Supercharge your Android Apps with Gemini API

Presented at Creating Tomorrow: Dive into Generative AI, GDG Ahmedabad.

https://gdg.community.dev/events/details/google-gdg-ahmedabad-presents-creating-tomorrow-dive-into-generative-ai/

Transcript

1. Supercharge your Android Apps Building with Gemini API Sohel Shaikh Lead Android Engineer Skylark Drones @thesohelshaikh
2. - 4+ YOE with Android - Lead Android Engineer @ Skylark Drones - I 💜 Kotlin! - @thesohelshaikh on Socials Hey, I am Sohel
3. GDG Ahmedabad
4. GDG Ahmedabad
5. GDG Ahmedabad
6. GDG Ahmedabad Ways of integration • Google AI Client SDK • Firebase Vertex SDK • Google AI Edge SDK for Gemini Nano
7. GDG Ahmedabad Google AI Client SDK • Coroutines as First Class Citizen • Written in Kotlin • Easy to use • Available on GitHub
8. GDG Ahmedabad
9. GDG Ahmedabad AI Client SDK Arch
10. GDG Ahmedabad val model = GenerativeModel( model = "gemini-1.5-flash-001" , apiKey = BuildConfig.apikey, generationConfig = generationConfig { temperature = 0.15f topK = 32 topP = 1f maxOutputTokens = 4096 }, safetySettings = listOf( SafetySetting(HarmCategory.HARASSMENT, BlockThreshold.MEDIUM_AND_ABOVE), SafetySetting(HarmCategory.HATE_SPEECH, BlockThreshold.MEDIUM_AND_ABOVE), ) )
11. GDG Ahmedabad val model = GenerativeModel( model = "gemini-1.5-flash-001" , apiKey = BuildConfig.apikey, generationConfig = generationConfig { temperature = 0.15f topK = 32 topP = 1f maxOutputTokens = 4096 }, safetySettings = listOf( SafetySetting(HarmCategory.HARASSMENT, BlockThreshold.MEDIUM_AND_ABOVE), SafetySetting(HarmCategory.HATE_SPEECH, BlockThreshold.MEDIUM_AND_ABOVE), ) )
12. GDG Ahmedabad val model = GenerativeModel( model = "gemini-1.5-flash-001" , apiKey = BuildConfig.apikey, generationConfig = generationConfig { temperature = 0.15f topK = 32 topP = 1f maxOutputTokens = 4096 }, safetySettings = listOf( SafetySetting(HarmCategory.HARASSMENT, BlockThreshold.MEDIUM_AND_ABOVE), SafetySetting(HarmCategory.HATE_SPEECH, BlockThreshold.MEDIUM_AND_ABOVE), ) )
13. GDG Ahmedabad val model = GenerativeModel( model = "gemini-1.5-flash-001" , apiKey = BuildConfig.apikey, generationConfig = generationConfig { temperature = 0.15f topK = 32 topP = 1f maxOutputTokens = 4096 }, safetySettings = listOf( SafetySetting(HarmCategory.HARASSMENT, BlockThreshold.MEDIUM_AND_ABOVE), SafetySetting(HarmCategory.HATE_SPEECH, BlockThreshold.MEDIUM_AND_ABOVE), ) )
14. GDG Ahmedabad scope.launch { val response = model.generateContent( content { image(bitmap) text("What is the object in this picture?") } ) }
15. Get started in 2 mins
16. Demo Create new project
18. GDG Ahmedabad Firebase Vertex AI
19. GDG Ahmedabad Gemini AI Core Arch
20. GDG Ahmedabad Low Rank Adaption (LoRA) • Fine tuning technique • Faster to train • Smaller on device footprint • Unique sets for specialized applications
21. GDG Ahmedabad
22. Prompt Engineering • Be specific • Few shot prompting • Avoid negative prompting • Image first, text second
25. GDG Ahmedabad Ways of integration** • Google AI Client SDK - Public Preview • Firebase Vertex SDK - Public Preview • Google AI Edge SDK for Gemini Nano - Private Preview
26. GDG Ahmedabad
27. GDG Ahmedabad
28. Unlocking the economic potential of the skies We’re Hiring! Skylark Drones
29. What are your questions? Too shy? Ping me @thesohelshaikh
30. Thank You! Sohel Shaikh Lead Android Engineer Skylark Drones @thesohelshaikh