Implementation:Langchain ai Langchain AzureOpenAIEmbeddings

Knowledge Sources	Langchain_ai_Langchain
Domains	Embeddings, Azure OpenAI, Cloud AI
Last Updated	2026-02-11 00:00 GMT

Overview

AzureOpenAIEmbeddings is a LangChain embeddings integration for generating text embeddings using Azure-hosted OpenAI models, extending the base OpenAIEmbeddings class with Azure-specific configuration.

Description

AzureOpenAIEmbeddings extends OpenAIEmbeddings from the langchain-openai package to provide Azure-specific configuration for embedding generation. It supports Azure endpoints, deployment names, API versioning, and multiple authentication methods including API keys, Azure Active Directory (AD) tokens, and AD token providers (both sync and async). The class creates openai.AzureOpenAI and openai.AsyncAzureOpenAI client instances with proper Azure configuration. It includes backward-compatibility validation for the transition from openai_api_base to the azure_endpoint parameter introduced in openai>=1.0.0.

Usage

Import this class when you need to generate text embeddings using Azure-hosted OpenAI models, particularly in enterprise environments that require Azure-specific authentication and endpoint configuration.

Code Reference

Source Location

• Repository: Langchain_ai_Langchain
• File: libs/partners/openai/langchain_openai/embeddings/azure.py
• Lines: 1-231

Signature

class AzureOpenAIEmbeddings(OpenAIEmbeddings):
    azure_endpoint: str | None = Field(...)
    deployment: str | None = Field(default=None, alias="azure_deployment")
    openai_api_key: SecretStr | None = Field(alias="api_key", ...)
    openai_api_version: str | None = Field(alias="api_version", ...)
    azure_ad_token: SecretStr | None = Field(...)
    azure_ad_token_provider: Callable[[], str] | None = None
    azure_ad_async_token_provider: Callable[[], Awaitable[str]] | None = None
    openai_api_type: str | None = Field(...)
    validate_base_url: bool = True
    chunk_size: int = 2048

Import

from langchain_openai import AzureOpenAIEmbeddings

I/O Contract

Inputs

Name	Type	Required	Description
azure_endpoint	None	No	Azure endpoint URL (e.g., https://example-resource.azure.openai.com/). Read from AZURE_OPENAI_ENDPOINT env var.
deployment	None	No	Azure model deployment name. Alias: azure_deployment.
openai_api_key	None	No	API key. Read from AZURE_OPENAI_API_KEY or OPENAI_API_KEY env vars.
openai_api_version	None	No	API version. Read from OPENAI_API_VERSION env var. Default: "2023-05-15".
azure_ad_token	None	No	Azure AD token. Read from AZURE_OPENAI_AD_TOKEN env var.
azure_ad_token_provider	Callable[[], str] | None	No	Function returning an Azure AD token, invoked on every sync request.
azure_ad_async_token_provider	Callable[[], Awaitable[str]] | None	No	Async function returning an Azure AD token, invoked on every async request.
openai_api_type	None	No	API type. Read from OPENAI_API_TYPE env var. Default: "azure".
validate_base_url	bool	No	Whether to validate and transform legacy base URL. Default: True.
chunk_size	int	No	Maximum number of texts to embed in each batch. Default: 2048.
model	str	No	Name of the Azure OpenAI model to use (inherited from OpenAIEmbeddings).

Outputs

Name	Type	Description
embed_documents return	list[list[float]]	List of embedding vectors (inherited from OpenAIEmbeddings).
embed_query return	list[float]	Single embedding vector (inherited from OpenAIEmbeddings).

Authentication Methods

The class supports three authentication approaches:

1. API Key -- Set via api_key parameter or AZURE_OPENAI_API_KEY environment variable.
2. Azure AD Token -- Set via azure_ad_token parameter or AZURE_OPENAI_AD_TOKEN environment variable.
3. Azure AD Token Provider -- Set via azure_ad_token_provider (sync) and/or azure_ad_async_token_provider (async) callables.

Usage Examples

Basic Usage

from langchain_openai import AzureOpenAIEmbeddings

embeddings = AzureOpenAIEmbeddings(
    model="text-embedding-3-large",
    # azure_endpoint="https://<your-endpoint>.openai.azure.com/",
    # api_key="your-api-key",
    # api_version="2024-02-01",
)

# Embed a single text
vector = embeddings.embed_query("The meaning of life is 42")
print(vector[:3])

# Embed multiple texts
vectors = embeddings.embed_documents(["Document 1...", "Document 2..."])
print(len(vectors))

Async Usage

from langchain_openai import AzureOpenAIEmbeddings

embeddings = AzureOpenAIEmbeddings(model="text-embedding-3-large")
vector = await embeddings.aembed_query("The meaning of life is 42")

Related Pages

• Requires langchain-openai and openai packages
• Extends langchain_openai.embeddings.base.OpenAIEmbeddings