当前位置: 首页 > news >正文

LangChain-15 Manage Prompt Size 管理上下文大小,用Agent的方式询问问题,并去百科检索内容,总结后返回

背景描述

这一节内容比较复杂:

  • 涉及到使用工具进行百科的检索(有现成的插件)
  • AgentExecutor来帮助我们执行
  • 后续由于上下文过大, 我们通过计算num_tokens,来控制我们的上下文

安装依赖

pip install --upgrade --quiet  langchain langchain-openai wikipedia

代码编写

GPT 3.5 Turbo 解决这个问题总是出错,偶尔可以正常解决,所以这里使用了 GPT-4-Turbo,准确率基本时100%

from operator import itemgetter
from langchain.agents import AgentExecutor, load_tools
from langchain.agents.format_scratchpad import format_to_openai_function_messages
from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser
from langchain.tools import WikipediaQueryRun
from langchain_community.utilities import WikipediaAPIWrapper
from langchain_core.prompt_values import ChatPromptValue
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI# Initialize Wikipedia tool with a wrapper for querying
wiki = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(top_k_results=5, doc_content_chars_max=10_000)
)
tools = [wiki]prompt = ChatPromptTemplate.from_messages([("system", "You are a helpful assistant"),("user", "{input}"),MessagesPlaceholder(variable_name="agent_scratchpad"),]
)
llm = ChatOpenAI(model="gpt-4-0125-preview")agent = ({"input": itemgetter("input"),"agent_scratchpad": lambda x: format_to_openai_function_messages(x["intermediate_steps"]),}| prompt| llm.bind_functions(tools)| OpenAIFunctionsAgentOutputParser()
)agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
# agent_executor.invoke(
#     {
#         "input": "Who is the current US president? What's their home state? What's their home state's bird? What's that bird's scientific name?"
#     }
# )agent_executor.invoke({"input": "大模型Grok是什么?作者是谁?他还干了什么?Grok是开源模型吗?如果是什么时候开源的?"}
)

