langchain-azure-ai

What it is and what it does

langchain-azure-ai bridges LangChain and LangGraph applications to Microsoft Foundry services, enabling developers to use Azure-hosted models, agents, and AI tools within the LangChain ecosystem. It provides chat model bindings for OpenAI-compatible endpoints, integration with Azure AI Agent Service for running agents in Foundry infrastructure, vector store support via azure-search-documents, and access to specialized tools like Document Intelligence and Content Understanding.

The package supports multiple deployment patterns: local development with API keys, production use with azure-identity credentials, and hosting of compiled LangGraph graphs on Foundry infrastructure using Responses or Invocations protocols. It also includes auto-tracing to Azure Application Insights via OpenTelemetry, allowing observability of LangChain and LangGraph execution. Optional extras provide access to specialized capabilities without bloating the base installation.

Use it for:

• Build LangChain applications that invoke Azure OpenAI or other Foundry models for chat completions and tool use.
• Compose multi-agent workflows using LangGraph with agents running in Azure AI Agent Service.
• Index and search documents using azure-search-documents as a vector store within LangChain retrieval chains.
• Extract structured data from documents using azure-ai-projects tools as LangChain tools.
• Host compiled LangGraph graphs on Microsoft Foundry with conversation state management and transcript history.
• Monitor and trace LangChain/LangGraph execution in production via Azure Application Insights integration.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Integrates Microsoft Foundry (Azure AI) capabilities into LangChain and LangGraph, providing access to chat models, agents, tools, vector stores, and tracing through a unified Python interface.

Yes. The package is actively maintained, has low install friction, carries no known vulnerabilities, and uses a permissive MIT license. It is the official integration layer for LangChain users targeting Microsoft Foundry services. Install it if you are building LangChain or LangGraph applications on Azure infrastructure or need access to Azure AI services as tools.

Install

langchain-azure-ai on PyPI

pip install langchain-azure-ai

uv add langchain-azure-ai

poetry add langchain-azure-ai

Installing langchain-azure-ai

Before you install

Low install friction with a pure-wheel distribution. Active maintenance with a recent release 45 days ago. Depends on 12 runtime packages including langchain, azure-ai-projects, and azure-identity, all standard ecosystem components.

License in practice

MIT license permits commercial and private use with minimal restrictions, making it suitable for most production deployments.

Quickstart

pip install langchain-azure-ai

from langchain_azure_ai.chat_models import AzureAIOpenAIApiChatModel

model = AzureAIOpenAIApiChatModel(
    endpoint="https://{your-resource-name}.services.ai.azure.com/openai/v1",
    credential="your-api-key",
    model="gpt-5"
)

model.invoke(messages)

Requires Python 3.10 or later; requires valid Azure credentials and endpoint URL to Microsoft Foundry services.

Verify before relying

• Whether all 12 runtime dependencies are always required or if some are optional based on feature selection
• Performance characteristics and latency expectations when calling remote Azure services
• Specific Azure service quotas or rate limits that may affect usage at scale

Package facts

Evidence: langchain_azure_ai-1.2.8-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading