如何从工具更新图状态¶
一个常见的用例是从工具内部更新图形状态。例如，在客户支持应用程序中，您可能希望在对话开始时查找客户的账户号码或ID。为了从工具中更新图形状态，您可以从工具返回 Command(update={"my_custom_key": "foo", "messages": [...]})：
@tool
def lookup_user_info(tool_call_id: Annotated[str, InjectedToolCallId], config: RunnableConfig):
"""使用此功能来查找用户信息，以便更好地回答他们的问题。"""
user_info = get_user_info(config)
return Command(
update={
# 更新状态键
"user_info": user_info,
# 更新消息历史
"messages": [ToolMessage("成功查找用户信息", tool_call_id=tool_call_id)]
}
)
Important
如果您想使用返回 Command 并更新图形状态的工具，您可以使用预构建的 create_react_agent / ToolNode 组件，或者实现自己的工具执行节点，该节点收集工具返回的 Command 对象并返回一个列表，例如：
本指南展示了如何使用LangGraph的预构建组件（create_react_agent / ToolNode）来完成此操作。
Note
对于返回 Command 的工具的支持是在LangGraph v0.2.59 中添加的。
设置¶
首先，让我们安装所需的包并设置API密钥：
import os
import getpass
def _set_if_undefined(var: str):
if not os.environ.get(var):
os.environ[var] = getpass.getpass(f"Please provide your {var}")
_set_if_undefined("OPENAI_API_KEY")
使用LangSmith进行LangGraph开发
注册LangSmith，可以快速发现并解决项目中的问题，提高LangGraph项目的性能。LangSmith允许您使用跟踪数据来调试、测试和监控使用LangGraph构建的LLM应用程序——更多关于如何开始使用的信息，请参阅这里。
让我们创建一个简单的ReAct风格的代理，它可以查找用户信息，并根据用户信息个性化响应。
定义工具¶
首先，让我们定义将用于查找用户信息的工具。我们将使用一个简单的实现，它只是使用字典查找用户信息：
USER_INFO = [
{"user_id": "1", "name": "Bob Dylan", "location": "New York, NY"},
{"user_id": "2", "name": "Taylor Swift", "location": "Beverly Hills, CA"},
]
USER_ID_TO_USER_INFO = {info["user_id"]: info for info in USER_INFO}
from langgraph.prebuilt.chat_agent_executor import AgentState
from langgraph.types import Command
from langchain_core.tools import tool
from langchain_core.tools.base import InjectedToolCallId
from langchain_core.messages import ToolMessage
from langchain_core.runnables import RunnableConfig
from typing_extensions import Any, Annotated
class State(AgentState):
# updated by the tool
user_info: dict[str, Any]
@tool
def lookup_user_info(
tool_call_id: Annotated[str, InjectedToolCallId], config: RunnableConfig
):
"""Use this to look up user information to better assist them with their questions."""
user_id = config.get("configurable", {}).get("user_id")
if user_id is None:
raise ValueError("Please provide user ID")
if user_id not in USER_ID_TO_USER_INFO:
raise ValueError(f"User '{user_id}' not found")
user_info = USER_ID_TO_USER_INFO[user_id]
return Command(
update={
# update the state keys
"user_info": user_info,
# update the message history
"messages": [
ToolMessage(
"Successfully looked up user information", tool_call_id=tool_call_id
)
],
}
)
API Reference: Command | tool | InjectedToolCallId | ToolMessage | RunnableConfig
定义提示¶
现在让我们添加个性化：我们将根据工具更新后的状态值以不同的方式响应用户。为了实现这一点，我们将定义一个函数，该函数将根据图的状态动态构建系统提示。每次调用LLM时都会调用该函数，并将函数的输出传递给LLM：
def prompt(state: State):
user_info = state.get("user_info")
if user_info is None:
return state["messages"]
system_msg = (
f"User name is {user_info['name']}. User lives in {user_info['location']}"
)
return [{"role": "system", "content": system_msg}] + state["messages"]
定义图¶
最后，我们将这合并成一个单图，使用预构建的create_react_agent：
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI
model = ChatOpenAI(model="gpt-4o")
agent = create_react_agent(
model,
# pass the tool that can update state
[lookup_user_info],
state_schema=State,
# pass dynamic prompt function
prompt=prompt,
)
API Reference: create_react_agent | ChatOpenAI
使用它！¶
现在让我们尝试运行我们的代理。我们需要在配置中提供用户ID，以便我们的工具知道要查找哪些信息：
for chunk in agent.stream(
{"messages": [("user", "hi, what should i do this weekend?")]},
# provide user ID in the config
{"configurable": {"user_id": "1"}},
):
print(chunk)
print("\n")
{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_7LSUh6ZDvGJAUvlWvXiCK4Gf', 'function': {'arguments': '{}', 'name': 'lookup_user_info'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 56, 'total_tokens': 67, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_9d50cd990b', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-57eeb216-e35d-4501-aaac-b5c6b26fb17c-0', tool_calls=[{'name': 'lookup_user_info', 'args': {}, 'id': 'call_7LSUh6ZDvGJAUvlWvXiCK4Gf', 'type': 'tool_call'}], usage_metadata={'input_tokens': 56, 'output_tokens': 11, 'total_tokens': 67, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}}
{'tools': {'user_info': {'user_id': '1', 'name': 'Bob Dylan', 'location': 'New York, NY'}, 'messages': [ToolMessage(content='Successfully looked up user information', name='lookup_user_info', id='168d8ff8-b021-4c8b-a11a-3b50c30a072c', tool_call_id='call_7LSUh6ZDvGJAUvlWvXiCK4Gf')]}}