运行结果

➜ python3 test15.py
/Users/wuzikang/Desktop/py/langchain_test/own_learn/env/lib/python3.12/site-packages/langchain/tools/__init__.py:63: LangChainDeprecationWarning: Importing tools from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead:`from langchain_community.tools import WikipediaQueryRun`.To install langchain-community run `pip install -U langchain-community`.warnings.warn(> Entering new AgentExecutor chain...Invoking: `wikipedia` with `Grok large model`Page: Grok (chatbot)
Summary: Grok is a generative artificial intelligence chatbot developed by xAI, based on a large language model (LLM). It was developed as an initiative by Elon Musk as a direct response to the rise of OpenAI's ChatGPT which Musk co-founded. The chatbot is advertised as "having a sense of humor" and direct access to Twitter (X). It is currently under beta testing for those with the premium version of X.Page: Large language model
Summary: A large language model (LLM) is a language model notable for its ability to achieve general-purpose language generation and other natural language processing tasks such as classification. LLMs acquire these abilities by learning statistical relationships from text documents during a computationally intensive self-supervised and semi-supervised training process. LLMs can be used for text generation, a form of generative AI, by taking an input text and repeatedly predicting the next token or word.LLMs are artificial neural networks. The largest and most capable are built with a decoder-only transformer-based architecture while some recent implementations are based on other architectures, such as recurrent neural network variants and Mamba (a state space model).Up to 2020, fine tuning was the only way a model could be adapted to be able to accomplish specific tasks. Larger sized models, such as GPT-3, however, can be prompt-engineered to achieve similar results. They are thought to acquire knowledge about syntax, semantics and "ontology" inherent in human language corpora, but also inaccuracies and biases present in the corpora.Some notable LLMs are OpenAI's GPT series of models (e.g., GPT-3.5 and GPT-4, used in ChatGPT and Microsoft Copilot), Google's PaLM and Gemini (the latter of which is currently used in the chatbot of the same name), xAI's Grok, Meta's LLaMA family of open-source models, Anthropic's Claude models, and Mistral AI's open source models.Page: Gemini (language model)
Summary: Gemini is a family of multimodal large language models developed by Google DeepMind, serving as the successor to LaMDA and PaLM 2. Comprising Gemini Ultra, Gemini Pro, and Gemini Nano, it was announced on December 6, 2023, positioned as a competitor to OpenAI's GPT-4. It powers the generative artificial intelligence chatbot of the same name.Page: Language model
Summary: A language model is a probabilistic model of a natural language. In 1980, the first significant statistical language model was proposed, and during the decade IBM performed ‘Shannon-style’ experiments, in which potential sources for language modeling improvement were identified by observing and analyzing the performance of human subjects in predicting or correcting text.Language models are useful for a variety of tasks, including speech recognition (helping prevent predictions of low-probability (e.g. nonsense) sequences), machine translation, natural language generation (generating more human-like text), optical character recognition, handwriting recognition, grammar induction, and information retrieval.Large language models, currently their most advanced form, are a combination of larger datasets (frequently using scraped words from the public internet), feedforward neural networks, and transformers. They have superseded recurrent neural network-based models, which had previously superseded the pure statistical models, such as word n-gram language model.Page: ChatGPT
Summary: ChatGPT (Chat Generative Pre-trained Transformer) is a chatbot developed by OpenAI and launched on November 30, 2022. Based on a large language model, it enables users to refine and steer a conversation towards a desired length, format, style, level of detail, and language. Successive prompts and replies, known as prompt engineering, are considered at each conversation stage as a context.By January 2023, it had become what was then the fastest-growing consumer software application in history, gaining over 100 million users and contributing to the growth of OpenAI's valuation to $29 billion. ChatGPT's release spurred the release of competing products, including Gemini, Ernie Bot, LLaMA, Claude, and Grok. Microsoft launched Copilot, based on OpenAI's GPT-4. Some observers raised concern about the potential of ChatGPT and similar programs to displace or atrophy human intelligence, enable plagiarism, or fuel misinformation.ChatGPT is available for use online in two versions, one built on GPT-3.5 and the other on GPT-4, both of which are members of OpenAI's proprietary series of generative pre-trained transformer (GPT) models, based on the transformer architecture developed by Google—and is fine-tuned for conversational applications using a combination of supervised learning and reinforcement learning from human feedback. ChatGPT was released as a freely available research preview, but due to its popularity, OpenAI now operates the service on a freemium model. It allows users on its free tier to access the GPT-3.5-based version, while the more advanced GPT-4-based version and priority access to newer features are provided to paid subscribers under the commercial name "ChatGPT Plus".
ChatGPT is credited with starting the AI boom, which has led to ongoing rapid and unprecedented investment in and public attention to the field of artificial intelligence.Grok是一个基于大型语言模型(LLM)的生成式人工智能聊天机器人,由xAI开发。Grok的开发是由Elon Musk作为对OpenAI推出的ChatGPT崛起的直接回应而启动的项目,其中Elon Musk是OpenAI的共同创始人。Grok的一个特点是它被宣传为“具有幽默感”,并且可以直接访问Twitter(现X)。目前,Grok仍处于Beta测试阶段,仅对X的高级版用户开放。至于Grok是否是一个开源模型,从目前的信息来看,并没有提及Grok是一个开源项目。通常,是否开源以及开源的时间点是由开发该模型的组织或团队决定的,关于Grok的开源状态,可能需要进一步从xAI或相关的官方消息中获取确切信息。Elon Musk是一位知名的企业家和工程师,他创办或领导了多个著名的技术和航天公司,包括SpaceX、Tesla Inc.、Neuralink和The Boring Company。他在推动太空探索、电动汽车发展和人工智能领域都有显著的贡献。> Finished chain.

