Table of Contents
Quiz solver comes from the curiosity to test the capabilities of GPT-3 model facing a real world problem.
It uses the device camera to take a picture of a question with related possible answers. Then, it reads all the text in the image with Google ML Kit Text Recognition and sends it to Openai GPT-3 chat model which in turn extracts the question with the possible answers and finally tries to guess which one of them is the right one.
This is neither bad or good by itself, the use you make of it makes it so
Ready for execution on iOS (simulator and physical devices), configuration needed for Android.
To get a local copy up and running follow these simple example steps.
To run the project you need flutter to be installed on your machine: follow the "Get started" manual on flutter.dev
- Clone the repo
git clone https://github.com/AndreFra96/quizsolver.git
- Install required packages
flutter pub get
- Get your OpenAI API Key at openai.com
- Update the 'openaiApiKey' in
lib/config.dartwith your OpenAI API Key - Run
flutter run
The usage in extremely simple, just point the camera to the quiz and click the photo button. In a few seconds a popup will show up with the recognized question and the correct answer.
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the MIT License. See LICENSE.txt for more information.
Andrea Brioschi - [email protected]
Project Link: https://github.com/AndreFra96/quizsolver