lightonai/fast-plaid
High-Performance Engine for Multi-Vector Search
This tool helps machine learning engineers and researchers build more accurate search and retrieval systems by finding nuanced matches between queries and documents or images. It takes fine-grained, per-token or per-patch representations of documents and queries, then outputs highly relevant search results by comparing these at a granular level. This is ideal for improving the precision of search in complex information retrieval tasks.
218 stars. Used by 1 other package. Available on PyPI.
Use this if you need highly accurate search results for documents or images by matching them at a very detailed, token-by-token or patch-by-patch level, especially for tasks where single-vector search isn't precise enough.
Not ideal if your search problem only requires broad, general similarity matching or if you are not working with per-token or per-patch embeddings for your data.
Stars
218
Forks
17
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Dependencies
8
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/lightonai/fast-plaid"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
databendlabs/databend
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from...
oceanbase/oceanbase
The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.
matrixorigin/matrixone
MySQL-compatible HTAP database with Git for Data, vector search, and fulltext search....
ArcadeData/arcadedb
ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB...
datalevin/datalevin
A simple, fast and versatile Datalog database