Overview
LandingAI ADE VPC Architecture
ADE Enterprise VPC deployed in the customer's AWS account on Amazon EKS, with Amazon Bedrock, AWS Secrets Manager, Amazon S3 and AWS License Manager.
LandingAI ADE VPC Architecture

Product video
Agentic Document Extraction (ADE) from LandingAI turns complex, real-world documents into structured data your systems can trust. Every extracted element carries its page and coordinates, so each result traces back to the source.
ADE Enterprise VPC runs the same platform inside your own AWS account. It installs with a single Helm chart on Amazon EKS. Documents never leave your environment except to the language model you choose, such as Amazon Bedrock. LandingAI has no access to your deployment, and the product sends no telemetry. Under a LandingAI license, it reports usage totals only.
Four APIs: Parse converts PDFs, images, Office documents and spreadsheets into structured Markdown and JSON. Extract pulls the fields you define in a JSON schema. Split separates multi-document files. Classify labels each page with your classes.
Built for regulated teams. Documents are deleted when each job completes, workloads run unprivileged on read-only filesystems, and every release ships with an SBOM and a vulnerability scan. LandingAI ships security releases monthly and feature releases twice a year.
Pricing is set through private offers. Request a private offer or contact Sales@landing.ai .
Highlights
- Your data stays in your account: ADE runs in your AWS account on Amazon EKS, with no LandingAI access and no telemetry.
- Visual grounding: every extracted field links to its page and coordinates for audit and review.
- Bring your own model: use Amazon Bedrock or another LLM endpoint you already run.
Details
Features and programs
Trust center
Financing for AWS Marketplace purchases
Pricing
Custom pricing options
How can we make this page better?
Legal
Content disclaimer
Delivery details
Helm chart on Amazon EKS
- Amazon EKS
Helm chart
Helm charts are Kubernetes YAML manifests combined into a single package that can be installed on Kubernetes clusters. The containerized application is deployed on a cluster by running a single Helm install command to install the seller-provided Helm chart.
Version release notes
ADE Enterprise VPC is sold through private offers. LandingAI ships each customer the current release during onboarding, with that release's customer release notes, installation guide, SBOM and vulnerability scan.
CURRENT RELEASE
- Four APIs: Parse, Extract, Split and Classify
- One Helm chart that installs into a single namespace and creates nothing cluster-wide
- Bring your own model: Google Gemini through Vertex AI (default), Amazon Bedrock, or another OpenAI-compatible endpoint
- Documents are deleted when each job completes, and the product sends no telemetry
- Monthly security releases and twice-yearly feature releases
Additional details
Usage instructions
INSTALLATION
- Run LandingAI's preflight check against your cluster and share the report.
- Store your LLM credentials and license key as Kubernetes Secrets or in AWS Secrets Manager.
- Install ADE into a single namespace with Helm.
- Verify that every service is running, the health endpoint answers, and a sample document parses end to end.
- Apply your license key to move from evaluation to production.
- Publish the API behind your own load balancer, TLS and authentication.
LandingAI provides the installation guide for your release and works alongside your platform engineer through each step. Contact Support@landing.ai to start onboarding.
Resources
Vendor resources
Support
Vendor support
Contact Customer Success by emailing Support@Landing.ai for assistance with LandingAI solutions.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.