{'agent': {'messages': [AIMessage(content="Hi Bob! Since you're in New York, NY, there are plenty of exciting things to do over the weekend. Here are some suggestions:\n\n1. **Explore Central Park**: Take a leisurely walk, rent a bike, or have a picnic in this iconic park.\n\n2. **Visit a Museum**: Check out The Metropolitan Museum of Art or the Museum of Modern Art (MoMA) for an enriching cultural experience.\n\n3. **Broadway Show**: Catch a Broadway show or an off-Broadway performance for some world-class entertainment.\n\n4. **Food Tour**: Explore different neighborhoods like Greenwich Village or Williamsburg for diverse culinary experiences.\n\n5. **Brooklyn Bridge Walk**: Take a walk across the Brooklyn Bridge for stunning views of the city skyline.\n\n6. **Visit a Rooftop Bar**: Enjoy a drink with a view at one of New York’s many rooftop bars.\n\n7. **Explore a New Neighborhood**: Discover the unique charm of areas like SoHo, Chelsea, or Astoria.\n\n8. **Live Music**: Check out live music venues for a night of great performances.\n\n9. **Art Galleries**: Visit some of the smaller art galleries around Chelsea or the Lower East Side.\n\n10. **Attend a Local Event**: Look up any local events or festivals happening this weekend.\n\nFeel free to let me know if you want more details on any of these activities!", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 285, 'prompt_tokens': 95, 'total_tokens': 380, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_9d50cd990b', 'finish_reason': 'stop', 'logprobs': None}, id='run-f13ce15b-02b6-40e6-8264-c4d9edd0d03a-0', usage_metadata={'input_tokens': 95, 'output_tokens': 285, 'total_tokens': 380, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}}
for chunk in agent.stream(
{"messages": [("user", "hi, what should i do this weekend?")]},
{"configurable": {"user_id": "2"}},
):
print(chunk)
print("\n")
{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_5HLtJtzcgmKbtmK6By21wW5Y', 'function': {'arguments': '{}', 'name': 'lookup_user_info'}, 'type': 'function'}], 'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 56, 'total_tokens': 67, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_c7ca0ebaca', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-bacacd7d-76cc-4f6b-9e9b-d9e6f00b9391-0', tool_calls=[{'name': 'lookup_user_info', 'args': {}, 'id': 'call_5HLtJtzcgmKbtmK6By21wW5Y', 'type': 'tool_call'}], usage_metadata={'input_tokens': 56, 'output_tokens': 11, 'total_tokens': 67, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}}
{'tools': {'user_info': {'user_id': '2', 'name': 'Taylor Swift', 'location': 'Beverly Hills, CA'}, 'messages': [ToolMessage(content='Successfully looked up user information', name='lookup_user_info', id='d81ef31e-6d77-4f13-ae86-e2e6ba567e3d', tool_call_id='call_5HLtJtzcgmKbtmK6By21wW5Y')]}}
{'agent': {'messages': [AIMessage(content="Hi Taylor! Since you're in Beverly Hills, here are a few suggestions for a fun weekend:\n\n1. **Hiking at Runyon Canyon**: Enjoy a scenic hike with beautiful views of Los Angeles. It's a great way to get some exercise and enjoy the outdoors.\n\n2. **Visit Rodeo Drive**: Spend some time shopping or window shopping at the famous Rodeo Drive. You might even spot some celebrities!\n\n3. **Explore the Getty Center**: Check out the art collections and beautiful gardens at the Getty Center. The architecture and views are stunning.\n\n4. **Relax at a Spa**: Treat yourself to a relaxing day at one of Beverly Hills' luxurious spas.\n\n5. **Dining Out**: Try a new restaurant or visit your favorite spot for a delicious meal. Beverly Hills has a fantastic dining scene.\n\n6. **Attend a Local Event**: Check out any local events or concerts happening this weekend. Beverly Hills often hosts exciting events.\n\nEnjoy your weekend!", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 198, 'prompt_tokens': 95, 'total_tokens': 293, 'completion_tokens_details': {'accepted_prediction_tokens': 0, 'audio_tokens': 0, 'reasoning_tokens': 0, 'rejected_prediction_tokens': 0}, 'prompt_tokens_details': {'audio_tokens': 0, 'cached_tokens': 0}}, 'model_name': 'gpt-4o-2024-08-06', 'system_fingerprint': 'fp_c7ca0ebaca', 'finish_reason': 'stop', 'logprobs': None}, id='run-2057df76-f192-4c69-a66a-1f0a86bf5d66-0', usage_metadata={'input_tokens': 95, 'output_tokens': 198, 'total_tokens': 293, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}})]}}