How to Add Custom GPTs to Instagram DMs (OpenAI GPTs Tutorial)

Liam Ottley
17 Nov 202327:53

Summary

TLDR本视频将向您展示如何快速将自定义GPT连接到Instagram,以完全自动化您的DM。通过使用GPT技术,您可以自动化客户支持和潜在客户生成等关键任务。视频提供了一个实时演示,展示了如何设置和避免常见错误。您将学习如何使用OpenAI的API、Repl托管代码、Mini Chat与Instagram集成,并处理潜在客户捕获。视频还提供了详细的步骤和模板,帮助您轻松复制和修改设置,以适应您自己的业务需求。

Takeaways

  • 🚀 本视频将展示如何快速将自定义GPT连接到Instagram,实现DMs的自动化。
  • 📈 Instagram是一个强大的销售渠道,正确使用可以大幅提升业务。
  • 🤖 连接AI助手到Instagram DMs的过程可能会非常复杂,视频提供了简化方法。
  • 🔍 视频通过实际演示,展示了如何设置自动化流程。
  • 📝 使用了特定的关键词触发自动化,如“测试”,并展示了如何与用户互动。
  • 📊 展示了如何通过GPT技术获取用户信息并进行潜在客户捕获。
  • 🛠️ 介绍了如何使用OpenAI的API和Repl托管代码来实现自动化。
  • 🔗 详细说明了如何设置和修改API密钥,以及如何与Airtable集成。
  • 🔄 解释了如何处理Mini Chat的10秒超时问题,以及如何循环检查响应。
  • 📌 提供了Mini Chat模板,用户可以根据自己的需求进行调整。
  • 📚 强调了视频教程的复杂性,并鼓励观众尝试并应用所学知识。
  • 📢 视频最后提供了资源链接,观众可以下载并使用这些资源。

Q & A

  • 视频中提到的最快的连接自定义GPT到Instagram的方法是什么?

    -视频提供了一个逐步教程,通过使用Mini Chat和Repl来自动化Instagram的DMs,从而连接GPT。

  • Instagram作为一个销售渠道有哪些优势?

    -Instagram是一个非常强大的销售渠道,当正确使用时,可以通过连接GPT来自动化关键任务,如客户支持和潜在客户生成。

  • 在Instagram DMS中连接AI助手遇到了哪些问题?

    -连接AI助手到Instagram DMS的过程可能非常痛苦,视频作者在过去几个月中遇到了持续的问题。

  • 视频中展示的自动化示例是关于什么的?

    -视频中的自动化示例是关于如何通过Instagram故事回复触发自动化,然后通过Mini Chat与GPT后端进行交互,以提供个性化的客户支持和潜在客户捕获。

  • 如何通过视频教程创建自己的GPT程序?

    -视频提供了一个模板,用户可以复制并按照步骤操作,以创建自己的GPT程序。这包括设置知识库、指令和工具。

  • 在Repl中设置GPT程序需要哪些API密钥?

    -需要OpenAI的API密钥来访问GPT模型,以及Airtable的API密钥来处理潜在客户捕获。

  • 如何确保GPT程序能够访问知识库?

    -在Repl的设置中,需要上传知识库文档,并确保在创建GPT程序时引用正确的文件名。

  • 视频教程中提到的Mini Chat的10秒超时问题是如何解决的?

    -通过将聊天端点分为两个部分:chat endpoint和check endpoint,以及在Mini Chat中设置循环检查,来解决10秒超时问题。

  • 如何将GPT程序部署到Instagram上?

    -通过在Mini Chat中设置触发器,如故事回复,然后通过Repl中的API调用与GPT程序交互,实现在Instagram上的自动化对话。

  • 视频教程中提到的AAA加速器计划是什么?

    -AAA加速器计划是一个旨在帮助个人在90天内建立盈利且可扩展的AI业务的项目。

Outlines

00:00

🚀 自动化Instagram DMs的快速方法

本视频将展示如何快速将自定义GPT连接到Instagram,以自动化DMs。Instagram是一个强大的销售渠道,通过连接GPT,可以自动化客户支持和潜在客户生成等关键任务。视频作者分享了自己过去几个月在连接AI助手到Instagram DMs时遇到的问题,并提供了一种简化的方法。

05:01

🛠️ 设置GPT自动化的步骤

视频作者详细介绍了如何设置GPT自动化,包括获取必要的API密钥,设置Airtable API密钥,以及如何在Replit上部署代码。还解释了如何通过修改代码中的特定部分来适应Instagram部署,以及如何处理Mini Chat的10秒超时问题。

10:01

🔗 连接Mini Chat并导入模板

视频展示了如何在Mini Chat上设置触发器,创建线程,并使用预设的关键词来启动自动化流程。作者提供了一个Mini Chat模板,用户可以通过简单的URL替换来自定义。同时,解释了如何通过Mini Chat与Replit后端通信,以及如何通过循环来处理超时问题。

15:02

📲 在Instagram上测试自动化流程

作者在Instagram上进行了实际测试,展示了如何通过发送特定关键词来触发自动化流程,并实时监控Replit后端的运行状态。测试包括用户输入处理、AI输出生成、以及如何通过Mini Chat与用户进行交互。

20:04

📝 捕获潜在客户信息

视频展示了如何通过自动化流程捕获潜在客户的信息,包括姓名和电话号码,并将其记录在Airtable中。作者还提到了如何通过Mini Chat的自动化流程来处理错误,并在必要时将对话转交给人工处理。

