ExaWizards Co., Ltd.
ExaWizards’ “RAGOps” now supports AWS’s generative AI service “Amazon Bedrock” ~Supporting secure business data linkage on the AI application development environment “exaBase Studio” and aiming to expand business opportunities with the cooperation of AWS~
……
ExaWizards Co., Ltd. (Minato-ku, Tokyo, President and CEO: Makoto Haruta, hereinafter referred to as ExaWizards) announced that “RAGOps,” an application template for ExaWizards’ AI application development environment “exaBase Studio,” has been developed by Amazon Web Services (AWS). ) is now compatible with Amazon Bedrock, a generation AI application construction service. It is expected that this will allow customers to select the optimal model on Amazon Bedrock and quickly develop and use generative AI applications that securely link business data. “RAGOps” will be available in May 2024.
[Image 1: https://prtimes.jp/i/30192/254/resize/d30192-254-48e3dd2da1543378cce9-0.jpg&s3=30192-254-49b7022b2f4dc75af5b500ed4aba727f-2400×1260.jpg] As the use of generative AI gains momentum, RAG*, which allows customers to process and analyze their own data using generative AI, is attracting increasing attention. On the other hand, issues such as “not getting the expected results” and “worried about the spread of incorrect answers due to hallucination” have also emerged. In response to this, ExaWizards has designed a RAGOps application template* that can continuously improve the quality of RAG responses on exaBase Studio. exaBase Studio maintains and provides application templates that integrate past delivery knowledge, and RAGOps is one of them. By utilizing these, it is possible to add and rearrange data management, AI, software processing, etc., and develop AI applications while running prototypes.
*Also called lag, an abbreviation for Retrieval Augmented Generation. *Application template: A system that can be deployed as a template on exaBase Studio and used as an application as is, or customized using other software and data.
☑︎️Realized service This time, with the support of AWS, ExaWizards designed a service that directly calls Amazon Bedrock through exaBase Studio, which runs on the AWS environment. This will enable AWS users to more securely send and receive business data handled on exaBase Studio to the generated AI. Amazon Bedrock provides services that allow you to use generative AI-based models provided by AI21 Labs, Anthropic, Cohere, Meta, Stability AI, Amazon, etc. via API. The feature is that it supports not only text but also multimodal data types such as images. Compatibility with Amazon Bedrock allows for flexible selection of highly effective underlying models, potentially improving the accuracy of RAGOps.
[Image 2: https://prtimes.jp/i/30192/254/resize/d30192-254-54b27b62f2f1d0f7dfdb-1.png&s3=30192-254-556a9279b6148a4b711171cbc6b5c74e-1570×790.png ]
Figure: System configuration of the service provided this time ☑︎Secure and compliance-friendly RAGOps can be used securely by making data communication between the platform exaBase Studio and Amazon Bedrock closed. Amazon Bedrock has the ability to securely and privately protect data and the AI applications it generates, with data encrypted both in transit and at rest. AWS PrivateLink allows you to establish a private connection without exposing your traffic to the internet. Amazon Bedrock is subject to general compliance standards such as ISO, SOC, and CSA STAR Level 2, as well as the U.S. healthcare IT security and privacy standard HIPAA, and is compliant with the EU General Data Protection Regulation (GDPR). Masu.
☑︎Provision conditions RAGOps has been available as an application template for exaBase Studio since May 2024. The ability to connect to a variety of generative AI-based models from Amazon Bedrock is also available and available through the template feature to exaBase Studio licensed customers and through ExaWizards Professional Services. Please contact us for details such as usage fees. With the cooperation of AWS, ExaWizards aims to provide new value to customers and expand business opportunities.
☑︎Features of exaBase Studio exaBase Studio is a development environment that allows you to build AI software by combining internal and external AI models, services, and data. We use an intuitive design and development UI (user interface) called Canvas to visualize processes, allowing for open design and updating that involves not only engineers but also managers and internal and external personnel who are familiar with the business. It will be easy. It is equipped with a mechanism to semi-automate the complicated steps of
development, which will greatly change the development process. We support in-house development using an agile style of “improving moving things by touching them.”
Please see the following website for exaBase Studio and RAGOps. exaBase Studio: https://exawizards.com/exabase/studio/RAGOps: https://exawizards.com/exabase/studio/ragops/
[ExaWizards Company Profile] Company name: ExaWizards Co., Ltd. (stock code 4259) Location: 5th floor, East Building, Sumitomo Fudosan Mita Twin Building, 4-2-8 Shibaura, Minato-ku, Tokyo Established: February 2016 Representative: President and CEO Makoto Haruta Business details: Industrial innovation and solving social issues through service development utilizing AI URL: https://exawizards.com/
More details about this release:
https://prtimes.jp/main/html/rd/p/000000254.000030192.html