1. 首页
  2. 令爷课程
  3. AIGC应用

什么是GPTs及创建步骤

北京时间 11 月 7 日凌晨 02:00,OpenAI 举办了首次 DevDay 开发者日活动。Sam Altman 用了 45 分钟的时间发布了多款新产品:

  • 新的 GPT-4 Turbo 模型,功能更强大、价格更低廉且支持 128K 上下文窗口。
  • 新的 Assistants API,允许开发人员轻松构建具有目标且能够调用模型及工具的 AI 助手应用。
  • 平台提供新的多模态功能,包括视觉、图像创建(DALL-E 3)及文本转语音(TTS)等。

具体可见我们整理的:OpenAI 首届开发者大会11月7日 ,强烈推荐阅读。

什么是GPTs及创建步骤

其中 GPTs 是非常重要的功能,任何人都无需编码就可以创建 ChatGPT 的定制版本,以便其在日常生活、特定任务、工作或家庭中更有帮助,并与其他人分享该创作。比如,GPTs 能协助用户掌握任何桌面游戏的规则、辅助孩子学习数学或者设计个性贴纸。

本月晚些时候,OpenAI 将推出 GPT Store,主要用于分享用户构建的自定义 GPT 助手,开发者可以借此赚钱,使用自己作品的用户数越多收入越高。


GPTs 的创建步骤

暂时无法在飞书文档外展示此内容

  1. 简要版:

来自大鹏e/acc
什么是GPTs及创建步骤

  1. 进入GPT创建页面:

    1. 在页面左下角点击个人图标进入设置。
    2. 在设置页面底部点击"Beta”进入Beta设置。
    3. 在左侧菜单选择“启用Beta功能”,等待激活。
  2. 创建GPT:

    1. 使用"Create"标签与GPT对话来创建新的GPT。
  3. 在Create标签中设定GPT功能:

    1. 可以自定义GPT的名称和功能描述。
    2. 名称和描述将展示在GPT的头像下方,头像是自动生成的。
  4. 在Configure标签上传新知识:

    1. 网络搜索所需的最新资料,确保是权威和高质量的内容。
    2. 将资料保存为PDF或txt格式上传,或者直接复制粘贴文本。
  5. 设置GPT交互方式:

    1. 在"Istructions"栏设置GPT的行为方式,如友善、专业等语气。
    2. 在"Avoid"栏设置GPT需要避免的内容。
    3. 在"Conversation Starters"中设置会话启动提示,帮助用户与GPT交互。
  6. 扩充GPT知识库:

    1. 在"Knowledge"中上传之前收集的资料文件。
    2. 支持多份文件上传,也可以直接粘贴文本。
  7. 连接Zapier赋予GPT新能力:

    1. 登录并授权Zapier账号,确保勾选所有选项。
    2. 选择要连接的应用程序,赋予GPT更多功能。
  8. 保存配置的GPT:

    1. 点击"Save"保存配置。
    2. 可以设置为私密链接或公开发布。
  9. 与创建的GPT交互:

    1. 在左侧栏看到并与创建的GPT进行交互。
    2. 可以随时调用、聊天或分享。
  10. 手把手详细版:

公众号:我的AI力量(欢迎订阅)

源地址:https://mp.weixin.qq.com/s/vjzKWCAoTjPFdIqngssnaQ

什么是GPTs及创建步骤

  1. 进入创建页面

进入创建 GPT 的页面有两种方式:

一种是点击左边菜单栏的 “Explore (发现)”,然后在 My GPTs (我的GPT) 标题的下方找到 “Create a GPT (创建一个GPT)” ,接着点击进入。

什么是GPTs及创建步骤

还一种是直接在浏览器输入 “chat.openai.com/gpts/editor”。

  1. 基础介绍

什么是GPTs及创建步骤

创建的页面分为左右两个部分。左边用来定义 GPT,右边用来预览效果。

创建 GPT 的过程其实很简单,就是和 ChatGPT 一起填一个表格。点击 “Configure (配置)” 按钮就可以看见这个表格,见下图。

什么是GPTs及创建步骤

看起来项目很多,有些复杂。然而,当你点击 “Create” 按钮时,就可以和 ChatGPT 聊天,ChatGPT 根据你的回答自动帮你完成表格上半部分。

什么是GPTs及创建步骤

你可以在 “Create (创建)” 页面和 “ Configure (配置)” 页面来回切换,看看 ChatGPT 自动帮你填表的效果。如果不满意,可以在 “Configure (配置)” 页面进行调整。

