本节是langchian源码阅读系列第六篇,下面进入代理模块👇:
某些应用程序需要基于用户输入的对LLM和其他工具的灵活调用链。Agents为此类应用程序提供了灵活性。代理可以访问单一工具,并根据用户输入确定要使用的工具。代理可以使用多个工具,并使用一个工具的输出作为下一个工具的输入。
主要有两种类型的代理:Plan-and-Execute Agents 用于制定动作计划;Action Agents 决定实施何种动作。
Agents模块还包含配合代理执行的工具(代理可以执行的操作。为代理提供哪些工具在很大程度上取决于希望代理做什么)和工具包(一套工具集合,这些工具可以与特定用例一起使用。例如,为了使代理与SQL数据库进行交互,它可能需要一个工具来执行查询,另一个工具来检查表)。
下面对不同的Agent类型进行说明
CONVERSATIONAL_REACT_DESCRIPTION
针对对话场景优化的代理
ini复制代码def test_conversation_agent():
search = GoogleSearchAPIWrapper()
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"
),
]
memory = ConversationBufferMemory(memory_key="chat_history")
llm=OpenAI(temperature=0)
agent_chain = initialize_agent(tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)
print(agent_chain.run(input="用中文回答中国人口数量"))
Agent执行过程
yaml复制代码> Entering new chain...
Thought: Do I need to use a tool? Yes
Action: Current Search
Action Input: 中国人口数量
Observation: 中华人民共和国成立时,中国大陆人口约5.4亿,占世界人口的22%。和许多发展中国家一样,从1950年起,由于社会较为稳定,死亡率下降,预期寿命逐渐延长,人口因此迅速增长 ... May 11, 2021 ... 十年一次的普查显示,以2020年11月1日为标准时间点,中国总人口为14亿1178万人。此前英国《金融时报》援引知情人士称中国总人口已低于14亿人,出现了“自 ... 中国是一个以汉族为主多民族国家,汉族目前占总人口的91%,其余为少数民族,及极少数的归化外国移民。据中华人民共和国国家统计局于2020年1月17日发布数据,2019年中国 ... Jan 18, 2020 ... 中国国家统计局17日公布的数据显示,中国大陆总人口在2019年突破14亿大关,正式 ... 出生人口数量受到育龄妇女总量、育龄妇女年龄结构和生育率变化的 ... May 17, 2021 ... 中国国务院人口普查小组和国家统计局不久前公布了第七次全国人口普查数据结果,称中国“人口总量达到14亿1178万”,与2010年的第六次人口普查数据相比, ... 人口普查是全面查清国家人口数量、结构、分布的重要. 途径,中国目前为止进行了七次人口普查,分别于. 1953、1964、1982、1990、2000、2010、2020年进. 行。在现行统计制度 ... Oct 26, 2022 ... 全国65周岁及以上老年人口抚养比20.8%。 图1 2012年—2021年全国60周岁及以上老年人口数量及占全国总人口比重. 图 ... Jan 18, 2019 ... 多年来,为减缓世界上这个人口最多国家的人口增长速度,中国执政的共产党实施了一系列的政策,包括把一对夫妇允许生育的孩子数量限制为一个。 Apr 10, 2012 ... 我国人口发展一直对世界人口格局有着举足轻重的影响。 一、人口和计划生育工作历程 ... 第一,人口数量有效控制,为经济快速增长创造了重要条件。 Jan 31, 2023 ... 2022年末,全国人口为141175万人,比2021年减少85万人;全年出生人口956万人,比2021年减少106万人;死亡人口1041万人,比2021年增加27万人。
Thought: Do I need to use a tool? No
AI: 根据中国国家统计局的数据,截至2020年11月1日,中国总人口为14亿1178万人。此外,中国汉族人口占总人口的91%,其余为少数民族,及极少数的归化外国移民。
> Finished chain.
根据中国国家统计局的数据,截至2020年11月1日,中国总人口为14亿1178万人。此外,中国汉族人口占总人口的91%,其余为少数民族,及极少数的归化外国移民。
CHAT_CONVERSATIONAL_REACT_DESCRIPTION 针对聊天场景优化的代理
OpenAI Functions Agent
这个是 LangChain对 OpenAI Function Call 的封装。关于 Function Calling的能力,可以看我这篇文章:OpenAI Function Calling 特性有什么用
ini复制代码llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
search = GoogleSearchAPIWrapper()
llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)
tools = [
Tool(
name = "Search",
func=search.run,
description="useful for when you need to answer questions about current events. You should ask targeted questions"
),
Tool(
name="Calculator",
func=llm_math_chain.run,
description="useful for when you need to answer questions about math"
)
]
agent = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)
print(agent.run("2的33次方是多少?"))e.OPENAI_FUNCTIONS, verbose=True)
下面看下是debug模式下的执行过程
ruby复制代码[chain/start] [1:chain:AgentExecutor] Entering Chain run with input:
{
"input": "2的33次方是多少?"
