本文属于机器翻译版本。若本译文内容与英语原文存在差异，则一律以英文原文为准。

# 保存和检索见解
<a name="long-term-saving-and-retrieving-insights"></a>

在为 AgentCore 内存配置了至少一种长期记忆策略并且该策略处于活动状态后，该服务将自动开始处理对话数据以提取和存储见解。此过程涉及两个不同的步骤：保存原始对话，然后在处理结构化见解后检索结构化见解。

## 第 1 步：保存对话事件以触发提取
<a name="long-term-step-1-save-conversational-events"></a>

当您使用该`create_event`操作将对话数据保存到短期记忆中时，将触发整个长期记忆过程。每次录制事件时，您都会为主动记忆策略提供新的原材料以供分析。

**重要**  
只有在内存策略的状态变**为**之后创建的事件才`ACTIVE`会被处理以进行长期内存提取。在添加和激活策略之前存储的任何对话都将不包括在内。

以下示例说明如何将多回合对话保存到内存资源。

 **示例：将对话另存为一系列事件 ** 

```
#'memory_id' is the ID of your memory resource with an active summary strategy.

from bedrock_agentcore.memory.session import MemorySessionManager
from bedrock_agentcore.memory.constants import ConversationalMessage, MessageRole
import time

actor_id = "User84"
session_id = "OrderSupportSession1"

# Create session manager
session_manager = MemorySessionManager(
    memory_id=memory_id,
    region_name="us-west-2"
)

# Create a session
session = session_manager.create_memory_session(
    actor_id=actor_id,
    session_id=session_id
)

print("Capturing conversational events...")

# Add all conversation turns
session.add_turns(
    messages=[
        ConversationalMessage("Hi, I'm having trouble with my order #12345", MessageRole.USER),
        ConversationalMessage("I am sorry to hear that. Let me look up your order.", MessageRole.ASSISTANT),
        ConversationalMessage("lookup_order(order_id='12345')", MessageRole.TOOL),
        ConversationalMessage("I see your order was shipped 3 days ago. What specific issue are you experiencing?", MessageRole.ASSISTANT),
        ConversationalMessage("The package arrived damaged", MessageRole.USER),
    ]
)

print("Conversation turns added successfully!")
```

## 第 2 步：检索提取的见解
<a name="long-term-step-2-retrieve-extracted-insights"></a>

长期记忆的提取和整合是一个在后台运行**的**异步过程。从新对话中获得的见解可能需要一分钟或更长时间才能可供检索。您的应用程序逻辑应该考虑这种延迟。

要检索结构化见解，可以使用该`retrieve_memory_records`操作。此操作对长期内存存储执行强大的语义搜索。您必须提供您在策略中定义的正确`namespace`信息以及描述您正在寻找的信息的内容。`searchQuery`

以下示例演示如何等待处理，然后检索上一步中保存的对话摘要。

 **示例：等待并检索会话摘要 ** 

```
# 'session' is an existing session object that you created when adding the coversation turns
# session should be created on a memory resource with an active summary strategy.

# --- Example 1: Retrieve the user's shipping issues under a specific namespace ---
memories = session.search_long_term_memories(
    namespace=f"/summaries/{actor_id}/{session_id}/",
    query="What problem did the user report with their order?",
    top_k=5
)

# --- Example 2: Retrieve the user's shipping issues under a particular namespace hierarchy (e.g.: shipping issues across multiple sessions) ---
memories = session.search_long_term_memories(
    namespace_path=f"/summaries/{actor_id}/",
    query="What problem did the user report with their order?",
    top_k=5
)

print(f"Found {len(memories)} memories:")
for memory_record in memories:
    print(f"Retrieved Issue Detail: {memory_record}")
    print("--------------------------------------------------------------------")

# Example Output:
# Retrieved Issue Detail: The user reported that their package for order #12345 arrived damaged.
```