# Online Embeddings Matching

A Google Cloud Platform sample that demonstrates real-time text semantic search end to end, extracting embeddings with the Universal Sentence Encoder and building an approximate nearest-neighbour index with the Annoy library.

This repository contains sample code demonstrating online embeddings matching using Google Cloud Platform and third-party libraries; it is explicitly not an officially supported Google product.

Its text semantic search example builds an end-to-end, real-time search pipeline: it extracts text embeddings with the Universal Sentence Encoder and constructs an approximate similarity matching index with the Annoy library, showing how the two pieces fit together into one working demonstration rather than shipping either as a standalone package.

Website: https://github.com/GoogleCloudPlatform/realtime-embeddings-matching