Learn how Solid State Drives (SSDs) can improve vector database scaling in Generative AI and Retrieval Augmented Generation (RAG) systems in this 12-minute technical presentation from the Open Compute Project. Explore how the growing size and dimensionality of vector databases present unique challenges for Large Language Model (LLM) inference, including precision, quality, performance, and cost considerations. Discover the multiple benefits of implementing SSD-based RAG solutions for billion-scale vector database deployments, as explained by Rory Bolt, Senior Fellow and Principal Architect at KIOXIA America.
Overview
Syllabus
How SSDs Enhance Vector Data Scaling in GenAI RAG Systems Presented by KIOXIA America, In
Taught by
Open Compute Project
Related Courses
-
Learn Embeddings and Vector Databases
-
Deploying and Maintaining RAG Systems
-
Retrieval Augmented Generation (RAG) with LangChain
-
Vector Databases: from Embeddings to Applications
-
Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search
-
Vector Databases for Embeddings with Pinecone
