Strands Agents SDK

Utilizza l'SDK Strands Agents per una perfetta integrazione con i framework degli agenti, fornendo la gestione e il recupero automatici della memoria all'interno degli agenti conversazionali.

Innanzitutto, crea una memoria con tutte e tre le strategie a lungo termine. Puoi farlo con la AgentCore CLI o tramite il codice SDK negli esempi seguenti.

Installare le dipendenze

pip install bedrock-agentcore
pip install strands-agents

Aggiungi memoria a breve termine

from datetime import datetime
from strands import Agent
from bedrock_agentcore.memory import MemoryClient
from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig, RetrievalConfig
from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager

client = MemoryClient(region_name="us-east-1")
basic_memory = client.create_memory(
    name="BasicTestMemory",
    description="Basic memory for testing short-term functionality"
)

MEM_ID = basic_memory.get('id')
ACTOR_ID = "actor_id_test_%s" % datetime.now().strftime("%Y%m%d%H%M%S")
SESSION_ID = "testing_session_id_%s" % datetime.now().strftime("%Y%m%d%H%M%S")

# Configure memory
agentcore_memory_config = AgentCoreMemoryConfig(
    memory_id=MEM_ID,
    session_id=SESSION_ID,
    actor_id=ACTOR_ID
)

# Create session manager
session_manager = AgentCoreMemorySessionManager(
    agentcore_memory_config=agentcore_memory_config,
    region_name="us-east-1"
)

# Create agent
agent = Agent(
    system_prompt="You are a helpful assistant. Use all you know about the user to provide helpful responses.",
    session_manager=session_manager,
)

agent("I like sushi with tuna")
# Agent remembers this preference

agent("I like pizza")
# Agent acknowledges both preferences

agent("What should I buy for lunch today?")
# Agent suggests options based on remembered preferences

Aggiungi memoria a lungo termine con strategie

from bedrock_agentcore.memory import MemoryClient
from strands import Agent
from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig, RetrievalConfig
from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager
from datetime import datetime

# Create comprehensive memory with all built-in strategies
client = MemoryClient(region_name="us-east-1")
comprehensive_memory = client.create_memory_and_wait(
    name="ComprehensiveAgentMemory",
    description="Full-featured memory with all built-in strategies",
    strategies=[
        {
            "summaryMemoryStrategy": {
                "name": "SessionSummarizer",
                "namespaceTemplates": ["/summaries/{actorId}/{sessionId}/"]
            }
        },
        {
            "userPreferenceMemoryStrategy": {
                "name": "PreferenceLearner",
                "namespaceTemplates": ["/preferences/{actorId}/"]
            }
        },
        {
            "semanticMemoryStrategy": {
                "name": "FactExtractor",
                "namespaceTemplates": ["/facts/{actorId}/"]
            }
        }
    ]
)

MEM_ID = comprehensive_memory.get('id')
ACTOR_ID = "actor_id_test_%s" % datetime.now().strftime("%Y%m%d%H%M%S")
SESSION_ID = "testing_session_id_%s" % datetime.now().strftime("%Y%m%d%H%M%S")

# Configure memory
agentcore_memory_config = AgentCoreMemoryConfig(
    memory_id=MEM_ID,
    session_id=SESSION_ID,
    actor_id=ACTOR_ID
)

# Create session manager
session_manager = AgentCoreMemorySessionManager(
    agentcore_memory_config=agentcore_memory_config,
    region_name="us-east-1"
)

# Create agent
agent = Agent(
    system_prompt="You are a helpful assistant. Use all you know about the user to provide helpful responses.",
    session_manager=session_manager,
)

agent("I like sushi with tuna")
# Agent remembers this preference

agent("I like pizza")
# Agent acknowledges both preferences

agent("What should I buy for lunch today?")
# Agent suggests options based on remembered preferences

Raggruppamento di messaggi

Quando batch_size è maggiore di 1, i messaggi vengono memorizzati nel buffer in memoria e inviati alla AgentCore memoria in una singola chiamata API una volta che il buffer raggiunge la dimensione configurata. Ciò riduce il numero di richieste API nelle conversazioni ad alto rendimento.

Consigliato: gestore del contesto

from strands import Agent
from bedrock_agentcore.memory.integrations.strands.config import AgentCoreMemoryConfig
from bedrock_agentcore.memory.integrations.strands.session_manager import AgentCoreMemorySessionManager

config = AgentCoreMemoryConfig(
    memory_id=MEM_ID,
    session_id=SESSION_ID,
    actor_id=ACTOR_ID,
    batch_size=10,  # Buffer up to 10 messages before sending
)

# The `with` block guarantees all buffered messages are flushed on exit
with AgentCoreMemorySessionManager(config, region_name='us-east-1') as session_manager:
    agent = Agent(
        system_prompt="You are a helpful assistant.",
        session_manager=session_manager,
    )
    agent("Hello!")
    agent("Tell me about AWS")
# All remaining buffered messages are automatically flushed here

Alternativa: chiusura esplicita ()

Se non puoi usare un with blocco, chiama close() manualmente:

session_manager = AgentCoreMemorySessionManager(config, region_name='us-east-1')
try:
    agent = Agent(
        system_prompt="You are a helpful assistant.",
        session_manager=session_manager,
    )
    agent("Hello!")
finally:
    session_manager.close()  # Flush any remaining buffered messages

Altri esempi sono disponibili su GitHub: https://github.com/aws/bedrock-agentcore-sdk-python/tree/main/src/bedrock_agentcore/memory/integrations/strands