跳到内容

记忆工具 API 参考

函数

create_manage_memory_tool 

create_manage_memory_tool(
    namespace: tuple[str, ...] | str,
    *,
    instructions: str = "Proactively call this tool when you:\n\n1. Identify a new USER preference.\n2. Receive an explicit USER request to remember something or otherwise alter your behavior.\n3. Are working and want to record important context.\n4. Identify that an existing MEMORY is incorrect or outdated.\n",
    schema: Type = str,
    actions_permitted: Optional[
        tuple[Literal["create", "update", "delete"], ...]
    ] = ("create", "update", "delete"),
    store: Optional[BaseStore] = None,
    name: str = "manage_memory",
)

创建一个用于管理对话中持久性记忆的工具。

此函数创建一个工具，允许 AI 助手创建、更新和删除可在对话之间保留的持久性记忆。该工具有助于在不同会话中维护上下文和用户偏好。

参数

  • instructions (str, default: '在以下情况下主动调用此工具：\n\n1. 识别到新的用户偏好。\n2. 收到用户明确请求记住某事或以其他方式改变您的行为。\n3. 在工作中想要记录重要上下文。\n4. 发现现有记忆不正确或已过时。\n' ) –

    关于何时使用记忆工具的自定义指令。默认为一组用于主动记忆管理的预定义指南。

  • namespace (tuple[str, ...] | str) –

    用于在 LangGraph 的 BaseStore 中组织记忆的命名空间结构。使用运行时配置，带有像 {langgraph_user_id} 这样的占位符。

  • store (Optional[BaseStore], default: None ) –

    用于搜索的 BaseStore。如果未提供，该工具将使用您在图或入口点中配置的 BaseStore。仅在您打算在 LangGraph 上下文之外使用这些工具时设置。

返回

  • memory_tool ( Tool ) –

    一个经过装饰的异步函数，可用作记忆管理工具。该工具支持通过适当的验证来创建、更新和删除记忆。

生成的工具具有如下所示的签名： 

from typing import Literal


def manage_memory(
    content: str | None = None,  # Content for new/updated memory
    id: str | None = None,  # ID of existing memory to update/delete
    action: Literal["create", "update", "delete"] = "create",
) -> str: ...
注意：该工具支持同步和异步使用。

命名空间配置

命名空间通过 config 参数在运行时进行配置。

# Example: Per-user memory storage
config = {"configurable": {"langgraph_user_id": "user-123"}}
# Results in namespace: ("memories", "user-123")

# Example: Team-wide memory storage
config = {"configurable": {"langgraph_user_id": "team-x"}}
# Results in namespace: ("memories", "team-x")

提示

此工具连接到您在图或入口点中配置的 LangGraph BaseStore。如果您不提供存储，它将无法工作。

示例

from langmem import create_manage_memory_tool
from langgraph.func import entrypoint
from langgraph.store.memory import InMemoryStore

memory_tool = create_manage_memory_tool(
    # All memories saved to this tool will live within this namespace
    # The brackets will be populated at runtime by the configurable values
    namespace=("project_memories", "{langgraph_user_id}"),
)

store = InMemoryStore(
    index={
        "dims": 1536,
        "embed": "openai:text-embedding-3-small",
    }
)


@entrypoint(store=store)
async def workflow(state: dict, *, previous=None):
    # Other work....
    result = await memory_tool.ainvoke(state)
    print(result)
    return entrypoint.final(value=result, save={})


config = {
    "configurable": {
        # This value will be formatted into the namespace you configured above ("project_memories", "{langgraph_user_id}")
        "langgraph_user_id": "123e4567-e89b-12d3-a456-426614174000"
    }
}
# Create a new memory
await workflow.ainvoke(
    {"content": "Team prefers to use Python for backend development"},
    config=config,
)
# Output: 'created memory 123e4567-e89b-12d3-a456-426614174000'

# Update an existing memory
result = await workflow.ainvoke(
    {
        "id": "123e4567-e89b-12d3-a456-426614174000",
        "content": "Team uses Python for backend and TypeScript for frontend",
        "action": "update",
    },
    config=config,
)
print(result)
# Output: 'updated memory 123e4567-e89b-12d3-a456-426614174000'

您可以在 LangGraph 的预构建 create_react_agent 中使用。

from langgraph.prebuilt import create_react_agent
from langgraph.config import get_config, get_store

def prompt(state):
    config = get_config()
    memories = get_store().search(
        # Search within the same namespace as the one
        # we've configured for the agent
        ("memories", config["configurable"]["langgraph_user_id"]),
    )
    system_prompt = f"""You are a helpful assistant.
<memories>
{memories}
</memories>
"""
    system_message = {"role": "system", "content": system_prompt}
    return [system_message, *state["messages"]]

agent = create_react_agent(
    "anthropic:claude-3-5-sonnet-latest",
    tools=[
        create_manage_memory_tool(namespace=("memories", "{langgraph_user_id}")),
    ],
    store=store,
)

agent.invoke(
    {"messages": [{"role": "user", "content": "We've decided we like golang more than python for backend work"}]},
    config=config,
)

