PrithivirajDamodaran/FlashRank
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.
When you have a search engine or retrieval system, it often returns many documents that might be relevant, but not necessarily in the best order. FlashRank helps improve this by taking your search query and a list of potentially relevant text passages, then re-orders them to put the most relevant results at the top. This is used by anyone who needs to quickly and accurately present the most pertinent information from a larger set of search results, such as in customer support, knowledge bases, or e-commerce search.
948 stars. Used by 2 other packages. Available on PyPI.
Use this if you need to quickly and efficiently improve the accuracy and relevance of search results presented to users, especially when working with existing search pipelines.
Not ideal if you need a full search engine from scratch, as this tool focuses specifically on re-ranking an already retrieved set of results.
Stars
948
Forks
67
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 01, 2026
Commits (30d)
0
Dependencies
5
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/PrithivirajDamodaran/FlashRank"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
meilisearch/meilisearch
A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.
nuclia/nucliadb
NucliaDB, The AI Search database for RAG
vespa-engine/vespa
AI + Data, online. https://vespa.ai
ICIJ/datashare
A self‑hosted search engine for documents
marcominerva/SqlDatabaseVectorSearch
A Blazor Web App and Minimal API for performing RAG (Retrieval Augmented Generation) and vector...