages = {3},
keywords = {nearest neighbors search, raspberry pi, retrieval},
location = {Padua, Italy},
series = {SIGIR '25}
}