A-RAG
StaleDescription
Agentic Retrieval-Augmented Generation framework achieving state-of-the-art on multi-hop QA benchmarks through hierarchical retrieval with keyword, semantic, and chunk read tools.
Agentic Retrieval-Augmented Generation framework achieving state-of-the-art on multi-hop QA benchmarks through hierarchical retrieval with keyword, semantic, and chunk read tools.
MTEB (Massive Text Embedding Benchmark) is a comprehensive benchmark framework for evaluating text embeddings across classification, retrieval, clustering, reranking, and more, helping select optimal embedding models for RAG systems.
A deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework for deep retrieval and reasoning across medical literature.
Open-source BGE series embedding models and retrieval tools from BAAI, providing state-of-the-art text embeddings and rerankers for Chinese and English, widely used in RAG systems and agent retrieval pipelines.
LightRAG is a simple and fast Retrieval-Augmented Generation framework using graph-enhanced retrieval, published at EMNLP 2025.