ParkingGPT is a cross-platform app that enables you to decide whether you want to park or not, all using the power of GPT-4o (Vision and Text. Speech coming soon).
The app is built using .NET MAUI and it is powered by both OpenAI and Azure OpenAI Service.
- Install .NET MAUI and refer to the .NET MAUI Documentation
- Secure OpenAI API or Azure OpenAI Service subscription
- The development style has been kept according to this Development Guide so that best practices are followed.
ParkingGPT is a cross-platform app that uses the power of GPT-4o (multimodal and multilanguage) to help you decide whether you want to park or not. With ParkingGPT, you can easily identify parking signs and make informed decisions about where to park. This app has a feature to directly use your phone's camera or you can upload a picture of a parking sign. Whether you’re a driver looking for a convenient parking spot or a parking enforcement officer looking to enforce parking regulations, ParkingGPT is your AI parking copilot.
- Support for multiple parking signs (no parking, no stopping, special assistance etc.)
Is it published on a Google Play Store?
- No, but you can get the .apk package and sideload it to your Android for now. If there's much interest, I can think of publishing it to the store.
Is it published on an Apple App Store?
- No. I do not own a Macbook which restricts me from creating a package (or .ipa) for this app. The developer program subscription is too expensive for a hobbyist.
Does it work seamlessly with multiple parking signs?
- I have tried 2 to 3 ones and it works fine. However, I am not sure how it would react to the more than 2 or 3 signs. I am still testing it.
Is it smart enough to make decision based upon the no parking signs and parking signs?
- Not for now. I will see this for future.
You can contribute to this repo with issues and pull requests (PRs). Simply filing issues for problems you encounter is a great way to contribute. Contributing code is greatly appreciated.
Special shoutout to Simon Waight for bringing up this idea with me. Check out my blog for all the details and motivation behind this.
This repository is licensed with the MIT license.