Metadata-Version: 2.1
Name: langchain-azure-ai
Version: 0.1.0
Summary: An integration package to support Azure AI Foundry capabilities for model inference in LangChain.
License: MIT
Requires-Python: >=3.9,<4.0
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Provides-Extra: opentelemetry
Requires-Dist: aiohttp (>=3.10.0,<4.0.0)
Requires-Dist: azure-ai-inference[opentelemetry] (>=1.0.0b6,<2.0.0)
Requires-Dist: azure-core (>=1.32.0,<2.0.0)
Requires-Dist: azure-identity (>=1.15.0,<2.0.0)
Requires-Dist: azure-monitor-opentelemetry (>=1.6.4,<2.0.0) ; extra == "opentelemetry"
Requires-Dist: langchain-core (>=0.3.0,<0.4.0)
Requires-Dist: opentelemetry-instrumentation-threading (>=0.49b2,<0.50) ; extra == "opentelemetry"
Requires-Dist: opentelemetry-semantic-conventions-ai (>=0.4.2,<0.5.0) ; extra == "opentelemetry"
Project-URL: Release Notes, https://github.com/langchain-ai/langchain-azure/releases
Project-URL: Source Code, https://github.com/langchain-ai/langchain-azure/tree/main/libs/azure-inference
Description-Content-Type: text/markdown

# langchain-azure-ai

This package contains the LangChain integration for Azure AI Foundry. To learn more about how to use this package, see the LangChain documentation in [Azure AI Foundry](https://aka.ms/azureai/langchain).

> [!NOTE]
> This package is in Public Preview. For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/support/legal/preview-supplemental-terms/).

## Installation

```bash
pip install -U langchain-azure-ai
```

For using tracing capabilities with OpenTelemetry, you need to add the extras `opentelemetry`:

```bash
pip install -U langchain-azure-ai[opentelemetry]
```

## Changelog

- **0.1.0**:

  - Introduce `AzureAIEmbeddingsModel` for embedding generation and `AzureAIChatCompletionsModel` for chat completions generation using the Azure AI Inference API. This client also supports GitHub Models endpoint.
  - Introduce `AzureAIInferenceTracer` for tracing with OpenTelemetry and Azure Application Insights.