}
[llm/start] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: 2的33次方是多少?"
]
}
[llm/end] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] [4.69s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "",
"generation_info": null,
"message": {
"content": "",
"additional_kwargs": {
"function_call": {
"name": "Calculator",
"arguments": "{\n \"__arg1\": \"2^33\"\n}"
}
},
"example": false
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 102,
"completion_tokens": 19,
"total_tokens": 121
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[tool/start] [1:chain:AgentExecutor > 3:tool:Calculator] Entering Tool run with input:
"2^33"
[chain/start] [1:chain:AgentExecutor > 3:tool:Calculator > 4:chain:LLMMathChain] Entering Chain run with input:
{
"question": "2^33"
}
[chain/start] [1:chain:AgentExecutor > 3:tool:Calculator > 4:chain:LLMMathChain > 5:chain:LLMChain] Entering Chain run with input:
{
"question": "2^33",
"stop": [
"```output"
]
}
[llm/start] [1:chain:AgentExecutor > 3:tool:Calculator > 4:chain:LLMMathChain > 5:chain:LLMChain > 6:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"Human: Translate a math problem into a expression that can be executed using Python's numexpr library. Use the output of running this code to answer the question.\n\nQuestion: ${Question with math problem.}\n```text\n${single line mathematical expression that solves the problem}\n```\n...numexpr.evaluate(text)...\n```output\n${Output of running the code}\n```\nAnswer: ${Answer}\n\nBegin.\n\nQuestion: What is 37593 * 67?\n```text\n37593 * 67\n```\n...numexpr.evaluate(\"37593 * 67\")...\n```output\n2518731\n```\nAnswer: 2518731\n\nQuestion: 37593^(1/5)\n```text\n37593**(1/5)\n```\n...numexpr.evaluate(\"37593**(1/5)\")...\n```output\n8.222831614237718\n```\nAnswer: 8.222831614237718\n\nQuestion: 2^33"
]
}
[llm/end] [1:chain:AgentExecutor > 3:tool:Calculator > 4:chain:LLMMathChain > 5:chain:LLMChain > 6:llm:ChatOpenAI] [987.549ms] Exiting LLM run with output:
{
"generations": [
[
{
"text": "```text\n2**33\n```\n...numexpr.evaluate(\"2**33\")...\n",
"generation_info": null,
"message": {
"content": "```text\n2**33\n```\n...numexpr.evaluate(\"2**33\")...\n",
"additional_kwargs": {},
"example": false
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 203,
"completion_tokens": 19,
"total_tokens": 222
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[chain/end] [1:chain:AgentExecutor > 3:tool:Calculator > 4:chain:LLMMathChain > 5:chain:LLMChain] [988.7ms] Exiting Chain run with output:
{
"text": "```text\n2**33\n```\n...numexpr.evaluate(\"2**33\")...\n"
}
[chain/end] [1:chain:AgentExecutor > 3:tool:Calculator > 4:chain:LLMMathChain] [991.249ms] Exiting Chain run with output:
{
"answer": "Answer: 8589934592"
}
[tool/end] [1:chain:AgentExecutor > 3:tool:Calculator] [991.919ms] Exiting Tool run with output:
"Answer: 8589934592"
[llm/start] [1:chain:AgentExecutor > 7:llm:ChatOpenAI] Entering LLM run with input:
{
"prompts": [
"System: You are a helpful AI assistant.\nHuman: 2的33次方是多少?\nAI: {'name': 'Calculator', 'arguments': '{\\n \"__arg1\": \"2^33\"\\n}'}\nFunction: Answer: 8589934592"
]
}
[llm/end] [1:chain:AgentExecutor > 7:llm:ChatOpenAI] [1.22s] Exiting LLM run with output:
{
"generations": [
[
{
"text": "2的33次方是8589934592。",
"generation_info": null,
"message": {
"content": "2的33次方是8589934592。",
"additional_kwargs": {},
"example": false
}
}
]
],
"llm_output": {
"token_usage": {
"prompt_tokens": 135,
"completion_tokens": 12,
"total_tokens": 147
},
"model_name": "gpt-3.5-turbo-0613"
},
"run": null
}
[chain/end] [1:chain:AgentExecutor] [6.91s] Exiting Chain run with output:
{
"output": "2的33次方是8589934592。"
}
2的33次方是8589934592。
这里就使用了封装的计算函数,并传入OpenAI接口
swift复制代码"message": {
"content": "",
"additional_kwargs": {
"function_call": {
"name": "Calculator",
"arguments": "{\n \"__arg1\": \"2^33\"\n}"
}
}
}
计划和执行代理
计划和执行代理通过首先计划要做什么,然后执行子任务来实现目标。这个想法很大程度上受到BabyAGI的启发。
ini复制代码from langchain.chat_models import ChatOpenAI
from langchain.experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner
search = GoogleSearchAPIWrapper()
llm = OpenAI(temperature=0)
llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)
tools = [
Tool(
name = "Search",
func=search.run,
description="useful for when you need to answer questions about current events"
),
Tool(
name="Calculator",
func=llm_math_chain.run,
description="useful for when you need to answer questions about math"
),
]
model = ChatOpenAI(temperature=0)
planner = load_chat_planner(model)
executor = load_agent_executor(model, tools, verbose=True)
agent = PlanAndExecute(planner=planner, executor=executor, verbose=True)
print(agent.run("用中文回答美国和日本的GDP相差多少?"))
