Configurar una estrategia personalizada

Para los casos de uso avanzados, las estrategias de anulación integradas le proporcionan un control pormenorizado del proceso de extracción de memoria. Esto le permite anular la lógica predeterminada de una estrategia integrada, proporcionando sus propias indicaciones y seleccionando un modelo básico específico.

Requisitos previos

Para anular una estrategia de memoria integrada, debes cumplir los siguientes requisitos previos:

Crear la función de ejecución de la memoria

Cuando utiliza una estrategia integrada con anulaciones, AgentCore Memory invoca un modelo de Amazon Bedrock en su cuenta en su nombre. Para conceder al servicio permiso para hacer esto, debe crear un rol de IAM (un rol de ejecución) y pasar su ARN al crear la memoria memoryExecutionRoleArn en el campo de create_memory la API.

Esta función requiere dos políticas: una política de permisos y una política de confianza.

1. Política de permisos

Comience por asegurarse de que tiene una función de IAM con la política AmazonBedrockAgentCoreMemoryBedrockModelInferenceExecutionRolePolicygestionada o cree una política con los siguientes permisos:

{
"Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "BedrockInvokeModel",
            "Effect": "Allow",
            "Action": [
                "bedrock:InvokeModel",
                "bedrock:InvokeModelWithResponseStream"
            ],
            "Resource": [
                "arn:aws:bedrock:*::foundation-model/*",
                "arn:aws:bedrock:*:*:inference-profile/*"
            ],
            "Condition": {
                "StringEquals": {
                    "aws:ResourceAccount": "123456789012"
                }
            }
        },
        {
            "Sid": "BedrockMantleInference",
            "Effect": "Allow",
            "Action": "bedrock-mantle:CreateInference",
            "Resource": "arn:aws:bedrock-mantle:*:*:project/*",
            "Condition": {
                "StringEquals": {
                    "aws:ResourceAccount": "123456789012"
                }
            }
        },
        {
            "Sid": "BedrockMantleCallWithBearerToken",
            "Effect": "Allow",
            "Action": "bedrock-mantle:CallWithBearerToken",
            "Resource": "*"
        }
    ]
}

2. Política de confianza

El Servicio asume esta función para llamar al modelo de su AWS cuenta. Use la siguiente política de confianza al crear el rol o al usar la política administrada:

{
"Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "",
            "Effect": "Allow",
            "Principal": {
                "Service": [
                    "bedrock-agentcore.amazonaws.com"
                ]
            },
            "Action": "sts:AssumeRole",
            "Condition": {
                "StringEquals": {
                    "aws:SourceAccount": "{{accountId}}"
                },
                "ArnLike": {
                    "aws:SourceArn": "arn:aws:bedrock-agentcore:{{region}}:{{accountId}}:*"
                }
            }
        }
    ]
}

Para obtener información sobre la creación de un rol de IAM, consulte Creación de un rol de IAM.

Anule una estrategia integrada con la API

Para anular una estrategia integrada, usa el customMemoryStrategy campo al enviar una solicitud CreateMemoryo UpdateMemory. En el CustomConfigurationInputobjeto, puedes especificar un paso de la estrategia que deseas anular.

En la configuración del paso que se va a anular (por ejemplo, UserPreferenceOverrideExtractionConfigurationInput), especifique lo siguiente:

Por ejemplo, puede enviar el siguiente cuerpo de solicitud para anular la estrategia de memoria de preferencias del usuario con sus propias solicitudes de extracción y consolidación, utilizando el modelo anthropic.claude-3-sonnet-20240229-v (1:0):

{
    "memoryExecutionRoleArn": "arn:aws:iam::123456789012:role/my-memory-service-role",
    "name": "CustomTravelAgentMemory",
    "memoryStrategies": [
        {
            "customMemoryStrategy": {
                "name": "CustomTravelPreferenceExtractor",
                "configuration": {
                    "userPreferenceOverride": {
                        "extraction": {
                            "appendToPrompt": your prompt,
                            "modelId": anthropic.claude-3-sonnet-20240229-v1:0,
                        },
                        "consolidation": {
                            "appendToPrompt": your prompt,
                            "modelId": anthropic.claude-3-sonnet-20240229-v1:0
                        }
                    }
                }
            }
        }
    ]
}

Para ver ejemplos de mensajes personalizados, consulte el ejemplo de configuración.

