[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"glossary-graph-rag::en":3,"gloss-cluster-graph-rag::en":23,"gloss-next-graph-rag::en":9},{"slug":4,"category":5,"name":6,"definition":7,"meta_desc":8,"faq":9,"schema_markup":9,"related":10},"graph-rag","data-infra","GraphRAG","GraphRAG augments retrieval-augmented generation with a knowledge graph built from the corpus. During indexing, an LLM extracts entities and relationships from every document, assembles them into a graph, clusters it into communities, and writes summaries at each level. At query time the system can traverse relationships and consult community summaries instead of only matching semantically similar chunks. This attacks the two places vanilla RAG is weakest: multi-hop questions (\"which customers were affected by the outage the vendor caused?\") whose answer spans documents no single chunk connects, and global questions (\"what are the main themes across this corpus?\") that similarity search cannot answer at all. Microsoft's 2024 open-source GraphRAG popularized the pattern. The costs are indexing expense — entity extraction burns LLM tokens over the whole corpus — plus graph maintenance as documents change. Most teams deploy it selectively, alongside vector retrieval, for relationship-heavy domains rather than as a replacement.","GraphRAG builds a knowledge graph over your corpus so retrieval can traverse relationships and answer multi-hop questions plain RAG misses.",null,[11,14,17,20],{"slug":12,"name":13},"chunking","Chunking",{"slug":15,"name":16},"graph-database","Graph Database",{"slug":18,"name":19},"retrieval-augmented-generation","Retrieval-Augmented Generation (RAG)",{"slug":21,"name":22},"semantic-search","Semantic Search",[24,28,31,34,37,41,44,47,50,53,57,60],{"slug":25,"category":5,"name":26,"updated_at":27},"acid","ACID","2026-08-24T02:46:37+00:00",{"slug":29,"category":5,"name":30,"updated_at":27},"ann-search","ANN Search",{"slug":32,"category":5,"name":33,"updated_at":27},"backpressure","Backpressure",{"slug":35,"category":5,"name":36,"updated_at":27},"batch-processing","Batch Processing",{"slug":38,"category":5,"name":39,"updated_at":40},"bm25","BM25","2026-08-24T02:46:38+00:00",{"slug":42,"category":5,"name":43,"updated_at":27},"cache","Cache",{"slug":45,"category":5,"name":46,"updated_at":27},"cap-theorem","CAP Theorem",{"slug":48,"category":5,"name":49,"updated_at":27},"change-data-capture","Change Data Capture (CDC)",{"slug":51,"category":5,"name":52,"updated_at":27},"chroma","Chroma",{"slug":54,"category":5,"name":55,"updated_at":56},"chunk-overlap","Chunk Overlap","2026-08-24T03:30:02+00:00",{"slug":58,"category":5,"name":59,"updated_at":27},"columnar-storage","Columnar Storage",{"slug":61,"category":5,"name":62,"updated_at":27},"connection-pooling","Connection Pooling"]