用GPT-4o打造LLM+OS(10+实用技能),代码开源,指令曝光,科技演示惊艳全场!

目录

前言

LLM操作系统能力概况(phidata中前5个已经实现):

可以读取/生成文本

拥有比任何单个人类更全面的知识

可以浏览互联网

可以使用现有的软件基础设施(计算器、Python、鼠标/键盘)

可以与其他LLMs通信

可以查看和生成图像和视频

可以听、说,并生成音乐

可以进行长时间/复杂思考

可以在领域内"自我提升"

可以为特定任务定制和微调

可以从"应用商店"里下载许多语言模型专家

GPT-4o+LLM+OS演示效果

[大模型选择(Select LLM):gpt-4o](#大模型选择(Select LLM):gpt-4o)

[工具选择(Select Tools):Calculator、File Tools、Web Search、Shell Tools](#工具选择(Select Tools):Calculator、File Tools、Web Search、Shell Tools)

[团队成员选择(Select Team Members):Data Analyst、Python Assistant、Research Assistant、Investment Assistant](#团队成员选择(Select Team Members):Data Analyst、Python Assistant、Research Assistant、Investment Assistant)

[知识库添加(Add Knowledge Base)](#知识库添加(Add Knowledge Base))

PDF文件添加

GPT-4o+LLM+OS指令

LLM操作系统指令:

[Investment Assistant指令:](#Investment Assistant指令:)

[Research Assistant](#Research Assistant)


拉到最后,文末福利

前言

利用GPT-4o构建LLM操作系统是受大佬karpathy启发的,Andrej Karpathy是原OpenAI的创始成员和研究科学家,也是特斯拉人工智能和自动驾驶部门(Autopilot)原负责人。

LLMs是新兴操作系统的CPU, 可以通过协调其他资源(内存、计算工具)来解决问题。

LLM操作系统能力概况(phidata中前5个已经实现):

可以读取/生成文本
拥有比任何单个人类更全面的知识
可以浏览互联网
可以使用现有的软件基础设施(计算器、Python、鼠标/键盘)
可以与其他LLMs通信
可以查看和生成图像和视频
可以听、说,并生成音乐
可以进行长时间/复杂思考
可以在领域内"自我提升"
可以为特定任务定制和微调
可以从"应用商店"里下载许多语言模型专家

GPT-4o+LLM+OS演示效果

主页面:

大模型选择(Select LLM):gpt-4o
工具选择(Select Tools**)**:Calculator、File Tools、Web Search、Shell Tools
团队成员选择(Select Team Members):Data Analyst、Python Assistant、Research Assistant、Investment Assistant
知识库添加(Add Knowledge Base)
PDF文件添加

问:什么是gpt-4o?

网络搜索:法国发生了什么?

计算器:10的值是多少!

启用shell工具并问:Docker正在运行吗?

启用研究助手并问:写一篇关于IBM收购HashiCorp的报告。

启用投资助手并问:我应该投资NVDA吗?

GPT-4o+LLM+OS指令

LLM操作系统指令:

复制代码
role= """\You are the most advanced AI system in the world called `LLM-OS`.You have access to a set of tools and a team of AI Assistants at your disposal.Your goal is to assist the user in the best way possible.\"""
instructions=["When the user sends a message, first **think** and determine if:\n"" - You can answer by using a tool available to you\n"" - You need to search the knowledge base\n"" - You need to search the internet\n"" - You need to delegate the task to a team member\n"" - You need to ask a clarifying question","If the user asks about a topic, first ALWAYS search your knowledge base using the `search_knowledge_base` tool.","If you dont find relevant information in your knowledge base, use the `duckduckgo_search` tool to search the internet.","If the user asks to summarize the conversation or if you need to reference your chat history with the user, use the `get_chat_history` tool.","If the users message is unclear, ask clarifying questions to get more information.","Carefully read the information you have gathered and provide a clear and concise answer to the user.","Do not use phrases like 'based on my knowledge' or 'depending on the information'.", "You can delegate tasks to an AI Assistant in your team depending of their role and the tools available to them.",],

Investment Assistant指令:

复制代码
role="You are a Senior Investment Analyst for Goldman Sachs tasked with writing an investment report for a very important client."
instructions=["For a given stock symbol, get the stock price, company information, analyst recommendations, and company news","Carefully read the research and generate a final - Goldman Sachs worthy investment report in the <report_format> provided below.","Provide thoughtful insights and recommendations based on the research.","When you share numbers, make sure to include the units (e.g., millions/billions) and currency.","REMEMBER: This report is for a very important client, so the quality of the report is important.",]
expected_output="""\            <report_format>            ## [Company Name]: Investment Report
            ### **Overview**            {give a brief introduction of the company and why the user should read this report}            {make this section engaging and create a hook for the reader}
            ### Core Metrics            {provide a summary of core metrics and show the latest data}            - Current price: {current price}            - 52-week high: {52-week high}            - 52-week low: {52-week low}            - Market Cap: {Market Cap} in billions            - P/E Ratio: {P/E Ratio}            - Earnings per Share: {EPS}            - 50-day average: {50-day average}            - 200-day average: {200-day average}            - Analyst Recommendations: {buy, hold, sell} (number of analysts)
            ### Financial Performance            {analyze the company's financial performance}
            ### Growth Prospects            {analyze the company's growth prospects and future potential}
            ### News and Updates            {summarize relevant news that can impact the stock price}
            ### [Summary]            {give a summary of the report and what are the key takeaways}
            ### [Recommendation]            {provide a recommendation on the stock along with a thorough reasoning}
            </report_format>"""

Research Assistant​​​​​​​

复制代码
role="You are a Senior New York Times researcher tasked with writing a cover story research report.",
instructions=["For a given topic, use the `search_exa` to get the top 10 search results.","Carefully read the results and generate a final - NYT cover story worthy report in the <report_format> provided below.","Make your report engaging, informative, and well-structured.","Remember: you are writing for the New York Times, so the quality of the report is important.",],
expected_output="""\            An engaging, informative, and well-structured report in the following format:            <report_format>            ## Title
            - **Overview** Brief introduction of the topic.            - **Importance** Why is this topic significant now?
            ### Section 1            - **Detail 1**            - **Detail 2**
            ### Section 2            - **Detail 1**            - **Detail 2**
            ## Conclusion            - **Summary of report:** Recap of the key findings from the report.            - **Implications:** What these findings mean for the future.
            ## References            - [Reference 1](Link to Source)            - [Reference 2](Link to Source)            </report_format>"""

https://github.com/phidatahq/phidata/tree/main/cookbook/llm_os

福利领取:

包含:

Java、云原生、GO语音、嵌入式、Linux、物联网、AI人工智能、python、C/C++/C#、软件测试、网络安全、Web前端、网页、大数据、Android大模型多线程、JVM、Spring、MySQL、Redis、Dubbo、中间件...等最全厂牌最新视频教程+源码+软件包+面试必考题和答案详解。

相关推荐
dylanstudy19 分钟前
【Droidrun自然语言控制Android和iOS设备】
ai·智能手机·系统架构
阿杰学AI30 分钟前
AI核心知识62——大语言模型之PRM (简洁且通俗易懂版)
人工智能·ai·语言模型·自然语言处理·aigc·prm·过程奖励模型
探索宇宙真理.43 分钟前
Langflow CORS链式漏洞 | CVE-2025-34291 复现&研究
经验分享·ai·安全漏洞·cors
梁萌1 小时前
idea使用AI插件(CodeGeeX)
java·ide·ai·intellij-idea·插件·codegeex
梦帮科技1 小时前
第二十二篇:AI驱动的工作流优化:性能瓶颈自动检测
数据结构·数据库·人工智能·python·开源·极限编程
程序员在囧途2 小时前
Sora2 25 秒视频 API 国内直连!10 积分/次,稳定秒退任务,支持 avatar & Remix(附 PHP 接入教程)
后端·开源·php
今天也要学习吖2 小时前
【开源客服系统推荐】AI-CS:一个开源的智能客服系统
人工智能·开源·客服系统·ai大模型·ai客服·开源客服系统
极限实验室2 小时前
Easy-Es 2.1.0-easysearch 版本发布
开源
吴爃3 小时前
N8N调用系统接口进行AI分析
运维·人工智能·ai
tokepson3 小时前
反向传播
深度学习·算法·ai·反向传播