svilupp/FlashRank.jl
Rapid Document Ranking, Powered by Lightweight Models.
When building applications that answer questions using large language models, you often need to find the most relevant information from many documents. This tool takes a question and a list of potential documents, then quickly identifies and orders the documents by how well they answer the question, even on standard laptops without special hardware. It's designed for developers building Retrieval Augmented Generation (RAG) systems who need fast and efficient document prioritization.
No commits in the last 6 months.
Use this if you are developing AI applications like chatbots or search engines that need to quickly sort through many text documents to find the most relevant ones for a given query.
Not ideal if your primary goal is to generate new text content or analyze very long documents beyond 512 tokens, as those will be truncated.
Stars
8
Forks
—
Language
Julia
License
MIT
Category
Last pushed
Nov 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/svilupp/FlashRank.jl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
beir-cellar/beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across...
HKUDS/RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
superlinear-ai/raglite
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
illuin-tech/vidore-benchmark
Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.