langchain-azure-ai
An integration package to support Microsoft Foundry (formerly Azure AI) capabilities in LangChain/LangGraph ecosystem.
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; requires valid Azure credentials and endpoint URL to Microsoft Foundry services.
- Low install friction with a pure-wheel distribution.
- Active maintenance with a recent release 45 days ago.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions, making it suitable for most production deployments.
last release 2026-06-30 (45 days) · last repo commit 2026-08-14 · 142 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 916,043 downloads/mo, #4,732 on PyPI
Alternatives
Verify before relying
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)- 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
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 on it.
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
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.
Requires Python 3.10 or later; requires valid Azure credentials and endpoint URL to Microsoft Foundry services.
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)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
| License | MIT permissive |
| Python support | Supports the current Python release <4.0,>=3.10.0 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 12 packagesaiohttpazure-ai-contentunderstandingazure-ai-projectsazure-ai-contentsafetyazure-coreazure-identityazure-search-documentslangchainlangchain-openailanggraphnumpysix |
| Maintenance | Actively maintained 45 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 916,043 / month, #4,732 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: langchain_azure_ai-1.2.8-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 › “langchain azure ai integration”
- langchain-azure-aiIntegrates Microsoft Foundry (Azure AI) capabilities into LangChain…
- uipath-langchain-clientProvides LangChain-compatible chat models and embeddings that route…
- uipath-llm-clientA Python client for accessing LLMs through UiPath's infrastructure,…
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 langchain-azure-dynamic-sessions · agent-framework-azure-ai · azure-ai-projects · agent-framework-foundry · azure-ai-contentunderstanding · langchain-neo4j · langchain-tavily · databricks-ai-bridge · uipath-langchain