DataArticle

GraphRAG has higher indexing cost (due to two LLM passes for extraction and merging) than standard RAG, but Microsoft's LazyGraphRAG variant reduces this cost to 0.1% by using NLP for indexing and deferring LLM work to query time.

GraphRAG's main cost is upfront indexing, which involves multiple LLM passes. A variant called LazyGraphRAG dramatically cuts this cost by simplifying indexing and doing more work at query time. ✦ AI generated

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

Share card ↓Export .md Export .txt

GraphRAG indexing runs two language model passes over the corpus... Graph extraction accounts for roughly 75 percent of indexing cost... LazyGraphRAG builds its index using NLP rather than a language model, skips summarization entirely, and defers all language model work to query time. In this case, indexing cost matches vector RAG and lands at 0.1 percent of full GraphRAG.

Read full article ↗excerpt · fair-use quotation

▦ Microsoft ✳ indexing cost ✳ LazyGraphRAG

Around this claim

Context · 1

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 70%

This moment responds to

gives example → Making trade-offs explicit so customers choose them in advance is far better than cutting costs and imposing the outcome on them without their knowledge.Rory Sutherland · My First Million