Discover Generative AI Apps on Azure

This repository contains demos and templates for building intelligent Apps using OpenAI on Azure.

Regions that this deployment can be executed:

• uksouth
• swedencentral
• canadaeast
• australiaeast

Inventory

The following scenarios are implemented in this repository:

Name	Description	Technology
Prompt Engineering	Basic prompt engineering examples	Azure Prompt Flow
Embeddings	Learning about embedding models for text and images	Azure OpenAI, Azure Computer Vision
Vector Search	Learning about low level retrieval augmented generation	Azure OpenAI, Azure AI Search
Orchestrated Vector Search	Learning about retrieval augmented generation with Orchestration	Azure OpenAI, Azure AI Search, LangChain, Streamlit
Persisting Chat Memory	Learning about persisting chat messages	Azure OpenAI, Azure AI Search, LangChain, Azure CosmosDB
Tracing Language Models	Learning about tracing language model invocations	Azure OpenAI, LangChain, Azure PromptFlow
Tracing Chat application	Learning about tracing a running application	Azure OpenAI, LangChain, Azure PromptFlow, Streamlit, Azure AI Search
Function Calling	Learning about using tools from a model	Azure OpenAI, Azure PromptFlow
Orchestrating tools	Learning about orchestrating tools from an application	Azure OpenAI, Azure PromptFlow, LangChain
Agentic RAG	Learning about using agentic retrieval augmented generation	Azure OpenAI, Azure PromptFlow, LangChain, Langgraph

Quickstart & Infrastructure setup

The following lines of code will connect your Codespace az cli and azd cli to the right Azure subscription:

az login

azd auth login

Now deploy the infrastructure components with azure cli

azd up

Get the values for some env variables

azd env get-values | grep AZURE_ENV_NAME
source <(azd env get-values)

Last but not least: deploy a dummy container in Azure Container Apps.

bash ./azd-hooks/deploy.sh 03-rag $AZURE_ENV_NAME

Start locally

python -m streamlit run app.py --server.port=8000

Deploy resources for Chapter 03

Run the following script

azd env get-values | grep AZURE_ENV_NAME
source <(azd env get-values | grep AZURE_ENV_NAME)
bash ./azd-hooks/deploy.sh 03-rag $AZURE_ENV_NAME

All the other chapters work the same.