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

Java实现检查多个时间段是否有重合

《Java实现检查多个时间段是否有重合》这篇文章主要为大家详细介绍了如何使用Java实现检查多个时间段是否有重合,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... 目录流程概述步骤详解China编程步骤1:定义时间段类步骤2:添加时间段步骤3:检查时间段是否有重合步骤4:输出结果示例代码结语作

使用C++实现链表元素的反转

《使用C++实现链表元素的反转》反转链表是链表操作中一个经典的问题,也是面试中常见的考题,本文将从思路到实现一步步地讲解如何实现链表的反转,帮助初学者理解这一操作,我们将使用C++代码演示具体实现,同... 目录问题定义思路分析代码实现带头节点的链表代码讲解其他实现方式时间和空间复杂度分析总结问题定义给定

Java覆盖第三方jar包中的某一个类的实现方法

《Java覆盖第三方jar包中的某一个类的实现方法》在我们日常的开发中,经常需要使用第三方的jar包,有时候我们会发现第三方的jar包中的某一个类有问题,或者我们需要定制化修改其中的逻辑,那么应该如何... 目录一、需求描述二、示例描述三、操作步骤四、验证结果五、实现原理一、需求描述需求描述如下:需要在

部署Vue项目到服务器后404错误的原因及解决方案

《部署Vue项目到服务器后404错误的原因及解决方案》文章介绍了Vue项目部署步骤以及404错误的解决方案,部署步骤包括构建项目、上传文件、配置Web服务器、重启Nginx和访问域名,404错误通常是... 目录一、vue项目部署步骤二、404错误原因及解决方案错误场景原因分析解决方案一、Vue项目部署步骤

如何使用Java实现请求deepseek

《如何使用Java实现请求deepseek》这篇文章主要为大家详细介绍了如何使用Java实现请求deepseek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... 目录1.deepseek的api创建2.Java实现请求deepseek2.1 pom文件2.2 json转化文件2.2

python使用fastapi实现多语言国际化的操作指南

《python使用fastapi实现多语言国际化的操作指南》本文介绍了使用Python和FastAPI实现多语言国际化的操作指南,包括多语言架构技术栈、翻译管理、前端本地化、语言切换机制以及常见陷阱和... 目录多语言国际化实现指南项目多语言架构技术栈目录结构翻译工作流1. 翻译数据存储2. 翻译生成脚本

如何通过Python实现一个消息队列

《如何通过Python实现一个消息队列》这篇文章主要为大家详细介绍了如何通过Python实现一个简单的消息队列,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... 目录如何通过 python 实现消息队列如何把 http 请求放在队列中执行1. 使用 queue.Queue 和 reque

Python如何实现PDF隐私信息检测

《Python如何实现PDF隐私信息检测》随着越来越多的个人信息以电子形式存储和传输,确保这些信息的安全至关重要,本文将介绍如何使用Python检测PDF文件中的隐私信息,需要的可以参考下... 目录项目背景技术栈代码解析功能说明运行结php果在当今,数据隐私保护变得尤为重要。随着越来越多的个人信息以电子形

使用 sql-research-assistant进行 SQL 数据库研究的实战指南(代码实现演示)

《使用sql-research-assistant进行SQL数据库研究的实战指南(代码实现演示)》本文介绍了sql-research-assistant工具,该工具基于LangChain框架,集... 目录技术背景介绍核心原理解析代码实现演示安装和配置项目集成LangSmith 配置(可选)启动服务应用场景

使用Python快速实现链接转word文档

《使用Python快速实现链接转word文档》这篇文章主要为大家详细介绍了如何使用Python快速实现链接转word文档功能,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... 演示代码展示from newspaper import Articlefrom docx import