Milvus
Open-source vector database for similarity search and RAG at scale.
Official website / GitHub ↗ Visit
What is this technology for?
Its role in production environments and why it is taught in our curriculums.
Milvus is the open-source vector database for similarity search at scale — powering semantic search, recommendation and RAG applications with billions of vectors.
What you will learn
The hands-on skills you will gain on this technology in our curriculums.
- Deploy Milvus on Kubernetes
- Ingest and index embeddings at scale
- Run similarity search queries
- Integrate Milvus in RAG pipelines
Latest News & Ecosystem Updates
Recent innovations, major releases, and key industry milestones in the ecosystem.
Milvus 2.5: GPU-Accelerated Vector Indexing & Hybrid Sparse-Dense Search
Sub-5ms query latency across billions of high-dimensional vectors for enterprise-grade real-time RAG.
Certified Kubernetes Operator for High-Availability OpenShift Deployments
Disaggregated storage-compute distributed architecture guaranteeing zero single point of failure.
Featured in the curriculum
Find this technology in the following modules of our Red Hat certified curriculums.
AS300 — AI Platform Engineer
View curriculum →
Projet final (setup + sprints + dry-run)
Projet · Module 11 — AS300
