Welcome to the AI jungle! Now what?
summary
Demonstrates a runnable, open source pipeline: find a model on Hugging Face (now over 1,000,000+ models on Hugging Face), fine‑tune with InstructLab using synthetic data generation (claims training can run on a laptop but may take hours), deploy on Kubernetes via OpenDataHub/KServe, expose an inference endpoint and use Backstage templates for app onboarding; shows local dev with Podman AI Lab serving a model at local model on port 35000, yields images (a fine‑tuned mascot Red Hat Teddy generated) and Java code via LangChain4j+Quarkus, includes retry/fallback and notes frequent hallucinations and many models being 80% likely derivatives.
AI-written summary · about
chapters (7)
- 0:00Introduction to AI landscape
- 4:00Generative AI adoption path
- 8:47Fine-tuning with InstructLab
- 16:28Building an AI platform
- 27:24Developer experience integration
- 32:21Local AI development tools
- 42:26Conclusion and next steps
related talks
26mWelcome to the AI Jungle! Now What?
37mAI Lab Recipes: Cooking up AI Applications on your Laptop
18mOpen Hybrid Cloud & AI Developer Experience
33mOperationalizing GenAI Applications with DevOps Practices
47mEmbedding AI: Don’t Burn Your Fingers in the Heat of the AI revolution
30mMind the Gap - A Developer's Roadmap To Building AI Agents
40mRolling out Enterprise AI: Tools, Insights, & Team Empowerment
33mMachine Learning 2.0 with Hugging Face