AI on Demand: Serverless AI

The workshop is scheduled to last three hours, with built-in breaks to ensure participants can stretch, use the facilities, and stay hydrated.

To set up an API token in Cloudflare, go to your profile, navigate to API tokens, create a new token with the necessary permissions for workers AI, and use this token in your application for authentication.

RAG is a method that combines information retrieval and text generation to provide more contextually relevant responses, often used in AI applications like chatbots and recommendation engines.

Benefits include ease of deployment, built-in scalability, cost-effectiveness due to its usage-based pricing, and low latency due to edge network execution.

LangChain is an ecosystem that simplifies building AI applications by allowing developers to chain different operations and interact with various AI models and vector databases.

The primary focus of the workshop is to teach participants about AI on demand, serverless architectures, and how to build a retrieval augmented generation (RAG) application.

The speaker is Nathan Visidor, an engineer at CloudFlare who works in the AI space, specifically on the vector DB.

Serverless computing is an architecture where the cloud provider dynamically manages the infrastructure, allowing developers to run code without managing servers.

Vector DB is a database optimized for storing and querying high-dimensional vectors, often used in AI and machine learning applications for tasks like similarity search.

The workshop utilizes Cloudflare Workers, HonoJS, LangChain, and Vectorize for building serverless AI applications.