25:04

🎉 完成教程和后续步骤

视频最后,作者总结了整个教程的复杂性,并鼓励观众尝试自己设置。同时,提供了关于如何将GPT技术应用于网站和Instagram的额外信息,并邀请观众订阅频道以获取更多关于AI解决方案销售的信息。

Mindmap

Keywords

💡Instagram

Instagram是一个流行的社交媒体平台,用户可以分享图片和视频。在视频中,Instagram被用作一个强大的销售渠道,通过连接GPT技术来自动化直接消息(DMs)以进行客户支持和潜在客户生成。

💡GPTs

GPTs指的是生成预训练变换器(Generative Pre-trained Transformer)的缩写,这是一种人工智能技术,能够生成连贯的文本。在视频中,GPTs被用来创建自动化的客户服务和潜在客户生成系统。

💡自动化

自动化是指使用技术来执行通常需要人工操作的任务。视频主要讲述了如何通过GPTs技术自动化Instagram上的客户支持和潜在客户生成过程。

💡客户支持

客户支持是指企业为帮助客户解决问题和提供信息而提供的服务。在视频中,通过GPTs技术,客户支持任务如回复客户询问可以被自动化,提高效率。

💡潜在客户生成

潜在客户生成是指吸引并识别可能对产品或服务感兴趣的潜在客户的过程。视频展示了如何利用GPTs技术在Instagram上自动化这一过程。

💡直接消息(DMs)

直接消息(DMs)是Instagram上的一种功能,允许用户之间进行私密通信。在视频中,DMs被用作与客户互动和自动化沟通的渠道。

💡Mini Chat

Mini Chat在视频中指的是一个用于与用户进行交互的聊天机器人平台。它与GPTs技术结合,用于处理Instagram上的客户咨询和潜在客户信息。

💡Airtable

Airtable是一个灵活的在线数据库工具,可以用于组织和跟踪信息。在视频中,Airtable用于存储和管理通过Instagram DMs捕获的潜在客户信息。

💡API

API(应用程序编程接口)是一种允许不同软件之间进行交互的技术。视频提到了OpenAI API和Airtable API,分别用于连接GPTs技术和Airtable数据库。

💡知识库

知识库是指存储信息和数据的集合,以便人工智能系统可以访问和使用。在视频中,知识库用于GPTs技术,以提供准确的客户支持信息。

💡CRM

CRM(客户关系管理)是一种用于管理公司与客户之间互动的策略和技术。在视频中,CRM系统(如Airtable)被用于跟踪潜在客户信息,以便销售团队跟进。

Highlights

视频展示了如何将自定义GPT连接到Instagram以自动化DMs(直接消息)

