Search Memory Node

S

AI/Memory

Search Memory

Searches the memory store using the configured recall strategy (recent, relevance, or hybrid)

memory_searchllmLong running

Inputs4

Outputs3

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.

4/10Medium

GovernancePolicy, audit, or compliance impact.

3/10High

ReliabilityOperational stability considerations.

2/10High

CostExternal or compute cost impact.

5/10Medium

Input Pins

4

Input

Execution

exec_in

Trigger

Memory Config

Struct

memory_config

MemoryConfig from Create Memory Config node

SchemaMemoryConfigMemoryConfigMemoryConfig7 fields

databaseNodeDBConnectionrequired

cache_keystringrequired

embedding_modelCachedEmbeddingModelrequired

cache_keystringrequired

model_typeBitTypesrequired

enum "Llm", "Vlm", "Tts", "Stt"...

max_context_tokensinteger:uint32required

format uint32min 0

recall_strategyRecallStrategyrequired

enum "RecentFirst", "Relevance", "Hybrid"

recall_top_kinteger:uint32required

format uint32min 0

auto_compressbooleanrequired

compress_thresholdinteger:uint32required

format uint32min 0

Schema enforced

Query

String

query

Search query text — used for vector similarity and/or full-text search

Role Filter

String

role_filter

Optional role filter (one of: user, assistant, observation, summary, context)

Output Pins

3

Done

Execution

exec_out

Fires when search completes

Results

Struct Array

results

Array of matching memory records (sorted by relevance/recency)

Result Count

Integer

result_count

Number of results returned

Node Info

Internal name

memory_search

Category

AI/Memory

Version

2