---
id: llama-index-vector-stores-azureaisearch
version: "0.5.1"
license: MIT
license_treatment: permissive
maintenance: active
---

# llama-index-vector-stores-azureaisearch — llama-index vector_stores azureaisearch integration

License: permissive · Maintenance: active · Downloads: 98.9K/mo

## What it is and what it does

This package provides a LlamaIndex vector store adapter for Azure AI Search, a managed search service on Azure. It bridges LlamaIndex's retrieval framework with Azure's vector and semantic search capabilities, allowing developers to build RAG (retrieval-augmented generation) applications that store and query embeddings in Azure rather than in a separate vector database.

The integration depends on azure-search-documents for Azure API communication and llama-index-core for the vector store abstraction layer. It's designed for teams already using Azure infrastructure who want to leverage Azure AI Search's native capabilities—including hybrid search, filtering, and managed scaling—without maintaining a separate vector database. The package is actively maintained and carries no known security vulnerabilities.

Use it for:

- Build RAG pipelines that store document embeddings in Azure AI Search and retrieve them for LLM context.
- Migrate existing LlamaIndex applications to Azure by swapping the vector store backend to Azure AI Search.
- Implement semantic search over enterprise documents stored in Azure without provisioning additional infrastructure.
- Combine Azure AI Search's hybrid search (keyword + vector) with LlamaIndex's retrieval and synthesis workflows.
- Deploy production RAG systems on Azure with managed scaling and built-in security features.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates Azure AI Search as a vector store backend for LlamaIndex, enabling semantic search and retrieval-augmented generation workflows using Azure's managed search service.

Yes, if you are already using LlamaIndex and Azure. The low install friction, active maintenance, MIT license, and zero known vulnerabilities make it a safe choice for Azure-based RAG projects. Skip it if you are not committed to Azure or if you need vector store features not yet supported by this integration—verify capability coverage first.

## Install

pip install llama-index-vector-stores-azureaisearch
uv add llama-index-vector-stores-azureaisearch
poetry add llama-index-vector-stores-azureaisearch

## Installing llama-index-vector-stores-azureaisearch

Before you install: Low friction: pure Python wheel with only two runtime dependencies (azure-search-documents and llama-index-core). Actively maintained as of 24 days ago.

License in practice: MIT license permits commercial and private use with minimal restrictions—suitable for most projects.

Quickstart:

pip install llama-index-vector-stores-azureaisearch

from llama_index.vector_stores.azureaisearch import AzureAISearchVectorStore

vector_store = AzureAISearchVectorStore()

Requires Python 3.10 or later (supports current Python versions). Azure AI Search credentials and endpoint configuration needed at runtime.

Verify before relying:

- Specific Azure AI Search API versions or feature compatibility constraints not documented in fact sheet.
- Performance characteristics (latency, throughput) for typical retrieval workloads.
- Whether the integration supports all Azure AI Search vector capabilities (hybrid search, filters, etc.).

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 98.9K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

azure ai search vector store, llama index azure integration, semantic search azure, rag with azure search, vector database azure, llama index vector store backend, azure cognitive search integration, rag, vector-search, azure

[View on SkillFed](https://skillfed.io/packages/llama-index-vector-stores-azureaisearch) · [View on PyPI](https://pypi.org/project/llama-index-vector-stores-azureaisearch/)