HealthGPT – Query your Apple Health data with natural language
HealthGPT is an experimental iOS app that allows users to interact with their health data stored in the Apple Health app using natural language.
Developed on top of CardinalKit, the CardinalKitTemplateApplication, and OpenAI. HealthGPT offers an easy-to-extend solution for those looking to make large language model powered apps within the Apple Health ecosystem.
Built by Varun Shenoy over the course of a caffeine-fueled weekend. Reach out with any questions 🙂
- Chat-style interface for user-friendly health data interaction
- Integration with the Apple Health app to ensure seamless first-party data usage
- Extensible architecture built on CardinalKit for easy customization
- GPT-3.5 + GPT-4 access through the OpenAI Swift module
- Out of the box support for querying sleep, step count, active energy, exercise minutes, heart rate, and body mass.
- Clone this repository.
HealthGPT.xcodeprojin Xcode. Wait for all dependencies to install and indexing to finish.
- Replace the OpenAI API key placeholder in
Supporting Files/OpenAI-Info.plistwith your own from OpenAI’s dashboard. You can also paste your key into the app during onboarding.
- Run the app (on device or in the simulator) and play with HealthGPT on your own data 🚀
Note: if you’re using the simulator, you will need to manually add data in the Health app. Otherwise, all of your results will read zero.
You can add queries for additional HealthKit quantities and categories as follows:
HealthGPT/HealthGPT/HealthDataFetcher.swiftto create an appropriate query for your data type.
- Update the prompt in
HealthGPT/HealthGPT/MessageInputView.swiftto pass the newly acquired data to the OpenAI API.
For any other quick changes (such as adding an onboarding flow), refer to the CardinalKitTemplateApplication repo.
Contributions to this project are welcome. Please make sure to read the contribution guidelines and the contributor covenant code of conduct first.
Mobile App Development Best Practices – 06.06
iOS SwiftUI Testing: a Pragmatic Approach Enhancing Security in iOS Applications: Best Practices and Code Examples Beautify Code Without Optionals...
Apple announces Vision Pro augmented reality headset
The Vision Pro is marketed primarily as an AR device, but it can switch between augmented and full virtual reality...
WWDC 2023 Keynote
Check out the WWDC23 keynote, where the latest Apple Vision Pro, MacBook Air 15″, software, services and operating systems were...
LeetCode by Swift – Solutions to LeetCode by Swift
LeetCode Online Judge is a website containing many algorithm questions. Most of them are real interview questions of Google, Facebook, LinkedIn, Apple, etc....
Mobile App Development Best Practices – 05.06
iOS Using Upcoming Feature Flags Network Path Monitoring What’s new in Swift 5.9? Building a robust clean architecture/VIPER iOS app...
Create a game with libGDX
In this exciting episode of our show, we dive into the thrilling world of game development with our guest, Daniele...