LangChain-25 ReAct 让大模型自己思考和决策下一步 AutoGPT实现途径、AGI重要里程碑

本文主要是介绍LangChain-25 ReAct 让大模型自己思考和决策下一步 AutoGPT实现途径、AGI重要里程碑,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

请添加图片描述

背景介绍

大模型ReAct(Reasoning and Acting)是一种新兴的技术框架,旨在通过逻辑推理和行动序列的构建,使大型语言模型(LLM)能够达成特定的目标。这一框架的核心思想是赋予机器模型类似人类的推理和行动能力,从而在各种任务和环境中实现更高效、更智能的决策和操作。

核心组成

ReAct框架主要由三个关键概念组成:Thought(思考)、Act(行动)、和Obs(观察)。

  • Thought:由LLM模型生成,是LLM产生行为和依据的基础。它代表了模型在面对特定任务时的逻辑推理过程,是决策的前提。
  • Act:指LLM判断本次需要执行的具体行为。这通常涉及选择合适的工具或API,并生成所需的参数,以实现目标行动。
  • Obs:LLM框架对于外界输入的获取,类似于LLM的“五官”,将外界的反馈信息同步给LLM模型,协助模型进一步的做分析或者决策。

安装依赖


Prompt

# Get the prompt to use - you can modify this!
# Answer the following questions as best you can. You have access to the following tools:
#
# {tools}
#
# Use the following format:
#
# Question: the input question you must answer
# Thought: you should always think about what to do
# Action: the action to take, should be one of [{tool_names}]
# Action Input: the input to the action
# Observation: the result of the action
# ... (this Thought/Action/Action Input/Observation can repeat N times)
# Thought: I now know the final answer
# Final Answer: the final answer to the original input question
#
# Begin!
#
# Question: {input}
# Thought:{agent_scratchpad}

编写代码

from langchain import hub
from langchain.agents import AgentExecutor, create_react_agent
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_openai import OpenAItools = [TavilySearchResults(max_results=1)]
# Get the prompt to use - you can modify this!
# Answer the following questions as best you can. You have access to the following tools:
#
# {tools}
#
# Use the following format:
#
# Question: the input question you must answer
# Thought: you should always think about what to do
# Action: the action to take, should be one of [{tool_names}]
# Action Input: the input to the action
# Observation: the result of the action
# ... (this Thought/Action/Action Input/Observation can repeat N times)
# Thought: I now know the final answer
# Final Answer: the final answer to the original input question
#
# Begin!
#
# Question: {input}
# Thought:{agent_scratchpad}
prompt = hub.pull("hwchase17/react")# Choose the LLM to use
llm = OpenAI(model="gpt-3.5-turbo",temperature=0
)# Construct the ReAct agent
agent = create_react_agent(llm, tools, prompt)
# Create an agent executor by passing in the agent and tools
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)message1 = agent_executor.invoke({"input": "what is LangChain?"})
print(f"message1: {message1}")

执行结果

我们可以看到,大模型自己进行思考,并进行下一步。(详细可看执行日志)

