fast-plaid 1.0.0

Fast Plaid.

FastPlaid

 

FastPlaid is a high-performance engine for multi-vector.

 

⚡️ Overview

Traditional vector search relies on single, fixed-size embeddings (dense vectors) for documents and queries. While powerful, this approach can lose nuanced, token-level details.

• Multi-vector search, used in models like ColBERT or ColPali, replaces a single document or image vector with a set of per-token vectors. This enables a "late interaction" mechanism, where fine-grained similarity is calculated term-by-term to boost retrieval accuracy.

• Higher Accuracy: By matching on a finer, token-level granularity, FastPlaid can capture relevance that single-vector models miss.

• Performance: Written in Rust, it offers blazing-fast indexing and search speeds.

• PLAID: stands for Per-Token Late Interaction Dense Search

 

💻 Installation

pip install fast-plaid

 

⚡️ Quick Start

Get started with creating an index and performing a search in just a few lines of Python.

import torch

from fast_plaid import search

fast_plaid = search.FastPlaid(index="index")

embedding_dim = 128

# Index 100 documents, each with 300 tokens, each token is a 128-dim vector
fast_plaid.create(
    documents_embeddings=[torch.randn(300, embedding_dim) for _ in range(100)] 
)

# Search for 2 queries, each with 50 tokens, each token is a 128-dim vector
scores = fast_plaid.search(
    queries_embeddings=torch.randn(2, 50, embedding_dim),
    top_k=10,
)

print(scores)

[
    [
        (20, 1334.5103759765625),
        (91, 1299.576171875),
        (59, 1285.788818359375),
        (10, 1273.534912109375),
        (62, 1267.9666748046875),
        (44, 1265.5655517578125),
        (15, 1264.426025390625),
        (34, 1261.19775390625),
        (19, 1261.0517578125),
        (86, 1260.94140625),
    ],
    [
        (58, 1313.8587646484375),
        (75, 1313.829833984375),
        (79, 1305.322509765625),
        (59, 1299.12158203125),
        (55, 1293.456787109375),
        (44, 1288.419189453125),
        (67, 1283.658935546875),
        (60, 1283.2884521484375),
        (53, 1282.522216796875),
        (9, 1280.863037109375),
    ],
]

Citation

FastPlaid is based on the original PLAID: Santhanam, Keshav, et al..

You can cite FastPlaid in your work as follows:

@misc{fastplaid2025,
  author = {Sourty, Raphaël},
  title = {FastPlaid: A High-Performance Engine for Multi-Vector Search},
  year = {2025},
  url = {https://github.com/lightonai/fast-plaid}
}

@inproceedings{santhanam2022plaid,
  title={{PLAID}: an efficient engine for late interaction retrieval},
  author={Santhanam, Keshav and Khattab, Omar and Potts, Christopher and Zaharia, Matei},
  booktitle={Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
  pages={1747--1756},
  year={2022}
}