# 1.Search Tool查询美国GDP 2.Calculator Tool查询日本GDP 3.Calculator Tool计算差值
ZERO_SHOT_REACT_DESCRIPTION
给LLM提供一个工具名称列表,包括它们的效用描述以及有关预期输入/输出的详细信息。指示LLM在必要时使用提供的工具来回答用户给出的提示。指令建议模型遵循ReAct格式:思考、行动、行动输入、观察,下面是一个例子:
vbnet复制代码> Entering new chain...
Thought: I need to find out the population of China.
Action: Search
Action Input: Population of China
Observation: The current population of China is 1,455,977,205 as of Wednesday, July 5, 2023, based on Worldometer elaboration of the latest United Nations data. · China 2020 ... Apr 24, 2023 ... China's population reached its peak size of 1.426 billion in 2022 and has started to fall. Projections indicate that the size of the Chinese ... Apr 24, 2023 ... Indeed, according to current projections, China's population is likely to drop below 1 billion by 2080 and below 800 million by 2100. Those ... It is the world's second-most populous country, with a population exceeding 1.4 billion. China spans the equivalent of five time zones and borders fourteen ... Mar 6, 2020 ... ... Associated Factors during the Initial Stage of the 2019 Coronavirus Disease (COVID-19) Epidemic among the General Population in China. Jun 12, 2023 ... China's population shrank in 2022 for the first time in more than 60 years, with just 6.77 births per 1,000 people – the lowest level since ... Feb 24, 2017 ... The National Clinical Research Center for Mental Disorders, China & Center of Depression, Beijing Institute for Brain Disorders & Mood Disorders ... Apr 19, 2023 ... Both China and India have more than 1.4 billion people, and combined they make up more than a third of the world's 8 billion people. “Actually, ... Population, total - China from The World Bank: Data. ... Population and Vital Statistics Reprot ( various years ), ( 5 ) U.S. Census Bureau: International ... (A total prison population of 2,340,000 would raise the prison population rate to 165 per 100,000.) Pre-trial detainees / remand prisoners (percentage ...
Thought: I now know the final answer.
Final Answer: The current population of China is 1,455,977,205.
> Finished chain.
The current population of China is 1,455,977,205.
其他
- AgentType.SELF_ASK_WITH_SEARCH:自我进行对话迭代的代理
- REACT_DOCSTORE:基于文档做ReAct的代理
- STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION:在聊天过程中接入工具性代理,相当于OpenAI Plugin
读者福利:如果大家对大模型感兴趣,这套大模型学习资料一定对你有用
对于0基础小白入门:
如果你是零基础小白,想快速入门大模型是可以考虑的。
一方面是学习时间相对较短,学习内容更全面更集中。
二方面是可以根据这些资料规划好学习计划和方向。
资源分享
大模型AGI学习包
资料目录
- 成长路线图&学习规划
- 配套视频教程
- 实战LLM
- 人工智能比赛资料
- AI人工智能必读书单
- 面试题合集
《人工智能\大模型入门学习大礼包》,可以扫描下方二维码免费领取!
![](https://img-blog.csdnimg.cn/img_convert/5e6f106a6b0c2b4948cd4da62dfc3a49.png)
1.成长路线图&学习规划
要学习一门新的技术,作为新手一定要先学习成长路线图,方向不对,努力白费。
对于从来没有接触过网络安全的同学,我们帮你准备了详细的学习成长路线图&学习规划。可以说是最科学最系统的学习路线,大家跟着这个大的方向学习准没问题。
2.视频教程
很多朋友都不喜欢晦涩的文字,我也为大家准备了视频教程,其中一共有21个章节,每个章节都是当前板块的精华浓缩。
3.LLM
大家最喜欢也是最关心的LLM(大语言模型)
《人工智能\大模型入门学习大礼包》,可以扫描下方二维码免费领取!
![](https://img-blog.csdnimg.cn/img_convert/5e6f106a6b0c2b4948cd4da62dfc3a49.png)