Azure
AI & ML
intermediate
RAG Chatbot — Azure Architecture Template
Retrieval-augmented chat: an orchestrator function grounds Azure OpenAI answers in indexed documents and stores chat history.
Why this architecture works
- Grounding responses in retrieved documents constrains hallucination and keeps answers current without retraining
- The orchestrator function is the only caller of OpenAI, centralizing prompt templates, quotas and content filters
- Document indexing runs from the storage source so the knowledge base updates without app deployments
- Chat history in Cosmos DB enables session context and offline evaluation of answer quality
- OpenAI keys stay in Key Vault and every call is traced in Application Insights with token counts
What's inside (8 resources)
Chat UI
web-app
Orchestrator API
function-app
Retrieval Index
cognitive-services
Azure OpenAI
openai
Docs Store
storage-account
Chat History
cosmos-db
Secrets
key-vault
APM
application-insights
From template to running infrastructure
- Open this template in the CloudForge visual designer (free account, no credit card).
- Customize resources, names, and connections on the drag-and-drop canvas — or ask Vani, the AI architect, to adapt it.
- Generate production-ready Terraform, ARM, or Bicep in one click.
- Review the plan diff and security scan, then deploy with human approval.