Search Azure terms

AI and Machine Learning premium Azure OpenAI Azure OpenAI provides OpenAI model capabilities through Azure resources, deployments, identity, networking, quota, and monitoring controls. Azure OpenAI intermediate 8 commands Aliases: Azure OpenAI Service Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI resource An Azure OpenAI resource is the Azure control-plane boundary that hosts deployments, endpoints, access, networking, and billing context. Azure OpenAI fundamentals 12 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI Service Azure OpenAI Service provides managed access to OpenAI model capabilities through Azure endpoints and enterprise controls. Generative AI fundamentals 11 commands Aliases: Azure OpenAI Quick peek Open full term page

AI and Machine Learning premium Azure OpenAI managed identity Azure OpenAI managed identity uses Microsoft Entra identities so Azure workloads can call model endpoints without stored keys. Azure OpenAI intermediate 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning field-manual-complete Azure OpenAI deployment An Azure OpenAI deployment is the practical handle your application uses when it calls a model. The resource may offer several models, but code usually sends requests to a deployment name such as summarizer-prod or support-gpt4o. That deployment records which model and. Azure OpenAI fundamentals 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning field-manual-complete Azure OpenAI private endpoint An Azure OpenAI private endpoint gives your model-calling applications a private network path to an Azure OpenAI resource. Instead of reaching the resource over its public endpoint, approved clients in a virtual network resolve the service name to a private IP address. This is useful for sensitive prompts, internal copilots, and retrieval systems that must stay inside controlled network boundaries. It still requires identity, DNS, and application configuration to be correct. Test callers before lockdown. Azure OpenAI intermediate 5 commands Aliases: OpenAI private endpoint, Azure OpenAI Private Link, private model endpoint, private endpoint for Azure OpenAI Quick peek Open full term page

AI and Machine Learning field-manual-complete Azure OpenAI quota Azure OpenAI quota is the guardrail that limits how much model capacity your workloads can use. It is not just a billing setting. Quota is commonly scoped by subscription, region, model, and deployment type, so a workload can have plenty of capacity. Azure OpenAI fundamentals 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning field-manual-complete Private endpoint for Azure OpenAI A private endpoint for Azure OpenAI is the private network doorway to an Azure OpenAI resource. Your application still calls the Azure OpenAI endpoint and authenticates normally, but from approved networks the name can resolve to a private IP instead of a public address. It is commonly used for enterprise chat, RAG, summarization, and agent workloads that handle sensitive prompts or documents. It protects the network path, not the prompt content by itself, so identity, logging, safety, and data controls still matter. Azure OpenAI advanced 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning top-250-pre130-priority-upgraded Customer managed key for Azure OpenAI Customer managed key for Azure OpenAI is a production Azure concept tied to Azure OpenAI. Azure OpenAI advanced 4 commands Aliases: Customer-managed key for Azure OpenAI, Customer managed key for Azure OpenAI Quick peek Open full term page

AI and Machine Learning premium Azure AI Foundry Create a governed project boundary where AI teams can build agents, evaluations, files, and model deployments without unmanaged sprawl.; Compare, evaluate, and approve model deployments before a generative AI feature is AI platform fundamentals 5 commands Aliases: AI Foundry, Microsoft Foundry, Foundry resource, Foundry project, Azure AI Foundry, azure ai foundry Quick peek Open full term page

AI and Machine Learning premium Azure AI Content Safety Azure AI Content Safety is the Azure AI service used to detect harmful text and image content before it reaches users, moderators, or automated workflows. In Azure, teams encounter it when applications accept user posts, comments, uploads, prompts, or model outputs that need moderation and policy review. The useful question is what behavior it proves, Responsible AI advanced 4 commands Aliases: Content Safety, Azure Content Safety, harm detection, content moderation API Quick peek Open full term page

