添加记忆

创建 MemorySaver 检查点

from langgraph.checkpoint.memory import MemorySaver

memory = MemorySaver()

这是一个内存中的检查点，方便本教程使用

然而，在生产应用程序中，可能会将其更改为使用 SqliteSaver 或 PostgresSaver 并连接数据库

使用提供的检查点编译图，图在遍历每个节点时将对 State 进行检查点

graph = graph_builder.compile(checkpointer=memory)

from IPython.display import Image, display

try:
    display(Image(graph.get_graph().draw_mermaid_png()))
except Exception:
    # This requires some extra dependencies and is optional
    pass

现在可以与机器人互动了：

1. 选择一个线程作为此对话的键

   config = {"configurable": {"thread_id": "1"}}
   

2. 调用聊天机器人

   user_input = "Hi there! My name is Will."
   
   # The config is the **second positional argument** to stream() or invoke()!
   events = graph.stream(
       {"messages": [{"role": "user", "content": user_input}]},
       config,
       stream_mode="values",
   )
   for event in events:
       event["messages"][-1].pretty_print()
   

   ================================ Human Message =================================
   
   Hi there! My name is Will.
   ================================== Ai Message ==================================
   
   Hello Will! It's nice to meet you. How can I assist you today? Is there anything specific you'd like to know or discuss?
   

在调用图时，配置作为第二个位置参数提供

重要的是，它不嵌套在图输入中 ({'messages': []})

user_input = "Remember my name?"

# The config is the **second positional argument** to stream() or invoke()!
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    config,
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

================================ Human Message =================================

Remember my name?
================================== Ai Message ==================================

Of course, I remember your name, Will. I always try to pay attention to important details that users share with me. Is there anything else you'd like to talk about or any questions you have? I'm here to help with a wide range of topics or tasks.

请注意，没有使用外部列表来处理记忆：这一切都由检查点器处理！

尝试使用不同的配置：

# The only difference is we change the `thread_id` here to "2" instead of "1"
events = graph.stream(
    {"messages": [{"role": "user", "content": user_input}]},
    {"configurable": {"thread_id": "2"}},
    stream_mode="values",
)
for event in events:
    event["messages"][-1].pretty_print()

================================ Human Message =================================

Remember my name?
================================== Ai Message ==================================

I apologize, but I don't have any previous context or memory of your name. As an AI assistant, I don't retain information from past conversations. Each interaction starts fresh. Could you please tell me your name so I can address you properly in this conversation?

所做的唯一更改是修改了配置中的thread_id

到现在为止，已经在两个不同的线程中创建了一些检查点

但是检查点中包含什么呢？

要随时检查给定配置的图的 state，请调用 get_state(config)

snapshot = graph.get_state(config)
snapshot

StateSnapshot(values={'messages': [HumanMessage(content='Hi there! My name is Will.', additional_kwargs={}, response_metadata={}, id='8c1ca919-c553-4ebf-95d4-b59a2d61e078'), AIMessage(content="Hello Will! It's nice to meet you. How can I assist you today? Is there anything specific you'd like to know or discuss?", additional_kwargs={}, response_metadata={'id': 'msg_01WTQebPhNwmMrmmWojJ9KXJ', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 405, 'output_tokens': 32}}, id='run-58587b77-8c82-41e6-8a90-d62c444a261d-0', usage_metadata={'input_tokens': 405, 'output_tokens': 32, 'total_tokens': 437}), HumanMessage(content='Remember my name?', additional_kwargs={}, response_metadata={}, id='daba7df6-ad75-4d6b-8057-745881cea1ca'), AIMessage(content="Of course, I remember your name, Will. I always try to pay attention to important details that users share with me. Is there anything else you'd like to talk about or any questions you have? I'm here to help with a wide range of topics or tasks.", additional_kwargs={}, response_metadata={'id': 'msg_01E41KitY74HpENRgXx94vag', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 444, 'output_tokens': 58}}, id='run-ffeaae5c-4d2d-4ddb-bd59-5d5cbf2a5af8-0', usage_metadata={'input_tokens': 444, 'output_tokens': 58, 'total_tokens': 502})]}, next=(), config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef7d06e-93e0-6acc-8004-f2ac846575d2'}}, metadata={'source': 'loop', 'writes': {'chatbot': {'messages': [AIMessage(content="Of course, I remember your name, Will. I always try to pay attention to important details that users share with me. Is there anything else you'd like to talk about or any questions you have? I'm here to help with a wide range of topics or tasks.", additional_kwargs={}, response_metadata={'id': 'msg_01E41KitY74HpENRgXx94vag', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 444, 'output_tokens': 58}}, id='run-ffeaae5c-4d2d-4ddb-bd59-5d5cbf2a5af8-0', usage_metadata={'input_tokens': 444, 'output_tokens': 58, 'total_tokens': 502})]}}, 'step': 4, 'parents': {}}, created_at='2024-09-27T19:30:10.820758+00:00', parent_config={'configurable': {'thread_id': '1', 'checkpoint_ns': '', 'checkpoint_id': '1ef7d06e-859f-6206-8003-e1bd3c264b8f'}}, tasks=())

上述快照包含当前状态值、相应的配置以及要处理的 next 节点

在我们的例子中，图已达到 END 状态，因此 next 为空

snapshot.next  # (since the graph ended this turn, `next` is empty. If you fetch a state from within a graph invocation, next tells which node will execute next) 

聊天机器人现在可以通过 LangGraph 的检查点系统维护会话状态。这为更自然、上下文相关的交互打开了激动人心的可能性：

from typing import Annotated

from langchain.chat_models import init_chat_model
from langchain_tavily import TavilySearch
from langchain_core.messages import BaseMessage
from typing_extensions import TypedDict

from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import StateGraph
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition

class State(TypedDict):
    messages: Annotated[list, add_messages]

graph_builder = StateGraph(State)

tool = TavilySearch(max_results=2)
tools = [tool]
llm_with_tools = llm.bind_tools(tools)

def chatbot(state: State):
    return {"messages": [llm_with_tools.invoke(state["messages"])]}

graph_builder.add_node("chatbot", chatbot)

tool_node = ToolNode(tools=[tool])
graph_builder.add_node("tools", tool_node)

graph_builder.add_conditional_edges(
    "chatbot",
    tools_condition,
)
graph_builder.add_edge("tools", "chatbot")
graph_builder.set_entry_point("chatbot")
memory = MemorySaver()
graph = graph_builder.compile(checkpointer=memory)

在下一个教程中，将为聊天机器人添加人工干预，以处理可能需要指导或验证才能继续的情况