Instagram是一个强大的销售渠道,正确使用可以大幅提升业务

连接AI助手到Instagram DMs可能非常困难,视频提供了一种简化的方法

视频通过实际操作演示了如何设置和避免常见错误

使用特定的关键词可以触发自动化流程

GPT能够根据用户的名字和问题提供个性化的回应

视频展示了如何通过Instagram故事自动回复并触发自动化

介绍了如何使用mini chat和repet后端进行自动化

展示了如何通过模板化代码简化GPT的创建和部署

解释了如何使用OpenAI的API来部署GPT

视频提供了如何通过mini chat模板实现Instagram的GPT部署

介绍了如何通过mini chat进行客户支持和潜在客户生成

展示了如何通过Instagram DMs捕获潜在客户信息并发送到CRM

提供了如何修改和定制GPT的知识库和提示文件

解释了如何设置OpenAI API密钥和Airtable API密钥

视频提供了如何使用mini chat模板进行Instagram自动化的详细步骤

展示了如何通过mini chat处理超过10秒的API请求超时问题

视频最后提供了如何测试和验证Instagram GPT自动化流程

Transcripts

00:00

in this video I'll be showing you step

00:01

by- step the fastest way to connect your

00:04

custom gpts to Instagram to completely

00:07

automate your DMs I'm making this video

00:09

today because Instagram can be an

00:10

incredibly powerful sales Channel when

00:12

used right and by connecting your gpts

00:14

to Instagram you can completely automate

00:17

key tasks like customer support and lead

00:19

generation for your business or for your

00:21

clients the issue is that connecting AI

00:24

assistance to Instagram DMS can be an

00:26

extremely painful process and something

00:28

that I've had constant issues with over

00:30

the past couple of months so I wanted to

00:32

create a video to walk you through the

00:34

easiest method that I've found so that

00:36

you can get things set up and avoid the

00:37

mistakes that I've made at this point in

00:39

the video I would normally give you a

00:40

big explanation of what we're building

00:42

but I think it's easier if I just show

00:43

you the finished product so we're going

00:45

to get a live demo here of exactly what

00:46

we're building in this case I'm using

00:47

the testing keyword it's going to

00:49

trigger the automation that I've set up

00:50

within mini chat which you'll see in a

00:51

second so in this case I've got some

00:53

stories up of me and Dubai if you're not

00:54

already following my Instagram it's

00:55

going to be available somewhere here you

00:56

get to see bit the behind the scenes of

00:58

my life and some of the stuff I get to

01:00

off camera um but in this case I've got

01:02

some stories up and I can reply to it of

01:05

testing and it's going to trigger the

01:09

Automation and you should see a pop up

01:11

at the top there we go so it says Hey

01:13

Liam what would you like to know about

01:14

the accelerator in this case it's

01:15

pulling the first name from my account

01:17

so if your name was Sandy or Smith that

01:19

would be using that name as the first

01:21

name um but because this account name is

01:23

Liam it's going to use Liam what would

01:24

you like to know about the accelerator

01:25

would be happy to help um who is the

01:28

owner so we can start asking some

01:31

questions in this case it's going to be

01:32

taking the question that I send there

01:33

it's going to be sending it to mini chat

01:35

and then mini chat is going to be

01:36

talking to our repet back end which

01:38

you're going to see all the code in a

01:39

second and I've templated it all so you

01:40

can just copy it and follow the steps

01:42

I'm about to show you and you'll be able

01:43

to get it up and writing so in this case

01:44

let come back Thea accelerator program

01:46

is Liam mle it's designed to help

01:48

individuals establish a profitable and

01:49

scalable AI business 90 days is there

01:51

any specific information you like to

01:52

know about the program um how how much

01:56

do the plans

01:58

cost

02:01

[Music]

