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.
Is it okay to use runBlocking?
In this video I’ll talk about when it’s fine to use the runBlocking function from Kotlin coroutines and when you...
Mobile App Development Best Practices – 07.12
KSP2 Preview, Mastering in SwiftUI, How to implement gamification and more!
Gemini is the new foundation for artificial intelligence in Android
Foundation models are trained on a variety of data sources to create artificial intelligence systems that can adapt to a...
Google has released AlphaCode 2 based on Gemini
Google today, along with its Gemini artificial intelligence model, unveiled AlphaCode 2, an improved version of the AlphaCode code generator...
ColorfulX – Metal for crafting multi-colored gradients
ColorfulX is an implementation using Metal for crafting multi-colored gradients. ColorfulX Platform UIKit and AppKit platforms are generally supported. Due to MTKView not...
Mobile App Development Best Practices – 06.12
Power of enums, A New Foundation for AI on Android, developer dogmas and more!