SelfManagedMemoryStrategy
- class aws_cdk.aws_bedrock_agentcore_alpha.SelfManagedMemoryStrategy(strategy_type, *, invocation_configuration, historical_context_window_size=None, trigger_conditions=None, name, description=None)
Bases:
object(experimental) Use AgentCore memory for event storage with custom triggers.
Define memory processing logic in your own environment.
- Stability:
experimental
- ExampleMetadata:
fixture=default infused
Example:
bucket = s3.Bucket(self, "memoryBucket", bucket_name="test-memory", removal_policy=cdk.RemovalPolicy.DESTROY, auto_delete_objects=True ) topic = sns.Topic(self, "topic") # Create a custom semantic memory strategy self_managed_strategy = agentcore.MemoryStrategy.using_self_managed( name="selfManagedStrategy", description="self managed memory strategy", historical_context_window_size=5, invocation_configuration=agentcore.InvocationConfiguration( topic=topic, s3_location=s3.Location( bucket_name=bucket.bucket_name, object_key="memory/" ) ), trigger_conditions=agentcore.TriggerConditions( message_based_trigger=1, time_based_trigger=cdk.Duration.seconds(10), token_based_trigger=100 ) ) # Create memory with custom strategy memory = agentcore.Memory(self, "MyMemory", memory_name="my-custom-memory", description="Memory with custom strategy", expiration_duration=cdk.Duration.days(90), memory_strategies=[self_managed_strategy] )
- Parameters:
strategy_type (
MemoryStrategyType) – The type of memory strategy.invocation_configuration (
Union[InvocationConfiguration,Dict[str,Any]]) – (experimental) Invocation configuration for self managed memory strategy.historical_context_window_size (
Union[int,float,None]) – (experimental) Define the number of previous events to be included when processing memory. A larger history window provides more context from past conversations. Default: - 4trigger_conditions (
Union[TriggerConditions,Dict[str,Any],None]) – (experimental) Trigger conditions for self managed memory strategy. Default: - undefinedname (
str) – (experimental) The name for the strategy.description (
Optional[str]) – (experimental) The description of the strategy. Default: No description
- Stability:
experimental
Methods
- grant(grantee)
(experimental) Grants the necessary permissions to the role.
- Parameters:
grantee (
IGrantable) –The grantee to grant permissions to.
- Return type:
Optional[Grant]- Returns:
The Grant object for chaining
- Stability:
experimental
- render()
(experimental) Renders internal attributes to CloudFormation.
- Stability:
experimental
- Return type:
Attributes
- description
(experimental) The description of the memory strategy.
- Stability:
experimental
- historical_context_window_size
(experimental) Historical context window size for self managed memory strategy.
- Stability:
experimental
- invocation_configuration
(experimental) Invocation configuration for self managed memory strategy.
- Stability:
experimental
- name
(experimental) The name of the memory strategy.
- Stability:
experimental
- strategy_type
(experimental) The type of memory strategy.
- Stability:
experimental
- trigger_conditions
(experimental) Trigger conditions for self managed memory strategy.
- Stability:
experimental