@langchain/openai

What is @langchain/openai?

@langchain/openai is an npm package that provides tools and utilities for integrating OpenAI's language models into your applications. It allows you to easily interact with OpenAI's API, enabling functionalities such as text generation, conversation handling, and more.

What are @langchain/openai's main functionalities?

Text Generation

This feature allows you to generate text based on a given prompt using OpenAI's language models. The code sample demonstrates how to use the `generate` method to create text.

const { OpenAI } = require('@langchain/openai');

const openai = new OpenAI('your-api-key');

async function generateText(prompt) {
  const response = await openai.generate({
    model: 'text-davinci-003',
    prompt: prompt,
    max_tokens: 100
  });
  console.log(response.data.choices[0].text);
}

generateText('Once upon a time');

Conversation Handling

This feature allows you to handle conversations by sending a series of messages to OpenAI's conversational models. The code sample demonstrates how to use the `converse` method to manage a conversation.

const { OpenAI } = require('@langchain/openai');

const openai = new OpenAI('your-api-key');

async function handleConversation(messages) {
  const response = await openai.converse({
    model: 'gpt-3.5-turbo',
    messages: messages
  });
  console.log(response.data.choices[0].message.content);
}

const messages = [
  { role: 'system', content: 'You are a helpful assistant.' },
  { role: 'user', content: 'What is the weather like today?' }
];

handleConversation(messages);

Custom Fine-Tuning

This feature allows you to fine-tune OpenAI's models with custom training data. The code sample demonstrates how to use the `fineTune` method to train a model with specific data.

const { OpenAI } = require('@langchain/openai');

const openai = new OpenAI('your-api-key');

async function fineTuneModel(trainingData) {
  const response = await openai.fineTune({
    model: 'text-davinci-003',
    training_data: trainingData
  });
  console.log(response.data);
}

const trainingData = [
  { prompt: 'Translate the following English text to French: "Hello, world!"', completion: 'Bonjour, le monde!' }
];

fineTuneModel(trainingData);

Other packages similar to @langchain/openai

openai

The `openai` npm package is the official OpenAI API client for Node.js. It provides similar functionalities for interacting with OpenAI's models, including text generation, conversation handling, and more. Compared to @langchain/openai, it is the direct client provided by OpenAI and may have more up-to-date features and support.

node-openai

The `node-openai` package is a community-maintained client for OpenAI's API. It provides basic functionalities for text generation and other interactions with OpenAI's models. It may lack some of the advanced features and optimizations found in @langchain/openai.

README

@langchain/openai

This package contains the LangChain.js integrations for OpenAI through their SDK.

Installation

npm install @langchain/openai @langchain/core

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:

{
  "name": "your-project",
  "version": "0.0.0",
  "dependencies": {
    "@langchain/core": "^0.3.0",
    "@langchain/openai": "^0.0.0"
  },
  "resolutions": {
    "@langchain/core": "^0.3.0"
  },
  "overrides": {
    "@langchain/core": "^0.3.0"
  },
  "pnpm": {
    "overrides": {
      "@langchain/core": "^0.3.0"
    }
  }
}

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 ChatOpenAI class, which is the recommended way to interface with the OpenAI series of models.

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

export OPENAI_API_KEY=your-api-key

Then initialize

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  modelName: "gpt-4-1106-preview",
});
const response = await model.invoke(new HumanMessage("Hello world!"));

Streaming

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  apiKey: process.env.OPENAI_API_KEY,
  modelName: "gpt-4-1106-preview",
});
const response = await model.stream(new HumanMessage("Hello world!"));

Embeddings

This package also adds support for OpenAI's embeddings model.

import { OpenAIEmbeddings } from "@langchain/openai";

const embeddings = new OpenAIEmbeddings({
  apiKey: process.env.OPENAI_API_KEY,
});
const res = await embeddings.embedQuery("Hello world");

Development

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

Install dependencies

yarn install

Build the package

yarn build

Or from the repo root:

yarn build --filter=@langchain/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:

$ yarn test
$ yarn test:int

Lint & Format

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

yarn 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 the entrypoints field in the config variable located inside langchain.config.js and run yarn build to generate the new entrypoint.