AI and Machine Learning premium Azure AI Language Azure AI Language is the Azure natural-language processing service for analyzing and understanding text with prebuilt and customizable language capabilities. AI services intermediate 4 commands Aliases: Azure Language, Azure Language in Foundry Tools, Azure Language service, Language in Foundry Tools, Language service Quick peek Open full term page

AI and Machine Learning premium Azure AI services Azure AI services is the family of Azure cloud AI APIs and resources, surfaced through Foundry Tools, for vision, speech, language, translation, content, and generative scenarios. AI services fundamentals 4 commands Aliases: AI services, Azure AI services account, Cognitive Services, Foundry Tools Quick peek Open full term page

AI and Machine Learning verified OpenAI deployment name An OpenAI deployment name is the customer-chosen name assigned to an Azure OpenAI or Foundry model deployment. Applications use that name, not necessarily the base model name, to route inference requests to the deployed model, quota, version, and deployment type. Azure OpenAI intermediate 6 commands Aliases: Azure OpenAI deployment name, model deployment name, deployment_name, Azure OpenAI model parameter, OpenAI deployment name, deploymentName, deployments route Quick peek Open full term page

AI and Machine Learning learning-path-anchor System message A system message is the instruction layer that tells an Azure OpenAI chat model how it should behave before it answers the user's request. It can define the assistant's role, tone, allowed sources, formatting rules, safety boundaries, and refusal behavior. It is stronger than an ordinary user message, but it is not magic and... Azure OpenAI fundamentals 5 commands Aliases: system prompt, metaprompt, developer instruction, assistant instruction Quick peek Open full term page

Databases premium Cosmos DB vector embedding policy Cosmos DB vector embedding policy is the container policy that defines vector paths, dimensions, data type, and distance function for embeddings stored in Cosmos DB for NoSQL. It tells Cosmos DB which item properties contain embeddings and how those vectors should be interpreted. You see it when teams build semantic search, recommendation, image similarity, or retrieval-augmented generation features on Cosmos DB data. The production check is whether the vector path, dimensions, data type, and distance function are correct before production data lands. Document the decision in code, templates, metrics, and runbooks. Azure Cosmos DB intermediate 7 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Exhaustive KNN Exhaustive KNN is a vector search algorithm that calculates distances across all candidate vectors to return the exact nearest neighbors for a query. Teams use it to test vector relevance, produce exact nearest-neighbor baselines, or serve smaller vector workloads where accuracy matters more than approximate search speed. It is not HNSW approximate search, semantic ranking, a text analyzer, an embedding model, or a fix for poor chunking and low-quality vectors. In production, confirm index schema, vector dimensions, algorithm configuration, vector profile, query k value, exhaustive flag, latency, throttling, relevance test set, and comparison with HNSW results before treating the design. Azure AI Search advanced 6 commands Aliases: exhaustive k-nearest neighbors, brute-force vector search, exhaustive vector search Quick peek Open full term page

AI and Machine Learning premium Foundry Agent A Foundry Agent is an AI agent built or hosted in Microsoft Foundry Agent Service with instructions, model selection, tools, knowledge, and runtime execution evidence. Teams use it to automate business tasks that require model reasoning, tool calls, enterprise knowledge, workflow steps, retrieval, approvals, and observable runs inside a governed Azure AI platform. It is not a magic autonomous worker, a security principal by itself, a replacement for process controls, or a safe production feature without tool permissions, evaluation, monitoring, and human escalation. Microsoft Foundry intermediate 6 commands Aliases: Microsoft Foundry agent, Foundry Agent Service agent, AI agent in Foundry, agent service agent Quick peek Open full term page

AI and Machine Learning premium Chat completion A AI platform capability in Azure OpenAI that helps teams build, secure, observe, and govern intelligent applications with clearer ownership, safety, and operational context. Azure OpenAI fundamentals 5 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Foundry Local Foundry Local is an on-device AI runtime and SDK for shipping applications that run curated generative AI models locally on user hardware. Microsoft Foundry intermediate 5 commands Aliases: Microsoft Foundry Local, Foundry Local CLI, on-device AI inference, local AI runtime Quick peek Open full term page

