做RAG系统优化的团队终于有了一个不依赖LLM抽取的图构建方案——ContextRAG用30次调用替代了数百万token的索引开销，多跳问答效果还更好，做知识密集型问答的开发者值得一试。
ContextRAG 提出了一种无需大模型进行实体和关系抽取的图RAG系统，通过残差量化k-means和形式概念分析构建模糊概念图，显著降低了索引阶段的token消耗和延迟。在130任务的UltraDomain子集上，ContextRAG仅需30次LLM调用和22,073个token完成索引，而对比方法HiRAG在20任务上就需要870次调用和354万token。ContextRAG在整体F1上达到33.6%，多跳任务F1为36.8%。分析表明，检索到格派生节点的查询比未检索到的F1高出3.9个百分点。该方法为构建高效、低成本的图RAG系统提供了新思路。
ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation
Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing. These calls add token and wall-clock costs that grow with corpus size. We present ContextRAG, a graph RAG system whose graph topology is constructed without LLM-based entity or relation extraction. ContextRAG derives a fuzzy concept graph over chunk embeddings using residual-quantization k-means and Formal Concept Analysis with Lukasiewicz residuated logic. Bridge-like and meet-derived context nodes are induced by soft fuzzy join and meet operations, rather than by LLM-written graph edges. On a 130-task UltraDomain subset, ContextRAG builds its index with 30 LLM calls and 22,073 tokens. In contrast, a local HiRAG reproduction stress test required 870 indexing calls and 3.54M tokens on a 20-task subset before failing during graph construction; linear extrapolation to 130 tasks implies over 23M indexing tokens. ContextRAG obtains 33.6% F1 overall and 36.8% F1 on multi-hop tasks. An activation analysis shows that queries retrieving at least one lattice-derived node in the top five achieve +3.9 percentage points F1 over queries that do not; this association is diagnostic rather than causal.