5 Unique Portfolio AI Projects (beginner to intermediate) | Python, OpenAI, ChatGPT, Langchain

Summary

In this video, Tina, an AI enthusiast, introduces five AI projects suitable for beginners to advanced learners. The projects range from creating a personal AI tutor to developing a content creator AI and an AI storytelling game. Each project is detailed with the necessary skills, such as Python, Open AI API, and additional APIs for specific tasks. Tina encourages viewers to explore, learn, and build their AI applications, offering a step-by-step approach and suggesting further exploration with tools like Lang Chain for more complex projects.

Takeaways

• 😀 Tina, an X meta data scientist, introduces five AI projects suitable for beginners to advanced learners.
• 📚 The first project is about creating an AI tutor that can teach based on individual skill levels and learning styles, requiring prompt engineering and chat team skills.
• 💻 Level two of the AI tutor project involves using the OpenAI API for more control and context retention, allowing for a more personalized learning experience.
• 🎮 Level three suggests exploring the difference between using Chat GPT directly and accessing GPT 3.5 via the OpenAI API for advanced customization.
• 📝 The second project is aimed at content creators, utilizing Python and the OpenAI API to generate content ideas, with additional tools like Streamlit for app development.
• 🍳 For the content creator AI, the script discusses using parameters like 'temperature' to introduce randomness in the generated content.
• 📈 The third project involves creating an app that can check the nutritional value of recipes using APIs, ensuring balanced meals.
• 📚 The fourth project is about summarizing readings or lecture notes using AI, with the option to upgrade to summarizing audio or video files.
• 🎓 Level three of the study aid project proposes building a full application with a user interface for summarizing and studying educational content.
• 🤖 The fifth project is about creating a realistic AI version of oneself that can write emails or generate content in one's unique style.
• 🏆 The final project suggests creating an AI storytelling game with rich narratives, possibly integrating image generation using tools like DALL-E or Mid Journey.

Q & A

What is the main topic of the video?

The main topic of the video is discussing five AI projects that viewers can start working on immediately, ranging from beginner to advanced levels.

Who is the presenter of the video?

The presenter of the video is Tina, who introduces herself as an X meta data scientist.

What are the basic skills required for the first AI project about the AI tutor?

The basic skills required for the AI tutor project are prompt engineering and chat team, with additional skills including Python, the Open AI API, and possibly other APIs or tools like Streamlit.

What is the purpose of the 'AI Tutor' project mentioned in the video?

The purpose of the 'AI Tutor' project is to create a private tutor that can teach anything custom to the user's skill level and learning style, available 24/7, and can even adopt the persona of a favorite fictional character or real person.

How does the video suggest improving the AI tutor from level one to level two?

The video suggests improving the AI tutor from level one to level two by introducing the coding component and using the Open AI API to have more control and provide more context to the AI, preventing it from forgetting previous discussions.

What is the 'Content Creator' project in the video about?

The 'Content Creator' project is about using AI to generate content for social media, such as creating recipes inspired by popular anime, with the AI adopting the role of an Instagram content creator who likes anime.

What additional skills are needed for the 'Content Creator' project beyond Python and the Open AI API?

Additional skills needed for the 'Content Creator' project include Streamlit and other third-party APIs, which may be used to create a GUI or for other functionalities.

What is the 'Speed Learner' project and how does it help with studying?

The 'Speed Learner' project is designed to help users quickly learn and summarize content, such as readings or lectures, using AI models like the whisper model from Open AI for transcribing audio and the GPT model for summarization.

What are some of the advanced ideas suggested for the 'Speed Learner' project?

Some advanced ideas for the 'Speed Learner' project include creating a full application with a user interface, hosting it on the web, and possibly integrating it with the YouTube API to automatically process video content.

What is the 'Tina GPT' project and what skills are needed to create it?

The 'Tina GPT' project is about creating a bot that mimics the personality and writing style of Tina. Skills needed include Python, the Open AI API, and additional skills like relational databases, SQL, and possibly using a tool like Link Chain for application development.

What is the 'AI Storytelling Game' project and what additional skills are suggested for it?

The 'AI Storytelling Game' project involves creating a narrative-rich game where the story unfolds step by step based on user input. Additional skills suggested for this project include using mid-journey or Dolly for generating images to accompany the story.

How can viewers get more insights or resources for the projects discussed in the video?

Viewers can get more insights or resources by leaving comments on the video, asking for specific domain projects or tools like Link Chain, and possibly requesting a sequel to the video for more complex projects.

Outlines

00:00

🤖 AI Tutor Project Overview

This paragraph introduces five AI projects suitable for various skill levels, from beginner to advanced. The speaker, Tina, a metadata scientist, outlines the first project: creating an AI tutor. This virtual tutor is personalized, non-judgmental, and available around the clock, potentially taking on the persona of a favorite character. Key skills for this project include prompt engineering, chat team, Python, the Open AI API, and possibly other APIs and tools like Streamlit for interface design. The explanation begins with a Level 1 focus on prompt engineering, crafting a prompt for an AI coding tutor, and evolves through levels, incorporating the Open AI API for context retention and advanced interface integration.

05:02

📚 Content Creator AI with Open AI API

The second paragraph delves into creating an AI for content creation, specifically for an Instagram content creator who likes anime. The process involves using Python to access the Open AI API and crafting prompts for the AI to generate content ideas. The speaker discusses using parameters like 'temperature' to control randomness in the AI's output. The project progresses from generating text-based content to ensuring nutritional balance in recipes using additional APIs, and finally, to automating the entire process, including image generation and posting on Instagram, to create a full-fledged application.

10:03

🎓 Procrastination Study Tool with Summarization

In the third paragraph, the focus shifts to a study tool for students who procrastinate. The project involves summarizing readings and creating study materials from audio or video lectures. Level 1 uses the Open AI API to summarize text documents, while Level 2 employs the whisper model from Open AI to transcribe and summarize audio files. The advanced Level 3 project suggests creating a full application that automates the process, including using the YouTube API to fetch videos, transcribe them, and summarize the content, potentially with a UI component for a complete web-based application.

15:04

💌 Personal Email Writing Assistant

The fourth paragraph introduces an AI project to create a personal email writing assistant. The project starts with using the Open AI API to generate emails in a specific style, in this case, mimicking 'Tina's' writing style. It progresses to providing the AI with past email contexts to improve the accuracy of the generated emails. The advanced Level 3 involves training the model with extensive context, such as transcripts from YouTube videos, storing them in a database, and using SQL to query the database for generating realistic and contextually accurate emails. The paragraph also mentions using a tool like Link Chain for rapid application development.

🎮 AI Storytelling Game with Rich Narratives

The final paragraph presents an AI storytelling game project where the AI acts as a narrator, crafting a rich and descriptive narrative based on user inputs. The game's context involves a character from Naruto opening the eight gates. The project starts with a simple text-based narrative and challenges the creator to expand it by integrating image generation using APIs like Mid Journey or Dolly, creating a more immersive and visually engaging experience.

Keywords

💡AI Projects

AI Projects refers to various tasks or applications that utilize artificial intelligence technologies. In the video, the host, Tina, discusses different AI projects ranging from beginner to advanced levels, which viewers can undertake to gain practical experience with AI. These projects are designed to help individuals learn and apply AI concepts in real-world scenarios.

💡Prompt Engineering

Prompt Engineering is the process of designing input prompts for AI models to guide their responses in a desired direction. In the context of the video, prompt engineering is essential for creating personalized AI tutors and content creators, where the prompts define the AI's role and behavior, as illustrated by crafting a prompt for a coding tutor named 'Goggin GPT'.

💡Chatbot

A Chatbot is an AI-powered conversational agent that interacts with users via text or voice. In the video, the chatbot is used as a tool for creating an AI tutor. The host explains the limitations of chatbots, such as lack of context awareness, and how using the Open AI API can enhance their functionality by providing more context and control.

💡Open AI API

The Open AI API is a set of tools provided by OpenAI that allows developers to integrate AI capabilities into their applications. In the video, the API is used to enhance the functionality of AI projects, such as creating a more context-aware AI tutor and generating content based on specific parameters.

💡Streamlit

Streamlit is an open-source Python library that makes it easy to create and share data apps. In the video, Streamlit is mentioned as a potential tool for creating a user interface for the AI tutor project, allowing users to interact with the AI through a more visually appealing and interactive platform.

💡Content Creator

A Content Creator in the video refers to an AI project where the AI generates content, such as recipes inspired by anime, based on given parameters. The host discusses using the Open AI API to create an AI that can produce content suitable for social media platforms like Instagram, with the help of parameters like 'temperature' to control randomness in output.

💡Nutritional Value

Nutritional Value pertains to the nutritional content of food, which includes vitamins, minerals, calories, and other nutrients. In the context of the video, the host suggests using APIs to check the nutritional value of recipes generated by the AI content creator to ensure that the content is not only engaging but also informative and accurate.

💡Procrastination

Procrastination is the act of delaying or postponing tasks or actions. The video humorously addresses the issue of students procrastinating on their readings or lectures and then using AI to quickly summarize and learn the material at the last minute. This is demonstrated through the 'Speed Learn' project, which uses AI to summarize and distill information from readings or audio files.

💡Whisper Model

The Whisper Model is an AI tool from OpenAI that specializes in transcribing audio files into text. In the video, it is mentioned as part of the 'Speed Learn' project, where it can be used to convert lecture recordings into transcripts, which can then be summarized by the GPT model for quick study.

💡Relational Database

A Relational Database is a type of database that stores data in a structured format, using rows and columns in tables. In the video, the host discusses using a relational database to store transcripts of their own speech and writing, which can then be used to train an AI model to mimic their communication style in the 'Tina GPT' project.

💡Lift Chain

Lift Chain is a technology mentioned in the video that abstracts away complex processes for building full applications. It is used in the 'Tina GPT' project to create a realistic version of the host by querying a database of transcripts and generating content in the host's unique style.

Highlights

Introduction of five AI projects varying from beginner to advanced levels.

Concept of an AI tutor that adapts to skill level and learning style.

Use of prompt engineering and chatbot technology for personalized tutoring.

Implementation of Python, Open AI API, and additional tools like Streamlit for creating an AI tutor.

Demonstration of creating a personal coding tutor using GPT and prompt engineering.

Challenges of context retention in AI chatbots and solutions using the Open AI API.

Exploration of creating content for an Instagram content creator using AI.

Utilization of the Whisper model and other APIs for generating recipes from anime themes.

Discussion on ensuring nutritional balance of generated recipes using APIs.

Ideas for expanding the project to include image generation and automatic Instagram posting.

Project for summarizing readings and audio/video courses using AI models.

Use of the YouTube API and Whisper model for creating study summaries.

Concept of building a full application for automated study material summarization.

Introduction of an AI email assistant that mimics a specific person's writing style.

Techniques for training the model with past emails to generate realistic responses.

Building a complete app using databases, SQL, and hosting technologies.

AI storytelling game project where users interact with a narrative AI.

Integration of image generation using mid-journey or DALL-E for a visual storytelling experience.

Encouragement for viewers to create their own AI projects and share their work.

Transcripts

Hello friends welcome back to another

video so in this video we're going to

talk about five AI projects that you can

start working on immediately and we're

going to go from very beginner to

intermediate and some Advanced things

too if you're up for a challenge oh and

in case you don't know me hello my name

is Tina and I am an X meta data

scientist all right without further Ado

let's go the AI tutor do you wish you

have a private tutor that can teach you

anything custom to your skill level your

learning style and will not judge you

for your incompetence and is available

24/7 it can even be your favorite

fictional character or real person like

Kakashi from Naruto if you want some

fast action or jira if you want some

tough love basic skills you will need is

prompt engineering and chat team

additional skills include python the

open AI API some sort of freten like

streamlit for example and if you're

feeling fancy other apis as well how I

would do this starting with level one

level one is going to focus on the

prompt engineering portion got to craft

a prompt for example of a AI coding

tutor so I already created this promps

if you're interested in how I made it

and the step-by-step details you can

check out this video over here but I'm

going to briefly go through it now so

here your name is goggin GPT a personal

coding tutor that has the personality of

David goggin so you don't know who David

goggin is he's like this motivational

speaker that's very much a tough love

motivational speaker very tough love

you're not afraid of having the up body

you're afraid of the effort so he's

going to periodically say mean things as

motivation such as you fat get off the

couch so you first say hi to your

student by name that is a weak then ask

them what they want to learn you then

tell them to input any of the following

so this is the part in which I explained

how it is to be a coding tutor um and

then in the end is going to be asked me

for my first task so this is going to be

the prompt that you will engineer so I'm

going to demonstrate what it's going to

be like just using chat GPT so without

using any coding at first so we can copy

paste this prompt over here and then we

can put it into chat

GPT it's going to say hey weak mother

I'm gogin gbt your personal coding Jewel

instructor let's get those weak coding

muscles into shape what do you want to

learn today so the issue with having

chbd do something like this first of all

is the fact that it doesn't have context

so when we ask they to greet You by name

unless you write my name is Tina for

example it will not know what your name

is going to be the second issue is that

as you keep talking you'll notice that

it starts becoming disjointed and Chacha

BT actually ends up forgetting a lot of

the context that you guys talked about

previously so level two is going to

introduce the coding component so now

we're actually going to use the open AI

API so first thing you're going to do is

PIP install open AI then you're going to

import OS and import open Ai and then

you're going to set your API key to your

API key and then you're going to insert

your open AI key Now using open AI API

you're going to have a lot more control

over your AI tutor and you're also going

to be able to provide it more context so

it's not going to just forget the things

that you tell it previously Plus instead

of just being confined to the chat gbt

interface you're able to pipe the

responses into another type of interface

for example maybe you want to create a

guey maybe you want to use something

like streamlet so here is the context

and then what we're doing over here is

that we're setting the system into the

context that we're giving it so as a

system to the chat bot you're telling it

this is what I want you to behave like

and then you can also give it more

context like the user is saying

something like my name is Tina so now

it's going to be able to greet you by

your name and the code over here is just

to initiate the gooey that we have so

try running this doing its thing so

these are the three things that I

imputed into the prom so kind of briefly

variations is going to give different

variations for how to solve a specific

coding problem um make a game for

learning topic is pretty

self-explanatory and then explain is to

explain a topic that you want to learn

okay so when we do this it's saying hi

Tina you week bleep what do you want to

learn today input one of the following

so these are the things that we ask it

to do so for example we want to write

something like explain

objectoriented programming start

learning yes okay so it says oh Tina you

want to learn about object-oriented

programming huh well let me break it

down to you in a way that even your weak

little brain can understand ah yes I

already feel motivated okay so then it's

going to explain objectoriented

programming to me and also give simple

code as an example um and it also

explains okay what's the difference

between procedural programming and

functional programming blah blah blah

here now what is your next move okay so

for a level three project I really want

you to explore the difference between

just entering the prompt in chat GPT

versus going through the open AI API in

order to access GPT 3.5 directly so what

are the things that you can do outside

of this for example for in terms of the

gooey that we already shown we can also

make a fancier gooey like streamlet for

example and if you're trying to build

out another app you're able to pipe the

responses that you're getting from from

gbt into some other thing for example

putting it into a Json file for the

responses and that is going to be going

to something else doing some sort of

computation and then being displayed

somewhere hopefully that gives you some

ideas of what you can do let me know in

the comments some ideas that you can do

content creator to put me out of a job

skills needed you will need Python and

the open AI API additional skills would

include streamlet and other thirdparty

API so I'll explain why that's important

later so level one prompt engineering is

something that we're always going to

have to be using so if you're going to

learn something properly learn how to do

prompt engineering let us come up with a

prompt for a content creator AI okay so

using python we're going to access the

open AI API to get gbt 3.5 again using

the chat completions API okay so now

we're going to create the prompts or a

series of messages to be feeding into

GPT first of all for the systems role

we're going to be giving it the

overarching who it is that you are what

is that you're supposed to do so you're

an Instagram content creator who likes

anime you will generate one recipe from

a popular anime with emojis that are

less than 300 characters long from

different anime we're actually going to

put a context in there where the user

says content is I want to create content

on easily balanced diets okay so instead

of just directly generating a label and

then using that what we can play around

with here is a parameter called

temperature so the temperature is

something that you feed into the model

that changes how much random is being

introduced to the output so zero is

going to be not random and then if

you're doing all the way up to one is

going to be very random so to Showcase

this we're going to have a temperature

and we're going to put that into a list

so varying from 0 0.5 0.8 all the way up

to 1 what we have over here is for

temperature in temperatures we're just

going to Loop through it we'll print

what the temperature is so we know what

temperature it is that we're getting and

then the content is going to be getting

completion for messages which is what we

defined previously and we're putting

messages as well as the temperature and

we're going to print the content so

let's click this and let it do its thing

all right so let's see what we have here

the first one is Anime inspired balance

diet a recipe from the world of food

Wars oo food Wars really good anime

highly recommend so the ingredients it

list this out and then the instructions

over here enjoy your balanced meal

inspired by the mouth poting dishes from

food Wars oh great and it also tells you

that you should always put tags on your

IG post so anime Inspire diet food words

recipe okay so next one is going to be

anime Inspire balance diet delicious and

nutritious recipes no Ruto Ramen Bowl so

two packs of ramen noodles chicken

vegetables and then it also gives you

the instructions over here okay so at

level two something else that you can

play around with is using an upst string

and then inputting the variables for

example I don't know instead of like

healthy food healthy balanced meal can

be exceedingly unhealthy heart attack

inducing meal something like that so try

using using the different variables and

then generating different types of

recipes as well let me know in the

comments if you do this and what' you

get okay so for some reason if you're

actually a responsible person and you

don't want to just be throwing out

random recipes here like is it actually

balanced meal we don't know right so in

order to make sure that it actually is

what you can do is plug into apis to

actually check the nutritional value of

the things that you get outputed for

example you can use this API called

adame API which is I feel like a spin on

edamame API and you can look at the

nutritional values of these things and

the ingredients um and to cross check

things before actually posting it okay

so if you really want to build this into

a full-blown app what you can do is you

create the content but we actually have

to create the image surrounding it as

well and then actually post it onto

Instagram so that's the full cycle so

this level is going to be much more

challenging so what you're going to do

is explore doly where mid journey and

figure out how it is that you can

generate images that match the things

the labels that you have and how do you

do that in automated Manner and finally

you can use the Instagram graph API to

automatically post it onto Instagram as

well okay so if you do this challenging

project put it in the description put

your GI Hub there because you should be

proud of yourself you just created a

fully functioning app are you too lazy

to do the readings for your class or

even go to lecture or watch your online

course do not fear now you can sleep in

and waste your time in many different

ways then freak out Panic on the last

minute and speed learn all the things

that you have to learn AKA how to

procrastinate more skills you will need

you know the drill got to have your

Python and your open AI API additional

skills include the whisper model also

from open Ai and other apis like the

YouTube API so level one project

summarizing those readings that you're

allegedly supposed to do before a class

so take those hideous PDFs and texts

make them into a transcript and pipe

them through the open a API using a

prompt telling it to summarize the

things that you're apparently supposed

to read and voila now you can just read

these lines before class and pretend you

did the readings level two is creating

summaries of audio files or video

courses what I used to do when I was

back in college is that I would put a

recorder down at the front where the

professor is talking about things and

then what I would do is just go take a

nap go do something I was like I don't

even know what I did and when the

lecture is over I would come back and

take the recorder so I would do this for

all the lectures until up to the project

or an exam in which I would then panic

and listen to the recording at like 3x

feed and try to transcribe it really

really fast and take notes on it it was

not a fun exercise but it did work out

somehow but now that we have wonderful

AI models that we can play with if you

have a video where audio file instead of

me sitting there and trying to

transcribe something really really fast

and then taking notes on it what you can

actually do is that you can take those

recordings and pipe them through the

whisper model and that would give you

the transcript of the things that we

talked about in the audio file you take

those transcripts create notes for it or

create like practice exams whatever it

is that you want to create using the GPT

model um and then voila you don't don't

have to speed listen to everything and

it would have been much faster let me

know in the comments what are other

things that you think you can do to

study better now that you have the

transcripts okay so level three is going

to be a full application again which is

going to be super fun I mean for me I

often times just learn things directly

through YouTube like YouTube playlist

and things like that you can use

additional apis for example like PBE

where you can directly use the YouTube

API um in order to get those video files

and automatically take them put them

through whisper and get that transcript

and then do all the summarization there

and to make it a simple complete app

just stick on some UI component um and

host it on the web and there you go

another application by the way there's

this plugin called harpa a that you can

install onto your Chrome window it's

able to do like YouTube summaries

generate different blog post from

content and things like that think about

how you can build something similar to

harpa doai except you can do it like in

your specific way seriously if you

actually think about it building these

things is not as hard as you probably

think it is right Tina GPT skills needed

python open a API additional skills

relational databases and of course

coming with that is going to be SQL and

L chain so level one super simple use

Python to access the open AI API and

then use the GPT 3.5 model and then

through the system role you can provide

the content for example your name is

Tina Tina likes to use a lot of

exclamation marks and she has the

reading level of an eighth grader

usually she's a stickler for punctuation

which is very important and she

generally likes to keep her emails short

to the point but polite and there you go

you just made Tina bot yay okay so level

two let's actually provide us some past

context like some more information so

that the model can actually see examples

and it's going to be a lot better than

you just you telling it uh who it is

that you are how is that you speak and

what we're going to do is put in some

example emails and just stick that into

a simple list and we're going to be

using the abst string again where you

can put in the different emails like

email 1 email 2 email 3 examples so

you're giving it context within the

prompt it would be better at generate

emails as if it is you and you will be

more likely to go undetected okay so

level three creating that full app we're

going to actually real real real train

the model so that it has a lot of

context a lot of information that you

can use to generate a very realistic

version of yourself so for me for

example I can take my YouTube videos

which I can get through the YouTube API

um and then just take that translate

them into transcripts using whisper

which we talked about earlier so now we

have all these transcripts which is

really large and you probably don't just

want to store it as an object read into

memory so what you can do is put it as a

database um any relational database is

probably great for this job and you'll

be using AWS to host the database and

SQL in order to query it to create it

all those good things let me know in the

comments if you want me to link some

really good resources for how to quickly

set that up so what's really cool now is

that you have this database full of

these transcripts for how it is that you

speak how it is that you write stuff you

can use this to answer any questions or

write anything that is using your

tonality in the way that you you would

normally do things so really realistic

and a way you can do this is that you

can use a really cool technology called

link chain it's a wonderful tool that

abstracts away a lot of things for you

to build full applications to production

really really quickly and it can do

things like provide context dependent

stuff it's able to take in your

databases and then search through your

databases for you um really really cool

stuff again let me know in the comments

if you want me to go through a video the

talk about projects that you can do

using link chain so those will be

probably like intermediate to Advanced

so a SE

do you see what I did there a sequel to

this video next project a fun AI

storytelling game skills needed is going

to be Python and open AI API additional

skills is going to be mid Journey or

Dolly okay so the prompt that we have

over here what we want our AI to do is

you are a narrator for a storytelling

game where Rock Le from Naruto opens the

eight Gates the game should be a

narrative rich descriptive and the final

result should be piecing together a

story describe the starting point and

ask the user what they would like to do

the story unravels as we progress step

by step and of course over here to the

system that's what we put as the context

um and then we're going to have the user

is going to say content start the game

and then from here the response is going

to be getting the completions using the

chat completions from the openai API and

we're going to try this out so what I

want you to think about about in this

level one level um in addition to the

prompt that we gave it already what are

some edge cases that could happen what

if something happens where the user say

something weird or you know additional

story lines that could be happening how

do you add complexity into this so these

are things that you can directly input

to the system role itself or perhaps

giving it more context so you're able to

redirect the story a lot of creating

these applications um it rests on the

prompt and then the API itself is

usually not that hard to call it's like

the surrounding infrastructure to

support the application that you're

building is really where a lot of that

time is spent so if you want to

challenge yourself a little bit more I'm

going to challenge you to making this

into not only a storytelling using text

but to integrate using mid Journey or do

so you're actually generating images of

the story line as they progress so think

about how you can do that so my

suggestion is to go and check out the

apis for both Dal and The Unofficial one

for Mid Journey 2 and see how it is that

you potentially incorporate that

together so I hope you found this video

helpful and then you feel inspired to

start creating one of these AI projects

um let me know if you want me to make a

sequel to this um where we're going to

be building things using Lang chain

maybe a little bit more complex or like

any specific domains or just like

anything else that you want me to make

okay I'll see you guys in the next video

or live stream