[SEO Subhead]
This Guidance demonstrates how to create an intelligent manufacturing digital thread through a combination of knowledge graph and generative artificial intelligence (AI) technologies. A digital thread offers an integrated approach to combine disparate data sources across enterprise systems, increasing traceability, accessibility, collaboration, and agility. By integrating knowledge graph and generative AI, you can enhance data integration, improve semantic understanding, and enable intelligent and context-aware applications—ultimately leading to a more personalized user experience.
Please note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
Identify key stakeholders in the manufacturing organization, and understand the business needs.
Step 2
Identify data sources to build a digital thread using graph and generative AI technologies.
Step 3
Ingest data into AWS using AWS Database Migration Service (AWS DMS) for databases and AWS DataSync for large datasets.
Step 4
Upload ingested data into Amazon Simple Storage Service (Amazon S3) for processing and analysis.
Step 5
Use the Amazon Neptune Bulk Loader to ingest the data from Amazon S3 to Neptune graph database.
Step 6
Select a foundation model (FM) from Amazon Bedrock, a fully managed service that offers a choice of high-performing FMs from leading AI companies and Amazon through a single API, along with a broad set of capabilities for building generative AI applications.
Step 7
Establish linkage between Amazon Bedrock and Neptune, and orchestrate the integration with AWS Lambda and Langchain. The orchestrator coordinates the process of generating the query from the FM (executing the query against the knowledge graph) and then returns the result in natural language.
Step 8
Create an application layer using Streamlit, AWS Fargate for hosting serverless containerized applications, Amazon Elastic Container Registry (Amazon ECR) for managing container images, Elastic Load Balancing (ELB) for traffic distribution, Amazon Route 53 for DNS, and Amazon Cognito for authentication.
Step 9
Use Amazon Virtual Private Cloud (Amazon VPC) to operate the application in a secure, isolated network. AWS Identity and Access Management (IAM) enhances access control. AWS Certificate Manager manages certificates, and AWS WAF supports web application security. Amazon GuardDuty monitors for malicious activity.
Data at rest is encrypted with AWS Key Management Service (AWS KMS) and can be integrated with third-party key management systems.
Step 10
Use AWS CloudTrail to track activities, Amazon CloudWatch to monitor resources, and AWS CloudFormation for automated resource deployment of digital thread application.
Step 1
Identify key stakeholders in the manufacturing organization, and understand the business needs.
Step 2
Identify data sources to build a digital thread using graph and generative AI technologies.
Step 3
Ingest data into AWS using AWS Database Migration Service (AWS DMS) for databases and AWS DataSync for large datasets.
Step 4
Upload ingested data into Amazon Simple Storage Service (Amazon S3) for processing and analysis.
Step 5
Use the Amazon Neptune Bulk Loader to ingest the data from Amazon S3 to Neptune graph database.
Step 6
Select a foundation model (FM) from Amazon Bedrock, a fully managed service that offers a choice of high-performing FMs from leading AI companies and Amazon through a single API, along with a broad set of capabilities for building generative AI applications.
Step 7
Establish linkage between Amazon Bedrock and Neptune, and orchestrate the integration with AWS Lambda and Langchain. The orchestrator coordinates the process of generating the query from the FM (executing the query against the knowledge graph) and then returns the result in natural language.
Step 8
Create an application layer using Streamlit, AWS Fargate for hosting serverless containerized applications, Amazon Elastic Container Registry (Amazon ECR) for managing container images, Elastic Load Balancing (ELB) for traffic distribution, Amazon Route 53 for DNS, and Amazon Cognito for authentication.
Step 9
Use Amazon Virtual Private Cloud (Amazon VPC) to operate the application in a secure, isolated network. AWS Identity and Access Management (IAM) enhances access control. AWS Certificate Manager manages certificates, and AWS WAF supports web application security. Amazon GuardDuty monitors for malicious activity.
Data at rest is encrypted with AWS Key Management Service (AWS KMS) and can be integrated with third-party key management systems.
Step 10
Use AWS CloudTrail to track activities, Amazon CloudWatch to monitor resources, and AWS CloudFormation for automated resource deployment of digital thread application.
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
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.
-
Operational ExcellenceRead the Operational Excellence whitepaper
DataSync automates and optimizes data synchronization, reducing manual intervention and helping ensure operational efficiency in managing digital thread data. To help you further improve operational efficiency across workloads, CloudWatch enables monitoring and logging capabilities to provide real-time insights into system performance. Additionally, CloudTrail helps ensure that you have a comprehensive audit trail, promoting governance and compliance.
-
SecurityRead the Security whitepaper
To protect data, IAM offers fine-grained permissions and role-based access control to AWS services and resources, enforcing least privilege and enhancing control over user permissions. Additionally, AWS KMS manages keys for encrypting and decrypting Neptune data at rest.
AWS WAF acts as a security layer by protecting against web application vulnerabilities and attacks, safeguarding the digital thread application, and protecting it from common vulnerability. GuardDuty provides automatic thread detection by continuously monitoring for malicious activities, using threat intelligence to promptly detect and respond to potential security risks.
Amazon VPC and the VPC endpoint establish a secure network environment, isolating resources and establishing private communication with AWS services to reduce exposure to potential threats.
Amazon Bedrock helps ensure data protection by refraining from using prompts for AWS model training, avoiding distribution to third parties, and not storing or logging data in service logs.
-
ReliabilityRead the Reliability whitepaper
This Guidance uses multiple serverless services that contribute to reliability. For example, Fargate supports reliability by offering serverless compute for containers, automatically scaling resources based on demand, and optimizing application performance. The Fargate serverless compute model helps ensure optimal resource utilization and automatic scalability to support overall reliability of containerized applications. As a serverless service, Lambda automatically manages compute resources and scales to meet the size of the workload. This reduces the risk of service disruptions due to scaling issues or resource limitations.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Neptune is a fully managed graph database service that automatically optimizes query execution and indexing, allowing you to retrieve complex interconnected data with low latency. Lambda's event-driven architecture supports performance efficiency by executing functions in response to specific events, allowing for rapid and efficient processing without the need for constant resource management.
-
Cost OptimizationRead the Cost Optimization whitepaper
The services in this Guidance are designed to help you save on costs by paying only for the resources you use. For example, Neptune allows you to pay only for the actual resources consumed during query execution, eliminating the need for constant provisioned capacity and minimizing costs during periods of low activity. Fargate provides serverless compute for containers, so that you pay only for the exact compute resources used during application execution, reducing costs associated with idle times and over-provisioning. Amazon ECR offers a secure and scalable repository for container images, streamlining deployment processes and minimizing storage costs.
-
SustainabilityRead the Sustainability whitepaper
Fargate automatically manages containerized workloads, optimizing compute resources and minimizing energy consumption during idle periods. The Neptune serverless option and the Fargate serverless compute model dynamically scale resources based on demand, reducing the overall energy consumption associated with constant provisioned capacity.
Additionally, Amazon S3 offers efficient storage options like frequent, infrequent, archival, and intelligent tiering for optimized storage, minimizing resource usage and energy consumption.
Implementation Resources
The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Related Content
[Title]
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.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.