fast-plaid

library1.4.7.2110pypypi✓ verified 84d ago

Fast Plaid is a GPU-accelerated approximate nearest neighbor search library for high-dimensional embeddings, designed for fast indexing and search with support for incremental updates, filtering, and deletions. Current version 1.4.6, requires Python >=3.10. Released irregularly.

vector-search ai-ml data

pip install fast-plaid

github ↗package ↗docs ↗

INSTALL

IMPORT

SIG · FAST-PLAID

fast-plaid

vector-searchpythonv1.4.7.2110

Install

67.7s avg

Import

6735ms

Disk

4813MB

Pass rate

4/ 10

Env Coverage4 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v1.4.7.2110 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✓ 78.2s

py 3.11

✕ build_error

✓ 69.6s

py 3.12

✕ build_error

✓ 64.8s

py 3.13

✕ build_error

✓ 58.3s

py 3.9

✕ build_error

✕ timeout

4813MB installed

● package 4813MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

FastPlaid

✓ from fast_plaid.search import FastPlaid

✗ from fast_plaid import FastPlaid

FastPlaid is in the search submodule, not the root package

✓ from fast_plaid import search

The search module contains FastPlaid and helper functions

Basic index creation and search with random embeddings

import torch from fast_plaid.search import FastPlaid # Create random embeddings (100 documents, 128 dimensions) docs = torch.randn(100, 128) queries = torch.randn(5, 128) # Build index plaid = FastPlaid() plaid.create(docs) # Search scores, indices = plaid.search(queries, top_k=3) print(indices)

Debug

Known issues

breakingPytorch's native quantile() can cause 'input tensor is too large' panic on large datasets. Versions before 1.4.5 are affected. Upgrade to >=1.4.5.

fix

Upgrade fast-plaid to 1.4.5 or later: pip install 'fast-plaid>=1.4.5'

affects: <1.4.5

deprecatedOlder code uses 'create(index='...')' incorrectly; index parameter in FastPlaid() constructor is for loading an existing index, not for creation.

fix

Use FastPlaid() without arguments for creation, then call .create(docs) or use FastPlaid(index='path') to load an existing index.

affects: all

gotchaThe `subset` filtering parameter expects a list of integer IDs, not boolean masks or tensors.

fix

Pass a list of document IDs (e.g., [2, 5, 10]) to the subset parameter in search().

affects: >=1.2.0

Errors

Common errors & fixes

ImportError: cannot import name 'FastPlaid' from 'fast_plaid'

FastPlaid class is in the search submodule, not the root package.

fix

Use 'from fast_plaid.search import FastPlaid' instead of 'from fast_plaid import FastPlaid'.

PanicException: input tensor is too large

The internal quantile computation fails on large datasets due to PyTorch size limits in versions <1.4.5.

fix

Upgrade to fast-plaid >=1.4.5, which replaces quantile with kthvalue-based approach.

AttributeError: 'FastPlaid' object has no attribute 'delete'

The delete method was introduced in version 1.2.3; using an older version.

fix

Upgrade to fast-plaid >=1.2.3: pip install 'fast-plaid>=1.2.3'

Upgrade

Version history

1.4.7.2110latest on PyPI · released May 28, 2026

Audit

Dependencies

torchrequiredCore dependency for tensor operations and GPU acceleration

Agent activity

53 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/lightonai/fast-plaid ↗

packagehttps://pypi.org/project/fast-plaid/ ↗

docshttps://github.com/lightonai/fast-plaid ↗