How Google Uses Retrieval Augmented Generation
8 engineering articles about Retrieval Augmented Generation from Google's engineering team
Other Google Technologies
Other Companies Using Retrieval Augmented Generation
Articles
Filter:
Deploying secure, real-time Edge AI on Raspberry Pi is now simplified using LiteRT and lightweight Gemma open models. LiteRT optimizes CPU and GPU performance, delivering fast token speeds for models like Gemma4, enabling real-time local reasoning for robotics. Developers can quickly convert, quantize, and run these models using the lightweight LiteRT CLI tool. Support for Hailo AI accelerators is also coming very soon.
Lu Wang, Terry Heo, Naushir Patuck, José María Casanova
9 min read
Includes Code
--
The article discusses the advancements in on-device AI powered by MediaTek's Neural Processing Unit (NPU) and the introduction of the LiteRT NeuroPilot Accelerator.
Lu Wang, Arian Arfaian, Luke Boyer
10 min read
Includes Code
Has Summary
--
The article discusses the launch of the Google AI Edge Gallery app, which now includes audio capabilities and is available on Google Play.
Alice Zheng, Na Li
3 min read
Has Summary
--
This article discusses the integration of Google's EmbeddingGemma model with Google Cloud's Dataflow to create a scalable embedding pipeline for AI applications.
Danny McCormick, Ian Ballantyne, Olivier Lacombe
5 min read
Includes Code
Has Summary
--
EmbeddingGemma is an innovative open embedding model designed for on-device AI applications, featuring 308 million parameters for efficient performance.
Min Choi, Sahil Dua, Alice Lisak
5 min read
Has Summary
--
The article discusses the expansion of Google's AI Edge platform to support on-device small language models (SLMs) with multimodal capabilities, including the introduction of the Gemma 3 and Gemma ...
Mark Sherwood, Matthew Chan, Marissa Ikonomidis
6 min read
Has Summary
--
The article discusses the Vertex AI RAG Engine, a tool designed to help developers build grounded generative AI applications by addressing challenges like hallucinations and outdated knowledge.
Crispin Velez, Holt Skinner
6 min read
Has Summary
--
The article discusses Firebase Demo Day 2024, showcasing how to build and run AI-powered applications using Firebase products like Firebase Genkit, Vertex AI, and Firebase App Hosting.
Yasmin Gehman
4 min read
Has Summary
--
You've reached the end! All 8 articles loaded.