langgraph学习--创建基本的agent执行器

本文介绍如何使用langgraph创建一个基本的Agent执行器，主要包括下面几个步骤：
1、定义工具
2、创建langchain Agent（由LLM、tools、prompt三部分组成）
3、定义图形状态
传统的LangChain代理的状态有几个属性:
（1） ’ input ‘:这是一个输入字符串，表示来自用户的主要请求，作为输入传入。
（2）’ chat_history ‘:这是以前的对话消息，也作为输入传入。
（3） ’ intermediate_steps ‘:这是代理在一段时间内采取的操作和相应观察的列表。这在代理的每次迭代中都会更新。
（4）’ agent_outcome’:这是代理的响应，可以是AgentAction，也可以是AgentFinish。当这是一个AgentFinish时，AgentExecutor应该完成，否则它应该调用所请求的工具。
4、定义节点
现在我们需要在图中定义几个不同的节点。在’ langgraph '中，节点可以是函数或可运行的。
我们需要两个主要节点:
（1）代理:负责决定采取什么(如果有的话)行动。
（2）调用工具的函数:如果代理决定采取操作，则该节点将执行该操作。
5、定义边
其中一些边可能是有条件的。它们是有条件的原因是，基于节点的输出，可能会采取几个路径中的一个。在运行该节点之前，所采取的路径是未知的(由LLM决定)。
（1）条件边:在代理被调用后，我们应该:
a.如果代理说要采取行动，那么应该调用调用工具的函数
b.如果代理说完成了，那就应该完成
（2）正常边:在工具被调用后，它应该总是回到代理来决定下一步做什么
6、编译

代码实现如下

from langchain import hub
from langchain.agents import create_openai_functions_agent
from langchain_openai.chat_models import ChatOpenAI
import os
os.environ["OPENAI_API_KEY"]="sk-XXXXXXXXXX"
os.environ["SERPAPI_API_KEY"] = 'XXXXXXXXXXXXXXXXXXXXX'
from langchain.agents.tools import Tool
from langchain_community.utilities import SerpAPIWrapper
search = SerpAPIWrapper()search_tool = Tool(name = "Search",func=search.run,description="useful for when you need to answer questions about current events")tools = [search_tool]#### Create the LangChain agent
# Get the prompt to use - you can modify this!
prompt = hub.pull("hwchase17/openai-functions-agent")
llm = ChatOpenAI(model="gpt-3.5-turbo-1106", streaming=True)
# Construct the OpenAI Functions agent
agent_runnable = create_openai_functions_agent(llm, tools, prompt)"""
from langchain.agents import AgentExecutor
agent_executor = AgentExecutor(agent=agent_runnable, tools=tools)
response = agent_executor.invoke({"input": "weather in San Francisco"})
"""#### Define the graph state
from typing import TypedDict, Annotated, List, Union
from langchain_core.agents import AgentAction, AgentFinish
from langchain_core.messages import BaseMessage
import operator
class AgentState(TypedDict):# The input stringinput: str# The list of previous messages in the conversationchat_history: list[BaseMessage]# The outcome of a given call to the agent# Needs `None` as a valid type, since this is what this will start asagent_outcome: Union[AgentAction, AgentFinish, None]# List of actions and corresponding observations# Here we annotate this with `operator.add` to indicate that operations to# this state should be ADDED to the existing values (not overwrite it)intermediate_steps: Annotated[list[tuple[AgentAction, str]], operator.add]####  Define the nodes
from langchain_core.agents import AgentFinish
from langgraph.prebuilt.tool_executor import ToolExecutor# It takes in an agent action and calls that tool and returns the result
tool_executor = ToolExecutor(tools)# Define the agent
def run_agent(data):agent_outcome = agent_runnable.invoke(data)return {"agent_outcome": agent_outcome}# Define the function to execute tools
def execute_tools(data):# Get the most recent agent_outcome - this is the key added in the `agent` aboveagent_action = data['agent_outcome']output = tool_executor.invoke(agent_action)return {"intermediate_steps": [(agent_action, str(output))]}# Define logic that will be used to determine which conditional edge to go down
def should_continue(data):if isinstance(data['agent_outcome'], AgentFinish):return "end"else:return "continue"#### Define the graphfrom langgraph.graph import END, StateGraphworkflow = StateGraph(AgentState)workflow.add_node("agent", run_agent)
workflow.add_node("action", execute_tools)
workflow.set_entry_point("agent")workflow.add_conditional_edges("agent",should_continue,{# If `tools`, then we call the tool node."continue": "action",# Otherwise we finish."end": END}
)workflow.add_edge('action', 'agent')# This compiles it into a LangChain Runnable, meaning you can use it as you would any other runnable
app = workflow.compile()inputs = {"input": "what is the weather in sf", "chat_history": []}
for s in app.stream(inputs):print(list(s.values())[0])print("----")