Azure Document Intelligence

azureAI serviceazure-document-intelligence

Extracts text, tables and structured fields from documents using read, layout, prebuilt and custom models.

Provider
azure
Category
Compute
Also known as
Form Recognizer
Properties · 5 set by this component
propertytypevaluesrequiredkind defaultthis component
analyzeTransactionsPerSecond · component propertyinteger—no15inherited
authenumapi-key | oauth | iam | noneno—▸ api-key
contentFilteringboolean—no—inherited
customerManagedKeysboolean—no—▸ false
dataResidency · advancedenumus | eu | asia | globalno—inherited
dataRetentionDaysinteger—no—inherited
keyStoreboolean—nofalseinherited
managedboolean—nofalse▸ true
maxDocumentSizeMb · component propertyinteger—no500inherited
maxPagesPerAnalysis · component propertyinteger—no2000inherited
modalityenumtext | vision | speech | multimodal | structured | image | video | audio | embedding | rerankno—▸ vision
modelType · component propertyenumread | layout | prebuilt | custom-template | custom-neural | classifierno—inherited
publicEndpointboolean—no—▸ true
quotaUnitsPerMinuteinteger—no—inherited
rateLimitRpm · advancedinteger—no—inherited
rateLimitTpm · advancedinteger—no—inherited
viaGatewayboolean—nofalseinherited
Rules that apply · 2

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

ai-api-key-unmanaged

This AI vendor is reached with an API key, and nothing in the design holds or rotates that key. It ends up in environment files or code, every caller shares it, and a single leak runs up the vendor bill until someone notices. Put the key in a key-management component, or say it is held there with keyStore.

  • — all of these hold:
  • — the node's `auth` is "api-key"
  • — the node's `keyStore` is false
  • — the node has at least one incoming edge from an app-server, worker or client
  • — this does not hold:
  • — the design contains a node of kind key-management
stateful-node-without-zone-redundancy

A stateful compute node pinned to exactly one availability zone disappears with that zone, and its state goes with it. Nodes inside a cell are exempt, because there the cell is deliberately single-zone and redundancy comes from the other cells.

  • — all of these hold:
  • — the node's `stateless` is false
  • — the node sits inside exactly 1 availability-zone group
  • — this does not hold:
  • — the node sits inside at least one cell group
Use it in a design
nodes:
  - { id: "document-intelligence", component: "azure-document-intelligence" }
Other AI service products · 125
Content Moderationalibaba-content-moderationalibabacloudai-serviceFraud Detectionalibaba-fraud-detectionalibabacloudai-serviceID Verificationalibaba-id-verificationalibabacloudai-serviceIntelligent Robotalibaba-intelligent-robotalibabacloudai-serviceModel Studioalibaba-model-studioalibabacloudai-serviceSmart Conversation Analysisalibaba-smart-conversation-analysisalibabacloudai-serviceAmazon Bedrockaws-bedrockawsai-serviceAmazon Bedrock AgentCoreaws-bedrock-agentcoreawsai-serviceAmazon Bedrock Data Automationaws-bedrock-data-automationawsai-serviceAmazon Bedrock Guardrailsaws-bedrock-guardrailsawsai-serviceAmazon Comprehendaws-comprehendawsai-serviceAmazon Comprehend Medicalaws-comprehend-medicalawsai-serviceAWS Elemental Inferenceaws-elemental-inferenceawsai-serviceAmazon Forecastaws-forecastawsai-serviceAmazon Fraud Detectoraws-fraud-detectorawsai-serviceAWS HealthScribeaws-healthscribeawsai-serviceAmazon Lex botaws-lexawsai-serviceAmazon Lookout for Equipmentaws-lookout-for-equipmentawsai-serviceAmazon Lookout for Metricsaws-lookout-for-metricsawsai-serviceAmazon Lookout for Visionaws-lookout-for-visionawsai-serviceAmazon Personalizeaws-personalizeawsai-serviceAmazon Pollyaws-pollyawsai-serviceAmazon Q Businessaws-q-businessawsai-serviceAmazon Rekognitionaws-rekognitionawsai-serviceAmazon Textractaws-textractawsai-serviceAmazon Transcribeaws-transcribeawsai-serviceAmazon Translateaws-translateawsai-serviceContent Safetyazure-ai-content-safetyazureai-serviceAzure AI Custom Visionazure-ai-custom-visionazureai-serviceAzure AI Faceazure-ai-faceazureai-serviceAzure Languageazure-ai-languageazureai-serviceAzure Speechazure-ai-speechazureai-serviceAzure Translatorazure-ai-translatorazureai-serviceAzure Visionazure-ai-visionazureai-serviceAzure Content Understandingazure-content-understandingazureai-serviceMicrosoft Discoveryazure-discoveryazureai-serviceFoundry Agent Serviceazure-foundry-agent-serviceazureai-serviceFoundry Modelsazure-foundry-modelsazureai-serviceAzure AI Immersive Readerazure-immersive-readerazureai-serviceAzure OpenAI in Foundry Modelsazure-openaiazureai-service
and 85 more → AI service page
Source
# yaml-language-server: $schema=../../schema/component.schema.json
# Azure Document Intelligence: OCR and structured extraction from documents with read, layout, prebuilt and custom models.
# "Service quotas and limits - Document Intelligence" gives the Standard (S0) defaults: 15 analyze transactions per second, 500 MB maximum document size, 2,000 pages per analysis and 5,000 template models.
schemaVersion: "1"
type: "component"
id: "azure-document-intelligence"
kind: "ai-service"
provider: "azure"
docs: "https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits"
aliases: ["Form Recognizer"]
defaults:
  auth: "api-key"
  managed: true
  modality: "vision"
  publicEndpoint: true
  customerManagedKeys: false
properties:
  modelType:
    type: "enum"
    values: ["read", "layout", "prebuilt", "custom-template", "custom-neural", "classifier"]
  analyzeTransactionsPerSecond:
    type: "integer"
    default: 15
  maxDocumentSizeMb:
    type: "integer"
    default: 500
  maxPagesPerAnalysis:
    type: "integer"
    default: 2000

The same page as markdown, for an agent: /catalogue/components/azure-document-intelligence.md