The emergence of generative AI with large language models has led to the creation of a highly efficient virtual assistant that integrates all AWS AI/ML services with OpenAI API or Hugging Face pre-trained models. This AI assistant is a serverless application that uses a simple static website hosted on Amazon S3 and fronted with Amazon CloudFront. It can respond to user queries via voice or text inputs and engages in continuous conversation with the host using Amazon Transcribe streaming in fully hands-free mode. Authentication is achieved through the use of an AWS API Gateway API key with usage plans, and conversations are saved in Amazon S3 for monitoring and assessment. The AI assistant also supports VR mode and the Awesome ChatGPT prompts integration. The system can be deployed using AWS CDK with just a few lines of commands.
Shing Seto is a highly motivated individual who is passionate about cloud computing and data centre administration. He is currently a first-year student pursuing a Higher Diploma in Cloud and Data Centre Administration under the guidance of Cyrus Wong. Shing is an AWS Community Builder, AWS Educate Student Ambassador, and Github Campus Expert, and is determined to become a multi-cloud certified full stack cloud developer.
Cyrus Wong is an accomplished senior lecturer who oversees the Higher Diploma program in Cloud and Data Centre Administration at the Department Information Technology of IVE(Lee Wai Lee) in Hong Kong in Hong Kong. He is a passionate advocate for the adoption of cloud technology across various media and events. With his extensive knowledge and expertise, he has earned prestigious recognitions such as AWS Machine Learning Hero, Microsoft Azure MVP, and Google Developer Expert for Google Cloud Platform. As an expert in cloud-based AI solutions, Cyrus has designed and developed various online education platforms using AWS AI services like Amazon Kendra, Amazon Comprehend, Amazon Rekognition, and Amazon AI language services, among others.
This presentation explores the Matter standard, a promising solution to the interpretability issues among various smart home ecosystems, and its integration with Home Assistant. It discusses the advantages and disadvantages of using Matter products within specific ecosystems (Google, Apple, Amazon) versus linking them to Home Assistant. The talk also provides guidance for planning smart home product investments in the upcoming year.
Amanda is an organiser of ProductTank Hong Kong and Women Techmakers Hong Kong, and co-hosts one of the most popular Cantonese tech podcast, HKPUG Podcast. She manages digital products in Hong Kong Disneyland as her day job.
Share my views on verilog coding paradigm
Developer from Hong Kong, doing few open-source projects
創業者。LikeCoin、DHK dao 發起人。
創作者。著有《區塊鏈社會學：金錢、媒體與民主的再想像》、《所謂「我不投資」，就是 all in 在法定貨幣》等。逢週四刊出《區塊鏈社會學週報》，文章全數收錄於 ckxpress.com。
As a developer using Postgres, I'm occasionally meeting some interesting cases. Some unexpected crashes, some unexpected huge performance optimizations, etc. I would like to share some of the cases I met during my 2 years of Postgres experience.