Skip to content

KG Summarize Node

AI/Memory/Graph

KG Summarize

Converts a subgraph (nodes + edges) into a natural-language summary for LLM consumption

kg_summarizellm
Inputs5
Outputs4
Security exposure2/10
Packagellm

Ratings

Scores range from 0 to 10. Higher values mean more impact, exposure, or operational weight.

SecurityAttack surface and exposure impact.
2/10High
PrivacyPotential sensitivity of processed data.
4/10Medium
PerformanceRuntime or resource pressure.
2/10High
GovernancePolicy, audit, or compliance impact.
3/10High
ReliabilityOperational stability considerations.
1/10High
CostExternal or compute cost impact.
9/10Low

Input Pins

5

Input

Execution
exec_in

Trigger

Graph Connection

Struct
graph

Graph connection reference (for label metadata)

NodeGraphConnectionNodeGraphConnection1 fields
cache_keystringrequired
Schema enforced

Subgraph

Struct
subgraph

Subgraph payload (output from KG Retrieve, Neighbors, or Subgraph nodes)

Max Tokens

Integer
max_tokens

Approximate maximum token budget for the summary (controls verbosity)

Default 500

Include Properties

Boolean
include_properties

Whether to include node/edge properties in the summary

Default true

Output Pins

4

Done

Execution
exec_out

Fires when summarization completes

Summary

String
summary

Natural-language summary of the subgraph

Node Count

Integer
node_count

Number of nodes in the input subgraph

Edge Count

Integer
edge_count

Number of edges in the input subgraph

Node Info

Internal name
kg_summarize
Category
AI/Memory/Graph