---
id: agent-framework-azure-ai-search
version: "1.0.0b260813"
license: unclear
license_treatment: permissive
maintenance: active
---

# agent-framework-azure-ai-search — Azure AI Search integration for Microsoft Agent Framework.

License: permissive · Maintenance: active · Downloads: 477.9K/mo

## What it is and what it does

This package integrates Azure AI Search into the Microsoft Agent Framework, enabling retrieval-augmented generation (RAG) for agent applications. It offers two retrieval modes: Semantic Mode performs fast hybrid search combining vector and keyword matching with semantic ranking, while Agentic Mode supports multi-hop reasoning over Knowledge Bases for complex queries that require iterative refinement. The package automatically detects which version of azure-search-documents is installed and adapts its behavior accordingly—stable builds use extractive output with minimal reasoning, while preview builds unlock advanced features like answer synthesis and extended reasoning effort levels.

The integration handles query-time user identity by forwarding caller-specific Azure AI Search authorization tokens, enabling document-level access control when the index uses permission fields. It supports both API key and managed identity authentication, and configuration is typically done via environment variables. The package is in active development (beta status) and requires Python 3.10 or later.

Use it for:

- Build RAG agents that retrieve context from Azure AI Search indexes using hybrid vector + keyword search with semantic ranking.
- Implement multi-hop reasoning agents that iteratively refine queries against Knowledge Bases to answer complex questions.
- Enforce document-level access control in agent queries by passing user-specific credentials to retrieve only authorized results.
- Migrate between stable and preview Azure AI Search API versions without code changes—just update the install command.
- Integrate Azure AI Search retrieval into larger agent-framework applications for context-aware decision-making.

## Worth the install?

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

Provides RAG (Retrieval Augmented Generation) context providers for Azure AI Search, supporting both semantic hybrid search and agentic multi-hop reasoning modes within the Microsoft Agent Framework.

Yes. The package is actively maintained, has no known vulnerabilities, and offers low install friction. It's permissively licensed (MIT) and supports current Python versions. The integration is well-suited if you're building agents that need RAG capabilities with Azure AI Search, especially if you require either semantic hybrid search or multi-hop reasoning. The auto-detection of API versions is a practical design choice that reduces maintenance burden.

## Install

pip install agent-framework-azure-ai-search
uv add agent-framework-azure-ai-search
poetry add agent-framework-azure-ai-search

## Installing agent-framework-azure-ai-search

Before you install: Low install friction with a pure-Python wheel. The package is actively maintained with a recent release and no known vulnerabilities. It requires agent-framework-core and azure-search-documents as runtime dependencies; the latter auto-detects its own API version, so no pinning is needed in code.

License in practice: Licensed under MIT (permissive), so you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.

Quickstart:

pip install agent-framework-azure-ai-search --pre

from agent_framework_azure_ai_search import AzureAISearchContextProvider

context_provider = AzureAISearchContextProvider(
    endpoint=search_endpoint,
    credential=application_credential,
    mode="agentic",
    knowledge_base_name=knowledge_base_name,
)

Requires Python 3.10 or later. Preview features (agentic output modes and extended reasoning) require azure-search-documents>=12.1.0b1 installed with --pre flag.

Verify before relying:

- Whether the package's Knowledge Base multi-hop reasoning scales to typical enterprise query complexity and latency requirements.
- Performance characteristics and cost implications of semantic ranking vs. agentic modes for typical workloads.
- Compatibility and integration patterns with other agent-framework components beyond what the excerpt covers.

## Package facts

- License: not declared (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 477.9K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

azure ai search rag integration, retrieval augmented generation azure, semantic hybrid search azure, agent framework context provider, knowledge base multi-hop reasoning, azure search vector keyword hybrid, agentic retrieval azure, rag-retrieval, azure-integration, agent-framework

[View on SkillFed](https://skillfed.io/packages/agent-framework-azure-ai-search) · [View on PyPI](https://pypi.org/project/agent-framework-azure-ai-search/)