reference deployment

Luna AI on AWS

Create a multimedia data pipeline to enrich data with AWS AI/ML services

This Partner Solution deploys Luna AI on the Amazon Web Services (AWS) Cloud. It's for developers that want a scalable cloud-native artificial intelligence and machine learning (AI/ML) media enrichment solution. The solution ingests text, image, video, and audio data, enriches them with AWS AI/ML services, and streams enriched data to Amazon Kendra and AWS Lake Formation. With it, developers can build applications that find images or text in data using label searches and natural language queries. 

General Dynamics Information Technology logo

This Partner Solution was developed by General Dynamics Information Technology and AWS. General Dynamics Information Technology is an AWS Partner.

  •  What you'll build
  • The Partner Solution sets up the following: 

    • Data ingestion services to ingest and queue user multimedia data for enrichment.
      • Amazon Simple Queue Service (Amazon SQS) for a data-ingestion event queue.
      • Amazon Simple Notification Service (Amazon SNS) to manage asynchronous messaging between Amazon EventBridge and enrichment services. 
      • AWS Lambda to do the following:
        • Poll the data-ingestion event queue and post events to EventBridge.
        • Process data flowing from EventBridge to enrichment services and between enrichment services.
      • EventBridge to route ingested data to enrichment services.
    • Data enrichment services to do the following:
      • Amazon Textract to extract text from PDF and image files.
      • Amazon Comprehend to extract entities from text such as key phrases, places, names, organizations, quantities, and events.
      • Amazon Rekognition to identify objects, people, text, scenes, and activities in images and videos.
      • Amazon Transcribe to convert audio input into text.
      • Amazon Translate to translate text documents.
      • AWS Elemental MediaConvert to transcode video files. 
    • Data storage and streaming services to do the following:
      • Amazon Simple Storage Service (Amazon S3) for landing zone and enriched data storage.
      • Amazon DynamoDB to store system data, system metadata, and media asset metadata, and keep a record of changes to database tables.
      • Amazon Kinesis Data Streams to stream enriched data to Amazon Kendra and AWS Lake Formation.
    • Amazon Kendra for searching enriched data with natural language processing and advanced search algorithms.
    • Lake Formation to set up, secure, and manage a data lake to run analytics.
  •  How to deploy
  • To deploy this Partner Solution, follow the instructions in the deployment guide, which includes these steps.

    1. Sign in to your AWS account. If you don't have an account, sign up at https://aws.amazon.com.
    2. Launch the Partner Solution. The stack takes about 15 minutes to deploy. Before you create the stack, choose the AWS Region from the top toolbar.

    Amazon may share user-deployment information with the AWS Partner that collaborated with AWS on this solution.  

  •  Costs and licenses
  • You are responsible for the cost of the AWS services and any third-party licenses used while running this solution. There is no additional cost for using the solution.

    This solution includes configuration parameters that you can customize. Some of these settings, such as instance type, affect the cost of deployment. For cost estimates, refer to the pricing pages for each AWS service you use. Prices are subject to change.

    Tip: After you deploy a solution, create AWS Cost and Usage Reports to track associated costs. These reports deliver billing metrics to an Amazon Simple Storage Service (Amazon S3) bucket in your account. They provide cost estimates based on usage throughout each month and aggregate the data at the end of the month. For more information, refer to What are AWS Cost and Usage Reports?