Whether organizations choose to build GenAI RAG services using DIY tools or partner with cloud providers like Azure, the integration of complex technologies can be simplified with a well-compiled GenAI toolkit. That’s why we’re announcing NetApp’s GenAI Toolkit with support for Azure NetApp Files, enabling organizations to extract greater value from their data and derive meaningful insights.
The NetApp GenAI Toolkit for Azure empowers you to take advantage of your private data stored in Azure NetApp Files by using OpenAI foundation models. The GenAI Toolkit comes with a chatbot app hosted on a NetApp artifact registry and a Terraform module (in a GitHub repository) that automates deployment of the chatbot app in your environment. In combination with the general availability of Azure NetApp Files large volumes with support for cross-zone and cross-region replication, this capability is particularly beneficial for AI/ML, and large file content repositories, ensuring data resilience and business continuity across various scenarios.
In the domain of generative AI (GenAI), the purpose extends beyond merely accumulating more datasets. It involves strategically utilizing a mix of publicly accessible data, OpenAI large language models (LLM), your proprietary datasets, and the distinctive insights that are exclusive to your organization. The combination of public data with your private data in a secure environment enables you to tailor both the learning process and outcomes to be more pertinent—and ultimately, a continually evolving foundation of intelligence.
Your AI Opportunity for Enhanced LLM Accuracy
With the NetApp GenAI toolkit and Azure NetApp Files, you gain AI-ready storage solutions that support retrieval-augmented generation (RAG) operations. By combining public data with your proprietary data in a secure environment, you not only enhance the relevance, but also improve the accuracy of your LLM workloads. Furthermore, NetApp enables the swift development of intelligent, containerized applications for the modern landscape.
The solution: NetApp GenAI Toolkit for Azure
The significance of RAG in the GenAI toolkit lies in its ability to enhance the inference capabilities of the LLMs specifically for private data. RAG allows the LLMs to draw upon the data stored in ANF, enabling customers to leverage their own proprietary data for generating accurate and relevant outputs.
As depicted in the following figure:
- You provision an Azure NetApp Files volume.
- You configure API access and transfer documents of interest to a NetApp volume.
- You download the GenAI Toolkit Terraform module from GitHub and apply it.
- The Terraform module creates a Linux VM, launches the RAG framework, and connects to the Azure NetApp Files provided in the configuration.
- You interact with the chatbot endpoint to get answers grounded in your proprietary data.
The toolkit, along with the accompanying reference architecture, allows you to implement RAG operations more quickly while enabling secure, consistent, and automated workflows that connect data stored in Azure NetApp Files with OpenAI models. The result is an enhanced ability to generate unique, high-quality, and relevant competitive insights.
Industry-leading capabilities
The NetApp GenAI Toolkit helps optimize RAG processes with industry-leading capabilities, such as:
- Common data footprint everywhere. You can easily include data from any environment to power your RAG efforts. NetApp ONTAP® data management software, the data management software powering Azure NetApp Files, lets you use common operational processes while reducing risk, cost, and time to results.
- Automated classification. The NetApp BlueXP™ classification service streamlines data categorization, classification, and cleansing for both the ingest and inferencing phases of the data pipeline. With this approach, the right data is used for queries, and sensitive data is protected according to your organization’s policy.
- Fast, scalable snapshot copies. Azure NetApp Files snapshot technology creates near-instant space-efficient, in-place copies of vector stores and databases for interval-based A/B testing and recovery. You can perform point-in-time analysis or, if data is inconsistent, immediately roll back to a previous version.
- Real-time cloning at scale. Azure NetApp Files clone technology can create instant clones of vector index stores for parallel processing of A/B prompt testing and result validation. With cloning, you can safely make uniquely relevant data instantly available for queries from different users, without affecting the core production.
The integration of the GenAI Toolkit with Azure NetApp Files and OpenAI models represents a powerful synergy that empowers you to harness advanced language generation capabilities while maintaining data privacy and security. The NetApp GenAI Toolkit for Azure is available for preview. To learn more, go to the Azure NetApp Files product page.
