agent-framework-azure-ai-search
Azure AI Search integration for Microsoft Agent Framework.
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
permissive license (permissive) — Licensed under MIT (permissive), so you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 12,804 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 477,949 downloads/mo, #6,441 on PyPI
Alternatives
Verify before relying
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,
)- 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.
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 on this page. Verify before relying on it.
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
agent-framework-azure-ai-search on PyPI
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.
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.
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,
)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 | permissive license permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 2 packagesagent-framework-coreazure-search-documents |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 477,949 / month, #6,441 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Typing :: Typed |
Evidence: agent_framework_azure_ai_search-1.0.0b260813-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 › “retrieval augmented generation azure”
- agent-framework-azure-ai-searchProvides RAG (Retrieval Augmented Generation) context providers for…
- haystack-aiHaystack is an open-source framework for building production-ready…
- open-webuiOpen WebUI is a self-hosted AI platform providing a web interface for…
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 azure-search-documents · agent-framework-azure-ai · llama-index-vector-stores-azureaisearch · redisvl · llama-index-embeddings-azure-openai · h2ogpte · needle-python · langchain-milvus · agent-framework-redis · strands-agents-tools