Building a Serverless GenAI Platform
summary
A serverless GenAI platform is already built and running for customers and internal teams it deploys as a CDK project and runs on AWS with Azure GCP and Kubernetes ports planned deployable via CDK into customer environments and it connects to hosted or self‑hosted models via APIs connects to Bedrock OpenAI or custom models The platform exposes an orchestrator, RAG/vector stores, APIs and observability, spins up a grounded chatbot in about five minutes and returns BI queries in 30s–3min chatbots agents AI-for-BI agent crews
AI-written summary · about
chapters (8)
- 0:00intro
- 0:14introduction and speaker background
- 2:05softrams and generative ai
- 3:54the impact of generative ai
- 9:55building the gen ai platform
- 22:42platform architecture overview
- 26:06training and adoption strategies
- 30:22conclusion and key takeaways
related talks
44mBuilding a Domain Specific GenAI Chatbot with Serverless
45mServerless & Event-driven Patterns for GenAI
07mServerless: Accelerate your AI
29mOpen Source Sovereign AI: Building Enterprise GenAI Platforms for Control & Comp...
48mHow to Make Smart Architecture Decisions when Building Gen AI Apps
34mUnlock the full potential of Generative AI with Agent Platforms
07mBuilding and Deploying GenAI Apps at Block
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!