Python samples for Azure AI Search

This repository contains Python code samples used in Azure AI Search documentation. Unless noted otherwise, all samples run on the shared (free) pricing tier of a search service.

If your configuration uses a search service managed identity for indexer connections, your search service must be on the Basic tier or higher.

Day-one quickstarts and tutorials

Sample	Description
Quickstart	Introduces the fundamental tasks of working with a classic search index: create, load, and query. The index is modeled on a subset of the hotels dataset, which is widely used in Azure AI Search samples but reduced in this sample for readability and comprehension.
Quickstart-Agentic-Retrieval	Create a knowledge base in Azure AI Search to integrate LLM reasoning into query planning.
Quickstart-Document-Permissions-Pull-API	Using an indexer "pull API" approach, flow access control lists from a data source to search results and apply permission filters that restrict access to authorized content. Indexer support is limited to Azure Data Lake Storage (ADLS) Gen2 permission metadata.
Quickstart-Document-Permissions-Push-API	Using the push APIs for indexing a JSON payload, flow embedded permission metadata to indexed documents and search results that are filtered based on user access to authorized content.
Quickstart-Semantic-Search	Extends the quickstart through modifications that invoke semantic ranking. This notebook adds a semantic configuration to the index and semantic query options that formulate the query and response.
Quickstart-Vector-Search	Introduces vector search in Azure AI Search. This notebook demonstrates how to create, load, and query a vector index.

Deeper dive tutorials

Sample	Description
agentic-retrieval-pipeline-example	Extends the quickstart by integrating Foundry Agent Service. Add an AI agent and MCP tool to your Azure AI Search agentic retrieval pipeline for an end-to-end conversational search experience.
azure-function-search	An Azure Function that sends query requests to an Azure AI Search service. You can substitute this code to replace the contents of the api folder in the C# sample azure-search-static-web-app.
bulk-insert	Create and load an index using the push APIs and sample data. You can substitute this code to replace the contents of the bulk-insert folder in the C# sample azure-search-static-web-app
cmk-encryption	Encrypt content using customer-managed keys.

Archived samples

• azureml-custom-skill: See the Archive branch of this repository.
• image-processing: See azure-search-sample-archive/tree/main/image-processing.