How to integrate ChatGPT and Whisper API into your project tutorial

ChatGPT and Whisper API are out!

Drumroll please… OpenAI finally (1.03.2023) released an official ChatGPT/Chat Completion and Whisper API endpoint! If you missed the news you can read it on their blog
page OpenAI Blog. If you missed all of the hype started last year and are not familiar with those 2 models, you can read more about them on our tech page.

But long story short ChatGPT is a large language model trained by OpenAI to generate human-like text in a conversational style. It is a variant of the GPT-3 model, which was specifically designed to be used to generate text in response to user input. Whisper is a general-purpose speech recognition model trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

What does it mean for us developers?

Regarding ChatGPT we can finally implement Chat Completion in our projects without some hacks and workarounds. We can use gpt-3.5-turbo and gpt-3.5-turbo-0301 models. We can leverage the cutting edge text to text and audio to text technology into our projects in no time!

Regarding Whisper it means that we don’t have to worry anymore about the infrastructure, how to deploy the model and how to scale it, and about the costs of
running a Virtual Machine with GPU all the time. We can just use the endpoint that is provided by OpenAI and we can start building right away.

But straight to the point – let’s add OpenAI’s technology to our project!

How to implement ChatGPT/Chat completion endpoint into our project?

ChatGPT is using the gpt-3.5-turbo model. Because in this model the price of the token is 10% of the price of gpt-3 even OpenAI advises to use it instead of GPT-3.
If you already have an implementation of GPT-3 it is pretty easy to migrate to GPT-3.5. Only thing that you need to keep in mind that GPT-3.5 is available in
chat model. Chat models are taking a series of messages as input instead of a single prompt.
The chat format is explained more in details here

Instead of adding a prompt to your request body you need to add a messages array.
for example in Python with openAI library it will look like this:

Messages variable must be an array of objects with 2 keys: role and content. Role can be user or assistant and system

The system role message is helping setting the behavior of the assistant.

How can we change gpt-3 completion into gpt-3.5 chat completion?

Very easy. For example if before we were doing hashtag creation with gpt-3 the prompt looked like this:

Now we need to change it to:

or

Super easy!

How can you implement Whisper OpenAI endpoint into your project?

If you already had this model deployed on your own infrastructure you can just change the endpoint to the OpenAI endpoint 🙂
Jokes aside, if you are just planning to implement this endpoint into your project you can use OpenAI library for Python
and also for Javascript or you can create the requests by yourself.

Modifying our React Frontend boilerplate to use OpenAI Whisper endpoint

We already have a React Frontend boilerplate that you can find [here]. (https://github.com/lablab-ai/react-audio-send)

Few things we need to do to make this work.
We need to change the App.js file WHISPER_ENDPOINT variable to the OpenAI endpoint https://api.openai.com/v1/audio/transcriptions.

We need to change some variables

We need to add the Authorization header with the Bearer token. You can get the token from the
OpenAI dashboard

And that’s it! You can now use the OpenAI Whisper endpoint in your previously created project to create transcription of audio files.
Keep in mind if you want to create a production ready application you will have to hide your API

Can I benefit from ChatGPT API?

Of course you can! The AI revolution is here and either you join it or you will be left behind. We’re not a fortune tellers, but we can read the numbers and with all of the attention LLM gets from tech giants and tech experts, with enormous amount of foundings into this tech industry and massive layoffs in different IT technology we can surely say the AI technology will be “it” for the ucpoming years. We already wrote it on our blog, but if you don;t want to take it from us but from the greatest startup Investor of all time – you can know more about his prediction regarding generative AI in tech.

But last not least – what’s from all of that for me? Well, you can build a ChatGPT or Whisper based app during a 7 days AI Hackathon, get to lablab.ai’s slingshot program and build your millions worth AI startup! Just identify the problem and build a solution to it with cutting edge technology!

If you want to learn more AI based tools, visit our Tutorial Pages. And if you want to give a spin to your AI skills,
join one of our AI Hackathons and create in a few days a working demo which can be the beginning of your start up!

Every journey starts with a single step and we encourage you to do it with lablab.ai!