langchain Agent代理简介

定义

LLM只提供了最通用的功能，如果想要一些更专业化的功能，比如数学运算、网页搜索等，就需要调用相应的Tool。包装了Tool的LLM会用Agent来进行封装，也就是代理。

代理的类型

一共9种，只列出了4种：

名称	描述
zero-shot-react-description（默认）	这种代理类型在没有任何先前信息的情况下，直接生成对问题的反应和回答。它依赖于模型本身的通用知识和理解能力来处理问题
react-docstore	这种代理类型与文档进行交互。它可以访问一个或多个预先定义的文档库，从中提取相关信息来回答问题。这对于需要引用具体文档或数据的任务非常有用
self-ask-with-search	这种代理类型会在回答问题前先进行自我提问，然后使用搜索引擎或其他信息检索工具来寻找答案。这种方法特别适用于需要实时获取信息或处理复杂问题的场景
conversational-react-description	这种代理类型在对话上下文中生成反应和回答。它能够记住对话的历史内容，并根据对话的上下文进行更为连贯和相关的回答。这对于持续对话或需要上下文理解的任务非常有效

后四种代理的代码示例如下：

react-docstore

from langchain import OpenAI, Wikipedia
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.agents.react.base import DocstoreExplorer# 以Wikipedia作为文档进行查询
docstore=DocstoreExplorer(Wikipedia())
# 定义工具
tools = [Tool(name="Search",func=docstore.search,description="useful for when you need to ask with search"),Tool(name="Lookup",func=docstore.lookup,description="useful for when you need to ask with lookup")
]
# 初始化LLM
llm = OpenAI(temperature=0, model_name="text-davinci-002")
# 初始化agent
react = initialize_agent(tools, llm, agent=AgentType.REACT_DOCSTORE, verbose=True)
# 定义prompt
question = "Author David Chanoff has collaborated with a U.S. Navy admiral who served as the ambassador to the United Kingdom under which President?"
react.run(question)

self-ask-with-search

from langchain import OpenAI, SerpAPIWrapper
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType# 初始化LLM
llm = OpenAI(temperature=0)
# 初始化谷歌搜索的装饰器
search = SerpAPIWrapper()
# 把搜索功能集成到tool中
tools = [Tool(name="Intermediate Answer",func=search.run,description="useful for when you need to ask with search")
]
# 定义并运行代理
self_ask_with_search = initialize_agent(tools, llm, agent=AgentType.SELF_ASK_WITH_SEARCH, verbose=True)
self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?")

conversational-react-description

from langchain.agents import Tool
from langchain.agents import AgentType
from langchain.memory import ConversationBufferMemory
from langchain import OpenAI
from langchain.utilities import SerpAPIWrapper
from langchain.agents import initialize_agent
# 一般会用谷歌搜索缝一个搜索功能，应对更复杂的提问
search = SerpAPIWrapper()
tools = [Tool(name = "Current Search",func=search.run,description="useful for when you need to answer questions about current events or the current state of the world"),
]
# 为了节省内存而造的缓冲器
memory = ConversationBufferMemory(memory_key="chat_history")
# 定义LLM
llm=OpenAI(temperature=0)
# 初始化agent
agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)#连续调用agent实现连续对话
agent_chain.run(input="hi, i am bob")
agent_chain.run(input="what's my name?")

自定义代理

自己创建一个代理类CustomAgent()，然后继承代理类模板。有两种模板：

名称	描述
BaseSingleActionAgent	设计用于只需要执行一个动作的任务；通常只需要实现 plan 和 finish 方法。
BaseMultiActionAgent	设计用于需要多个步骤才能完成的任务；需要实现 plan, react, 和 finish 方法，并且需要在 plan 和 react 之间进行多次循环。

代码示例如下：

BaseSingleActionAgent

from langchain.agents import BaseSingleActionAgent
from langchain.schema import AgentAction, AgentFinishclass AdditionAgent(BaseSingleActionAgent):def plan(self, inputs: dict) -> AgentAction:num1 = inputs.get('num1')num2 = inputs.get('num2')if num1 is None or num2 is None:raise ValueError("Inputs must include 'num1' and 'num2'.")action = AgentAction(action="addition",action_input={"num1": num1, "num2": num2})return actiondef response(self, action: AgentAction) -> AgentFinish:if action.action != "addition":raise ValueError("Unsupported action. This agent only supports 'addition' action.")num1 = action.action_input['num1']num2 = action.action_input['num2']result = num1 + num2return AgentFinish(return_values={"result": result})# Usage example
agent = AdditionAgent()# Plan the action
inputs = {'num1': 3, 'num2': 5}
action = agent.plan(inputs)# Perform the action and get the response
result = agent.response(action)
print(result.return_values)  # Output: {'result': 8}

BaseMultiActionAgent

from langchain.agents import BaseMultiActionAgent
from langchain.schema import AgentAction, AgentFinishclass AdditionAgent(BaseMultiActionAgent):def plan(self, inputs: dict) -> AgentAction:num1 = inputs.get('num1')num2 = inputs.get('num2')if num1 is None or num2 is None:raise ValueError("Inputs must include 'num1' and 'num2'.")action = AgentAction(action="addition",action_input={"num1": num1, "num2": num2})return actiondef response(self, action: AgentAction) -> AgentFinish:if action.action != "addition":raise ValueError("Unsupported action. This agent only supports 'addition' action.")num1 = action.action_input['num1']num2 = action.action_input['num2']result = num1 + num2return AgentFinish(return_values={"result": result})def react(self, inputs: dict) -> AgentFinish:"""React to inputs by planning and executing an action.Args:inputs (dict): The inputs should include two keys: 'num1' and 'num2'.Returns:AgentFinish: The result of the addition."""action = self.plan(inputs)result = self.response(action)return result# Usage example
agent = AdditionAgent()# React to inputs
inputs = {'num1': 3, 'num2': 5}
result = agent.react(inputs)
print(result.return_values)  # Output: {'result': 8}