AI and Machine Learning premium Foundry Models Foundry Models is the Microsoft Foundry model catalog and deployment experience for discovering, evaluating, and using cloud AI models through managed endpoints. Microsoft Foundry intermediate 5 commands Aliases: Microsoft Foundry Models, Foundry model catalog, AI Foundry models, model catalog Quick peek Open full term page

AI and Machine Learning premium Inference endpoint Inference endpoint is the Azure concept that controls how applications invoke deployed machine learning models securely, reliably, and measurably in Azure. Teams see it when working with azure machine learning online endpoints, batch endpoints. It is not a model artifact, a training job, an Azure OpenAI deployment, or an application API gateway by itself; that distinction matters because bad assumptions create failed predictions, public exposure. Use the term when reviewing ownership, access, monitoring, cost, recovery, or performance. It keeps architects, operators, security reviewers, and support teams focused on the same resource, setting, or behavior. Azure Machine Learning Intermediate 5 commands Aliases: ML inference endpoint, online endpoint, managed online endpoint, batch endpoint, scoring endpoint Quick peek Open full term page

AI and Machine Learning premium Input token Input token controls how much information an AI request can send to the model and how that request consumes quota, cost, latency, and context capacity. Teams see it in azure openai requests, chat completions. It is not an output token, API key, authentication token, session token, or tokenizer algorithm; confusing them can create truncated prompts, high cost. Use the term when reviewing access, monitoring, cost, recovery, or performance. It keeps architects, operators, security reviewers, and support teams focused on the same setting, resource, or behavior. Azure OpenAI Fundamentals 5 commands Aliases: prompt token, input tokens, request tokens, model input token, context input token Quick peek Open full term page

AI and Machine Learning premium Jailbreak detection Jailbreak detection is the AI safety capability that identifies prompts or embedded document instructions attempting to bypass system rules, policies, or intended model behavior. AI safety intermediate 5 commands Aliases: Prompt Shields, prompt attack detection, jailbreak risk detection, user prompt attack detection, document attack detection Quick peek Open full term page

AI and Machine Learning premium JSON mode JSON mode is the Azure OpenAI response format option that asks supported chat models to return syntactically valid JSON instead of ordinary prose. Azure OpenAI intermediate 5 commands Aliases: response_format json_object, valid JSON output mode, Azure OpenAI JSON mode, chat completions JSON mode Quick peek Open full term page

Security premium Key Key controls how protected workloads use cryptographic material for encryption, signing, key wrapping, customer-managed keys, and regulated data protection. Teams see it in key vault keys, managed hsm keys. It is not a password, secret value, certificate, storage account key, shared access signature, or application configuration setting; confusing them can create failed encryption operations, accidental key deletion. Use the term when reviewing access, monitoring, cost, recovery, or performance. It keeps architects, operators, security reviewers, and support teams focused on the same setting, resource, or behavior. Secrets and cryptography Fundamentals 5 commands Aliases: Azure Key Vault key, cryptographic key, key object, encryption key Quick peek Open full term page

AI and Machine Learning premium Search vectorizer A search vectorizer is an Azure AI Search index configuration that converts text or images into vectors at query time. It references an embedding model, connects through a vector profile, and should match the model used to create indexed vector content. Search advanced 5 commands Aliases: vectorizer, search vectorizer, Azure AI Search vectorizer, query-time vectorization, integrated vectorization Quick peek Open full term page

AI and Machine Learning premium Abuse monitoring Abuse monitoring is the safety layer that looks for harmful or policy-violating use of AI services. It is not a performance feature; it exists to help detect misuse, protect the service, and support responsible operation of model deployments. Azure OpenAI intermediate 4 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Batch inference Batch inference is the process of generating predictions over larger sets of input data asynchronously, often using Azure Machine Learning batch endpoints and deployments. Azure OpenAI fundamentals 4 commands Aliases: No aliases yet Quick peek Open full term page