可以看到 Agent 帮助我们执行总结出了结果:

Grok是一个基于大型语言模型(LLM)的生成式人工智能聊天机器人,由xAI开发。Grok的开发是由Elon Musk作为对OpenAI推出的ChatGPT崛起的直接回应而启动的项目,其中Elon Musk是OpenAI的共同创始人。Grok的一个特点是它被宣传为“具有幽默感”,并且可以直接访问Twitter(现X)。目前,Grok仍处于Beta测试阶段,仅对X的高级版用户开放。至于Grok是否是一个开源模型,从目前的信息来看,并没有提及Grok是一个开源项目。通常,是否开源以及开源的时间点是由开发该模型的组织或团队决定的,关于Grok的开源状态,可能需要进一步从xAI或相关的官方消息中获取确切信息。Elon Musk是一位知名的企业家和工程师,他创办或领导了多个著名的技术和航天公司,包括SpaceX、Tesla Inc.、Neuralink和The Boring Company。他在推动太空探索、电动汽车发展和人工智能领域都有显著的贡献。

在这里插入图片描述

消耗情况

由于上下文过大,资费是非常恐怖的
在这里插入图片描述

优化代码

我们通过定义了一个condense_prompt函数来计算和控制上下文

# 控制上下文大小
def condense_prompt(prompt: ChatPromptValue) -> ChatPromptValue:messages = prompt.to_messages()num_tokens = llm.get_num_tokens_from_messages(messages)ai_function_messages = messages[2:]# 这里限制了while num_tokens > 4_000:ai_function_messages = ai_function_messages[2:]num_tokens = llm.get_num_tokens_from_messages(messages[:2] + ai_function_messages)messages = messages[:2] + ai_function_messagesreturn ChatPromptValue(messages=messages)

完整的代码如下

from operator import itemgetter
from langchain.agents import AgentExecutor, load_tools
from langchain.agents.format_scratchpad import format_to_openai_function_messages
from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser
from langchain.tools import WikipediaQueryRun
from langchain_community.utilities import WikipediaAPIWrapper
from langchain_core.prompt_values import ChatPromptValue
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI# Initialize Wikipedia tool with a wrapper for querying
wiki = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(top_k_results=5, doc_content_chars_max=10_000)
)
tools = [wiki]prompt = ChatPromptTemplate.from_messages([("system", "You are a helpful assistant"),("user", "{input}"),MessagesPlaceholder(variable_name="agent_scratchpad"),]
)
llm = ChatOpenAI(model="gpt-4-0125-preview")# 控制上下文大小
def condense_prompt(prompt: ChatPromptValue) -> ChatPromptValue:messages = prompt.to_messages()num_tokens = llm.get_num_tokens_from_messages(messages)ai_function_messages = messages[2:]# 这里限制了while num_tokens > 4_000:ai_function_messages = ai_function_messages[2:]num_tokens = llm.get_num_tokens_from_messages(messages[:2] + ai_function_messages)messages = messages[:2] + ai_function_messagesreturn ChatPromptValue(messages=messages)# 注意在Chain中加入
agent = ({"input": itemgetter("input"),"agent_scratchpad": lambda x: format_to_openai_function_messages(x["intermediate_steps"]),}| prompt| condense_prompt| llm.bind_functions(tools)| OpenAIFunctionsAgentOutputParser()
)agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
# agent_executor.invoke(
#     {
#         "input": "Who is the current US president? What's their home state? What's their home state's bird? What's that bird's scientific name?"
#     }
# )agent_executor.invoke({"input": "大模型Grok是什么?作者是谁?他还干了什么?Grok是开源模型吗?如果是什么时候开源的?"}
)

在这里插入图片描述

相关文章:

LangChain-15 Manage Prompt Size 管理上下文大小,用Agent的方式询问问题,并去百科检索内容,总结后返回

背景描述 这一节内容比较复杂: 涉及到使用工具进行百科的检索(有现成的插件)有AgentExecutor来帮助我们执行后续由于上下文过大, 我们通过计算num_tokens,来控制我们的上下文 安装依赖 pip install --upgrade --qu…...