如果您想自定义记忆的预期模式（schema），可以通过提供一个 schema 参数来实现。

from pydantic import BaseModel


class UserProfile(BaseModel):
    name: str
    age: int | None = None
    recent_memories: list[str] = []
    preferences: dict | None = None


memory_tool = create_manage_memory_tool(
    # All memories saved to this tool will live within this namespace
    # The brackets will be populated at runtime by the configurable values
    namespace=("memories", "{langgraph_user_id}", "user_profile"),
    schema=UserProfile,
    actions_permitted=["create", "update"],
    instructions="Update the existing user profile (or create a new one if it doesn't exist) based on the shared information.",
)
store = InMemoryStore(
    index={
        "dims": 1536,
        "embed": "openai:text-embedding-3-small",
    }
)
agent = create_react_agent(
    "anthropic:claude-3-5-sonnet-latest",
    prompt=prompt,
    tools=[
        memory_tool,
    ],
    store=store,
)

result = agent.invoke(
    {
        "messages": [
            {
                "role": "user",
                "content": "I'm 60 years old and have been programming for 5 days.",
            }
        ]
    },
    config=config,
)
result["messages"][-1].pretty_print()
# I've created a memory with your age of 60 and noted that you started programming 5 days ago...

result = agent.invoke(
    {
        "messages": [
            {"role": "user", "content": "Just had by 61'st birthday today!!"}
        ]
    },
    config=config,
)
result["messages"][-1].pretty_print()
# Happy 61st birthday! 🎂 I've updated your profile to reflect your new age. Is there anything else I can help you with?
print(
    store.search(
        ("memories", "123e4567-e89b-12d3-a456-426614174000", "user_profile")
    )
)
# [Item(
#     namespace=['memories', '123e4567-e89b-12d3-a456-426614174000', 'user_profile'],
#     key='1528553b-0900-4363-8dc2-c6b72844096e',
#     value={
# highlight-next-line
#         'content': UserProfile(
#             name='User',
#             age=61,
#             recent_memories=['Started programming 5 days ago'],
#             preferences={'programming_experience': '5 days'}
#         )
#     },
#     created_at='2025-02-07T01:12:14.383762+00:00',
#     updated_at='2025-02-07T01:12:14.383763+00:00',
#     score=None
# )]

如果您想限制该工具可以执行的操作，可以通过提供一个 actions_permitted 参数来实现。

create_search_memory_tool 

create_search_memory_tool(
    namespace: tuple[str, ...] | str,
    *,
    instructions: str = _MEMORY_SEARCH_INSTRUCTIONS,
    store: BaseStore | None = None,
    response_format: Literal[
        "content", "content_and_artifact"
    ] = "content",
    name: str = "search_memory",
)

创建一个用于搜索存储在 LangGraph BaseStore 中的记忆的工具。

此函数创建一个工具，允许 AI 助手通过语义匹配或精确匹配来搜索先前存储的记忆。该工具返回记忆内容和原始记忆对象以供高级使用。

参数

  • instructions (str, default: _MEMORY_SEARCH_INSTRUCTIONS ) –

    关于何时使用搜索工具的自定义指令。默认为一组预定义指南。

  • namespace (tuple[str, ...] | str) –

    用于在 LangGraph 的 BaseStore 中组织记忆的命名空间结构。使用运行时配置，带有像 {langgraph_user_id} 这样的占位符。请参阅记忆命名空间。

  • store (BaseStore | None, default: None ) –

    用于搜索的 BaseStore。如果未提供，该工具将使用您在图或入口点中配置的 BaseStore。仅在您打算在 LangGraph 上下文之外使用这些工具时设置。

返回

  • search_tool ( Tool ) –

    一个经过装饰的函数，可用作记忆搜索工具。该工具返回序列化后的记忆和原始记忆对象。

生成的工具具有如下所示的签名： 
def search_memory(
    query: str,  # Search query to match against memories
    limit: int = 10,  # Maximum number of results to return
    offset: int = 0,  # Number of results to skip
    filter: dict | None = None,  # Additional filter criteria
) -> tuple[list[dict], list]: ...  # Returns (serialized memories, raw memories)

注意：该工具支持同步和异步使用。

提示

此工具连接到您在图或入口点中配置的 LangGraph BaseStore。如果您不提供存储，它将无法工作。

示例

from langmem import create_search_memory_tool
from langgraph.func import entrypoint
from langgraph.store.memory import InMemoryStore

search_tool = create_search_memory_tool(
    namespace=("project_memories", "{langgraph_user_id}"),
)

store = InMemoryStore(
    index={
        "dims": 1536,
        "embed": "openai:text-embedding-3-small",
    }
)


@entrypoint(store=store)
async def workflow(state: dict, *, previous=None):
    # Search for memories about Python
    memories, _ = await search_tool.ainvoke(
        {"query": "Python preferences", "limit": 5}
    )
    print(memories)
    return entrypoint.final(value=memories, save={})

评论