02:02

the AAA accelerator offers two

02:04

membership tiers standard plan which is

02:05

$97 monthly Premium plan which is 197

02:08

which is currently sold out and so I can

02:10

keep asking questions about the program

02:12

I can ask it what are all the benefits

02:13

what do I get out of it

02:15

Etc what are the benefits on the

02:20

standard

02:22

plan

02:25

for

02:28

97

02:30

what do I

02:35

get you get access to over 15 live

02:38

workshops a month you get 24 assistant

02:40

from aam you get exclusive tools

02:41

accountability groups vets Community

02:43

templates all the good stuff so what we

02:45

can say now is to try initiate the lead

02:47

capture if I say I'd like to

02:54

join great to here I'll need your full

02:57

name and phone number including your

02:58

country code to get started so so this

02:59

is going for the lead capture now I can

03:01

say my name is um

03:06

Bruce

03:09

Wayne um plus 971 5 2 7 7

03:16

8 there we go I can send that

03:18

information it's going to pull out the

03:19

name and it's going to pull out the

03:20

phone number and it's going to send that

03:22

off to air table to log that lead so

03:24

that our sales team can follow up with

03:25

them so that's the that's the build

03:27

that's what we're going to be creating

03:28

here you can easily modify this by

03:30

changing out the knowledge base as

03:31

you'll see in the steps that are coming

03:32

in a second and you can also change the

03:34

CRM from Air table to whatever you want

03:35

but you'll be able to take the template

03:37

modified as you need and I'll be walking

03:38

you through step by step the most

03:40

valuable part of this is going to be the

03:41

mini chat template that I'm going to

03:42

give you which took me like an entire

03:44

day to create because there's so much so

03:46

many issues that I have with it due to

03:47

timeouts and stuff like this which we go

03:48

into in a sec we have a ton of stuff to

03:50

get through so let's get into it to

03:51

achieve the functionality that we just

03:52

saw we're going to need of course the

03:54

assistance API from open AI we're going

03:56

to need a repet to host that code then

03:58

we're going to call our rep code from

04:00

mini chat and I will mention it again if

04:02

you haven't seen any of my other videos

04:03

but we have the two sort of sides of

04:05

this gpts release which is firstly the

04:07

gpts on the chat GPT site where you can

04:10

create them and sort of go through them

04:11

and use them use them on the browser and

04:13

things like this and then we have the

04:14

assistance API which is really the the

04:16

meat and potatoes and how this thing is

04:18

going to be used and rolled out to

04:19

businesses and to real world

04:20

applications so while gpts are fun and

04:22

all and they're cool to create around

04:24

and sort of share around with people

04:26

most of the value is going to be created

04:27

with this assistant API so you can

04:29

deploy your gpts and your your setups

04:32

essentially to different channels in

04:33

this case we're going for an Instagram

04:35

deployment and using the GPT technology

04:37

for that on my prior videos we've done

04:39

website deployment so if you want to

04:40

check out how to put these on a website

04:42

rather than on Instagram you can do the

04:44

exact same process but put it onto a

04:45

website watching the video that's up

04:47

here I've got a couple of them now but

04:48

this is the best one to start with okay

04:49

so to get started with this build you

04:50

first need to get access to my repet as

04:52

always this is going to be available in

04:54

the first link in the description you

04:55

can go to my resource Hub sign up for

04:57

free and it's going to be at the bottom

04:58

of the list in the left panel you can

05:00

click on it there'll be a link that will

05:01

take you to this ret and you should be

05:03

greeted with a screen like this first

05:05

step is to go to the fork button on the

05:07

right we can click Fork here and we can

05:09

call it I'm just going to put a fork at

05:11

the end and then I can Fork the tripple

05:14

give it a second to boot

05:17

up then you should be greeted with

05:19

something like this for those of you who

05:20

don't know how to code don't freak out

05:21

you don't need to change any of this

05:22

really and there's only a couple parts

05:24

that I'll walk you through the process

05:25

of and that's mainly around API key so I

05:28

build this in a way that it's all ready

05:29

to go out of the box I'll just take you

05:31

through a bit of a breakdown of how this

05:32

is different from some of my other

05:33

tutorials and the way that I've had to

05:35

modify this so that it works with the

05:36

Instagram deployment this actually took

05:38

me quite a while to get working because

05:40

there's limitations of Min chat which

05:42

I'll go into later um but we can start

05:43

off where they breakdown of the main. pi

05:45

file which is where all the all the

05:47

action is happening when we're actually

05:49

interacting with this application

05:50

similar to the other builds that I've

05:51

done firstly we have the SL start

05:53

endpoint which is going to start the

05:55

conversation whenever we start a

05:56

conversation within mini chat a new

05:58

person interact with my story they hit

06:00

that trigger it's going to call this mpo

06:02

the/ start and it's going to create a

06:03

new thread we're going to give that

06:05

thread back to our mini application so

06:07

here we are giving the thread ID back

06:09

and then when the user actually asks

06:10

their question it's going to be sent to

06:12

this chat inpo and that chat inpo is

06:14

going to grab the thread ID and the

06:16

message then let's go to start a run

06:18

what's called a run in the new open AI

06:20

documentation and the way that they've

06:21

set up the assistant API so you have

06:23

what's called a run and in this

06:25

particular build we have split the chat

06:26

endpoint between this chat one and then

06:29

the second one called check now the

06:30

reason we've done that is because of the

06:32

Timeout on Mini chat is 10 seconds and

06:34

when I was testing this before I wasn't

06:36

able to get responses on Mini chat

06:38

because it was running over that

06:39