OR-TOOL 背包算法

起因&#xff1a;最近公司要发票自动匹配&#xff0c; 比如财务输入10000W块&#xff0c;找到发票中能凑10000的。然后可以快速核销。 废话不多&#xff0c; 一 官方文档 https://developers.google.cn/optimization/pack/knapsack?hlzh-cn 二 POM文件 <!--google 算法包…...

前端h5录音

时隔差不多半个月&#xff0c; 现在才来写这编博客。由于某些原因&#xff0c;我一直没有写&#xff0c;请大家原谅。前段时间开发了一个小模块。模块的主要功能就是有一个录音的功能。也就是说&#xff0c;模仿微信发送语音的功能一样。不多说&#xff0c;直接来一段代码 //自…...

Android Studio 使用Flutter开发第一个Web页面(进行中)

附上Flutter官方文档 1、新建Flutter项目&#xff08;需要勾选web选项&#xff09; 新建项目构成为&#xff1a; 2、配置 Flutter 使用 path 策略 官方文档 在main.dart中&#xff0c;需要导入flutter_web_plugins/url_strategy.dart包&#xff0c;并在main(){}函数中usePath…...

Vue.js组件精讲 第2章 基础:Vue.js组件的三个API:prop、event、slot

如果您已经对 Vue.js 组件的基础用法了如指掌&#xff0c;可以跳过本小节&#xff0c;不过当做复习稍读一下也无妨。 组件的构成 一个再复杂的组件&#xff0c;都是由三部分组成的&#xff1a;prop、event、slot&#xff0c;它们构成了 Vue.js 组件的 API。如果你开发的是一个…...

npm install 报 ERESOLVE unable to resolve dependency tree 异常解决方法

问题 在安装项目依赖时&#xff0c;很大可能会遇到安装不成功的问题&#xff0c;其中有一个很大的原因&#xff0c;可能就是因为你的npm版本导致的。 1.npm ERR! code ERESOLVE npm ERR! ERESOLVE unable to resolve dependency tree 2.ERESOLVE unable to resolve dependenc…...

RPC还是HTTP

RPC是一个远程调用的通讯协议 RPC要比HTTP快一些 1. HTTP体积大 原因是HTTP协议会带着一堆无用信息 HTTP由三部分组成 请求头 请求行 请求体 这三部分只有请求体是需要的 2. HTTP支持的序列化协议比较少 RPC支持更多轻量级的通讯协议 3. RPC协议支持定制...

Conda 常用命令总结

创建虚拟环境 conda create -n name python[your_version] 激活环境 conda activate name 退出环境 conda deactivate 查看虚拟环境 conda info --envs 删除虚拟环境 conda remove -n name --all 删除所有的安装包及cache(索引缓存、锁定文件、未使用过的包和tar包) …...

Spring MVC 文件上传和下载

文章目录 Spring MVC 中文件上传利用 commons-fileupload 文件上传使用 Servlet 3.1 内置的文件上传功能 Spring MVC 中文件下载 Spring MVC 中文件上传 为了能上传文件&#xff0c;必须将 from 表单的 method 设置为 POST&#xff0c;并将 enctype 设置为 multipart/form-data…...

WSL访问adb usb device

1.Windows上用PowerShell运行&#xff1a; winget install --interactive --exact dorssel.usbipd-win 2.在WSLUbuntu上终端运行&#xff1a; sudo apt install linux-tools-generic hwdata sudo update-alternatives --install /usr/local/bin/usbip usbip /usr/lib/linux-too…...

