如何从头开始创建ReAct代理(函数式API)¶
本指南演示了如何使用LangGraph的函数式API实现一个ReAct代理。
ReAct代理是一个工具调用代理,其操作如下:
这是一个简单且通用的设置,可以扩展记忆、人机交互能力和其他功能。请参阅专门的操作指南以获取示例。
设置¶
首先,让我们安装所需的包并设置我们的API密钥
import getpass
import os
def _set_env(var: str):
if not os.environ.get(var):
os.environ[var] = getpass.getpass(f"{var}: ")
_set_env("OPENAI_API_KEY")
设置LangSmith以获得更好的调试体验
注册LangSmith可以快速发现问题并提高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——请在文档中了解如何开始。
创建ReAct代理¶
现在您已经安装了所需的包并设置了环境变量,我们可以创建代理了。
定义模型和工具¶
我们首先定义将在示例中使用的工具和模型。这里我们将使用一个简单的占位工具,它获取某个位置的天气描述。
本示例将使用OpenAI聊天模型,但任何支持工具调用的模型都可以。
API参考:ChatOpenAI | tool
from langchain_openai import ChatOpenAI
from langchain_core.tools import tool
model = ChatOpenAI(model="gpt-4o-mini")
@tool
def get_weather(location: str):
"""Call to get the weather from a specific location."""
# This is a placeholder for the actual implementation
if any([city in location.lower() for city in ["sf", "san francisco"]]):
return "It's sunny!"
elif "boston" in location.lower():
return "It's rainy!"
else:
return f"I am not sure what the weather is in {location}"
tools = [get_weather]
定义任务¶
接下来我们定义将要执行的任务。这里有两种不同的任务:
- 调用模型:我们希望用消息列表查询我们的聊天模型。
- 调用工具:如果模型生成了工具调用,我们希望执行它们。
API参考:ToolMessage | entrypoint | task
from langchain_core.messages import ToolMessage
from langgraph.func import entrypoint, task
tools_by_name = {tool.name: tool for tool in tools}
@task
def call_model(messages):
"""Call model with a sequence of messages."""
response = model.bind_tools(tools).invoke(messages)
return response
@task
def call_tool(tool_call):
tool = tools_by_name[tool_call["name"]]
observation = tool.invoke(tool_call["args"])
return ToolMessage(content=observation, tool_call_id=tool_call["id"])
定义入口点¶
我们的入口点将处理这两个任务的编排。如上所述,当我们的call_model
任务生成工具调用时,call_tool
任务将为每个调用生成响应。我们将所有消息附加到一个消息列表中。
提示
请注意,由于任务返回类似Future的对象,下面的实现会并行执行工具。
API参考:add_messages
from langgraph.graph.message import add_messages
@entrypoint()
def agent(messages):
llm_response = call_model(messages).result()
while True:
if not llm_response.tool_calls:
break
# Execute tools
tool_result_futures = [
call_tool(tool_call) for tool_call in llm_response.tool_calls
]
tool_results = [fut.result() for fut in tool_result_futures]
# Append to message list
messages = add_messages(messages, [llm_response, *tool_results])
# Call model again
llm_response = call_model(messages).result()
return llm_response
用法¶
要使用我们的代理,我们使用消息列表调用它。根据我们的实现,这些可以是LangChain消息对象或OpenAI风格的字典。
user_message = {"role": "user", "content": "What's the weather in san francisco?"}
print(user_message)
for step in agent.stream([user_message]):
for task_name, message in step.items():
if task_name == "agent":
continue # Just print task updates
print(f"\n{task_name}:")
message.pretty_print()
{'role': 'user', 'content': "What's the weather in san francisco?"}
call_model:
================================== Ai Message ==================================
Tool Calls:
get_weather (call_tNnkrjnoz6MNfCHJpwfuEQ0v)
Call ID: call_tNnkrjnoz6MNfCHJpwfuEQ0v
Args:
location: san francisco
call_tool:
================================= Tool Message =================================
It's sunny!
call_model:
================================== Ai Message ==================================
The weather in San Francisco is sunny!
get_weather
工具,并在收到工具信息后响应用户。在此处查看LangSmith跟踪。
添加线程级持久性¶
添加线程级持久性使我们能够支持代理的对话体验:后续调用将附加到之前的消息列表,保留完整的对话上下文。
要为代理添加线程级持久性:
- 选择一个检查点器:这里我们将使用MemorySaver,一个简单的内存检查点器。
- 更新我们的入口点以接受之前的消息状态作为第二个参数。这里,我们只是将消息更新附加到之前的消息序列中。
- 使用
entrypoint.final
(可选)选择将从工作流返回哪些值,以及将哪些值作为previous
由检查点器保存。
API参考:MemorySaver
from langgraph.checkpoint.memory import MemorySaver
checkpointer = MemorySaver()
@entrypoint(checkpointer=checkpointer)
def agent(messages, previous):
if previous is not None:
messages = add_messages(previous, messages)
llm_response = call_model(messages).result()
while True:
if not llm_response.tool_calls:
break
# Execute tools
tool_result_futures = [
call_tool(tool_call) for tool_call in llm_response.tool_calls
]
tool_results = [fut.result() for fut in tool_result_futures]
# Append to message list
messages = add_messages(messages, [llm_response, *tool_results])
# Call model again
llm_response = call_model(messages).result()
# Generate final response
messages = add_messages(messages, llm_response)
return entrypoint.final(value=llm_response, save=messages)
我们现在需要在运行应用程序时传入一个配置。该配置将指定对话线程的标识符。
我们以与之前相同的方式启动一个线程,这次传入配置
user_message = {"role": "user", "content": "What's the weather in san francisco?"}
print(user_message)
for step in agent.stream([user_message], config):
for task_name, message in step.items():
if task_name == "agent":
continue # Just print task updates
print(f"\n{task_name}:")
message.pretty_print()
{'role': 'user', 'content': "What's the weather in san francisco?"}
call_model:
================================== Ai Message ==================================
Tool Calls:
get_weather (call_lubbUSdDofmOhFunPEZLBz3g)
Call ID: call_lubbUSdDofmOhFunPEZLBz3g
Args:
location: San Francisco
call_tool:
================================= Tool Message =================================
It's sunny!
call_model:
================================== Ai Message ==================================
The weather in San Francisco is sunny!
user_message = {"role": "user", "content": "How does it compare to Boston, MA?"}
print(user_message)
for step in agent.stream([user_message], config):
for task_name, message in step.items():
if task_name == "agent":
continue # Just print task updates
print(f"\n{task_name}:")
message.pretty_print()
{'role': 'user', 'content': 'How does it compare to Boston, MA?'}
call_model:
================================== Ai Message ==================================
Tool Calls:
get_weather (call_8sTKYAhSIHOdjLD5d6gaswuV)
Call ID: call_8sTKYAhSIHOdjLD5d6gaswuV
Args:
location: Boston, MA
call_tool:
================================= Tool Message =================================
It's rainy!
call_model:
================================== Ai Message ==================================
Compared to San Francisco, which is sunny, Boston, MA is experiencing rainy weather.