At Touch, we are developing a unique personal health experience for our users through the use of AI health assistants. To achieve this, we have built an ecosystem of persistent models that incorporate expert systems, machine learning, and content distribution. Our main challenge has been to scale this stateful ecosystem in a robust way. In this talk, we will discuss the challenges we faced in developing and scaling our AI health assistants, including issues with model and state management, and maintaining the health and reliability of the interconnected components within the persistent ecosystem. We will describe our solution, which is built on top of Ray. Our talk will cover the overarching principles and design considerations that guided the development of our solution provide key takeaways for building and scaling similar products in other contexts.
Find the slide deck here: drive.google.com/file/d/1Zizj...
About Anyscale
---
Anyscale is the AI Application Platform for developing, running, and scaling AI.
www.anyscale.com/
If you're interested in a managed Ray service, check out:
www.anyscale.com/signup/
About Ray
---
Ray is the most popular open source framework for scaling and productionizing AI workloads. From Generative AI and LLMs to computer vision, Ray powers the world’s most ambitious AI workloads.
docs.ray.io/en/latest/
#llm #machinelearning #ray #deeplearning #distributedsystems #python #genai
Негізгі бет Scaling AI Health Assistants: Challenges and Solutions
Пікірлер