Class: AWSCDK::BedrockAgentCore::MemoryStrategy

Inherits:
Jsii::Object
  • Object
show all
Defined in:
bedrock_agent_core/memory_strategy.rb

Overview

Factory class for creating memory strategies If you need long-term memory for context recall across sessions, you can setup memory extraction strategies to extract the relevant memory from the raw events.

Use built-in strategies for quick setup, use built-in strategies with override to specify models and prompt templates.

See Also:

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ MemoryStrategy

Returns a new instance of MemoryStrategy.



12
13
14
 
# File 'bedrock_agent_core/memory_strategy.rb', line 12

def initialize
  Jsii::Object.instance_method(:initialize).bind(self).call
end

Class Method Details

.jsii_overridable_methods ⇒ Object 



16
17
18
19
 
# File 'bedrock_agent_core/memory_strategy.rb', line 16

def self.jsii_overridable_methods
  {
  }
end

.using_built_in_episodic ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Default strategies for organizing and extracting memory data, each optimized for specific use cases.

Captures meaningful slices of user and system interactions, preserve them into compact records after summarizing. Extracted memory example: User first asked about pricing on Monday, then requested feature comparison on Tuesday, finally made purchase decision on Wednesday.

Returns:



27
28
29
 
# File 'bedrock_agent_core/memory_strategy.rb', line 27

def self.using_built_in_episodic()
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingBuiltInEpisodic", [])
end

.using_built_in_semantic ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Default strategies for organizing and extracting memory data, each optimized for specific use cases.

Distills general facts, concepts, and underlying meanings from raw conversational data, presenting the information in a context-independent format. Extracted memory example: In-context learning = task-solving via examples, no training needed.

Returns:



37
38
39
 
# File 'bedrock_agent_core/memory_strategy.rb', line 37

def self.using_built_in_semantic()
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingBuiltInSemantic", [])
end

.using_built_in_summarization ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Default strategies for organizing and extracting memory data, each optimized for specific use cases.

This strategy compresses conversations into concise overviews, preserving essential context and key insights for quick recall. Extracted memory example: Users confused by cloud setup during onboarding.

Returns:



47
48
49
 
# File 'bedrock_agent_core/memory_strategy.rb', line 47

def self.using_built_in_summarization()
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingBuiltInSummarization", [])
end

.using_built_in_user_preference ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Default strategies for organizing and extracting memory data, each optimized for specific use cases.

Captures individual preferences, interaction patterns, and personalized settings to enhance future experiences. Extracted memory example: User needs clear guidance on cloud storage account connection during onboarding.

Returns:



57
58
59
 
# File 'bedrock_agent_core/memory_strategy.rb', line 57

def self.using_built_in_user_preference()
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingBuiltInUserPreference", [])
end

.using_episodic(config) ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Creates an episodic memory strategy with custom configuration.

Captures meaningful slices of user and system interactions, preserve them into compact records after summarizing. Extracted memory example: User first asked about pricing on Monday, then requested feature comparison on Tuesday, finally made purchase decision on Wednesday.

Parameters:

Returns:



68
69
70
71
72
 
# File 'bedrock_agent_core/memory_strategy.rb', line 68

def self.using_episodic(config)
  config = config.is_a?(Hash) ? ::AWSCDK::BedrockAgentCore::ManagedStrategyProps.new(**config.transform_keys(&:to_sym)) : config
  Jsii::Type.check_type(config, JSON.parse(Base64.strict_decode64("eyJmcW4iOiJhd3MtY2RrLWxpYi5hd3NfYmVkcm9ja2FnZW50Y29yZS5NYW5hZ2VkU3RyYXRlZ3lQcm9wcyJ9")), "config")
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingEpisodic", [config])
end

.using_self_managed(config) ⇒ AWSCDK::BedrockAgentCore::SelfManagedMemoryStrategy

Creates a self-managed memory strategy.

A self-managed strategy gives you complete control over your memory extraction and consolidation pipelines.

Parameters:

Returns:



80
81
82
83
84
 
# File 'bedrock_agent_core/memory_strategy.rb', line 80

def self.using_self_managed(config)
  config = config.is_a?(Hash) ? ::AWSCDK::BedrockAgentCore::SelfManagedStrategyProps.new(**config.transform_keys(&:to_sym)) : config
  Jsii::Type.check_type(config, JSON.parse(Base64.strict_decode64("eyJmcW4iOiJhd3MtY2RrLWxpYi5hd3NfYmVkcm9ja2FnZW50Y29yZS5TZWxmTWFuYWdlZFN0cmF0ZWd5UHJvcHMifQ==")), "config")
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingSelfManaged", [config])
end

.using_semantic(config) ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Creates a semantic memory strategy with custom configuration.

Distills general facts, concepts, and underlying meanings from raw conversational data, presenting the information in a context-independent format. Extracted memory example: In-context learning = task-solving via examples, no training needed.

Parameters:

Returns:



93
94
95
96
97
 
# File 'bedrock_agent_core/memory_strategy.rb', line 93

def self.using_semantic(config)
  config = config.is_a?(Hash) ? ::AWSCDK::BedrockAgentCore::ManagedStrategyProps.new(**config.transform_keys(&:to_sym)) : config
  Jsii::Type.check_type(config, JSON.parse(Base64.strict_decode64("eyJmcW4iOiJhd3MtY2RrLWxpYi5hd3NfYmVkcm9ja2FnZW50Y29yZS5NYW5hZ2VkU3RyYXRlZ3lQcm9wcyJ9")), "config")
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingSemantic", [config])
end

.using_summarization(config) ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Creates a summarization memory strategy with custom configuration.

This strategy compresses conversations into concise overviews, preserving essential context and key insights for quick recall. Extracted memory example: Users confused by cloud setup during onboarding.

Parameters:

Returns:



106
107
108
109
110
 
# File 'bedrock_agent_core/memory_strategy.rb', line 106

def self.using_summarization(config)
  config = config.is_a?(Hash) ? ::AWSCDK::BedrockAgentCore::ManagedStrategyProps.new(**config.transform_keys(&:to_sym)) : config
  Jsii::Type.check_type(config, JSON.parse(Base64.strict_decode64("eyJmcW4iOiJhd3MtY2RrLWxpYi5hd3NfYmVkcm9ja2FnZW50Y29yZS5NYW5hZ2VkU3RyYXRlZ3lQcm9wcyJ9")), "config")
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingSummarization", [config])
end

.using_user_preference(config) ⇒ AWSCDK::BedrockAgentCore::ManagedMemoryStrategy

Creates a user preference memory strategy with custom configuration.

Captures individual preferences, interaction patterns, and personalized settings to enhance future experiences. Extracted memory example: User needs clear guidance on cloud storage account connection during onboarding.

Parameters:

Returns:



119
120
121
122
123
 
# File 'bedrock_agent_core/memory_strategy.rb', line 119

def self.using_user_preference(config)
  config = config.is_a?(Hash) ? ::AWSCDK::BedrockAgentCore::ManagedStrategyProps.new(**config.transform_keys(&:to_sym)) : config
  Jsii::Type.check_type(config, JSON.parse(Base64.strict_decode64("eyJmcW4iOiJhd3MtY2RrLWxpYi5hd3NfYmVkcm9ja2FnZW50Y29yZS5NYW5hZ2VkU3RyYXRlZ3lQcm9wcyJ9")), "config")
  Jsii::Kernel.instance.call_static("aws-cdk-lib.aws_bedrockagentcore.MemoryStrategy", "usingUserPreference", [config])
end