# GeckoEmbeddingModel Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/geckoembeddingmodel
> Markdown URL: https://aitinkerers.org/technologies/geckoembeddingmodel.md
> Technology record last updated: 2026-03-23T01:37:34Z
> Generated: 2026-09-22T06:50:58Z

The Gecko family of models (e.g., `textembedding-gecko`) converts text into dense numerical vectors for high-performance semantic search and AI clustering on Google Cloud's Vertex AI.

GeckoEmbeddingModel is Google Cloud's premier text embedding technology, hosted on Vertex AI. It efficiently transforms text data into high-dimensional, dense numerical vectors, capturing deep semantic meaning. This is critical for applications like building powerful semantic search engines, performing text classification, and identifying data anomalies (outliers). For example, the `textembedding-gecko@001` model supports a maximum input length of 3072 tokens, ensuring high-fidelity representation for large documents. We use this model to power similarity-based retrieval and vector database operations across our core services.

- Official technology site: https://cloud.google.com/vertex-ai/docs/generative-ai/embeddings/overview
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Offline AI Tutor on Android: Gemma 3n + MediaPipe GenAI with Local RAG+CAG implementation](https://seattle.aitinkerers.org/talks/rsvp_8B20pGxfZiw)

I’ll live-demo an offline AI tutor running entirely on an Android phone using Gemma 3n via MediaPipe. The app ingests local text files, chunks and semantically indexes them in SQLite, and performs retrieval-augmented generation with on-device embeddings. Please suggest what from code would be interesting to present..

- Event context: AI Tinkerers Seattle September Meetup — September 30, 2025 — 2025-10-01 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_8B20pGxfZiw

## Related Technologies

- [Android](https://aitinkerers.org/technologies/android) ([Markdown](https://aitinkerers.org/technologies/android.md)) — 11 public demos
- [Gemma 3n](https://aitinkerers.org/technologies/gemma-3n) ([Markdown](https://aitinkerers.org/technologies/gemma-3n.md)) — 3 public demos
- [Markwon](https://aitinkerers.org/technologies/markwon) ([Markdown](https://aitinkerers.org/technologies/markwon.md)) — 1 public demo
- [MediaPipe GenAI](https://aitinkerers.org/technologies/mediapipe-genai) ([Markdown](https://aitinkerers.org/technologies/mediapipe-genai.md)) — 1 public demo