This post explores the 'From Local to Global' GraphRAG approach, combining text extraction, network analysis, and LLM summarization for improved Retrieval-Augmented Generation (RAG) over graphs. It details the process of constructing a knowledge graph from documents using Neo4j and LangChain, including entity extraction,

32m read timeFrom medium.com
Post cover image
Table of contents
Combine text extraction, network analysis, and LLM prompting and summarization for improved RAG accuracyIndexing — Graph GenerationRetrieval — Answeringblogs/llm/ms_graphrag.ipynb at master · tomasonjo/blogsSetting Up the Neo4j EnvironmentDatasetText ChunkingExtracting Nodes and RelationshipsEntity ResolutionElement SummarizationConstructing and Summarizing CommunitiesSummaryblogs/llm/ms_graphrag.ipynb at master · tomasonjo/blogsGraph Algorithms for Data Science
1 Comment

Sort: