Bootcamp
Study group
Collaborate with peers in your dedicated #study-group channel.
Code reviews
Submit projects for review using the /review command in your #code-reviews channel
Join 11190 other students
Log in to get
Subscribe to access to this course and ALL other courses. You get a 30-day money-back guarantee, no questions asked.
Subscription includes
Course level: Intermediate
Stay ahead of the web dev game by harnessing the power of AI. Build a movie pitch generator, a GPT-4 chatbot, and a fine-tuned bot trained on your own dataset.
This course contains 76 interactive scrims spread across 3 modules.
27 lessons2 hours 5 min
22 lessons1 hour 9 min
27 lessons1 hour 20 min
Building fetch requests for the OpenAI API
OpenAI’s models
OpenAI tools
The Create Completions endpoint
Prompt engineering
The ‘zero shot’ approach
The ‘few shot’ approach
The temperature property
The Create Image endpoint
Building chatbots
Chatbot specific prompt syntax
The Create Chat Completions endpoint
Frequency Penalty
Presence Penalty
Controlling a chatbot’s personality
Persisting the chat with Firebase
Fine-tuning
n_epochs
The Stop Sequence
Deploying with API key hidden
Turn a one sentence idea into a synopsis for a movie with a title, cast and cover art!
An ask-me-anything chatbot built with GPT-4.
A chatbot fine-tuned to answer questions using our own specific dataset.
Before taking this course, you should have a basic understanding of HTML, CSS, and JavaScript. Below are our suggested resource to get you up to speed.
I’m a tutor at Scrimba and I’ve been messing around with websites since 2004. I’m aiming to take the pain out of learning to code.
Have you been jealously looking at all the OpenAI-powered apps appearing and thinking, 'I wish I could have a piece of that'?
If so, your wait is over.
In this course, you'll build three projects using the OpenAI API.
In the first project, MoviePitch, we learn all the basics of working with the OpenAI API and harness the power of artificial intelligence to generate ideas and images.
In our second project, KnowItAll, we’ll move to the GPT-4 model and get to grips with building chatbots - one of the most common uses of AI for web devs.
Finally, we will fine-tune our chatbot in the third project. Fine-tuning is where you upload a dataset to OpenAI and use it to train a model. Doing this allows the chatbot to answer questions specific to your data - a critical skill when working with AI.
By the end of this course, you'll know how to use the OpenAI API to add excellent AI features to your apps and have the expertise to fine-tune a model.
That's not all!
During this course, you will also learn how to use a Firebase database to store a conversation and reference its information in subsequent uses.
On top of that, you'll also use a Netlify serverless function to hide an API key - an essential skill when using APIs with secret keys in portfolio projects and live sites.
As this is a Scrimba course, there will be a ton of challenges for you to solve throughout the course, allowing you to put your new skills to the test and gain the code muscle memory you need to become a rock star developer.
Let's do this!
to the QAI (artificial intelligence) is like having a super-smart computer buddy who can do things that humans normally do, like recognize pictures of cats or tell you what the weather is like outside. They're kind of like a cross between R2-D2 and Hermione Granger - nerdy, helpful, and always up for a challenge! Just don't expect them to have feelings or opinions on whether pineapple belongs on pizza.
The OpenAI API gives us access to AI models in our apps. By interacting with the API, we can leverage the power of these AI models to perform a wide range of tasks, such as natural language understanding, text generation, image generation, and more.
Yes, this course contains two chatbots. From the outside they look similar but they are in fact completely different. The first (KnowItAll) uses the new GPT-4 model which is mind-blowing for general Q and A tasks and natural language generation. The second (We-Wingit) is fine-tuned to answer questions from our own dataset. This skill is useful for aspiring web developers who want their chatbot (or any other AI app) to have a specific focus.