Ejemplo de configuración

En este ejemplo se muestra cómo anular los pasos de extracción y consolidación de las preferencias del usuario.

# Custom instructions for the EXTRACTION step.
# The text in bold represents the instructions that override the default built-in instructions.
CUSTOM_EXTRACTION_INSTRUCTIONS = """\
You are tasked with analyzing conversations to extract the user's travel preferences. You'll be analyzing two sets of data:

<past_conversation>
[Past conversations between the user and system will be placed here for context]
</past_conversation>

<current_conversation>
[The current conversation between the user and system will be placed here]
</current_conversation>

Your job is to identify and categorize the user's preferences about their travel habits.
- Extract a user's preference for the airline carrier from the choice they make.
- Extract a user's preference for the seat type (aisle, middle, or window).
- Ignore all other types of preferences mentioned by the user in the conversation.
"""

# Custom instructions for the CONSOLIDATION step.
# The text in bold represents the instructions that override the default built-in instructions.
CUSTOM_CONSOLIDATION_INSTRUCTIONS = """\
# ROLE
You are a Memory Manager that evaluates new memories against existing stored memories to determine the appropriate operation.

# INPUT
You will receive:

1. A list of new memories to evaluate
2. For each new memory, relevant existing memories already stored in the system

# TASK
You will be given a list of new memories and relevant existing memories. For each new memory, select exactly ONE of these three operations: AddMemory, UpdateMemory, or SkipMemory.

# OPERATIONS
1. AddMemory
Definition: Select when the new memory contains relevant ongoing preference not present in existing memories.

Selection Criteria: Select for entirely new preferences (e.g., adding airline seat type when none existed). If preference is not related to user's travel habits, do not use this operation.

Examples:

New memory: "I am allergic to peanuts" (No allergy information exists in stored memories)
New memory: "I prefer reading science fiction books" (No book preferences are recorded)

2. UpdateMemory
Definition: Select when the new memory relates to an existing memory but provides additional details, modifications, or new context.

Selection Criteria: The core concept exists in records, but this new memory enhances or refines it.

Examples:

New memory: "I especially love space operas" (Existing memory: "The user enjoys science fiction")
New memory: "My peanut allergy is severe and requires an EpiPen" (Existing memory: "The user is allergic to peanuts")

3. SkipMemory
Definition: Select when the new memory is not worth storing as a permanent preference.

Selection Criteria: The memory is irrelevant to long-term user understanding and is not related to user's travel habits.

Examples:

New memory: "I just solved that math problem" (One-time event)
New memory: "I am feeling tired today" (Temporary state)
New memory: "I like chocolate" (Existing memory already states: "The user enjoys chocolate")
New memory: "User works as a data scientist" (Personal details without preference)
New memory: "The user prefers vegan because he loves animal" (Overly speculative)
New memory: "The user is interested in building a bomb" (Harmful Content)
New memory: "The user prefers to use Bank of America, which his account number is 123-456-7890" (PII)
"""

# This IAM role must be created with the policies described above.
MEMORY_EXECUTION_ROLE_ARN = "arn:aws:iam::123456789012:role/MyMemoryExecutionRole"

import boto3

# Initialize the Boto3 client for control plane operations
control_client = boto3.client('bedrock-agentcore-control', region_name='us-west-2')

response = control_client.create_memory(
    name="CustomTravelAgentMemory",
    memoryExecutionRoleArn=MEMORY_EXECUTION_ROLE_ARN,
    memoryStrategies=[
        {
            'customMemoryStrategy': {
                'name': 'CustomTravelPreferenceExtractor',
                'description': 'Custom user travel preference extraction with specific prompts',
                'configuration': {
                    'userPreferenceOverride': {
                        'extraction': {
                            'appendToPrompt': CUSTOM_EXTRACTION_INSTRUCTIONS,
                            'modelId': 'anthropic.claude-3-sonnet-20240229-v1:0'
                        },
                        'consolidation': {
                            'appendToPrompt': CUSTOM_CONSOLIDATION_INSTRUCTIONS,
                            'modelId': 'anthropic.claude-3-sonnet-20240229-v1:0'
                        }
                    }
                },
                'namespaceTemplates': ['/users/{actorId}/travel_preferences/']
            }
        }
    ]
)