OpenAI Stack Hack

Join us to find out how developers can interact with Redis, a real-time data platform with its blazing-fast vector database

Redis Talk

Paweł Czech and Mathias Asberg, co-founders of New Native will talk about lablab.ai's mission and vision. https://www.twitch.tv/lablabai

Start

We will shortly introduce you to the OpenAI Whisper, GPT3, Codex & DALL-E 2 Hackathon, Challenge, lablab.ai platform, Discord server.

Introduction to the Challenge

Short intro from lablab.ai's partner - Redis, the leading provider of enterprise-class solutions for vector search, data storage, and ML feature workloads

Redis Introduction

Startup lessons especially when it comes to actually applied NLP AI

Useful tips from lablab.ai developer Fabian

ChatGPT for developers/ how are for what to use

Whisper Tutorial for developers

Go-to-market strategy, basics of pricing, funding and valuation for AI startups

GPT-3 Live Coding Session

Under the hood: Building a QA app using Redis

Time's up! Submit your solution before the deadline

Galacticos

Mudit Garg

YashD

Akshay_2003

Tejas Rathod

adityarane

Sadhana Sharma

Our website enhances online content accessibility for the visually impaired with a cost-effective text-to-speech service using contemporary AI tools. Current market solutions lack necessary amenities and are costly.
Working on the website:
> once the website loads, the user inputs the URL of the website to be analyzed
> this website is parsed using Beautiful Soup to gather the meaningful text content available on the page
> this content is passed to the OpenAI text-davinci-003 model as a prompt and a summary is generated for the same
> this summary is read out to the user using Azure in natural human tone
> next, the website is again parsed using Beautiful Soup with the aim to download relevant images on that website
> these images are then analyzed using Google Cloud Vision API and feature labels describing the prominent objects/contents of that image are generated
> these labels are passed as a prompt to the OpenAI text-davinci-003 model and a meaningful sentence is generated which describes the images
> the prompt already includes a set of sample labels and outputs that the model can use to understand the format of the desired output. 
> the image description generated in the above step is then read aloud using Azure.
For Redis:
Redis caches URL results for up to 3 hours, if URL exists in cache, output is displayed/read aloud. Otherwise, website is processed for new output. Results are removed after 3 hours for possible content changes. It allows for fast data access making it suitable for high performance use cases.

For voice control:
> using space bar, user can ask queries regarding summary through available chatbot
> above query is converted to text via speech recognition library of python
> this text and the summary are given to the OpenAI text-davinci-003 model as a prompt and the query is resolved
> the result is spoken out and if speech unrecognized, an error message stating to retry is read aloud


With our website, visually impaired people can hear human-like text-to-speech. We strive to provide brief but informative image descriptions. Only relevant text is converted to speech. Chatbots will summarize and answer questions. 

"Galacticos team on OpenAI Stack Hack Hackathon"

Team Idea

Submission