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

使用Python实现在Word中添加或删除超链接

《使用Python实现在Word中添加或删除超链接》在Word文档中,超链接是一种将文本或图像连接到其他文档、网页或同一文档中不同部分的功能,本文将为大家介绍一下Python如何实现在Word中添加或... 在Word文档中,超链接是一种将文本或图像连接到其他文档、网页或同一文档中不同部分的功能。通过添加超

windos server2022里的DFS配置的实现

《windosserver2022里的DFS配置的实现》DFS是WindowsServer操作系统提供的一种功能,用于在多台服务器上集中管理共享文件夹和文件的分布式存储解决方案,本文就来介绍一下wi... 目录什么是DFS?优势:应用场景:DFS配置步骤什么是DFS?DFS指的是分布式文件系统(Distr

NFS实现多服务器文件的共享的方法步骤

《NFS实现多服务器文件的共享的方法步骤》NFS允许网络中的计算机之间共享资源,客户端可以透明地读写远端NFS服务器上的文件,本文就来介绍一下NFS实现多服务器文件的共享的方法步骤,感兴趣的可以了解一... 目录一、简介二、部署1、准备1、服务端和客户端:安装nfs-utils2、服务端:创建共享目录3、服

Golang的CSP模型简介(最新推荐)

《Golang的CSP模型简介(最新推荐)》Golang采用了CSP(CommunicatingSequentialProcesses,通信顺序进程)并发模型,通过goroutine和channe... 目录前言一、介绍1. 什么是 CSP 模型2. Goroutine3. Channel4. Channe

C#使用yield关键字实现提升迭代性能与效率

《C#使用yield关键字实现提升迭代性能与效率》yield关键字在C#中简化了数据迭代的方式,实现了按需生成数据,自动维护迭代状态,本文主要来聊聊如何使用yield关键字实现提升迭代性能与效率,感兴... 目录前言传统迭代和yield迭代方式对比yield延迟加载按需获取数据yield break显式示迭

Python实现高效地读写大型文件

《Python实现高效地读写大型文件》Python如何读写的是大型文件,有没有什么方法来提高效率呢,这篇文章就来和大家聊聊如何在Python中高效地读写大型文件,需要的可以了解下... 目录一、逐行读取大型文件二、分块读取大型文件三、使用 mmap 模块进行内存映射文件操作(适用于大文件)四、使用 pand

python实现pdf转word和excel的示例代码

《python实现pdf转word和excel的示例代码》本文主要介绍了python实现pdf转word和excel的示例代码,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... 目录一、引言二、python编程1,PDF转Word2,PDF转Excel三、前端页面效果展示总结一

Python xmltodict实现简化XML数据处理

《Pythonxmltodict实现简化XML数据处理》Python社区为提供了xmltodict库,它专为简化XML与Python数据结构的转换而设计,本文主要来为大家介绍一下如何使用xmltod... 目录一、引言二、XMLtodict介绍设计理念适用场景三、功能参数与属性1、parse函数2、unpa

C#实现获得某个枚举的所有名称

《C#实现获得某个枚举的所有名称》这篇文章主要为大家详细介绍了C#如何实现获得某个枚举的所有名称,文中的示例代码讲解详细,具有一定的借鉴价值,有需要的小伙伴可以参考一下... C#中获得某个枚举的所有名称using System;using System.Collections.Generic;usi

Go语言实现将中文转化为拼音功能

《Go语言实现将中文转化为拼音功能》这篇文章主要为大家详细介绍了Go语言中如何实现将中文转化为拼音功能,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... 有这么一个需求:新用户入职 创建一系列账号比较麻烦,打算通过接口传入姓名进行初始化。想把姓名转化成拼音。因为有些账号即需要中文也需要英