liveBook · Manning

Community

A graph community is a group of nodes that are more densely connected to one another than to nodes outside the group.

How 5 Manning books explain it

Graph Algorithms for Data Science

Community structure is the organization of a graph into groups of nodes with comparatively dense internal connections.

How it is used
Uses community detection to characterize networks, find tightly connected users, and support recommendations or marketing segmentation.
How deep it goes
Defines communities through connection density and demonstrates detection on social and hashtag co-occurrence networks without detailing algorithm internals.
Examples
Uses social-platform users, an eight-person friendship network, and tweet hashtags transformed into a co-occurrence network.
What you can do after
Apply it via Neo4j Graph Data Science algorithms to identify tightly connected groups and interpret them for analysis or targeting.

Read how Graph Algorithms for Data Science explains community →

Domain-Specific Small Language Models

A group of graph nodes that are more densely connected to each other than to the rest of the graph.

How it is used
Groups related nodes for graph summarization and query-time answer generation.
How deep it goes
Defines the term and shows how GraphRAG detects, summarizes, and reuses communities, but stops short of full community-detection theory.
Examples
Uses a movie-database graph and the GraphRAG workflow diagram as teaching examples.
What you can do after
Evaluate and apply community summaries to improve question answering over a knowledge graph.

Read how Domain-Specific Small Language Models explains community →

Financial AI in Practice

A group of graph nodes more densely connected to one another than to the rest of the graph.

How it is used
Uses communities to identify potentially coordinated accounts and shared resources in fraud investigations.
How deep it goes
Explains partitioning and community analysis through size, density, entity counts, and visualization, without detailing Louvain’s internals.
Examples
Examines detected communities containing users, IPs, devices, phones, and cards, including a visualization of the largest group.
What you can do after
Evaluate detected communities using structural measures and visual inspection to prioritize potentially suspicious groups.

Read how Financial AI in Practice explains community →

Essential GraphRAG

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

How it is used
Organizes graph entities into summarized groups for global and local GraphRAG retrieval.
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 you can do after
Operate/configure Louvain detection, persist community assignments, generate summaries, and retrieve community-level information.

Read how Essential GraphRAG explains community →

Retrieval Augmented Generation, The Foundational Ideas

A graph community is a group of nodes identified as more strongly or densely connected to one another than to the rest of the graph.

How it is used
Supports global summarization in GraphRAG by clustering related graph nodes before retrieval.
How deep it goes
Explains density, Leiden partitioning, modularity optimization, hierarchy, and identifier recovery, but not community-quality evaluation.
Examples
Uses vendor-dispute themes and a Leiden-based Python implementation as concrete examples.
What you can do after
Build it from scratch with NetworkX, igraph, and leidenalg, then store node memberships for GraphRAG summarization.

Read how Retrieval Augmented Generation, The Foundational Ideas explains community →

Also covered in

What to know first

Related concepts

Questions about community

What is community?

A graph community is a group of nodes that are more densely connected to one another than to nodes outside the group.

Which Manning books explain community?

Graph Algorithms for Data Science, Domain-Specific Small Language Models, Financial AI in Practice, Essential GraphRAG and Retrieval Augmented Generation, The Foundational Ideas.

What should I know before learning community?

Manning books that teach community usually introduce Leiden algorithm, Louvain algorithm, modularity and edge first.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.