10-second timeout when I was making the

06:41

API Co so we've had to split it into

06:43

these two different parts this chat

06:44

endpoint is just going to create the run

06:46

and sort of send our information and

06:48

what we need to do up to the open AI

06:50

servers and it's going to be like okay

06:51

that's what we want now give us a couple

06:53

seconds and we'll wait for it to come

06:54

back and the way we actually grab the

06:56

response from that endpoint and we've

06:58

called the open AI API to give us our

07:00

response then we go down to this check

07:01

in point we're going to be periodically

07:03

checking in to see if our process our

07:06

our operation has been completed and if

07:08

it has been completed then we can pluck

07:09

it out and send it back to the user so

07:11

might sound a bit complicated but in

07:12

this case it's going to make a lot more

07:14

sense when we get into the mini chat

07:15

side of thing so bear with me next I'll

07:17

take you to the functions. pi file this

07:18

is where a lot of the the core

07:20

functionality is happening um in this

07:22

case we have the lead capture so this is

07:23

a air table lead capture we going to be

07:25

replacing this URL with a new one um as

07:27

you set it up on your end we have API

07:29

Keys which we'll be setting up in a

07:31

second this is the logic for creating a

07:33

new lead in the air table as I mentioned

07:35

and this is the create assistant

07:36

function which is really the main bit

07:38

that you need to wrap your head around

07:39

before going out and trying this on your

07:41

own so the create assistant function is

07:43

because when you're trying to create a

07:44

new GPT programmatically in this case

07:46

we're not using the GPT Builder we are

07:48

creating our own programmatically we

07:50

need to give the instructions or the

07:52

ingredients to the open AI API to create

07:54

our new assistant so in this case we

07:56

have of course the knowledge component

07:58

which is going to be a document here on

07:59

the left called knowledge. dox then we

08:01

have the instructions which are going to

08:03

be in the prompts dop file which we show

08:04

you in a second then we have the

08:06

functions which is set up here so I'll

08:08

show you how to change each of these

08:09

around so that you can modify this so

08:10

that you can create your own gpts for

08:12

your own use case so in this case we

08:14

have the file here which is going to be

08:16

the knowledge based document if you want

08:18

to change the knowledge base to your own

08:19

document you need to delete the

08:21

knowledge based document on the left

08:22

here and then click upload file here

08:24

upload a new file and then you need to

08:26

change the name of this file here from

08:28

knowledge. do to whatever it is in the

08:30

left panel so name here should match the

08:32

name of the document on the left hand

08:34

panel next if you want to change the

08:35

promp thing or the instruction for your

08:37

gbt it's going to be stored in this

08:39

variable here so the assistent

08:40

instructions is imported from our

08:42

prompt. piy file which is over on the

08:44

left here so if you want to change the

08:45

promp thing or the instructions for your

08:47

GPT click on the prompt stop High file

08:49

on the left I've taken this out because

08:51

it doesn't look very clean to have this

08:52

massive amount of text sort of stuffed

08:54

into your functions of P file so I've

08:56

moved it out to here so you can go in

08:58

and modify this as you like and any

08:59

changes that you make here are going to

09:00

be automatically pulled in to this

09:02

create assistant function when you

09:04

create it to to reiterate we have the

09:06

knowledge component here which we can

09:07

change we have the prompting component

09:09

here which we can change via the prompts

09:10

dop file and then finally we have the

09:13

tools section uh now the tools and order

09:15

to be able to use I should have

09:17

mentioned this in some of my other

09:18

videos so thank you for those of you who

09:19

pointed it out but the model here that

09:21

we're calling the GPT 4 preview you

09:23

actually need to have a card put on your

09:24

open AI account and you need to add some

09:26

credit to your account if you haven't

09:28

yet done that going to need that which

09:29

will show you in a sec but in order to

09:31

be able to access this new model which

09:33

is able to use GPT the much larger GPT 4

09:37

which is faster and and better in a

09:38

number of ways we need to do that step

09:40

so just to be clear some of you had

09:42

issues with that last time that is the

09:43

reason why and I'm going to be showing

09:45

you in a second how to fix that so when

09:47

it comes to tools this is the more

09:48

difficult part to change around I will

09:50

be completely honest but just to walk

09:51

you through it firstly we have the

09:53

retrieval tool here this is the

09:55

knowledge base as you can see I put a

09:56

lot of comments throughout all this

09:57

document so if you get stuck you have a

09:59

question about something not working or

10:01

you want to know how to modify things

10:03

take a look at these green comments and

10:04

you'll get a much better idea of how

10:05

this application is set up so we have

10:08

the retrieval tool which is the

10:09

knowledge base this needs to be on for

10:10

it to be able to access that knowledge

10:12

document then secondly we have just one

10:14

function here which is the lead capture

10:16

the lead capture in this case is using

10:17

the create lead function which is up

10:19

here it's referencing that name then we

10:21

get to the two parameters required to

10:23

call this function firstly we have the

10:25

name which is obviously the full name of

10:27

the lead and then we have the phone

10:28

which is the phone number of the lead

10:29

including the country code it's

10:31

important to know that to operate this

10:32

application when you have the three

10:33

different ingredients you have your

10:34

knowledge base your instructions then

10:36

these and then the tooling here as well

10:38

when you go to create an assistant when

10:40

we run this app up here for the first

10:41

time it's going to look on this left

10:43

panel and see if there's an assistant.

10:45

Json file in this case you can see that

10:46

we don't have one so it's going to

10:48

follow this and say okay if there is an

10:50

assistant. Json file let's load that but

10:53

if there is not then let's go through

10:54

the creation process and then create a

10:56

new file down here so this is our way of

10:58

of not duplicating and making a ton of

11:00

different assistants when we don't need

11:01

it you're going to be charged API usage

11:03

by how many assistants that you have up

11:05

especially if you're putting a lot of

11:06

knowledge in them you get charged by the

11:08

the amount of storage that you're taking

11:09

out with your documents as well so in

11:11

this case it's only going to create a

11:13

new assistant when there isn't one

11:15

already in the side file and this also

11:16

means if you've already run the app once

11:18

and you have a assistant. Json file on

11:21

the side panel here if you want to

11:23

modify the knowledge the prompting or

11:25

the tools then you need to delete that

11:27

file and then run the app again it will

11:29

recreate your assistant. Json file with

11:31

a new set of settings okay and with that

11:33

orientation out of the way we can get

11:34

into modifying the very few parts of the

11:37

code that we actually need to change in

11:38

order for it to work on your system

11:40

firstly we have our open AI API key

11:42

pretty straightforward one you can go to

11:43

platform. open

11:45

a.com then on the left panel here you'll

11:47

have an API key section and you can

11:49

click here and create a new secret key

11:51

it's going to pop up with a a key that

11:53

you can copy and you can copy that you

11:55

can take it back over to reflet here

11:56

then you need to go to the secret

11:58

section down the bottom left we can

12:00

delete this Google Cloud API key cuz

12:02

that's not needed for this one um but in

12:04

this case we have open AI API key you

12:06

can edit this and then you can paste

12:08

yours in and then update the secret and

12:10

as I mentioned before in order to make

12:12

sure that you get access to these newer

12:13

models that we need to make this app run

12:16

on the left hand panel here you can

12:17

click on settings and then billing you

12:19

can add a payment method and then you

12:20

can click on this buy credits button and

12:22

put 5 to10 in so that you have full

12:24

access and permissions to use all of the

12:26

latest models next we need to set up our

12:27

air table and get our air table API key

12:30

so in this case you'll be going to the

12:31

resource Hub again which is in the first

12:32

link of the description you can sign up

12:34

to there and then on the resource Hub

12:35

there'll be a link to firstly sign up to

12:37

air table if you haven't already and

12:38

there'll also be another link for you to

12:40

be able to clone my air table base here

12:42

so when you click on that link it should

12:44

look like this in this case we have

12:45

these two tabs here this is just going

12:47

to be the accelerator lead is what we're

12:48

looking for and you should have this

12:50

button up here that says copy base so

12:51

when you click that it should clone it

12:53

over to your account and look a bit like

12:54

this so just to take you through quickly

12:56

we have the the names of the leads we

12:58

have the phone numbers and we have the

12:59

questions and a status so the main ones

13:01

that we're going to be dealing with

13:02

within this app are the name and the

13:03

phone number I'll talk a little bit more

13:05

about these questions at the end once

13:06

you see it live once you have this base

13:08

created we need to get our API Key by

13:09

going to the right panel here clicking

13:11

on this little uh profile icon then

13:13

going to the developer Hub then you'll

13:16

be on this page where you can create API

13:18

key so you can click create new token

13:20

you can call it uh

13:23

Instagram lead genin bot you can go to

13:27

Scopes and click right and we'll give it

13:29

read as well and access you need to

13:32

scroll down to your Smith solo CRM and

13:35

you can click the create token button

13:36

and it should pop up with an API key

13:38

that you can copy so you want to copy

13:40

that and then head back to repet and in

13:42

the same way we just did with the open

13:44

AI key you can click on the three dots

13:45

to the right of your air table API key

13:48

and if you haven't found Secrets it's in

13:49

the bottom left here click on that and

13:51

this should appear and you can edit

13:52

again copy all of this and paste or

13:54

delete all of this and put your API key

13:56

in inste and update secret and then one

13:58

final thing that we need to do is go

14:00

back to our air table developers page

14:02

and then click on this web API

14:03

documentation on the left then you need

14:05

to scroll down to the bottom and click

14:07

on the Smith solar CRM and then can

14:09

click on the accelerator leads table and

14:11

then click on create records then you

14:13

need to take this URL

14:16

here copy all of that from https all the

14:19

way to the end of leads copy that head

14:21

back to repet and go to the create leads

14:24

function in the functions. py file and

14:27

then just copy Within delete within the

14:30

quotations there and then paste in that

14:32

URL so mine's the same so it doesn't

14:34

need to change obviously but yours will

14:35

have changed a little bit with this

14:37

little section here and with all of

14:38

those changes made we are ready to run

14:40

our application for the first time we

14:41

need to click this big green button up

14:43

the top and on the left pan panel you'll

14:45

see that we'll get our assistant. Json

14:47

file created because now it's going to

14:49

create an entirely new assistant based

14:50

off our settings inside our create

14:53

assistant function so the settings we

14:55

have here with the knowledge base with

14:57

the prompting and the tools it's going

14:58

to sort of smoos that all together and

15:00

create this assistant. Json file and all

15:02

it has in here is this so yours will be

15:04

a little bit different but this is what

15:05

we're going to be reloading it from so

15:06

if I stop it and restart it it's going

15:08

to this time read from this file and

15:11

pull in that and save that as the

15:12

variable in our main function if all has

15:14

gone well you should see something

15:15

similar to this in the bottom right

15:16

corner and you'll also see a web view

15:18

that's popped up here saying not found

15:20

it's not an issue we can click on this

15:21

new tab button in the corner and it's

15:23

going to open up a new tab for us here

15:25

this is the URL that we're going to be

15:26

calling within Min chat to get access

15:28

access to all of the functionality that

15:29

we have in our main.py file so our start

15:32

chat and check endpoints that we can

15:34

access by mini chat with that all of and

15:35

running correctly now we can get onto

15:37

the mini chat side of things I've

15:38

created a template for you that you can

15:40

just plug and play and change a couple

15:41

URLs so if you want to get access to

15:43

that again you can sign up with the

15:44

first link in the description then you

15:46

can get access to the mini chat template

15:48

when you click on it it should look like

15:49

this when you get on screen if you don't

15:51

already have an account for Min chat

15:53

you'll need to click on the sign up

15:54

button then it allow you to log in with

15:56

Facebook and you can go through the

15:57

whole setup in this case you want to

15:58

click on Instagram and go through the

16:00

process this can be a little bit tricky

16:02

so I've actually got a a recommended

16:03

tutorial from someone else when I had a

16:06

bunch of issues with getting this set up

16:07

earlier today I walked me through some

16:08

of the basic setup for creating a

16:10

Facebook page and linking it and the

16:12

right way so that it works so there's a

16:13

lot of moving Parts when it comes to

16:15

your Facebook pages and accounts and

16:16

your profiles and all these different

16:18

things so I don't want to try and drag

