Rolling out Enterprise AI: Tools, Insights, & Team Empowerment
summary
Live demos show a working retrieval‑augmented system built with RAG with ChromaDB and PGVector, ingestion that OCRs conference images and enriches metadata via OpenAI, and a local LLM stack—Llama 32 local on MacBook and Mistral small—running fast on a four‑year‑old MacBook. Deployment notes list Kubernetes, cloud endpoints, and metrics; production practices include AB testing models, feedback loops, citationed answers, and a GitHub repo with runnable CLI and demo code.
AI-written summary · about
chapters (12)
- 0:00Enterprise AI journey
- 1:24Choosing LLMs and strategies
- 4:56Model trustworthiness and performance
- 8:46Enterprise data with RAG
- 15:01Data cleaning and vector databases
- 18:11Live RAG system demo
- 22:58Local models and coding assistants
- 25:47Feedback loops for improvement
- 29:40AI application frameworks
- 32:47Enterprise AI deployment
- 36:19AI governance and risk
- 38:45Scaling AI and adoption
related talks
41mFrom RAGs to riches: Build an AI document interrogation app in 30 mins
01h 13mBuilding Production-Ready AI Systems in 90 Minutes
01h 36mTutorial: From Planni...
38mIntroducing Open Platform for Enterprise AI
45mFrom RAG to Enterprise AI Agents: Building Intelligent Java Apps
27mFrom RAGs to riches: Build an AI document interrogation app in 30 mins
33mOperationalizing GenAI Applications with DevOps Practices
26mWelcome to the AI Jungle! Now What?