Azure OpenAI in Foundry Models provides access to OpenAI models such as the GPT chat models and the gpt-image image-generation models through Azure with enterprise security and networking. AI-103 covers provisioning, deploying, and consuming these models.
Microsoft Foundry is Microsoft's unified platform for building, deploying, and managing generative AI apps and agents on Azure.
The Foundry Agent Service is the Microsoft Foundry capability for creating and running AI agents with tools, knowledge, and memory.
An agent is an AI system that pursues goals by reasoning over tools, knowledge, and conversation memory rather than answering a single prompt.
RAG (retrieval-augmented generation) is a pattern that grounds a language model's responses in retrieved data to improve accuracy and reduce fabrication.
Grounding is the practice of anchoring a generative model's output in trusted source data so responses are factual and cite evidence.
Vector search retrieves content by comparing embedding vectors for semantic similarity rather than exact keywords.
Azure AI Search is the Azure service that indexes content and serves semantic, hybrid, and vector queries for grounding AI applications.
Function calling lets a language model invoke defined tools or APIs by returning structured arguments the application executes.
The model catalog is the Microsoft Foundry gallery where you browse, compare, and deploy foundation models — including LLMs, small language models, and multimodal models — from Microsoft, OpenAI, and partners.
Azure OpenAI in Foundry Models provides access to OpenAI models such as the GPT chat models and the gpt-image image-generation models through Azure with enterprise security and networking.
Azure Content Understanding in Foundry Tools extracts structured information from documents, images, video, and audio for grounding and analysis.
Azure Document Intelligence is the Azure service that extracts text, key-value pairs, and tables from documents using prebuilt or custom models.
OCR (optical character recognition) converts text in images and scanned documents into machine-readable text.
Prompt shields are an Azure content-safety capability that detects and blocks prompt-injection and jailbreak attempts against a model.
Responsible AI is the set of principles and controls — fairness, safety, privacy, transparency, and accountability — applied across an AI solution.