AI Pipelines With OPEA: Best Practices for Cloud Native ML Operati...
Talkat KubeCon + CloudNativeCon Europe 2025 · on Thursday, 2025-04-03· at 11:45· Level 1 | Hall Entrance S10 | Room B·
summary
Open Platform for Enterprise AI (OPEA) provides composable, Kubernetes-first pipelines with concrete artifacts: 20+ blueprints (Docker Compose and Helm) that wire embeddings, vector databases, LLMs and agents into RAG flows, Terraform/EKS examples for AWS/Azure, and an orchestration proxy (NGINX + a “mega” orchestrator). The demo shows URL retrieval into a vector store, 512-d embeddings, similarity search, and LLM augmentation working end-to-end; the project lists 55+ partners, supports pluggable stores/models, offers model/artifact management guidance (Artifactory patterns), and includes contributed guard rails like the prediction guard.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:11Scavenger hunt
- 2:36Live RAG demo
- 6:11How RAG works
- 9:41Microservices and containers
- 11:52Standards for AI pipelines
- 14:00Lego analogy for AI
- 15:26Introducing OPEA
- 18:16JFrog’s role in OPEA
- 20:23OPEA project structure
- 22:48Live OPEA demo
- 25:14Getting involved and next steps
related talks
43mAI Pipelines With OPEA: Best Practices for Cloud Native ML Operati...
38mIntroducing Open Platform for Enterprise AI
25mComposable RAG Pipelines With OPEA Highlighting GraphRAG
33mSimplifying Generative AI App Development Why Standards Matter- 33mSimplifying Generative AI App Development Why Standards Matter
25mCloud Native GenAI Using KServe and OPEA- 38mIntroducing Open Platform for Enterprise AI
38mLeveraging the OPEA Platform and GraphRAG Architectures To Drive Cl...