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
Context · 3
Standard RAG works by chunking documents, embedding them into vectors, and retrieving chunks whose vectors are closest to the query vector, relying on the assumption that the text answering a question will be similar to the question itself.article author · ByteByteGo Newsletter · conf 80%Standard RAG's similarity-based assumption fails for 'global queries' that require reasoning across a large collection of documents, because the relevant information is distributed, not located in a few text regions that resemble the query.article author · ByteByteGo Newsletter · conf 70%A knowledge graph stores entities (nouns) and typed relationships between them, each with a description, which preserves the connections between concepts that plain text chunking discards.article author · ByteByteGo Newsletter · conf 70%