16:19

this thing out to be 40 minutes long so

16:21

there's like a 3 or four minute tutorial

16:23

where the guy explains it really well

16:24

that'll be linked down below if you

16:25

haven't got an account I'd watch that so

16:27

you can set up firstly your Facebook

16:28

faceb page and then connect that to your

16:30

Instagram account so that everything's

16:31

all tied up there then you can come back

16:33

here all signed in and ready to go once

16:34

you've signed in to mini chat you can

16:36

come back to this page and again click

16:38

on save to mini chat and it's going to

16:40

this time loaded into your account so I

16:41

can click on Save flow here for the

16:43

account that I've set up view

16:47

flow and just like that you have

16:49

imported the template that I spent hours

16:51

working on today to get working for you

16:52

all so this is going to save you a ton

16:54

of time I'll walk through it briefly now

16:55

and we'll be updating what we need to

16:57

along the way to save time starting off

16:58

we have a trigger if you're familiar

17:00

with these automation platforms you'll

17:01

know that triggers are how things start

17:03

off in this case we are using a story

17:05

reply trigger that I have set up on the

17:07

keyword testing I'm actually going to

17:08

change this to test two so you know that

17:10

I'm actually testing the one that I

17:12

built in front of you this is set up to

17:13

be listing on all stories when a reply

17:16

contains specific words or reaction in

17:18

this case the test two word is going to

17:19

be what it's looking for if that trigger

17:20

is hit then it goes to the first step in

17:22

our application which is to create a

17:24

thread creating a thread is the first

17:25

step in our application and this calls

17:27

the Slash so this is creating a new

17:29

thread under your assistant that's

17:31

essentially the start of a new

17:32

conversation or a new bucket of chat

17:34

history that we're going to be tracking

17:35

the conversation for in this case we can

17:37

grab our URL from the repet not found

17:40

page copy this head back to mini chat

17:43

and we need to replace this URL up to

17:46

the start point with our URL so M should

17:49

just pop and Fork there make sure you

17:51

don't have two for slashes like that so

17:53

it should just be your URL and then SL

17:56

start if we go through here yeah not

17:59

much you need to worry about here we're

18:00

saving the thread ID into a custom field

18:02

code thread ID don't touch any of this

18:04

here just leave it with all the numbers

18:05

included by this point we've created a

18:07

thread and now we can say hey first name

18:09

what would you like to know about the

18:10

accelerator I'd be happy to help and

18:12

then we are going to be listening for a

18:13

response so this is a a free keyboard

18:16

input so it's just waiting for them to

18:17

send something through what we're doing

18:19

is saving that to the variable called

18:20

last reply which is what we're going to

18:22

send off to our next endpoint in order

18:24

to start the process of generating a

18:26

result so we send that off to this first

18:27

step which is just a clear AI output

18:30

field just to make sure that the

18:31

variable is empty don't need to worry

18:32

about that too much the key point is

18:34

that after that we go to the start run

18:36

step now here we are doing the same

18:38

thing with the URL again you need to

18:40

paste in your URL and have the entire

18:43

URL and then slash chat this time so

18:45

again first one will start this time

18:47

it's chat next one will be check and

18:49

these will correspond to the different

18:51

endpoints that we've set up in our

18:52

application so they start creates a new

18:54

thread starts the conversation the chat

18:57

endpoint starts the Run sends off the

18:59

information to openai to start

19:01

processing the answer and then the final

19:03

one which we're about to see in a second

19:04

is what checks it and Returns the answer

19:06

so going back to Min chat you can leave

19:07

these as they are but just to give you

19:09

an idea we are sending away to our chat

19:11

endpoint to start the processing the

19:14

thread ID and the message from the user

19:16

which we are getting from earlier where

19:17

we created the thread ID we've saved

19:19

that and we're referencing it here and

19:21

the message which we are pulling from

19:22

the last reply that we just got from the

19:24

user we're sending that off and what

19:26

this returns to us is a run run ID now

19:29

this run ID is what we need to be able

19:30

to check the status of the sort of order

19:33

that we've sent off to open AI now that

19:35

we have created the thread we've got the

19:36

users input we've sent that off and said

19:38

can you work on this for us now we can

19:40

periodically check back in to see the

19:42

status of that response and we do that

19:44

via our run ID run ID is already set up

19:46

here and then we pass that run ID to our

19:49

final endpoint which is of course the

19:51

check endpoint which is checking the

19:53

status of the Run make sure you have

19:55

your url here/ check in the body of this

19:57

request we sending away the thread ID

20:00

and the Run ID to check the status of

20:02

that run and the response that we should

20:03

be getting back here is the answer to

20:05

the user's question so this is the final

20:07

output that we do present to the user

20:08

and send within the Instagram DMS and

20:10

this part here is probably the most

20:12

difficult but to understand but this is

20:14

how we are allowing it to Loop through

20:15

as I mentioned before mini chat has a

20:17

10c uh cut off a Timeout on the API

20:20

request so the issue I was having here

20:22

is that when I was trying to create this

20:23

earlier today I kept running into this

20:25

issue of it would answer the shorter

20:27

questions but then whenever I asked for

20:29

a longer response it would just

20:30

completely blank and wouldn't send

20:32

anything and after a lot of searching

20:33

around I eventually figured out that

20:35

there is a 10 second Timeout on this and

20:37

unfortunately a lot of the stuff that we

20:38

do particularly with function calling

20:40

and and knowledge bases can take longer

20:42

than 10 seconds to get back to us the

20:44

way that we get around this timeout is

20:45

this conditional block here in which if

20:47

the check end point returns timeout then

20:50

we're going to loop back around and try

20:52

it again so if you look back at our code

20:54

we have this check Endo here and it has

20:56

a timer of 9 seconds so it's going to

20:59

check the status of the run over and

21:01

over and over again which you'll see in

21:02

the bottom right here in a second it's

21:04

going to be printing out run and

21:05

progress run and progress run in

21:06

progress run in progress and then when

21:08

it's complete it's going to send it off

21:09

but if the run is still in progress and

21:12

by the time it gets to the end of that 9

21:14

seconds it's going to send back a

21:16

timeout and say hey look we've run out

21:17

of time then we're going to try it again

21:19

and check how much longer so this will

21:21

make more sense when you see it in

21:22

action in a second but it does work and

21:24

I'm very happy that I was able to get

21:25

this working for you all and then we

21:27

have an error handling step where if the

21:28

AI outputs some kind of error we're just

21:30

going to assign it to a human to to

21:31

handle the conversation and the final

21:33

part of this conditional check is that

21:35

if there isn't a timer as in we don't

21:37

have to keep waiting for a response and

21:39

there isn't an error then we can go down

21:41

and send the final AI output that we get

21:43

back from the check inpoint and we can

21:45

send it to the user and await their next

21:47

input this final step here is printing

21:50

out the AI output and we're also at the

21:52

same time expecting input from them and

21:53

saving it to last reply and with that

21:56

last reply we can Loop right back up to

21:58

here and then go through the whole

21:59

