AI Apps on Steroids: Scaling Vector Databases with Pinecone and Pulumi
What does it take to go from an idea in a notebook to an application handling real-world traffic?
In this workshop, the Pinecone and Pulumi teams will explore the infrastructure and service architecture you need to scale AI apps in production.
The workshop will also discuss industry best practices in scalability and security for production-grade AI systems in a cloud-native landscape.
▬▬▬ Workshop Pre-requirements ▬▬▬
► Sign up for a Pulumi account. It's free: https://pulumip.us/Free-Sign-Up
► Pinecone free account: https://app.pinecone.io/?sessionType=...
► AWS account, the free tier is ok
👨💻Source Code: https://github.com/pinecone-io/aws-re...
▬▬▬▬▬▬ Timestaps⏰ ▬▬▬▬▬▬
00:00 Introduction
02:45 What is Infrastructure as Code (IaC)?
14:24 What does one AI application require?
15:27 Pinecone as Code
16:57 Navigating from Jupyter Notebooks to Production
24:29 Major component: IaC
26:14 "How do I start?"
30:40 "How much of a lift is it going to be?"
34:22 Quick but Powerful Aside - Embeddings
38:35 Back to the example...
49:30 Pitfalls and risks
51:18 Q&A
56:35 Closing
▬▬▬▬▬ Pinecone + Pulumi IaC ▬▬▬▬▬
Pinecone is a fully managed vector database that is frequently used to build GenAI applications like Retrieval Augmented Generation (RAG). You can now manage Pinecone's new serverless indexes using Pulumi's infrastructure as code in any general-purpose programming language.
Pulumi makes it easy to manage and scale every layer of your AI applications, from the microservices backends to the vector databases.
▬▬▬▬ Want to learn more? ▬▬▬▬▬
🎓 Register for live workshops and Q&A: https://pulumip.us/Upcoming-Workshops
🚀 Get Started with Pulumi: https://pulumip.us/Get-Started
🤖 Try Pulumi AI: https://www.pulumi.com/ai/
💬 Talk with us: https://slack.pulumi.com/
Note: this workshop was held on January 24, 2024