This repository contains many notebooks that explain how Azure AI Search works, including several showcasing how vector search works.
Environment setupRun azd up on azure-search-openai-demo with GPT-4-vision enabled. This will create the necessary resources for the Azure OpenAI, Azure AI Search services, and the Computer Vision service.
Create a .env with these variables, and the values taken from .azure/ENV-NAME/.env
AZURE_OPENAI_SERVICE=YOUR-SERVICE-NAMEAZURE_OPENAI_DEPLOYMENT_NAME=YOUR-OPENAI-DEPLOYMENT-NAMEAZURE_OPENAI_ADA_DEPLOYMENT=YOUR-EMBED-DEPLOYMENT-NAMEAZURE_SEARCH_SERVICE=YOUR-SEARCH-SERVICE-NAMEAZURE_COMPUTERVISION_SERVICE=YOUR-COMPUTERVISION-SERVICE-NAMELogin to the Azure Developer CLI:
azd auth loginIf you deployed your resource group to a tenant other than your home tenant, set the tenant ID:
export TENANT_ID=YOUR-TENANT-IDNotebooksThese are the available notebooks, in suggested order:
Vector Embeddings NotebookAzure AI Search NotebookImage Search NotebookAzure AI Search Relevance NotebookRAG with Azure AI SearchRAG EvaluationYou can find video recordings going through the notebooks here.