process again I'm saying okay now we

22:01

have a new user input let's firstly send

22:02

it off to the chat endpoint get that

22:04

cooking away and the open a servers then

22:06

we can check into it over and over and

22:08

over again until it comes back as a

22:09

complete response I think that's enough

22:11

talking we are ready to get this thing

22:12

tested I just want to do one final check

22:14

and you guys should all make sure you do

22:15

this that we have updated the URLs for

22:17

all of them so Instagram accelerator ass

22:19

for/ start yep that's correct go here

22:24

slash chat yep that's the second one and

22:27

then SL check yep we are all good to go

22:31

here now I can click the update button

22:33

here and I'm ready to give it a test on

22:35

the phone we're on the phone here and I

22:37

can pull up my story and I can say test

22:40

to send that we should get an automated

22:42

message any second yep there we go hey

22:45

Liam what would you like to know about

22:46

the accelerator would be happy to help

22:48

um what coaching do you

22:53

offer now I do want to pull up on the

22:55

other side the repet back end so so it's

22:58

handy to watch it as I send this we

23:00

should see things pop up like it start

23:02

to thread checking for status and

23:04

progress and progress and progress so

23:06

you can see the debug here the way that

23:08

I've set it up it's going to be printing

23:09

out and giving you updates very

23:11

constantly on how things

23:12

up oh there we go you can see here in

23:15

the console that it's been checking for

23:16

the status of the run and it's been in

23:18

progress and progress and progress and

23:20

when it gets to the end of that 9-second

23:21

period it goes okay I need to send a

23:23

timeout response and then we need to try

23:25

loop back again and continue to check in

23:27

this case it's timed out once then it

23:29

started the next Loop and then

23:30

immediately found that the response was

23:31

ready and then we sent it in this case

23:33

we have it on our phone here

23:35

personalized assistance regular one-on

23:36

ones exclusive resources Etc Great and

23:40

then we can try to get a lead capture

23:41

going here so I'm ready to

23:45

start and again watching the console

23:48

here in progress in progress in

23:52

progress completed and boom it sends it

23:54

through now we need a full name and

23:56

phone uh um P to

24:02

Parker like a

24:06

jacket and that should ask for my phone

24:08

number as well sure I'll give you my

24:10

phone

24:17

number now it should go for a lead

24:20

capture here requir action action and

24:25

process lead created success F checking

24:29

run status and progress and

24:32

progress completed and it sends it back

24:35

and now we should pull up our air table

24:37

here we should have Peter Parker there

24:40

we go we've got two of them and that's

24:41

the builds we can continue to ask

24:42

questions here and going through and

24:44

learning more about the product but we

24:45

have done the lead capture I think it

24:46

will allow us to do another lead capture

24:48

even but in this case we've gotten what

24:49

we wanted out of it they've been able to

24:51

ask questions make a decision and we've

24:53

captured the lead that we can send to

24:54

the sales team and they can follow up on

24:56

there is this column here of question

24:57

that I was going to include but it made

24:59

it a little bit more complex and I think

25:01

many chat has already made this as

25:02

complex as it needs to be but this

25:04

questions column was intended to be a an

25:06

additional field for the lead capture

25:08

function which can pull out of the

25:09

thread out of the transcript of the

25:10

conversation it can pull some of the

25:12

questions that the user ask and add them

25:14

to this field when you capture the lead

25:16

so that the sales person can look at the

25:17

questions column and go okay this person

25:19

was worried about price or this person

25:20

was worried about the features or or the

25:22

team Etc that's not something I've

25:24

included in this build but it is

25:25

possible if you guys want me to make a

25:26

video breaking down how you can get all

25:28

of the transcripts from your assistants

25:30

from say your Instagram deployment from

25:32

your website deployments anywhere you

25:34

want it we can be pulling those and

25:35

centralizing them somewhere so if you

25:36

want me to do a video on it I have had

25:37

some requests already but please let me

25:39

know in the comments below and I'll I'll

25:40

make sure I get that out as soon as

25:41

possible as I mentioned in my last video

25:43

there's repet application is not

25:45

properly deployed it's not production

25:47

grade and production read this just

25:48

allows you to spin it up and see how it

25:50

works quickly if you do want me to do a

25:51

video breaking down how you can actually

25:53

do a live production grade deployment of

25:55

one of these applications using repet or

25:57

other ser Services also let me know in

25:58

the comments because I can make that

26:00

video too if you've got this far

26:01

congratulations this is definitely one

26:03

of the tougher tutorials I've done and

26:05

there's definitely a lot more complexity

26:06

that I've had to to work into this to

26:08

get it working on Instagram which is

26:09

just really the nature of the platform

26:11

right now so I hope You' been able to

26:12

follow along and get as much out of this

26:14

as possible if you have enjoyed please

26:15

hit down below and leave a like I put a

26:17

timeon of work into this thing it's

26:19

actually been delayed a bit just by the

26:20

amount of issues that I've had with

26:22

trying to get a way that works for you

26:23

guys as easy as possible so I'm sure

26:25

many of you going to take this and be

26:26

able to do some awesome stuff with it um

26:28

I hope the use case is a little bit

26:30

different from the solar one that I've

26:31

I've talked about a lot I wanted to show

26:32

you how this can be used for more

26:34

educational products or coaching offers

26:35

and things like this and not only handle

26:37

questions and sort of customer support

26:39

but also go for lead capture and things

26:40

like this to create a lead generation

26:42

chatbot on Instagram using your GPT

26:44

technology and of course while you're

26:45

down there you can subscribe to the

26:46

channel if you haven't already this is

26:48

kind of all we talk about on the channel

26:49

AI business how to sell AI solution so

26:52

if you want to stay in the loop on how

26:53

I'm attacking this gpts opportunity and

26:56

how you can best take advantage but to

26:58

make your business better or to sell

26:59

better things to your clients be sure to

27:01

subscribe to the channel because I have

27:02

a ton of really cool stuff coming I have

27:04

a sort of Mastery GPT development guide

27:06

that takes you through all of this and

27:08

Beyond just a little tutorial like this

27:09

it's really a comprehensive look at how

27:11

you can Master building these things so

27:13

that you can really unlock the value of

27:14

this new technology if you don't want to

27:16

miss that and any other future uploads

27:17

you can subscribe down below but if you

27:18

want to learn how to create your own AI

27:20

automation agency and Sell Solutions

27:22

just like this to businesses then you

27:24

can join the biggest community of AI

27:25

agency owners in the world who are

27:26

already moving on this opportunity you

27:28

can also join my free telegram down

27:30

below if you want daily updates on my

27:32

learnings and the things that I'm doing

27:33

with these gpts and how I'm selling them

27:35

as well as always all of the resources

27:36

mentioned in this video will be

27:38

available on my resource hub for you to

27:39

download and steal and build and sell

27:42

and do whatever you want to do with if

27:43

you enjoyed this video and also want to

27:44

know how you can put your gpts on

27:46

websites you can check out this video

27:47

here where I go to depth on it but aside

27:49

from that thank you so much for watching

27:51

and I'll see you in the next one