This Guidance demonstrates how to use NetApp BlueXP Workload Factory for AWS, a software as a service (SaaS) framework that connects Amazon FSx for NetApp ONTAP data volumes with Amazon Bedrock. It provides step-by-step instructions for implementing Retrieval-Augmented Generation (RAG) workflows, allowing AWS customers to create chatbots that deliver customized responses based on their knowledge base. Users can also embed data into a vector database that integrates with Amazon Bedrock to reveal valuable insights from unstructured enterprise data. This Guidance offers a secure, efficient path to optimizing the capabilities of generative artificial intelligence (AI) for various applications, including RAG chatbots and SQL deployment assistants.

Please note: [Disclaimer]

Architecture Diagram

[Architecture diagram description]

Download the architecture diagram PDF 

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.

  • FSx for ONTAP offers resilient, high-performance storage with enterprise features like data replication from on-premises arrays, supporting data integrity and availability. Amazon Bedrock accelerates generative AI application development by providing access to pre-trained models, while Amazon EC2 delivers secure cloud compute capacity. This integration allows for data replication from on-premises to AWS using NetAPP SnapMirror, a software that can quickly replicate snapshot data to one or more storage systems.

    Read the Operational Excellence whitepaper 
  • FSx for ONTAP, Amazon Bedrock, and AWS Identity and Access Management (IAM) provide comprehensive security and enhanced user management capabilities. FSx for ONTAP is a managed-file storage service, providing encryption at rest and in transit, along with compliance certifications like HIPAA and FedRAMP. Amazon Bedrock integrates with various AWS security services to secure the use of foundation models within applications; it also supports data encryption in transit and gives users full control over their data. IAM enforces fine-grained access controls, allowing administrators to implement the principle of least privilege.

    Finally, as an independent software vendor (ISV) application running within the user's account, this Guidance prevents data leakage from the user's environment. The combination of these services, along with the identity-based policies of IAM, provides comprehensive security measures and enhanced user management capabilities.

    Read the Security whitepaper 
  • FSx for ONTAP supports high availability through multiple Availability Zone (AZ) deployment options and offers robust data protection features, including NetApp ONTAP snapshots and integration with AWS Backup, supporting data durability and availability. Amazon Bedrock, as a managed AWS service, reduces downtime risk and maintains consistent performance by using the expertise of AWS in managing complex AI infrastructure. This Guidance, installed on Amazon EC2, allows for easy system restarts or rebuilds during instance maintenance.

    Read the Reliability whitepaper 
  • FSx for ONTAP delivers high performance with solid state drive (SSD) support for active data and uses SnapMirror and FlexCache to improve data mobility between on-premises and AWS environments. Amazon Bedrock gives users access to foundation models without having to manage complex infrastructure. This Guidance, installed on Amazon EC2, integrates with AWS Nitro System, a lightweight hypervisor supporting high performance for workloads. This combination of services provides performance efficiency from experimentation to full-scale production deployment.

    Read the Performance Efficiency whitepaper 
  • FSx for ONTAP offers data efficiency features like deduplication, compression, and compaction, while tiering colder data into a capacity pool reduces storage costs. Amazon Bedrock helps users avoid the expensive process of building and training custom models, significantly reducing development costs. This Guidance also fully utilizes hardware resources for computing, networking, and I/O acceleration, passing savings to users. The efficiency features of FSx for ONTAP directly lower storage costs, often a significant portion of generative AI application expenses. Amazon Bedrock, as a managed service, simplifies AI model development and deployment processes, further reducing associated costs. Lastly, the flexible pricing options of Amazon EC2, including Savings Plans, On-Demand, and Reserved Instances, provide additional avenues for cost optimization.

    Read the Cost Optimization whitepaper 
  • The services selected for this Guidance were chosen as optimal services for their respective workloads, balancing efficiency and sustainability. By using native AWS managed services, users can benefit from the ongoing commitment to sustainability of AWS, which includes investments in renewable energy and efficient data center designs. This approach allows organizations to reduce their carbon footprint compared to running similar workloads on-premises or with less optimized cloud solutions. The use of these managed services also means that resources are more efficiently shared and utilized across multiple customers, potentially leading to overall energy savings and a more sustainable IT infrastructure.

    Read the Sustainability whitepaper 
[Content Type]


This [blog post/e-book/Guidance/sample code] demonstrates how [insert short description].


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.

Was this page helpful?