Skip to main content

Deployment Options

DocAI Fabric offers flexible deployment options to fit your infrastructure requirements, security policies, and operational preferences.

Choose Your Deployment Model

OptionBest ForInfrastructureManaged By
SaaSFastest start, no infra to manageOur cloudUs
Managed in Azure (Dedicated Subscription)New subscription, we handle everythingYour AzureUs (everything)
Managed in Azure (Existing Subscription)Deploy alongside other workloads, you control AI resourcesYour AzureUs (deployment & updates)
Self-Hosted (Docker)Full control, on-premisesYour serversYou
Managed in AWSAWS-native environmentsYour AWSUs (deployment & updates)
GCPGCP-native environmentsYour GCPYou

Comparison

FeatureSaaSManaged AzureManaged AWSSelf-HostedGCP
Setup timeMinutes~1 hour~1 hour~2 hours~2 hours
Data locationOur Azure tenantYour Azure subscriptionYour AWS accountYour infrastructureYour cloud
UpdatesAutomaticManaged by usManaged by usManualManual
Custom domainIncludedSupportedSupportedYour responsibilityYour responsibility
ScalingAutomaticAutomatic (Container Apps)Automatic (ECS)ManualManual
AI servicesIncludedYour Azure OpenAIAWS Bedrock + Textract (your account)Your endpointsYour endpoints
MonitoringIncludedYour Application InsightsYour CloudWatchYour toolsYour tools

What Every Deployment Needs

Regardless of deployment model, DocAI Fabric requires:

  • An LLM for classification and extraction: Azure OpenAI (GPT-4.1-mini or newer recommended), or Anthropic Claude on Amazon Bedrock for AWS deployments (in development)
  • An OCR service: Azure Document Intelligence (Read model), or Amazon Textract for AWS deployments (in development)
  • Container runtime: Docker or a managed container service
  • Redis: for job queue and caching
  • Blob / file storage: for document persistence