--- title: GraphRAG: How AI Answers Questions Hidden Across Many... description: GraphRAG addresses a gap in standard vector-based RAG: while similarity search handles local questions whose answers resemble the query and sit in a specific... canonical: https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: GraphRAG: How AI Answers Questions Hidden Across Many Documents | daily.dev og:description: GraphRAG addresses a gap in standard vector-based RAG: while similarity search handles local questions whose answers resemble the query and sit in a specific... og:url: https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz og:image: https://api.daily.dev/og/posts/y6pRjKnJz.png og:image:alt: GraphRAG: How AI Answers Questions Hidden Across Many Documents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # GraphRAG: How AI Answers Questions Hidden Across Many Documents **[ByteByteGo](https://daily.dev/sources/bytebytego)** · 16 min read · 7 upvotes · 1 comments ## Summary GraphRAG addresses a gap in standard vector-based RAG: while similarity search handles local questions whose answers resemble the query and sit in a specific document, it fails on global questions requiring reasoning across an entire corpus, since the true answer emerges as a pattern rather than a retrievable location. GraphRAG solves this by extracting entities and relationships into a knowledge graph, clustering it hierarchically via Leiden clustering into communities, and generating summary reports for each community during indexing. Local search expands from matched entities into a ranked context window, while global search runs map-reduce over community reports. Microsoft's data shows graph extraction accounts for roughly 75% of indexing cost, and larger context windows (64K tokens) don't close the gap on global queries. Cost-reduction variants like LazyGraphRAG and FastGraphRAG trade graph quality for cheaper indexing, and agentic RAG adds a routing layer that picks a retrieval strategy per query rather than committing to one architecture. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is the difference between local search and global search in GraphRAG? Local search matches a query against entity description embeddings, then expands along five parallel directions (text units, community reports, neighboring entities, relationships, and claims) before ranking results into one context window. Global search instead runs community reports from a chosen hierarchy level through a map stage that produces rated intermediate answers, then a reduce stage combines the highest-rated points into a final answer. _Comparing retrieval architectures like GraphRAG gets easier with grounded technical breakdowns on daily.dev._ ### How much cheaper is LazyGraphRAG than full GraphRAG for indexing? LazyGraphRAG cuts indexing cost to roughly 0.1 percent of full GraphRAG by building its index with NLP instead of a language model and skipping summarization entirely, deferring all language model work to query time. Global-query answer quality stays comparable to standard global search, while per-query cost drops by more than a factor of 700. _Engineers weighing GraphRAG cost tradeoffs can track approaches like LazyGraphRAG on daily.dev._ ### Does GraphRAG reduce hallucination compared to standard RAG? Not on a per-claim basis. Microsoft's evaluations found GraphRAG's measured advantage lies in comprehensiveness, diversity, and supporting source material for global queries, but on faithfulness it scored at a similar level to baseline vector RAG, meaning the evidence supports better coverage and sourcing rather than higher factual accuracy per claim. _Teams evaluating RAG architectures for hallucination risk can follow findings like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@kartiknvj** · 0 upvotes > GraphRAG earns its keep on questions whose answer is spread across documents, where flat top-k just misses the connective tissue. I learned this the hard way when a PDF bot cited page 47 of a 30-page contract and the retriever was the actual bug: [https://medium.com/@kartik.nvj/my-pdf-qa-bot-cited-page-47-of-a-30-page-contract-the-retriever-was-the-bug-97fa17760424](https://medium.com/@kartik.nvj/my-pdf-qa-bot-cited-page-47-of-a-30-page-contract-the-retriever-was-the-bug-97fa17760424) . Once retrieval is the suspect, a graph makes the missing hop visible in a way a similarity score never does. ## Similar posts on daily.dev - [GraphRAG enables more context-aware and verifiable responses from LLMs](https://daily.dev/posts/graphrag-enables-more-context-aware-and-verifiable-responses-from-llms-z2aky0qtg) · SD Times · 1 upvotes · 0 comments - [Knowledge graph RAG: structured retrieval for AI agents](https://daily.dev/posts/knowledge-graph-rag-structured-retrieval-for-ai-agents-k6cymxiik) · Redis · 1 upvotes · 0 comments - [Navigating the Nuances of