CDF与PDF(描述随机变量的分布情况)

一、概念解释 CDF(Cumulative Distribution Function)和PDF(Probability Density Function)是概率论和统计学中常用的两个评价指标,用于描述随机变量的分布情况。 1. CDF(累积分布函数): - CDF是描述随机变量在某个取值及其之前所有可能取值的概率的函数。它表示了累…...

react项目中需要条形码功能,安装react-barcode使用时报错

react项目中需要条形码功能&#xff0c;用yarn add安装react-barcode后&#xff0c;在项目中使用import Barcode from ‘react-barcode’&#xff0c;页面中一直白屏&#xff0c;加载中 查看控制台报以下错误 load component failed Error: Module "./react-barcode"…...

ES6基础(JavaScript基础)

本文用于检验学习效果&#xff0c;忘记知识就去文末的链接复习 1. ECMAScript介绍 ECMAScript是一种由Ecma国际&#xff08;前身为欧洲计算机制造商协会&#xff0c;英文名称是European Computer Manufacturers Association&#xff09;通过ECMA-262标准化的脚本程序设计语言…...

[蓝桥杯] 纸张尺寸(C语言)

题目链接 蓝桥杯2022年第十三届省赛真题-纸张尺寸 - C语言网 题目理解 输入一行包含一个字符串表示纸张的名称&#xff0c;该名称一定是 A0、A1、A2、A3、A4、A5、A6、A7、A8、A9 之一&#xff0c;输出两行&#xff0c;每行包含一个整数&#xff0c;依次表示长边和短边的长度…...

AI推介-多模态视觉语言模型VLMs论文速览(arXiv方向):2024.04.05-2024.04.10

文章目录~ 1.BRAVE: Broadening the visual encoding of vision-language models2.ORacle: Large Vision-Language Models for Knowledge-Guided Holistic OR Domain Modeling3.MedRG: Medical Report Grounding with Multi-modal Large Language Model4.InternLM-XComposer2-4…...

【golang】动态生成微信小程序二维码实战下:golang 生成 小程序二维码图片 并通过s3协议上传到对象存储桶 | 腾讯云 cos

项目背景 在自研的系统&#xff0c;需要实现类似草料二维码的功能 将我们自己的小程序&#xff0c;通过代码生成相想要的小程序二维码 代码已经上传到 Github 需要的朋友可以自取 https://github.com/ctra-wang/wechat-mini-qrcode 一、生成Qrcode并提交到对象存储 通过源生A…...

kubeadm k8s 1.24之后版本安装,带cri-dockerd

最后编辑时间&#xff1a;2024/3/26 适用于1.24之后的版本 单节点配置 检查是否已经安装kubectl, kubelet, kubeadm直接输入命令确定&#xff0c;如果提示没有该指令则正确 kubectl kubelet kubeadm如果之前安装&#xff0c;首先reset&#xff0c;然后使用apt remove和snap r…...

13-pyspark的共享变量用法总结

目录 前言广播变量广播变量的作用 广播变量的使用方式 累加器累加器的作用累加器的优缺点累加器的使用方式 PySpark实战笔记系列第四篇 10-用PySpark建立第一个Spark RDD(PySpark实战笔记系列第一篇)11-pyspark的RDD的变换与动作算子总结(PySpark实战笔记系列第二篇))12-pysp…...

BI数据分析软件:行业趋势与功能特点剖析

随着数据量的爆炸性增长&#xff0c;企业对于数据的需求也日益迫切。BI数据分析软件作为帮助企业实现数据驱动决策的关键工具&#xff0c;在当前的商业环境中扮演着不可或缺的角色。本文将从行业趋势、功能特点以及适用场景等方面&#xff0c;深入剖析BI数据分析软件&#xff0…...

centos7上docker搭建vulhub靶场

1 vulhub靶场概述 VulHub是一个在线靶场平台&#xff0c;提供了丰富的漏洞环境供安全爱好者学习和实践。 该平台主要面向网络安全初学者和进阶者&#xff0c;通过模拟真实的漏洞环境&#xff0c;帮助用户深入了解漏洞的成因、利用方式以及防范措施。 此外&#xff0c;VulHub还…...

