LightRAG and rag-fusion
About LightRAG
HKUDS/LightRAG
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Constructs a dual-level retrieval system combining vector similarity search with knowledge graph extraction to handle both entity-centric and content-based queries. Supports multiple storage backends including Neo4j, MongoDB, and PostgreSQL, with integrated reranking, citation tracking, and multimodal document processing via RAG-Anything. Designed for Python 3.10+ with built-in evaluation (RAGAS) and tracing (Langfuse) capabilities.
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.
Multi-query generation is powered by OpenAI's GPT to explore different facets of user intent, with results aggregated via Reciprocal Rank Fusion for re-ranking across multiple retrieval perspectives. The implementation combines vector search (ChromaDB) with optional BM25 keyword search in a hybrid architecture, and includes a quantitative evaluation harness against NFCorpus/BEIR benchmarks showing +22% NDCG and +40% recall gains over baseline vector search through diverse prompt variants and result fusion strategies.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work