29 lines (23 loc) · 3.04 KB

Showcase complex end-to-end use cases

This folder houses the companion notebooks for the "Build with AI" video series, along with code examples from mobile app demos. Here you'll find practical examples and ready-to-run code to help you bring AI-powered features to life.

Accompanying notebooks for the Build with AI video series

Folder	Description
Business email assistant	Business Email AI Assistant with Gemma This project tackles the specific problem of extracting order information from emails to a bakery into structured data, so it can be quickly added to an order handling system.
Personal code assistant	Personal AI Code Assistant with Gemma This project shows you how to set up your own web service for hosting Gemma and connecting it to a Microsoft Visual Studio Code extension, to make using the model more convenient while coding.
Spoken language tasks	Spoken Language AI Assistant with Gemma Learn how to tune a model to perform specific tasks in a specific language, without requiring extensive data or training time.

Mobile App Demo

Folder	Description
Gemma on Android	Android app to deploy fine-tuned Gemma-2B-it model using MediaPipe LLM Inference API.
PaliGemma on Android	Inference PaliGemma on Android using Hugging Face and Gradio Client API for tasks like zero-shot object detection, image captioning, and visual question-answering.

Web App Demo

Folder	Description
PaliGemma 2 on Web	Inference PaliGemma 2 on the web using its ONNX weights and Transformers.js for tasks like object detection, image captioning, OCR, and visual Q&A.
Gemma 3 on Web	Run the Gemma 3 270M model on the web using its ONNX weights and Transformers.js, focusing on chat capabilities along with customization of the system prompt.
Emoji Gemma on Web	Learn how to fine-tune a Gemma 3 270M model for emoji translation and run it client-side in the browser using MediaPipe LLM Inference API or Transformers.js.

Cloud Run Demo

Folder	Description
Gemma on Cloud run	This folder contains a Dockerfile for building and deploying a Gemma-powered application on Cloud Run, featuring Gemini APIs.