LightRAG and rag-fusion

These tools are competitors, as both aim to improve retrieval-augmented generation: LightRAG focuses on a simple and fast approach, while rag-fusion employs multi-query generation and Reciprocal Rank Fusion.

LightRAG
70
Verified
rag-fusion
56
Established
Maintenance 22/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 20/25
Stars: 29,302
Forks: 4,198
Downloads:
Commits (30d): 309
Language: Python
License: MIT
Stars: 908
Forks: 110
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About LightRAG

HKUDS/LightRAG

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

LightRAG helps developers build efficient AI applications that can answer questions accurately using large amounts of information. It takes your unstructured data (like documents, images, and videos) and a user's question, then provides a precise answer with citations to the original sources. This tool is designed for AI developers and engineers who are creating advanced conversational AI or knowledge retrieval systems.

AI development conversational AI knowledge retrieval multimodal AI large language models

About rag-fusion

Raudaschl/rag-fusion

RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.

This helps scientists and researchers find more relevant information from their document collections. You input your original search query, and it generates multiple refined queries to cast a wider net. The output is a re-ranked list of documents, providing more comprehensive results than traditional searches. This is for anyone who struggles to find that crucial piece of information hidden deep within their documents using standard search tools.

research-discovery information-retrieval document-search knowledge-management scientific-literature

Scores updated daily from GitHub, PyPI, and npm data. How scores work