🗓️ 48 hours of building (24-26th March)
💻 Create innovative new apps with OpenAI's latest ChatGPT and Whisper APIs
💡 Learn from top AI professionals
⚒️ Combine new GPT 3,5 Turbo and Whisper APIs to build your AI app
🐱‍💻 Now is the time to register and let's get started!

ChatGPT API & Whisper API Global Hackathon

No-rank

Apprentice

Jeroencverboom

Building a useful and generalizable tool for businesses to use ChatGPT.

Clippy

abdibrokhim

shreyamohanty

krvi2110

Rishikesh

We have created a no-code platfrom that caters to the 'customer care' department of the ecommerce websites, wherein the user can chat with our bot and the bot will figure out the problem/issue with the order and take action accordingly. Like for example, the user starts chatting with the bot and tells that the product does not fit his size, then the bot will traverse through the dataset and extract the order details and see if the product is elligible for return, if it is, then it will accordingly inform the user that the product can be returned and will place an order for the same. This no - code platform caters to the needs of ecommerce and similar online businesses that need 'customer care' service but cannot afford one. By means of this bot we are enabling that feature and making the platform no-code so that anyone can use it.

We have created a no code platform that will perform the responsibilities of a customer care executive, figure out the problem with the product and take action accordingly.

No code customer care bot

Whisper is a general-purpose speech recognition model. It is 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.

Whisper

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. The ChatGPT model has been trained on a vast amount of text data, including conversations and other types of human-generated text, which allows it to generate text that is similar in style and content to human conversation. ChatGPT can be used to generate responses to questions, code, make suggestions, or provide information in a conversational manner, and it is able to do so in a way that is often indistinguishable from human-generated text. The initial model has been trained using Reinforcement Learning from Human Feedback (RLHF), using methods similar to InstructGPT, but with slight differences in the data collection setup. The model is trained using supervised fine-tuning, where human AI trainers provided conversations in which they played both sides—the user and an AI assistant. The trainers would have had access to model-written suggestions to help them compose their responses.

Jeroen Verboom@Jeroencverboom

Events attended

Submissions made

I built with

Socials

🤝 Top Collabolators

Ibrohim Abdivokhidov

Shreya Mohanty

Kristian Vind

Rishikesh Fulari

🤓 Submissions

No code customer care bot

👌 Attended Hackathons

ChatGPT API & Whisper API Global Hackathon

📝 Certificates

ChatGPT API & Whisper API Global Hackathon | Certificate