ATRIUMsearch → argument graph
MechanismArticle

GraphRAG provides two distinct search paths: local search expands from matched entities through related text units, reports, and neighbors, while global search aggregates pre-written community reports using a map-reduce process.

GraphRAG offers different search strategies: local search for entity-focused questions and global search that synthesizes pre-written summaries to answer questions spanning the entire document collection. ✦ AI generated

article author · ByteByteGo Newsletter · 2026-08-19 · original ↗

Local search begins by matching the query against entity description embeddings... Global search leaves the entity graph untouched. Community reports from a chosen hierarchy level are split into batches... a map stage runs each batch through a language model and produces an intermediate answer... a reduce stage then collects the highest-rated points across all batches and generates the final answer.

Read full article ↗excerpt · fair-use quotation

Around this claim