Skip to main content

AWS Solutions Library

Guidance for Automatic Image Matching for Articles Using Machine Learning on AWS

Overview

This Guidance shows how you can use AWS machine learning (ML) services to return semantically similar images to an article. It also uses artificial intelligence (AI) services and pre-trained large language models (LLMs) to summarize the article and extract key points, which become a search input parameter for an Amazon OpenSearch Service index. A search of the index will then return the most relevant images along with key points from the article, such as celebrity names, contributing to quicker discoverability of images from the article.

How it works

These technical details feature an architecture diagram to illustrate how to effectively use this solution. The architecture diagram shows the key components and their interactions, providing an overview of the architecture's structure and functionality step-by-step.

Download the architecture diagram

Well-Architected Pillars

The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.

CloudWatch and X-Ray provide visibility into the health of the application and allow you to identify where there may be issues through correlation IDs provided by X-Ray. X-Ray integrates with many of the AWS services in this Guidance and can surface where in the chain of events the issue occurred.

Additionally, CloudWatch offers monitoring dashboards and sets thresholds against metrics to alert you when there are issues. Many of the services can also write logs to CloudWatch for post-analysis of an issue. CloudWatch automatically monitors the infrastructure and enables build automation into the workflows to notify you of operational issues.

Read the Operational Excellence whitepaper 

To access the APIs, Amazon Cognito must provide authentication. Without authenticating, an individual cannot access any of the backend services. Amazon Cognito is scalable to set up and has native integration with API Gateway. API Gateway automatically delivers protection from distributed denial-of-service (DDoS) attacks for the backend services.

AWS Identity and Access Management (IAM) allows you to provide granular, least privilege access to resources. IAM restricts access across the Guidance by applying policies to Lambda to confirm it can only invoke certain APIs explicitly provided in the IAM policy.

Read the Security whitepaper 

CloudFront allows you to reduce the latency of page load times, so editors can access the system from multiple geographies. CloudFront serves images back to the editor and allows the editor to cache images closer to their location, reducing latency of larger files.

Read the Reliability whitepaper 

CloudFront uses a global network of 450+ Points of Presence, which provides low latency and faster HTTPS connections. Lambda allows the user to optimize how much memory is required to run the function and can scale out to thousands of requests per second within seconds. Amazon OpenSearch Serverless will automatically upgrade as new versions are released, removing overhead of managing indexes as storage and traffic scales.

Read the Performance Efficiency whitepaper 

With the services in this Guidance, you do not need to plan for capacity as the cost is per request, and the services will automatically scale out to meet demand. For example, OpenSearch Serverless will scale with your demand, so you don’t need to state how many indexes you require upfront. As these services are serverless, there is no infrastructure to manage, which significantly reduces the total cost of ownership.

Read the Cost Optimization whitepaper 

Amazon S3 scales as data volumes increase, and you can set up S3 Lifecycle policies to automatically archive or delete data you no longer need. Amazon S3 provisions underlying resources as your storage grows and scales back when you delete objects, reducing overall resource consumption.

Read the Sustainability whitepaper 

Disclaimer

The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.