AI in Production
A path from language models and retrieval to tool use, APIs, and the infrastructure that runs an AI application.
6 terms
AI in Production connects model capabilities to a running application. Start with an LLM, add relevant information through RAG, and explore how tool calling reaches external capabilities through an API. Then follow the application into containers and Kubernetes, which package and coordinate the software that serves it.
This Line joins AI Foundations, Model Basics, Agent Systems, How Software Talks, and Cloud Foundations. It describes one possible production path; retrieval, tool use, containers, and Kubernetes are choices rather than requirements for every AI application.
Along this line
6 terms
1.LLMA large language model: an AI model trained on large amounts of text to understand and generate language.AI & Automation2.RAGRetrieval-augmented generation: a technique that gives an AI model access to external information at request time so it can generate responses using retrieved context.AI & Automation3.Tool CallingA capability that lets an AI model request the use of an external tool, function, API, or service as part of completing a task.AI & Automation4.APIApplication programming interface: a defined interface that allows software systems to request data or functionality from one another.Software & Data5.ContainerAn isolated software environment that packages an application with the dependencies it needs to run consistently.Cloud & Systems6.KubernetesAn open-source platform for deploying, managing, and scaling containerized applications across clusters of computers.Cloud & Systems