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

SpringBoot实现微信小程序支付功能

《SpringBoot实现微信小程序支付功能》小程序支付功能已成为众多应用的核心需求之一,本文主要介绍了SpringBoot实现微信小程序支付功能,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... 目录一、引言二、准备工作(一)微信支付商户平台配置(二)Spring Boot项目搭建(三)配置文件

基于Python实现高效PPT转图片工具

《基于Python实现高效PPT转图片工具》在日常工作中,PPT是我们常用的演示工具,但有时候我们需要将PPT的内容提取为图片格式以便于展示或保存,所以本文将用Python实现PPT转PNG工具,希望... 目录1. 概述2. 功能使用2.1 安装依赖2.2 使用步骤2.3 代码实现2.4 GUI界面3.效

MySQL更新某个字段拼接固定字符串的实现

《MySQL更新某个字段拼接固定字符串的实现》在MySQL中,我们经常需要对数据库中的某个字段进行更新操作,本文就来介绍一下MySQL更新某个字段拼接固定字符串的实现,感兴趣的可以了解一下... 目录1. 查看字段当前值2. 更新字段拼接固定字符串3. 验证更新结果mysql更新某个字段拼接固定字符串 -

java实现延迟/超时/定时问题

《java实现延迟/超时/定时问题》:本文主要介绍java实现延迟/超时/定时问题,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Java实现延迟/超时/定时java 每间隔5秒执行一次,一共执行5次然后结束scheduleAtFixedRate 和 schedu

Java Optional避免空指针异常的实现

《JavaOptional避免空指针异常的实现》空指针异常一直是困扰开发者的常见问题之一,本文主要介绍了JavaOptional避免空指针异常的实现,帮助开发者编写更健壮、可读性更高的代码,减少因... 目录一、Optional 概述二、Optional 的创建三、Optional 的常用方法四、Optio

在Android平台上实现消息推送功能

《在Android平台上实现消息推送功能》随着移动互联网应用的飞速发展,消息推送已成为移动应用中不可或缺的功能,在Android平台上,实现消息推送涉及到服务端的消息发送、客户端的消息接收、通知渠道(... 目录一、项目概述二、相关知识介绍2.1 消息推送的基本原理2.2 Firebase Cloud Me

Spring Boot项目中结合MyBatis实现MySQL的自动主从切换功能

《SpringBoot项目中结合MyBatis实现MySQL的自动主从切换功能》:本文主要介绍SpringBoot项目中结合MyBatis实现MySQL的自动主从切换功能,本文分步骤给大家介绍的... 目录原理解析1. mysql主从复制(Master-Slave Replication)2. 读写分离3.

Redis实现延迟任务的三种方法详解

《Redis实现延迟任务的三种方法详解》延迟任务(DelayedTask)是指在未来的某个时间点,执行相应的任务,本文为大家整理了三种常见的实现方法,感兴趣的小伙伴可以参考一下... 目录1.前言2.Redis如何实现延迟任务3.代码实现3.1. 过期键通知事件实现3.2. 使用ZSet实现延迟任务3.3

基于Python和MoviePy实现照片管理和视频合成工具

《基于Python和MoviePy实现照片管理和视频合成工具》在这篇博客中,我们将详细剖析一个基于Python的图形界面应用程序,该程序使用wxPython构建用户界面,并结合MoviePy、Pill... 目录引言项目概述代码结构分析1. 导入和依赖2. 主类:PhotoManager初始化方法:__in

springboot filter实现请求响应全链路拦截

《springbootfilter实现请求响应全链路拦截》这篇文章主要为大家详细介绍了SpringBoot如何结合Filter同时拦截请求和响应,从而实现​​日志采集自动化,感兴趣的小伙伴可以跟随小... 目录一、为什么你需要这个过滤器?​​​二、核心实现:一个Filter搞定双向数据流​​​​三、完整代码