Building Offline AI Agent in your Flutter app
summary
A custom Flutter Gemma plugin runs MediaPipe-backed models on Android, iOS and web, enabling function calling to trigger local methods and tools offline. It uses Gemma variants (Gemma 3n mentioned, and Gemma Free Nano for small multimodal on-device use), covers model sizes and quantization (500MB+ examples), adds embedding support for on-device RAG, and ships sample apps that change UI, call functions, run vision+language tasks and demonstrate tradeoffs for offline agents.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 5:06Offline AI agents matter
- 8:27Cloud-based AI challenges
- 13:45On-device AI basics
- 17:26Flutter AI integration
- 20:01Model selection for inference
- 22:55Multimodality and multilingual
- 25:24AI agents with function calling
- 27:38Model capabilities
- 30:26Retrieval augmented generation
- 31:52Embedding models for search
- 33:21Thinking mode tracking
- 34:46Offline AI examples
- 39:50Medical AI applications
- 40:32Closing and future
related talks
08mDemo: Gemma on-device with MediaPipe and TensorFlow Lite
14mGemma on mobile and web. Best and worst practices
39mFlutter Project with Gemma: A State-of-the-Art Open Model
44mBuilding amazing Front-End Project with Gemma: A State-of-the-Art Open Model
40mBuilding amazing Front-End Project with Gemma: A State-of-the-Art Open Model
10mBuilding intelligent agents with Gemma 3
15mGemma, DeepMind's Family of Open Models
15mRunning Google's Gemma LLMs in the browser with MediaPipe Web