Chapter Eight
AI & Machine Learning
Six services spanning the AI surface of Azure — a platform for building models, the OpenAI models behind generative apps, and pre-trained APIs for vision, language, speech, and documents.
Core Terminology
Azure's AI services range from raw model training to ready-made APIs. These terms recur across the chapter.
Azure AI Foundry
The umbrella studio for building generative-AI applications — model catalog, deployments, evaluation, and prompt management.
Pre-trained API
A managed model you call over HTTP without training anything — vision, language, speech, document — billed per transaction.
Deployment
A provisioned instance of a model (such as GPT-4o) in Azure OpenAI with its own throughput quota, measured in tokens per minute.
Token
The unit generative models read and write text in, and the unit Azure OpenAI bills. Prompt plus completion tokens determine cost and latency.
Endpoint
The deployed, network-addressable target that serves a model for real-time or batch inference in Azure Machine Learning.
Grounding
Supplying a model with retrieved, authoritative context (often via Azure AI Search) so its answers reflect your data, not just its training.
Services in This Chapter
Service 53
Azure Machine Learning
The platform for training, deploying, and managing custom models — notebooks, pipelines, a model registry, and managed endpoints. For teams that build models, not just call them.
Service 54
Azure OpenAI Service
GPT, embeddings, and other OpenAI models served with Azure's networking, identity, and compliance. The foundation for generative-AI features on Azure.
Service 55
Azure AI Vision
Pre-trained image and video analysis — OCR, object detection, and image description — over a simple API. Add sight without training a model.
Service 56
Azure AI Language
Pre-trained natural-language processing — entity recognition, sentiment, summarization, and question answering — as a managed API.
Service 57
Azure AI Speech
Speech-to-text, text-to-speech, translation, and speaker recognition over an API, with custom voice and model options.
Service 58
Document Intelligence
Pre-built and custom models that extract text, key-value pairs, and tables from forms, invoices, and receipts. OCR plus structure, not just characters.