Community

As explained in Essential GraphRAG

A graph community is a group of graph entities that is more densely connected internally than to the rest of the graph.

A community is a group of graph entities with denser internal connections than connections to the rest of the graph. Detecting communities reveals themes, groups, and higher-level relationships that individual entity links may miss. section 7.2.4

Use communities in a GraphRAG indexing and retrieval workflow:

• Apply the Louvain algorithm to identify densely connected groups and store each community as a node property. section 7.2.4
• Generate a domain-specific summary from each community’s nodes and relationships, then persist the summary for downstream retrieval. section 7.2.4
• Use community-, entity-, and relationship-level summaries to support global and local search in RAG applications. section 7.0

Narrative communities

In a narrative such as The Odyssey, a community might group characters involved in a particular event or location. A small graph run detected nine communities ranging from two to thirteen nodes; results can vary because Louvain is nondeterministic. section 7.2.4

Figure 7.1 Microsoft’s GraphRAG pipeline. (Image from Edge et al., 2024, licensed under CC BY 4.0)

Trace the pipeline from entity and relationship extraction through community detection, summarization, and retrieval. section 7.0

How Essential GraphRAG covers it

How deep it goes

Explains density, Louvain implementation, persistence, variability, and summarization while deferring hierarchical detection for larger graphs.

Examples

Uses The Odyssey, a nine-community graph run, figures, and Neo4j listings for detection and summary retrieval.

What it assumes

Assumes an extracted knowledge graph of entities and relationships, then builds community processing on top of it.

What you can do after

Operate/configure Louvain detection, persist community assignments, generate summaries, and retrieve community-level information.

How it connects

Connects knowledge graphs, entities, relationships, Louvain, Leiden, community summaries, and global and local search.

liveBookmanning.com

Read Essential GraphRAG on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Graph Algorithms for Data ScienceCommunity structure is the organization of a graph into groups of nodes with comparatively dense internal connections.
• 

  liveBookmanning.com
  Domain-Specific Small Language ModelsA group of graph nodes that are more densely connected to each other than to the rest of the graph.
• 

  liveBookmanning.com
  Financial AI in PracticeA group of graph nodes more densely connected to one another than to the rest of the graph.

Compare how 4 books explain community →

Related concepts

• graph densitymeasured by · Graph density is the proportion of possible edges between a graph’s nodes that are present.
• PageRankused by · PageRank is a link-analysis algorithm that estimates the relative importance of nodes in a directed graph from the structure and importance of incoming links.
• graph analyticsused by · Graph analytics is the analysis of entities and their relationships represented as a graph to identify patterns, properties, or predictive signals in its structure.
• community summarizationused by · Community summarization is the production of concise summaries describing groups of closely related entities, content, and relationships in a knowledge graph.
• label propagationproduced by · Label propagation is a graph-learning technique that iteratively propagates node labels through connections to assign labels or identify communities.
• graph clustering methodproduced by · A graph clustering method groups vertices into clusters based on their connectivity, structural patterns, or related attributes.

This explainer was generated by Manning's knowledge graph from the text of Essential GraphRAG. The section links point to the parts of the book it draws on.