ManagedMemoryStrategy

class aws_cdk.aws_bedrock_agentcore_alpha.ManagedMemoryStrategy(strategy_type, *, namespaces, custom_consolidation=None, custom_extraction=None, reflection_configuration=None, name, description=None)

Bases: object

(experimental) Managed memory strategy that handles both built-in and override configurations.

This strategy can be used for quick setup with built-in defaults or customized with specific models and prompt templates.

Stability:: experimental
ExampleMetadata:: fixture=_generated

Example:

# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
import aws_cdk.aws_bedrock_agentcore_alpha as bedrock_agentcore_alpha
import aws_cdk.aws_bedrock_alpha as bedrock_alpha

# bedrock_invokable: bedrock_alpha.IBedrockInvokable

managed_memory_strategy = bedrock_agentcore_alpha.ManagedMemoryStrategy(bedrock_agentcore_alpha.MemoryStrategyType.SUMMARIZATION,
    name="name",
    namespaces=["namespaces"],

    # the properties below are optional
    custom_consolidation=bedrock_agentcore_alpha.OverrideConfig(
        append_to_prompt="appendToPrompt",
        model=bedrock_invokable
    ),
    custom_extraction=bedrock_agentcore_alpha.OverrideConfig(
        append_to_prompt="appendToPrompt",
        model=bedrock_invokable
    ),
    description="description",
    reflection_configuration=bedrock_agentcore_alpha.EpisodicReflectionConfiguration(
        namespaces=["namespaces"]
    )
)

(experimental) Constructor to create a new managed memory strategy.

Parameters:

strategy_type (MemoryStrategyType) – the strategy type.
namespaces (Sequence[str]) – (experimental) The namespaces for the strategy Represents a namespace for organizing memory data Use a hierarchical format separated by forward slashes (/). Use a hierarchical format separated by forward slashes (/) to organize namespaces logically. You can include these defined variables: - {sessionId} - the user identifier to be created in the CreateEvent API - {memoryStrategyId} - an identifier for an extraction strategy - {sessionId} - an identifier for each session Example namespace path: /strategies/{memoryStrategyId}/actions/{actionId}/sessions/{sessionId} After memory creation, this namespace might look like: /actor/actor-3afc5aa8fef9/strategy/summarization-fy5c5fwc7/session/session-qj7tpd1kvr8
custom_consolidation (Union[OverrideConfig, Dict[str, Any], None]) – (experimental) The configuration for the custom consolidation. This configuration provides customization to how the model identifies and extracts relevant information for memory storage. Default: - No custom extraction
custom_extraction (Union[OverrideConfig, Dict[str, Any], None]) – (experimental) The configuration for the custom extraction. This configuration provides customization to how the model identifies and extracts relevant information for memory storage. Default: - No custom extraction
reflection_configuration (Union[EpisodicReflectionConfiguration, Dict[str, Any], None]) – (experimental) Configuration for episodic memory reflection (only applicable for EPISODIC strategy type) Defines additional namespaces for reflection-based episodic recall. Default: - No reflection configuration
name (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.

[disable-awslint:no-grants]

Parameters:

grantee (IGrantable) –

The grantee to grant permissions to.

Return type:

Optional[Grant]

Returns:

The Grant object for chaining

Stability:

experimental

render()

(experimental) Renders the network configuration as a CloudFormation property.

Return type:: MemoryStrategyProperty
Returns:: The CloudFormation property for the memory strategy.
Stability:: experimental

Attributes

consolidation_override

(experimental) The configuration for the custom consolidation.

Stability:: experimental

description

(experimental) The description of the memory strategy.

Stability:: experimental

extraction_override

(experimental) The configuration for the custom extraction.

Stability:: experimental

name

(experimental) The name of the memory strategy.

Stability:: experimental

namespaces

(experimental) The namespaces for the strategy.

Stability:: experimental

reflection_configuration

(experimental) The configuration for episodic reflection.

Stability:: experimental

strategy_type

(experimental) The type of memory strategy.

Stability:: experimental