国防科技大学计算机基础课程笔记02信息编码

1.机内码和国标码 国标码就是我们非常熟悉的这个GB2312,但是因为都是16进制&#xff0c;因此这个了16进制的数据既可以翻译成为这个机器码&#xff0c;也可以翻译成为这个国标码&#xff0c;所以这个时候很容易会出现这个歧义的情况&#xff1b; 因此&#xff0c;我们的这个国…...

TDengine 快速体验(Docker 镜像方式)

简介 TDengine 可以通过安装包、Docker 镜像 及云服务快速体验 TDengine 的功能&#xff0c;本节首先介绍如何通过 Docker 快速体验 TDengine&#xff0c;然后介绍如何在 Docker 环境下体验 TDengine 的写入和查询功能。如果你不熟悉 Docker&#xff0c;请使用 安装包的方式快…...

MySQL 隔离级别:脏读、幻读及不可重复读的原理与示例

一、MySQL 隔离级别 MySQL 提供了四种隔离级别,用于控制事务之间的并发访问以及数据的可见性,不同隔离级别对脏读、幻读、不可重复读这几种并发数据问题有着不同的处理方式,具体如下: 隔离级别脏读不可重复读幻读性能特点及锁机制读未提交(READ UNCOMMITTED)允许出现允许…...

vscode(仍待补充)

写于2025 6.9 主包将加入vscode这个更权威的圈子 vscode的基本使用 侧边栏 vscode还能连接ssh&#xff1f; debug时使用的launch文件 1.task.json {"tasks": [{"type": "cppbuild","label": "C/C: gcc.exe 生成活动文件"…...

解决Ubuntu22.04 VMware失败的问题 ubuntu入门之二十八

现象1 打开VMware失败 Ubuntu升级之后打开VMware上报需要安装vmmon和vmnet&#xff0c;点击确认后如下提示 最终上报fail 解决方法 内核升级导致&#xff0c;需要在新内核下重新下载编译安装 查看版本 $ vmware -v VMware Workstation 17.5.1 build-23298084$ lsb_release…...

从深圳崛起的“机器之眼”:赴港乐动机器人的万亿赛道赶考路

进入2025年以来&#xff0c;尽管围绕人形机器人、具身智能等机器人赛道的质疑声不断&#xff0c;但全球市场热度依然高涨&#xff0c;入局者持续增加。 以国内市场为例&#xff0c;天眼查专业版数据显示&#xff0c;截至5月底&#xff0c;我国现存在业、存续状态的机器人相关企…...

Linux简单的操作

ls ls 查看当前目录 ll 查看详细内容 ls -a 查看所有的内容 ls --help 查看方法文档 pwd pwd 查看当前路径 cd cd 转路径 cd .. 转上一级路径 cd 名 转换路径 …...

反射获取方法和属性

Java反射获取方法 在Java中&#xff0c;反射&#xff08;Reflection&#xff09;是一种强大的机制&#xff0c;允许程序在运行时访问和操作类的内部属性和方法。通过反射&#xff0c;可以动态地创建对象、调用方法、改变属性值&#xff0c;这在很多Java框架中如Spring和Hiberna…...

Linux-07 ubuntu 的 chrome 启动不了

文章目录 问题原因解决步骤一、卸载旧版chrome二、重新安装chorme三、启动不了&#xff0c;报错如下四、启动不了&#xff0c;解决如下 总结 问题原因 在应用中可以看到chrome&#xff0c;但是打不开(说明&#xff1a;原来的ubuntu系统出问题了&#xff0c;这个是备用的硬盘&a…...

GitHub 趋势日报 (2025年06月08日)

&#x1f4ca; 由 TrendForge 系统生成 | &#x1f310; https://trendforge.devlive.org/ &#x1f310; 本日报中的项目描述已自动翻译为中文 &#x1f4c8; 今日获星趋势图 今日获星趋势图 884 cognee 566 dify 414 HumanSystemOptimization 414 omni-tools 321 note-gen …...