Build and scale AI apps with Azure OpenAI, AI Search, and HCP Terraform
summary
Demonstrates a working RAG pipeline that ingests thousands of PDFs (JFK archive), extracts text and images with Azure Document Intelligence and Azure Vision, indexes chunks in Azure Search, and serves a React front end + REST API that calls Azure OpenAI for contextual responses. Infrastructure uses HCP Terraform and Terraform stacks to split network/shared/AI/apps stacks, stamp dev/test/prod deployments, use secretless federated identity, manage model capacity (increased live) and prompt config reliably for scalable, auditable AI apps.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:12AI architecture patterns
- 3:57Operational challenges
- 5:23RAG solution overview
- 7:50Implementing the RAG stack
- 12:49Managing AI workload complexity
- 15:03Terraform stacks configuration
- 18:50Deploying and managing stacks
- 20:16Live demo: model management
- 23:28Demonstrating stack application
- 25:50Conclusion and takeaways
related talks
01h 03mAI Templates
01h 29mRunning AI Application in Minutes w/ AI Templates
44mSupercharge your data with Azure AI Search and OpenAI
56mBuilding web apps with Cloud and AI
50mAzure AI, Power new possibilities for every organization
25mBuilding AI-Powered Applications with Azure Serverless Functions and C# .NET
37mHarnessing OpenAI to help millions
40mBuilding secure and efficient AI solutions in Azure with Partners