➜ python3 test26.py> Entering new AgentExecutor chain...I should search for LangChain to see what it is
Action: tavily_search_results_json
Action Input: "LangChain"[{'url': 'https://towardsdatascience.com/getting-started-with-langchain-a-beginners-guide-to-building-llm-powered-applications-95fc8898732c', 'content': 'linkedin.com/in/804250ab\nMore from Leonie Monigatti and Towards Data Science\nLeonie Monigatti\nin\nTowards Data Science\nRetrieval-Augmented Generation (RAG): From Theory to LangChain Implementation\nFrom the theory of the original academic paper to its Python implementation with OpenAI, Weaviate, and LangChain\n--\n2\nMarco Peixeiro\nin\nTowards Data Science\nTimeGPT: The First Foundation Model for Time Series Forecasting\nExplore the first generative pre-trained forecasting model and apply it in a project with Python\n--\n22\nRahul Nayak\nin\nTowards Data Science\nHow to Convert Any Text Into a Graph of Concepts\nA method to convert any text corpus into a Knowledge Graph using Mistral 7B.\n--\n32\nLeonie Monigatti\nin\nTowards Data Science\nRecreating Andrej Karpathy’s Weekend Project\u200a—\u200aa Movie Search Engine\nBuilding a movie recommender system with OpenAI embeddings and a vector database\n--\n3\nRecommended from Medium\nKrishna Yogi\nBuilding a question-answering system using LLM on your private data\n--\n6\nRahul Nayak\nin\nTowards Data Science\nHow to Convert Any Text Into a Graph of Concepts\nA method to convert any text corpus into a Knowledge Graph using Mistral 7B.\n--\n32\nLists\nPredictive Modeling w/ Python\nPractical Guides to Machine Learning\nNatural Language Processing\nChatGPT prompts\nOnkar Mishra\nUsing langchain for Question Answering on own data\nStep-by-step guide to using langchain to chat with own data\n--\n10\nAmogh Agastya\nin\nBetter Programming\nHarnessing Retrieval Augmented Generation With Langchain\nImplementing RAG using Langchain\n--\n6\nAnindyadeep\nHow to integrate custom LLM using langchain. This is part 1 of my mini-series: Building end to end LLM powered applications without Open AI’s API\n--\n3\nAkriti Upadhyay\nin\nAccredian\nImplementing RAG with Langchain and Hugging Face\nUsing Open Source for Information Retrieval\n--\n6\nHelp\nStatus\nAbout\nCareers\nBlog\nPrivacy\nTerms\nText to speech\nTeams A Beginner’s Guide to Building LLM-Powered Applications\nA LangChain tutorial to build anything with large language models in Python\nLeonie Monigatti\nFollow\nTowards Data Science\n--\n27\nShare\n GitHub - hwchase17/langchain: ⚡ Building applications with LLMs through composability ⚡\n⚡ Building applications with LLMs through composability ⚡ Production Support: As you move your LangChains into…\ngithub.com\nWhat is LangChain?\nLangChain is a framework built to help you build LLM-powered applications more easily by providing you with the following:\nIt is an open-source project (GitHub repository) created by Harrison Chase.\n --\n--\n27\nWritten by Leonie Monigatti\nTowards Data Science\nDeveloper Advocate @'}] I should read the first search result to learn more about LangChain
Action: tavily_search_results_json
Action Input: "LangChain tutorial"[{'url': 'https://python.langchain.com/docs/get_started/quickstart', 'content': "Once we have a key we'll want to set it as an environment variable by running:\nIf you'd prefer not to set an environment variable you can pass the key in directly via the openai_api_key named parameter when initiating the OpenAI LLM class:\nLangSmith\u200b\nMany of the applications you build with LangChain will contain multiple steps with multiple invocations of LLM calls.\n The fact that LLM and ChatModel accept the same inputs means that you can directly swap them for one another in most chains without breaking anything,\nthough it's of course important to think about how inputs are being coerced and how that may affect model performance.\n The base message interface is defined by BaseMessage, which has two required attributes:\nLangChain provides several objects to easily distinguish between different roles:\nIf none of those roles sound right, there is also a ChatMessage class where you can specify the role manually.\n This chain will take input variables, pass those to a prompt template to create a prompt, pass the prompt to a language model, and then pass the output through an (optional) output parser.\n Next steps\u200b\nWe've touched on how to build an application with LangChain, how to trace it with LangSmith, and how to serve it with LangServe.\n"}] I should read the LangChain tutorial to learn more about LangChain
Action: tavily_search_results_json
Action Input: "LangChain tutorial"[{'url': 'https://python.langchain.com/docs/additional_resources/tutorials', 'content': 'Learn how to use Langchain, a Python library for building AI applications with natural language processing and generation. Explore books, handbooks, cheatsheets, courses, and tutorials by various authors and topics.'}] I should read the LangChain tutorial to learn more about LangChain
Action: tavily_search_results_json

在这里插入图片描述

这篇关于LangChain-25 ReAct 让大模型自己思考和决策下一步 AutoGPT实现途径、AGI重要里程碑的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/904917