GraphRAG vs. RAG](https://daily.dev/posts/navigating-the-nuances-of-graphrag-vs-rag-e6vhvz3cd) · Foojay.io · 1 upvotes · 0 comments - [GraphRAG vs. Vector RAG: Side-by-side comparison guide](https://daily.dev/posts/graphrag-vs-vector-rag-side-by-side-comparison-guide-ljp41mq1n) · Meilisearch · 2 upvotes · 0 comments - [GraphRAG in Practice: How to Build Cost-Efficient, High-Recall Retrieval Systems](https://daily.dev/posts/graphrag-in-practice-how-to-build-cost-efficient-high-recall-retrieval-systems-fuq6fm64z) · Towards Data Science · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#rag](https://daily.dev/tags/rag), [#vector-search](https://daily.dev/tags/vector-search) [View this post on daily.dev](https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"GraphRAG: How AI Answers Questions Hidden Across Many Documents","url":"https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz"},"datePublished":"2026-08-19T15:34:36.880Z","dateModified":"2026-09-13T21:47:13.656Z","description":"GraphRAG addresses a gap in standard vector-based RAG: while similarity search handles local questions whose answers resemble the query and sit in a specific...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8d10a5c24d100a038d7a9bebec44a795?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8d10a5c24d100a038d7a9bebec44a795?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"ByteByteGo","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"ByteByteGo","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/35be29234ee14d01a9cd049c52e12753","url":"https://daily.dev/sources/bytebytego"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":7},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"llm,rag,vector-search","timeRequired":"PT16M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"ByteByteGo","item":"https://daily.dev/sources/bytebytego"},{"@type":"ListItem","position":3,"name":"GraphRAG: How AI Answers Questions Hidden Across Many Documents"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz","comment":[{"@type":"Comment","text":"GraphRAG earns its keep on questions whose answer is spread across documents, where flat top-k just misses the connective tissue. I learned this the hard way when a PDF bot cited page 47 of a 30-page contract and the retriever was the actual bug: https://medium.com/@kartik.nvj/my-pdf-qa-bot-cited-page-47-of-a-30-page-contract-the-retriever-was-the-bug-97fa17760424 . Once retrieval is the suspect, a graph makes the missing hop visible in a way a similarity score never does.","datePublished":"2026-08-19T18:59:44.677Z","url":"https://daily.dev/posts/y6pRjKnJz#c-8EXIHwvtM","author":{"@type":"Person","name":"kartik-nvjk","url":"https://daily.dev/kartiknvj","image":"https://media.daily.dev/image/upload/s--3gGgsVCw--/f_auto/v1781456774/avatars/avatar_TvTVeiMdkRCqWUDullFmy?_a=BAMAMiWQ0"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/graphrag-how-ai-answers-questions-hidden-across-many-documents-y6prjknjz#faq","mainEntity":[{"@type":"Question","name":"What is the difference between local search and global search in GraphRAG?","acceptedAnswer":{"@type":"Answer","text":"Local search matches a query against entity description embeddings, then expands along five parallel directions (text units, community reports, neighboring entities, relationships, and claims) before ranking results into one context window. Global search instead runs community reports from a chosen hierarchy level through a map stage that produces rated intermediate answers, then a reduce stage combines the highest-rated points into a final answer. Comparing retrieval architectures like GraphRAG gets easier with grounded technical breakdowns on daily.dev."}},{"@type":"Question","name":"How much cheaper is LazyGraphRAG than full GraphRAG for indexing?","acceptedAnswer":{"@type":"Answer","text":"LazyGraphRAG cuts indexing cost to roughly 0.1 percent of full GraphRAG by building its index with NLP instead of a language model and skipping summarization entirely, deferring all language model work to query time. Global-query answer quality stays comparable to standard global search, while per-query cost drops by more than a factor of 700. Engineers weighing GraphRAG cost tradeoffs can track approaches like LazyGraphRAG on daily.dev."}},{"@type":"Question","name":"Does GraphRAG reduce hallucination compared to standard RAG?","acceptedAnswer":{"@type":"Answer","text":"Not on a per-claim basis. Microsoft's evaluations found GraphRAG's measured advantage lies in comprehensiveness, diversity, and supporting source material for global queries, but on faithfulness it scored at a similar level to baseline vector RAG, meaning the evidence supports better coverage and sourcing rather than higher factual accuracy per claim. Teams evaluating RAG architectures for hallucination risk can follow findings like this on daily.dev."}}]} ```