Security premium Customer-managed key rotation Customer-managed key rotation is the planned creation and adoption of new versions of a customer-managed encryption key while Azure services keep accessing protected data safely. Key management advanced 4 commands Aliases: Customer-managed key rotation Quick peek Open full term page

AI and Machine Learning premium Deployment capacity Deployment capacity is the throughput allocation configured for an Azure OpenAI or Foundry model deployment, affecting available request volume, quota use, latency, and cost. Azure OpenAI intermediate 4 commands Aliases: Azure OpenAI deployment capacity, model deployment capacity, deployment throughput capacity, PTU deployment capacity Quick peek Open full term page

AI and Machine Learning premium Deployment type Deployment type is the Azure AI or Microsoft Foundry model hosting option, such as standard, global, data-zone, regional, batch, serverless, or provisioned deployment, that determines availability, data processing location, capacity model, cost, and operational behavior. Microsoft Foundry intermediate 4 commands Aliases: Microsoft Foundry deployment type, Azure AI deployment type, model deployment type, Foundry Models deployment type Quick peek Open full term page

AI and Machine Learning premium Embedding An embedding is a list of numbers that captures meaning in a way software can compare. Instead of matching only exact words, an application can compare the embedding for a user question with embeddings for documents, products, tickets, or records. Similar ideas end up near each other in vector space even when the wording differs. In Azure, embeddings commonly come from Azure OpenAI models and are stored in vector indexes. Generative AI fundamentals 4 commands Aliases: Embedding, text embedding, vector embedding, embedding vector, embedding Quick peek Open full term page

AI and Machine Learning premium Embedding model An embedding model converts text into numerical vector form so applications can perform text similarity, retrieval, and other semantic comparison tasks. Azure OpenAI intermediate 4 commands Aliases: text embedding model, Azure OpenAI embedding model, vector embedding model Quick peek Open full term page

AI and Machine Learning premium Embeddings Embeddings are the many vectors your system creates when it turns a collection of text, records, or documents into searchable meaning. One embedding represents one input or chunk; embeddings as a set become a retrieval layer. Applications compare a new query embedding against stored embeddings to find similar content. In Azure workloads, embeddings often connect Azure OpenAI model deployments with Azure AI Search, Cosmos DB, Azure SQL, PostgreSQL, or Redis.. Azure OpenAI fundamentals 4 commands Aliases: Embeddings, text embeddings, vector embeddings, embedding vectors, embeddings Quick peek Open full term page

AI and Machine Learning premium Embeddings model An embeddings model is a deployed model used to convert text into vector representations for semantic similarity, retrieval, and vector search workloads. Azure OpenAI intermediate 4 commands Aliases: embedding model deployment, embeddings deployment, text embeddings model Quick peek Open full term page

AI and Machine Learning premium Fine-tuned model Fine-tuned model is a customized model produced from a supported base model by a completed fine-tuning job and then deployed for inference in Azure. Azure AI Foundry and Azure OpenAI intermediate 4 commands Aliases: Fine-tuned model, fine tuned model Quick peek Open full term page

AI and Machine Learning premium Fine-tuning Fine-tuning is the process of customizing a supported model with curated training examples so it performs better for a specific task in Azure. Azure AI Foundry and Azure OpenAI intermediate 4 commands Aliases: Fine-tuning, fine tuning Quick peek Open full term page

AI and Machine Learning premium Fine-tuning job Fine-tuning job is the tracked training run that uses prepared data and a supported base model to produce a customized model candidate in Azure. Azure AI Foundry and Azure OpenAI intermediate 4 commands Aliases: Fine-tuning job, fine tuning job Quick peek Open full term page

