Think inside the box: Container use cases, examples and applications

Container management has come a long way. For decades, managing containerized environments was a relatively simple affair. The modern idea of a computer container originally appeared back in the 1970s, with the concept first being used to help define application code on Unix systems. Modern containerization technology has moved on steadily from those early beginnings, …

ml 15928 1

Use RAG for drug discovery with Knowledge Bases for Amazon Bedrock

Amazon Bedrock provides a broad range of models from Amazon and third-party providers, including Anthropic, AI21, Meta, Cohere, and Stability AI, and covers a wide range of use cases, including text and image generation, embedding, chat, high-level agents with reasoning and orchestration, and more. Knowledge Bases for Amazon Bedrock allows you to build performant and …

Unleash the power of generative AI with BigQuery and Vertex AI

Organizations dream of unlocking new insights and efficiencies with AI. To do this, they need a data and AI platform that makes it easy and seamless to access all enterprise data, both structured and unstructured, in a secure and governed way. To help customers accomplish this, we are announcing innovations that further connect data and …

What is managed DNS, anyway?

Managed DNS is where a third-party hosts and optimizes your DNS resolution architecture to provide the fastest, most secure, most reliable experience. Perhaps the easiest way to explain it is by looking at the opposite scenario: what if you don’t have a managed DNS service in place? Every query in the Domain Name System (DNS) follows the …

ML 16098 image01 Architecture

Build a robust text-to-SQL solution generating complex queries, self-correcting, and querying diverse data sources

Structured Query Language (SQL) is a complex language that requires an understanding of databases and metadata. Today, generative AI can enable people without SQL knowledge. This generative AI task is called text-to-SQL, which generates SQL queries from natural language processing (NLP) and converts text into semantically correct SQL. The solution in this post aims to …

Code samples to get started building generative AI apps on Google Cloud

Last year, we surveyed over 100 senior executives from leading companies on the top generative AI use cases for 2024. They told us their top use cases delivered near-term benefits for their business and had a lower time to and risk to implement. Specifically, they identified improving customer service, increasing the productivity of software development …

SynthDST: Synthetic Data is All You Need for Few-Shot Dialog State Tracking

In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning methods involve retrieving and adding similar examples to the prompt, requiring access to labeled training data. Procuring such training data for a wide range of domains and applications is time-consuming, …

How to mitigate the risks of DIY authoritative DNS

While many network admins outsource the management of authoritative domain name system (DNS) infrastructure to a third party like IBM® NS1 Connect®, there is a sizable community of network operators who prefer to dig in and build something themselves. These do it yourself (DIY) authoritative DNS architectures can be cobbled together from various tools. BIND is most …

ML 15027 arch diagram

How Axfood enables accelerated machine learning throughout the organization using Amazon SageMaker

This is a guest post written by Axfood AB.  In this post, we share how Axfood, a large Swedish food retailer, improved operations and scalability of their existing artificial intelligence (AI) and machine learning (ML) operations by prototyping in close collaboration with AWS experts and using Amazon SageMaker. Axfood is Sweden’s second largest food retailer, …

Multichannel Voice Trigger Detection Based on Transform-average-concatenate

This paper was accepted at the workshop HSCMA at ICASSP 2024. Voice triggering (VT) enables users to activate their devices by just speaking a trigger phrase. A front-end system is typically used to perform speech enhancement and/or separation, and produces multiple enhanced and/or separated signals. Since conventional VT systems take only single-channel audio as input, …