<Warning>
**You are currently on a page documenting the use of OpenAI [text completion models](/oss/javascript/concepts/text_llms). The latest and most popular OpenAI models are [chat completion models](/oss/javascript/langchain/models).**


Unless you are specifically using `gpt-3.5-turbo-instruct`, you are probably looking for [this page instead](/oss/javascript/integrations/chat/openai/).
</Warning>
OpenAI is an artificial intelligence (AI) research laboratory. This will help you get started with OpenAI completion models (LLMs) using LangChain. For detailed documentation on OpenAI features and configuration options, please refer to the API reference.

​
Overview

​
Integration details

ClassPackageLocalSerializablePY supportDownloadsVersion
OpenAI@langchain/openai❌✅✅NPM - DownloadsNPM - Version

​
Setup

To access OpenAI models you’ll need to create an OpenAI account, get an API key, and install the @langchain/openai integration package.

​
Credentials

Head to platform.openai.com to sign up to OpenAI and generate an API key. Once you’ve done this set the OPENAI_API_KEY environment variable: 
export OPENAI_API_KEY="your-api-key"
If you want to get automated tracing of your model calls you can also set your LangSmith API key by uncommenting below: 
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

​
Installation

The LangChain OpenAI integration lives in the @langchain/openai package: 
import IntegrationInstallTooltip from "@mdx_components/integration_install_tooltip.mdx";
<IntegrationInstallTooltip></IntegrationInstallTooltip>

<Npm2Yarn>
  @langchain/openai @langchain/core
</Npm2Yarn>

​
Instantiation

Now we can instantiate our model object and generate chat completions: 
import { OpenAI } from "@langchain/openai"

const llm = new OpenAI({
  model: "gpt-3.5-turbo-instruct",
  temperature: 0,
  maxTokens: undefined,
  timeout: undefined,
  maxRetries: 2,
  apiKey: process.env.OPENAI_API_KEY,
  // other params...
})

​
Invocation

const inputText = "OpenAI is an AI company that "

const completion = await llm.invoke(inputText)
completion

develops and promotes friendly AI for the benefit of humanity. It was founded in 2015 by Elon Musk, Sam Altman, Greg Brockman, Ilya Sutskever, Wojciech Zaremba, John Schulman, and Chris Olah. The company's mission is to create and promote artificial general intelligence (AGI) that is safe and beneficial to humanity.

OpenAI conducts research in various areas of AI, including deep learning, reinforcement learning, robotics, and natural language processing. The company also develops and releases open-source tools and platforms for AI research, such as the GPT-3 language model and the Gym toolkit for reinforcement learning.

One of the main goals of OpenAI is to ensure that the development of AI is aligned with human values and does not pose a threat to humanity. To this end, the company has established a set of principles for safe and ethical AI development, and it actively collaborates with other organizations and researchers in the field.

OpenAI has received funding from various sources, including tech giants like Microsoft and Amazon, as well as individual investors. It has also partnered with companies and organizations such as Google, IBM, and the United Nations to advance its research and promote responsible AI development.

In addition to its research and development

​
Chaining

We can chain our completion model with a prompt template like so: 
import { PromptTemplate } from "@langchain/core/prompts"

const prompt = new PromptTemplate({
  template: "How to say {input} in {output_language}:\n",
  inputVariables: ["input", "output_language"],
})

const chain = prompt.pipe(llm);
await chain.invoke(
  {
    output_language: "German",
    input: "I love programming.",
  }
)

Ich liebe Programmieren.
If you’re part of an organization, you can set process.env.OPENAI_ORGANIZATION to your OpenAI organization id, or pass it in as organization when initializing the model.

​
Custom URLs

You can customize the base URL the SDK sends requests to by passing a configuration parameter like this: 
const llmCustomURL = new OpenAI({
  temperature: 0.9,
  configuration: {
    baseURL: "https://your_custom_url.com",
  },
});
You can also pass other ClientOptions parameters accepted by the official SDK. If you are hosting on Azure OpenAI, see the dedicated page instead.

​
API reference

For detailed documentation of all OpenAI features and configurations head to the API reference.