Navigating Innovation with Open Hybrid Cloud and Openshift AI
summary
Claims that 80% of enterprises will deploy Gen AI apps in the next few years and a survey showing 93% of unicorns use multiple public clouds and 81% combine public and private clouds drive the architecture here: a concrete OpenShift stack with OpenShift AI, Open Data Hub, notebook-to-MVP flow, model registry, and runtimes like TGI and vM that expose OpenAI‑compatible APIs. Example doc‑QA pipeline chunks documents, creates embeddings, stores them in vector DB Milas, performs RAG via LangChain orchestration, and streams answers — reducing time to production and enabling model versioning.
AI-written summary · about
chapters (11)
- 0:00Introduction and speaker intro
- 1:49Open source role in AI
- 4:40Hybrid cloud for AI workloads
- 6:55Operating systems for AI
- 8:00OpenShift AI platform structure
- 11:58Open Data Hub and AI integration
- 13:23Model development to MVP
- 17:40Reference architecture overview
- 21:54Vector databases in AI
- 24:44Model server workflow
- 28:59Q&A
related talks
16mDriving innovation through Azure Red Hat OpenShift and Azure OpenAI
11mOpen source GenAI vs. enterprise GenAI: Navigating the future of AI innovation
41mGetting real DevOps ROI with your Generative AI
47mEmbedding AI: Don’t Burn Your Fingers in the Heat of the AI revolution
14mHarnessing GenAI to Optimize Hybrid Cloud Workloads
43mKeynote: Building AI in the Open: How the Cloud Native Community Shapes What Comes Next
29mOpen Source Sovereign AI: Building Enterprise GenAI Platforms for Control & Comp...
27mFrom Chatbots to Agents: Orchestrating Agentic AI on Existing Enterprise Kubernetes Infrastructure.