Home icon

How Arcanum AI Migrated Models from OpenAI to AWS Using Amazon Bedrock and Amazon SageMaker JumpStart

AWS Partner Network Blog

This article discusses how Arcanum AI, an AWS Partner, migrated their generative AI models from OpenAI to AWS using Amazon Bedrock and Amazon SageMaker JumpStart.

Specifically, the article covers:

  • Arcanum AI's two-iteration model evaluation process to assess open-source models before migrating from OpenAI
  • The architecture design for applications consuming LLMs in AWS, including Amazon Route 53, Amazon VPC, Application Load Balancer, Amazon ECS/EKS, Amazon SageMaker JumpStart, and Amazon Bedrock
  • Implementation details using AWS SDK for Python (Boto3) and open-source libraries like LangChain
  • Benefits of migrating to Amazon Bedrock and SageMaker JumpStart, such as enhanced security, access control, and network isolation
  • Conclusion highlighting Arcanum AI's improved performance and the advantages of AWS for generative AI adoption in enterprises and SMBs
Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

May 7
2024
Build generative AI applications with Amazon Bedrock Studio (preview)
May 14
2024
Build generative AI applications with Amazon Titan Text Premier, Amazon Bedrock, and AWS CDK
May 8
2024
How Dialog Axiata used Amazon SageMaker to scale ML models in production with AI Factory and reduced customer churn within 3 months
Aug 6
2025
OpenAI open weight models now in Amazon Bedrock and Amazon SageMaker JumpStart

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.