diff --git a/docs/docs/integrations/providers/microsoft.mdx b/docs/docs/integrations/providers/microsoft.mdx index 518d4869d47..64ac3c61361 100644 --- a/docs/docs/integrations/providers/microsoft.mdx +++ b/docs/docs/integrations/providers/microsoft.mdx @@ -4,9 +4,15 @@ keywords: [azure] # Microsoft -All functionality related to `Microsoft Azure` and other `Microsoft` products. +All functionality related to [Microsoft Azure](https://portal.azure.com) and other [Microsoft](https://www.microsoft.com) products. -## Chat Models +## Chat Models + +Microsoft offers three main options for accessing chat models through Azure: + +1. [Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-services/openai/) - Provides access to OpenAI's powerful models like o3, 4.1, and other models through Microsoft Azure's secure enterprise platform. +2. [Azure AI](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models) - Offers access to a variety of models from different providers including Anthropic, DeepSeek, Cohere, Phi and Mistral through a unified API. +3. [Azure ML](https://learn.microsoft.com/en-us/azure/machine-learning/) - Allows deployment and management of your own custom models or fine-tuned open-source models with Azure Machine Learning. ### Azure OpenAI @@ -29,11 +35,36 @@ os.environ["AZURE_OPENAI_API_KEY"] = "your AzureOpenAI key" See a [usage example](/docs/integrations/chat/azure_chat_openai) - ```python from langchain_openai import AzureChatOpenAI ``` +### Azure AI + +>[Azure AI Foundry](https://learn.microsoft.com/en-us/azure/developer/python/get-started) provides access to a wide range of models from various providers including Azure OpenAI, DeepSeek R1, Cohere, Phi and Mistral through the `AzureAIChatCompletionsModel` class. + +```bash +pip install -U langchain-azure-ai +``` + +Configure your API key and Endpoint. + +```bash +export AZURE_INFERENCE_CREDENTIAL=your-api-key +export AZURE_INFERENCE_ENDPOINT=your-endpoint +``` + +```python +from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel + +llm = AzureAIChatCompletionsModel( + model_name="gpt-4o", + api_version="2024-05-01-preview", +) +``` + +See a [usage example](/docs/integrations/chat/azure_ai) + ### Azure ML Chat Online Endpoint See the documentation [here](/docs/integrations/chat/azureml_chat_endpoint) for accessing chat @@ -59,6 +90,9 @@ from langchain_openai import AzureOpenAI ``` ## Embedding Models + +Microsoft offers two main options for accessing embedding models through Azure: + ### Azure OpenAI See a [usage example](/docs/integrations/text_embedding/azureopenai) @@ -67,6 +101,27 @@ See a [usage example](/docs/integrations/text_embedding/azureopenai) from langchain_openai import AzureOpenAIEmbeddings ``` +### Azure AI + +```bash +pip install -U langchain-azure-ai +``` + +Configure your API key and Endpoint. + +```bash +export AZURE_INFERENCE_CREDENTIAL=your-api-key +export AZURE_INFERENCE_ENDPOINT=your-endpoint +``` + +```python +from langchain_azure_ai.embeddings import AzureAIEmbeddingsModel + +embed_model = AzureAIEmbeddingsModel( + model_name="text-embedding-ada-002" +) +``` + ## Document loaders ### Azure AI Data