Integrating the Gemini API in Android | Android Build Time

Integrating the Gemini API in Android | Android Build Time

7.975 Lượt nghe
Integrating the Gemini API in Android | Android Build Time
Welcome to Android Build Time! The show where the Android team talks with Android developers about building great apps, so you can listen while building your Android app. In today’s episodes we have Jomin George - CEO Hitbytes Technologies building the journal app Life, Thomas Ezan - Developer Relations Engineer at Google and your host Christopher Cartland - Developer Relations Engineer at Google. A few months ago, the team behind the journal app Life wanted to provide an innovative way to let their users log entries. They created "Leo", an AI diary assistant chatting with users and converting conversations into a journal entry. To modify the behavior of the model and the tone of its responses, the team used system instructions to define the chatbot persona. This allows the user to set the behavior and tone of the assistant: Pick “Professional and formal” and the model will keep the conversation strict, select “Friendly and cheerful” and it will lighten up the dialogue with lots of emojis! The team saw an increase of user engagement following the launch of the feature. Listen to this episode to learn more about how you can leverage Gemini API in your app. Chapters: 0:00 - Introduction 1:38 - Life app 2:17 - What is GenAI? 3:28 - User challenges 4:12 - Getting started tips 5:29 - Gemini models 7:42 - Chatbot user experience 9:48 - System instructions 13:17 - Memory and context window 18:34 - Model cost and capabilities 20:37 - How to summarize? 21:46 - Experimenting with multimodal 24:28 - User feedback 27:03 - Production and model versioning 31:33 - What’s next? 33:19 - Json Generation 35:40 - Function calling 38:38 - Unlocking delightful experiences 40:07 - Multi language support 41:37 - Conclusion Resources: Link to podcast → https://goo.gle/3Nbo5Sv Life app → https://goo.gle/47O40ex Learn more about the advanced features of the Gemini Cloud models by reading this blog post → https://goo.gle/4epeHqk For an introduction to generative AI for Android developers, check out this blog post → https://goo.gle/4dyYPAe To get started with Vertex AI in Firebase, see the documentation → https://goo.gle/3Y8GYMc Watch more Android Build Time → https://goo.gle/AndroidBuildTime Subscribe to Android Developers → https://goo.gle/AndroidDevs #Featured #AndroidDevelopers #AndroidBuildTime Speaker: Christopher Cartland, Thomas Ezan, Products Mentioned: Gemini Gemini 1.5 Flash Gemini 1.5 Pro Gemini API Google AI Generative AI Google AI Studio