# 📷 Searching for images from text with EmbeddingGemma 2

## Executive summary

This video demonstrates the use of EmbeddingGemma 2, a lightweight, open multimodal embedding model, to enable advanced, completely offline media search directly on a mobile device. The system uses natural language queries and semantic similarity to locate specific photos and even precise moments within videos, eliminating the need for external APIs or intermediate transcription.

## Key takeaways

- Semantic Media Search: Users can search their entire media library using natural language queries (e.g., 'dog playing fetch in the ocean'), allowing the system to find relevant content based on meaning, not just keywords.
- Video Moment Finding: The Video Moment Finder feature allows users to pinpoint specific segments within videos (e.g., searching for 'blowing out candles') instantly.
- Offline Capability: The entire search process operates directly on the phone, ensuring complete privacy and requiring no external API calls or intermediate transcription.

## Technical details

- EmbeddingGemma 2 Model: EmbeddingGemma 2 is identified as a lightweight, natively multimodal embedding model designed for edge deployment.
- Search Mechanism: The system relies on semantic similarity to process natural language queries and match them against media content, enabling robust search functionality.
- Deployment Environment: The application, Google AI Edge Gallery, is designed to run entirely offline on mobile devices (Android/iOS).

## Practical implications

- Build engineers can leverage lightweight, multimodal models like EmbeddingGemma 2 to create privacy-preserving, resource-constrained applications that function entirely offline.
- The architecture demonstrates a viable pattern for integrating advanced AI features (like semantic search) at the edge device level, reducing reliance on cloud infrastructure and external APIs.

## Topics

Multimodal AI, Edge Computing, Natural Language Processing (NLP), Mobile Development, Embedding Models, Google AI Edge Gallery app, Google AI Edge

Source: https://www.youtube.com/watch?v=XnIXupxiRo4