Engram Admin icon

Engram Admin

Manage and administer the Engram knowledge graph

Actions19

Analysis → Detect Communities

AI-generated

Summary

Detects entity communities for a group using the selected graph backend, with an optional LLM-generated summary for each community.

Inputs

  • Backend — Select Embedded (Graphology) or Neo4j (Remote); defaults to Embedded. The custom storage path applies only to Embedded.
  • Group ID (required) — The group or session ID whose entities are analyzed.
  • Min Community Size — Minimum entity count for a community; defaults to 2, with a range of 2–100.
  • Generate Summaries — Enable LLM-generated natural-language summaries for communities; defaults to off and requires an Engram Extraction LLM credential.
  • Summary Model — Model name used for summaries when summary generation is enabled.
  • Summary Concurrency — Number of communities summarized concurrently when enabled; defaults to 3, with a range of 1–10.
  • Custom Storage Path — Custom directory for embedded graph data. Leave blank to use n8n's default storage directory; a custom directory must be writable by the n8n process.

Output shape

Not determinable from the provided source pack.

The source pack lists the detector and operation handler but omits their method bodies, so it does not show the returned fields or whether detection persists any changes.

Links

Discussion