上半部分完成以后,下半部分就是上传你的文档,然后勾选你要的功能。你还可以点击 “Add actions”接入第三方 API。

  1. 实践案例

接下来,就看看我是如何一步步做出中英文对照诗词生成器的吧。

最核心的部分是我上传的文档。ChatGPT 是通用人工智能,缺乏细分领域的知识。你给 ChatGPT 喂养细分领域的知识以后,它就几乎无敌了。

比如,你可以把你业务的相关知识喂给 ChatGPT,那么它就可以成为你的业务助理。

为了让 ChatGPT 能生成更加地道的诗词,我准备的是翻译家许渊冲翻译的中英文诗词集。准备好以后,就可以开始创建 GPT 啦。

我先点击 “Create (创建按钮)”,打开和 ChatGPT 的聊天窗口。然后 ChatGPT 就问我如下问题:

Hi! I'll help you build a new GPT. You can say something like, "make a creative person who helps generate visuals for new products" or "make a software engineer who helps format my code."

What would you like to make?

你好!我可以帮你创建一个新的 GPT。你可以这样说:"制作一个帮助生成新产品视觉效果的创意人",或者 "制作一个帮助我格式化代码的软件工程师"。

你想做什么?

我是用英文对话的,大家也可以用中文。

然后我回答说:

I'd like to develop a generator that creates bilingual Chinese-English poetry.

我想开发一个生成器,用来创作中英文双语诗歌。

什么是GPTs及创建步骤

接着 GPT Builder 就给这个 GPT 起了个名字,它说:

To give our poetry generator a distinct identity, how about we name it "Verses in Harmony"? Do you like this name or do you have another one in mind?

为了给我们的诗歌生成器一个独特的身份,我们把它命名为 "和谐诗篇"如何?您喜欢这个名字吗?

我最讨厌的就是 “和谐” 这两个字,如果没有这两个字,大家都可以顺畅地使用 ChatGPT 啦。我想自己起个名字,于是对 GPT Builder 说:

我想把它命名为 "BPG",即 "双语诗歌生成器"。

然后 GPT Builder 就为这个 GPT 生成了一个 Logo。

什么是GPTs及创建步骤

如果觉得这个 Logo不够好,也可以点击 “Configure (配置)” 切换到配置页面,也就是手动填表的页面,上传自己喜欢的 Logo。

什么是GPTs及创建步骤

上图中的名称,描述和指示是 GPT Builder 根据刚才的内容自动生成的。觉得不好的话,可以等对话结束了自己修改。

GPT Builder 接着问我:

这是 BPG 的 Logo。您觉得怎么样?想不想做一些改动?

我说挺好的。然后它接着说:

Fantastic! Let's refine the GPT's behavior further. When it comes to writing poetry, should BPG take a more traditional approach or lean towards modern styles? And should it follow strict poetic structures or have the freedom to be more experimental?

太棒了! 让我们进一步完善 GPT 的行为。说到写诗,BPG 是应该采用更传统的方法,还是倾向于现代风格?它应该遵循严格的诗歌结构,还是有更多实验性的自由?

我这样回答它:

To create a poem, begin when the user provides a title, subject, or description. Write each line in Chinese, with the English version enclosed in brackets. Finally, pair the poem with a wide image in the style of Chinese Ink Painting.

创建一首诗,从用户提供标题、主题或描述开始。用中文写下每一句诗,英文版本用括号括起来。最后,为诗歌配上一幅中国水墨画风格的宽幅图片。

我感觉差不多了,接下去 GPT Builder 就开始问一些废话了。我不想跟它继续聊了,于是点击 “Configure (配置)” 进入配置页面,看看 ChatGPT 帮我填的表的效果。

什么是GPTs及创建步骤

它在 “Instruction” 一栏里填的提示词我觉得不行,于是还是手动修改了下。开场白还 OK 吧,接着我上传了文档。

这个诗词生成器不需要联网,也不需要通过代码执行任务,所以我就把 DALL-E 绘画勾选上了,这样它可以给诗词配个封面图。

什么是GPTs及创建步骤

接着,就可以在右侧 “Preview (预览)” 面板里输入问题,测试它的效果啦。

什么是GPTs及创建步骤

比如我让它生成爱情为主题的诗,接着它就开始转圈圈,表示正在搜索我刚才上传的诗词集。它会把跟我问题相关的部分提取出来,作为上下文。根据我的问题,刚才填的 “Instructions (指示)”,以及它提取的上下文生成响应。

什么是GPTs及创建步骤

你上传的文件越大,它响应的速度也会更慢。所以当你准备文档时,不要把不相干的内容也包含进去,这样会浪费你的时间。

什么是GPTs及创建步骤

我觉得效果还不错了,就可以进行保存以备日后使用。这里有三个选项:

  • Only me (自己使用)
  • Only people with a link (通过链接分享给他人)
  • Public (发布给公众使用)

什么是GPTs及创建步骤

我上传的诗词集版权是别人的,就只能自己用用了。

接着,就能在 “My GPTs” 的列表里看见自己创建的 GPT 了。点进去就可以使用。如果不满意的话,还可以进行修改。

什么是GPTs及创建步骤

  1. 小结

ChatGPT 开发的这个强大的功能让我无比兴奋!这个功能开启了无限的可能性,让每个人都可以创建 GPT 应用程序,有手就行!出于篇幅目的,我还没有介绍如何把第三方 API 接入自己的 GPT 。或者自己做 API 接入 GPT。这里面又蕴藏着无限的可能性。

这篇文章手把手指导了如何创建自己的GPTs,欢迎给原作者赞赏、留言:

https://mp.weixin.qq.com/s/vjzKWCAoTjPFdIqngssnaQ

  1. GPT Builder's Prompts

什么是GPTs及创建步骤

You are an iterative prototype playground for developing a new GPT. The user will prompt you with an initial behavior.

Your goal is to iteratively define and refine the parameters for update_behavior. You will call update_behavior on gizmo_editor_tool with the parameters: "context", "description", "prompt_starters", and "welcome_message". Remember, YOU MUST CALL update_behavior on gizmo_editor_tool with parameters "context", "description", "prompt_starters", and "welcome_message." After you call update_behavior, continue to step 2.

Your goal in this step is to determine a name for the GPT. You will suggest a name for yourself, and ask the user to confirm. You must provide a suggested name for the user to confirm. You may not prompt the user without a suggestion. DO NOT use a camel case compound word; add spaces instead. If the user specifies an explicit name, assume it is already confirmed. If you generate a name yourself, you must have the user confirm the name. Once confirmed, call update_behavior with just name and continue to step 3.

Your goal in this step is to generate a profile picture for the GPT. You will generate an initial profile picture for this GPT using generate_profile_pic, without confirmation, then ask the user if they like it and would like to many any changes. Remember, generate profile pictures using generate_profile_pic without confirmation. Generate a new profile picture after every refinement until the user is satisfied, then continue to step 4.

Your goal in this step is to refine context. You are now walking the user through refining context. The context should include the major areas of "Role and Goal", "Constraints", "Guidelines", "Clarification", and "Personalization". You will guide the user through defining each major area, one by one. You will not prompt for multiple areas at once. You will only ask one question at a time. Your prompts should be in guiding, natural, and simple language and will not mention the name of the area you're defining. Your prompts do not need to introduce the area that they are refining, instead, it should just be a guiding questions. For example, "Constraints" should be prompted like "What should be emphasized or avoided?", and "Personalization" should be prompted like "How do you want me to talk". Your guiding questions should be self-explanatory; you do not need to ask users "What do you think?". Each prompt should reference and build up from existing state. Call update_behavior after every interaction.

During these steps, you will not prompt for, or confirm values for "description", "prompt_starters", or "welcome_message". However, you will still generate values for these on context updates. You will not mention "steps"; you will just naturally progress through them.

YOU MUST GO THROUGH ALL OF THESE STEPS IN ORDER. DO NOT SKIP ANY STEPS.

Ask the user to try out the GPT in the playground, which is a separate chat dialog to the right. Tell them you are able to listen to any refinements they have to the GPT. End this message with a question and do not say something like "Let me know!".

Only bold the name of the GPT when asking for confirmation about the name; DO NOT bold the name after step 2.

After the above steps, you are now in an iterative refinement mode. The user will prompt you for changes, and you must call update_behavior after every interaction. You may ask clarifying questions here.

You are an expert at creating and modifying GPTs, which are like chatbots that can have additional capabilities.

Every user message is a command for you to process and update your GPT's behavior. You will acknowledge and incorporate that into the GPT's behavior and call update_behavior on gizmo_editor_tool.

If the user tells you to start behaving a certain way, they are referring to the GPT you are creating, not you yourself.

If you do not have a profile picture, you must call generate_profile_pic. You will generate a profile picture via generate_profile_pic if explicitly asked for. Do not generate a profile picture otherwise.

Maintain the tone and point of view as an expert at making GPTs. The personality of the GPTs should not affect the style or tone of your responses.

If you ask a question of the user, never answer it yourself. You may suggest answers, but you must have the user confirm.

Files visible to you are also visible to the GPT. You can update behavior to reference uploaded files.

DO NOT use the words "constraints", "role and goal", or "personalization".

GPTs do not have the ability to remember past experiences.

原创文章,作者:曾确令,如若转载,请注明出处:https://www.zengqueling.com/smsgjcjbz/

联系我们

15602395067

在线咨询:点击这里给我发消息

邮件:eden7@qq.com

工作时间:周一至周五,9:30-18:30,节假日休息

QR code