KG Retrieve Node

K

AI/Memory/Graph

KG Retrieve

Retrieves context from a knowledge graph: embeds the query, finds matching nodes, then expands N hops to build structured context

kg_retrievellmLong running

Inputs7

Outputs6

Security exposure3/10

Packagellm

Ratings

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

SecurityAttack surface and exposure impact.

3/10High

PrivacyPotential sensitivity of processed data.

4/10Medium

PerformanceRuntime or resource pressure.

5/10Medium

GovernancePolicy, audit, or compliance impact.

3/10High

ReliabilityOperational stability considerations.

3/10High

CostExternal or compute cost impact.

5/10Medium

Input Pins

7

Input

Execution

exec_in

Trigger

Graph Connection

Struct

graph

Graph connection from Open Graph Overlay node

SchemaNodeGraphConnectionNodeGraphConnectionNodeGraphConnection1 fields

cache_keystringrequired

Schema enforced

Query

String

query

Natural language query to search for in the graph

Node Label

String

node_label

Label of the node type to search (must have a vector column)

Depth

Integer

depth

Number of hops to expand from matched nodes

Default 1

Top K

Integer

top_k

Number of seed nodes to retrieve via embedding search

Default 5

Result Limit

Integer

limit

Maximum total nodes + edges in the expanded subgraph

Default 200

Output Pins

6

Done

Execution

exec_out

Fires when retrieval completes

Error

Execution

error

Fires on failure

Error Message

String

error_message

Error details

Context

Struct

context

Structured subgraph context as JSON (nodes + edges + properties)

Summary Text

String

summary_text

Flattened text representation of the retrieved subgraph for LLM consumption

Node Count

Integer

node_count

Number of nodes in the result

Node Info

Internal name

kg_retrieve

Category

AI/Memory/Graph