Web premium Function app managed identity Function app managed identity is a Microsoft Entra identity assigned to a function app so its code and supported bindings can access Azure resources without storing passwords or connection strings. Teams use it to replace secrets in app settings with identity-based access to services such as Storage, Service Bus, Key Vault, Event Hubs, SQL, or monitoring resources. In daily Azure work, it shows up when engineers grant a function app data-plane permissions, remove leaked connection strings, configure identity-based bindings, or investigate why a trigger cannot reach its dependency. Azure Functions intermediate 4 commands Aliases: Azure Functions managed identity, managed identity for Functions, function app identity Quick peek Open full term page

AI and Machine Learning premium Function calling Function calling is an AI application pattern where a model chooses a developer-defined tool and returns structured arguments so the application can call real business logic. Teams use it to let assistants retrieve data, create tickets, schedule work, search systems, or call APIs while the application remains responsible for execution and validation. In daily Azure work, it shows up when engineers build agents, connect chat to backend tools, audit model-selected actions, validate JSON arguments, or debug why a model called the wrong function. Azure OpenAI advanced 4 commands Aliases: tool calling, OpenAI function calling, model tool call Quick peek Open full term page

AI and Machine Learning premium Groundedness detection Groundedness detection checks whether a generated text response is supported by provided source material and flags responses that appear ungrounded or inconsistent with that material. Azure AI Content Safety advanced 4 commands Aliases: groundedness filter, ungroundedness detection, AI groundedness check Quick peek Open full term page

AI and Machine Learning premium Grounding data Grounding data is the source content, retrieved documents, indexed chunks, tool results, or external information supplied to a model so generated output can be based on approved facts. Azure OpenAI intermediate 4 commands Aliases: RAG grounding data, source grounding data, AI source material Quick peek Open full term page

Databases premium Hybrid search in Cosmos DB Hybrid search in Cosmos DB is a Cosmos DB for NoSQL capability that combines vector search with full-text search scoring, then merges results with Reciprocal Rank Fusion. Azure Cosmos DB advanced 4 commands Aliases: Cosmos DB hybrid search, Cosmos DB RRF search, Hybrid search in Azure Cosmos DB, hybrid search in cosmos db, Hybrid search in Cosmos DB Quick peek Open full term page

AI and Machine Learning premium Image generation model Image generation model is an Azure OpenAI or Foundry model deployment that creates images from prompts, commonly using the current gpt-image model family. Azure OpenAI intermediate 4 commands Aliases: Azure OpenAI image model, gpt-image model, image generation model, Image generation model, text-to-image model Quick peek Open full term page

AI and Machine Learning premium Microsoft Foundry Microsoft Foundry is the Microsoft AI platform experience used to build, evaluate, deploy, and manage AI applications, models, agents, and related project assets. Teams should manage it with clear ownership, monitoring, rollback evidence, and production change discipline. AI platform intermediate 4 commands Aliases: Azure AI Foundry, Foundry, AI Foundry Quick peek Open full term page

AI and Machine Learning premium AI quota AI quota is the Azure allocation that limits model deployment capacity, usually by subscription, region, model, and deployment type, using measures such as tokens per minute, requests per minute, concurrent requests, or provisioned throughput. Microsoft Foundry intermediate 3 commands Aliases: Foundry quota, Azure OpenAI quota, model quota, TPM quota, RPM quota Quick peek Open full term page

AI and Machine Learning premium AI token An AI token is a unit of text processed by a language model. Azure AI and Foundry model quotas, cost, and rate limits commonly use tokens to measure prompt input, generated output, and throughput such as tokens per minute. Azure OpenAI and Foundry Models fundamentals 3 commands Aliases: model token, LLM token, input token, output token, TPM Quick peek Open full term page

AI and Machine Learning premium Chat completions Chat completions are API calls to chat-capable models where the client sends role-based messages and receives the next model response, commonly through Azure OpenAI or Microsoft Foundry endpoints. Azure OpenAI intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page

AI and Machine Learning premium Completion the generated text or structured output returned by an AI model after an application sends prompt, message, or inference request data Azure OpenAI Intermediate 3 commands Aliases: No aliases yet Quick peek Open full term page