llama-index-vector-stores-azureaisearch
llama-index vector_stores azureaisearch integration
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later (supports current Python versions).
- Azure AI Search credentials and endpoint configuration needed at runtime.
- Low friction: pure Python wheel with only two runtime dependencies (azure-search-documents and llama-index-core).
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions—suitable for most projects.
last release 2026-07-21 (24 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 98,871 downloads/mo, #13,054 on PyPI
Alternatives
Verify before relying
pip install llama-index-vector-stores-azureaisearch
from llama_index.vector_stores.azureaisearch import AzureAISearchVectorStore
vector_store = AzureAISearchVectorStore()- 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.).
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 on this page. Verify before relying on it.
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
llama-index-vector-stores-azureaisearch on PyPI
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.
Requires Python 3.10 or later (supports current Python versions). Azure AI Search credentials and endpoint configuration needed at runtime.
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()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 the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesazure-search-documentsllama-index-core |
| Maintenance | Actively maintained 24 days since the last release |
| First released | |
| Downloads | 98,871 / month, #13,054 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: llama_index_vector_stores_azureaisearch-0.5.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “azure ai search vector store”
- llama-index-vector-stores-azureaisearchIntegrates Azure AI Search as a vector store backend for LlamaIndex,…
- langchain-azure-aiIntegrates Microsoft Foundry (Azure AI) capabilities into LangChain…
- deeplakeDeep Lake is a serverless database for storing, searching, and…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also llama-index-embeddings-azure-openai · llama-index-vector-stores-lancedb · llama-index-vector-stores-qdrant · llama-index-vector-stores-redis · llama-index-vector-stores-faiss · llama-index-vector-stores-pinecone · llama-index-vector-stores-chroma · agent-framework-azure-ai-search · llama-index-vector-stores-milvus · llama-index-embeddings-openai