Take an Azure OpenAI chat application from PoC to enterprise-ready
summary
Starts from a Prompt Flow POC that queries Wikipedia and shows how to productionize it using Azure OpenAI, Azure AI Search, App Service behind Application Gateway + WAF, private endpoints and a managed virtual network; adds a gateway for throttling and failover that routes between a PTU and pay‑as‑you‑go endpoint to avoid 429s; introduces a pipeline for chunking, enrichment and embeddings and the open‑source RAG Experiment Accelerator that runs ML workspace jobs, logs hyperparameters and finds best configs (different chunk sizes and embedding models) before promoting an index.
AI-written summary · about
chapters (10)
- 0:00Introduction to azure ai
- 1:09Understanding the poc
- 4:25Infrastructure design
- 8:26Well-architected framework
- 12:31Reference implementation
- 15:34Implementing a gateway
- 21:54Developing rag solutions
- 26:31Rag experiment accelerator
- 35:53Productionizing applications
- 37:43Recap and q&a
related talks
37mHarnessing OpenAI to help millions
48mGetting started with generative AI using Azure OpenAI Service
01h 03mGoing production scale with Gen AI - Patterns for your API
19mIntegrating Azure Kubernetes Service and Azure OpenAI To Build Intelligent Apps
24mInfuse Generative AI in your apps using
01h 58mBuild, Evaluate and Deploy a RAG-Based Retail Copilot with Azure AI
01h 29mRunning AI Application in Minutes w/ AI Templates
28mBuild and scale AI apps with Azure OpenAI, AI Search, and HCP Terraform