[!IMPORTANT] This package is now deprecated in favor of the new Azure integration in the OpenAI SDK. Please use the package @langchain/openai instead. You can find the migration guide here.

@langchain/azure-openai

This package contains the Azure SDK for OpenAI LangChain.js integrations.

It provides Azure OpenAI support through the Azure SDK for OpenAI library.

Installation

1npm install @langchain/azure-openai

This package, along with the main LangChain package, depends on @langchain/core. If you are using this package with other LangChain packages, you should make sure that all of the packages depend on the same instance of @langchain/core. You can do so by adding appropriate fields to your project's package.json like this:

1{
2  "name": "your-project",
3  "version": "0.0.0",
4  "dependencies": {
5    "@langchain/azure-openai": "^0.0.4",
6    "langchain": "0.0.207"
7  },
8  "resolutions": {
9    "@langchain/core": "0.1.5"
10  },
11  "overrides": {
12    "@langchain/core": "0.1.5"
13  },
14  "pnpm": {
15    "overrides": {
16      "@langchain/core": "0.1.5"
17    }
18  }
19}

The field you need depends on the package manager you're using, but we recommend adding a field for the common yarn, npm, and pnpm to maximize compatibility.

Chat Models

This package contains the AzureChatOpenAI class, which is the recommended way to interface with deployed models on Azure OpenAI.

To use, install the requirements, and configure your environment.

1export AZURE_OPENAI_API_ENDPOINT=<your_endpoint>
2export AZURE_OPENAI_API_KEY=<your_key>
3export AZURE_OPENAI_API_DEPLOYMENT_NAME=<your_deployment_name>

Then initialize the model and make the calls:

1import { AzureChatOpenAI } from "@langchain/azure-openai";
2
3const model = new AzureChatOpenAI({
4  // Note that the following are optional, and will default to the values below
5  // if not provided.
6  azureOpenAIEndpoint: process.env.AZURE_OPENAI_API_ENDPOINT,
7  azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
8  azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
9});
10const response = await model.invoke(new HumanMessage("Hello world!"));

Streaming

1import { AzureChatOpenAI } from "@langchain/azure-openai";
2
3const model = new AzureChatOpenAI({
4  // Note that the following are optional, and will default to the values below
5  // if not provided.
6  azureOpenAIEndpoint: process.env.AZURE_OPENAI_API_ENDPOINT,
7  azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
8  azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
9});
10const response = await model.stream(new HumanMessage("Hello world!"));

Embeddings

This package also supports embeddings with Azure OpenAI.

1import { AzureOpenAIEmbeddings } from "@langchain/azure-openai";
2
3const embeddings = new AzureOpenAIEmbeddings({
4  // Note that the following are optional, and will default to the values below
5  // if not provided.
6  azureOpenAIEndpoint: process.env.AZURE_OPENAI_API_ENDPOINT,
7  azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
8  azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME,
9});
10const res = await embeddings.embedQuery("Hello world");

Using Azure managed identity

If you're using Azure Managed Identity, you can also pass the credentials directly to the constructor:

1import { DefaultAzureCredential } from "@azure/identity";
2import { AzureOpenAI } from "@langchain/azure-openai";
3
4const credentials = new DefaultAzureCredential();
5
6const model = new AzureOpenAI({
7  credentials,
8  azureOpenAIEndpoint: process.env.AZURE_OPENAI_API_ENDPOINT,
9  azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_API_DEPLOYMENT_NAME,
10});

Compatibility with OpenAI API

This library is provides compatibility with the OpenAI API. You can use an API key from OpenAI's developer portal like in the example below:

1import { AzureOpenAI, OpenAIKeyCredential } from "@langchain/azure-openai";
2
3const model = new AzureOpenAI({
4  modelName: "gpt-3.5-turbo",
5  credentials: new OpenAIKeyCredential("<your_openai_api_key>"),
6});

Development

To develop the Azure OpenAI package, you'll need to follow these instructions:

Install dependencies

1yarn install

Build the package

1yarn build

Or from the repo root:

1yarn build --filter=@langchain/azure-openai

Run tests

Test files should live within a tests/ file in the src/ folder. Unit tests should end in .test.ts and integration tests should end in .int.test.ts:

1$ yarn test
2$ yarn test:int

Lint & Format

Run the linter & formatter to ensure your code is up to standard:

1yarn lint && yarn format

Adding new entrypoints

If you add a new file to be exported, either import & re-export from src/index.ts, or add it to scripts/create-entrypoints.js and run yarn build to generate the new entrypoint.