相关文章

MySQL中查找重复值的实现

《MySQL中查找重复值的实现》查找重复值是一项常见需求,比如在数据清理、数据分析、数据质量检查等场景下,我们常常需要找出表中某列或多列的重复值,具有一定的参考价值,感兴趣的可以了解一下... 目录技术背景实现步骤方法一:使用GROUP BY和HAVING子句方法二:仅返回重复值方法三:返回完整记录方法四:

IDEA中新建/切换Git分支的实现步骤

《IDEA中新建/切换Git分支的实现步骤》本文主要介绍了IDEA中新建/切换Git分支的实现步骤,通过菜单创建新分支并选择是否切换,创建后在Git详情或右键Checkout中切换分支,感兴趣的可以了... 前提:项目已被Git托管1、点击上方栏Git->NewBrancjsh...2、输入新的分支的

Python实现对阿里云OSS对象存储的操作详解

《Python实现对阿里云OSS对象存储的操作详解》这篇文章主要为大家详细介绍了Python实现对阿里云OSS对象存储的操作相关知识,包括连接,上传,下载,列举等功能,感兴趣的小伙伴可以了解下... 目录一、直接使用代码二、详细使用1. 环境准备2. 初始化配置3. bucket配置创建4. 文件上传到os

关于集合与数组转换实现方法

《关于集合与数组转换实现方法》:本文主要介绍关于集合与数组转换实现方法,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地方,望不吝赐教... 目录1、Arrays.asList()1.1、方法作用1.2、内部实现1.3、修改元素的影响1.4、注意事项2、list.toArray()2.1、方

使用Python实现可恢复式多线程下载器

《使用Python实现可恢复式多线程下载器》在数字时代,大文件下载已成为日常操作,本文将手把手教你用Python打造专业级下载器,实现断点续传,多线程加速,速度限制等功能,感兴趣的小伙伴可以了解下... 目录一、智能续传:从崩溃边缘抢救进度二、多线程加速:榨干网络带宽三、速度控制:做网络的好邻居四、终端交互

java实现docker镜像上传到harbor仓库的方式

《java实现docker镜像上传到harbor仓库的方式》:本文主要介绍java实现docker镜像上传到harbor仓库的方式,具有很好的参考价值,希望对大家有所帮助,如有错误或未考虑完全的地... 目录1. 前 言2. 编写工具类2.1 引入依赖包2.2 使用当前服务器的docker环境推送镜像2.2

C++20管道运算符的实现示例

《C++20管道运算符的实现示例》本文简要介绍C++20管道运算符的使用与实现,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧... 目录标准库的管道运算符使用自己实现类似的管道运算符我们不打算介绍太多,因为它实际属于c++20最为重要的

Java easyExcel实现导入多sheet的Excel

《JavaeasyExcel实现导入多sheet的Excel》这篇文章主要为大家详细介绍了如何使用JavaeasyExcel实现导入多sheet的Excel,文中的示例代码讲解详细,感兴趣的小伙伴可... 目录1.官网2.Excel样式3.代码1.官网easyExcel官网2.Excel样式3.代码

python实现对数据公钥加密与私钥解密

《python实现对数据公钥加密与私钥解密》这篇文章主要为大家详细介绍了如何使用python实现对数据公钥加密与私钥解密,文中的示例代码讲解详细,感兴趣的小伙伴可以跟随小编一起学习一下... 目录公钥私钥的生成使用公钥加密使用私钥解密公钥私钥的生成这一部分,使用python生成公钥与私钥,然后保存在两个文

浏览器插件cursor实现自动注册、续杯的详细过程

《浏览器插件cursor实现自动注册、续杯的详细过程》Cursor简易注册助手脚本通过自动化邮箱填写和验证码获取流程,大大简化了Cursor的注册过程,它不仅提高了注册效率,还通过友好的用户界面和详细... 目录前言功能概述使用方法安装脚本使用流程邮箱输入页面验证码页面实战演示技术实现核心功能实现1. 随机