-
MCP vs. Agent Skills - What are the differences, and why do they matter for NetApp?
In the AI world new concepts and approaches come and go almost daily. In 2023, Retrieval-Augmented Generation (RAG) received all the attention because it was the first efficient way to add your own data to Large Language Models (LLMs) without having to train or fine-tune the model itself. It quickly became visible that,…
-
User access mapping with Amazon S3 Access Points for Amazon FSx for NetApp ONTAP
Amazon Web Service (AWS) and NetApp recently announced integration of Amazon FSx for NetApp ONTAP (FSx for ONTAP) with a wide variety of AI and machine learning (AI/ML) and analytics services using Amazon S3 Access Points. You can now attach S3 access points to your FSx for ONTAP file systems, enabling access to file data…
-
KV cache offloading - exploring the benefits of shared storage
Today, we continue our exploration of KV cache offloading. If you missed my previous posts on this topic, be sure to check them out here, here, and here. In this post, I will further explore the benefits of offloading your KV cache to shared storage. I will show the benefits of a shared storage tier and explain why, with…
-
Hybrid RAG in the Real World: Graphs, BM25, and the End of Black-Box Retrieval
In the earlier posts in this series, we talked about what happens when Retrieval-Augmented Generation leans too hard on vector search. The first post, From "Trust Me" to "Prove It": Why Enterprises Need GraphRAG, walked through why enterprises need retrieval that behaves more like a knowledge graph than a fuzzy lookup…
-
Designed for devs: Introducing the Visual Studio Code extension for Amazon FSx for NetApp ONTAP
AI-assisted coding with GitHub Copilot has transformed how millions of developers write code. Yet, when provisioning the infrastructure their applications depend on, developers still face time-consuming manual workflows that break focus and slow delivery. That’s because, while infrastructure-as-code (IaC) automates many…
-
DocumentRAG Using OpenSearch: GraphRAG-like Structure Without the Graph Overhead
Vector embeddings changed how teams build RAG systems. They made it easy to scan large datasets and pull back passages that feel semantically close to a question. And for a while, that was enough. You could drop your documents into an embedding model, compute vectors, plug everything into your favorite vector database, and…
-
KV cache offloading - CPU RAM vs. storage
Today, we continue our exploration of KV cache offloading. If you missed my previous posts on this topic, be sure to check them out here and here. In this post, I will explore the nuances of offloading your KV cache to CPU RAM vs. storage. Using empirical results, I will demonstrate when you might want to go with one over…
-
KV CacheBlend - What is it, and why it matters
In this Blog article I want to continue Mike’s work on KV Cache Offloading by adding the concept and principle of CacheBlend. Also take his vLLM stack article into consideration before approaching this article. Before going into the details about CacheBlend, let’s summarize the essential points of the previous articles.…
-
Launching Agentic AI with Google Cloud NetApp Volumes and Google Gemini Enterprise
We are thrilled to announce the preview of the integration between Google Gemini Enterprise and Google Cloud NetApp Volumes. Starting today, as a customer of NetApp Volumes, you have a direct and secure data channel to Gemini Enterprise that enables you to seamlessly subject your data to cutting-edge agentic AI use cases.…
-
Doing More with Less: The Quiet Revolution Powering AI Through IoT and Edge
Edge AI is transforming the way we approach deploying machine learning. Instead of confining intelligence to cloud servers or data centers, models are now being pushed to the farthest corners of our networks… to IoT sensors, industrial gateways, and even microcontrollers. We are talking about drones like the Skydio…