Optimize Memory Node

O

AI/Memory

Optimize Memory

Runs LanceDB maintenance on the memory table: flush buffered writes, compact fragments, prune old versions, and rebuild indices. Run periodically or after bulk writes.

memory_optimizellmLong running

Inputs3

Outputs1

Security exposure0/10

Packagellm

Ratings

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

SecurityAttack surface and exposure impact.

0/10High

PrivacyPotential sensitivity of processed data.

0/10High

PerformanceRuntime or resource pressure.

6/10Medium

GovernancePolicy, audit, or compliance impact.

0/10High

ReliabilityOperational stability considerations.

2/10High

CostExternal or compute cost impact.

0/10High

Input Pins

3

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

Keep Versions

Boolean

keep_versions

Whether to keep old row versions (false = prune for disk savings)

Default false

Output Pins

1

Done

Execution

exec_out

Fires when optimization completes

Node Info

Internal name

memory_optimize

Category

AI/Memory

Version

1