@fern-api/openai v0.0.32

OpenAI Node Library

The OpenAI Node.js library provides access to the OpenAI API from JavaScript/TypeScript.

Documentation

API reference documentation is available here.

Installation

npm install @fern-api/openai

yarn add @fern-api/openai

Authentication

The OpenAI API uses API keys for authentication. Visit your API Keys page to retrieve the API key you'll use in your requests.

Remember that your API key is a secret! Do not share it with others or expose it in any client-side code (browsers, apps). Production requests must be routed through your own backend server where your API key can be securely loaded from an environment variable or key management service.

Usage

import { OpenAIClient } from '@fern-api/openai';

const client = new OpenAIClient({
  token: 'YOUR_API_KEY',
});

const response = await client.edit.create({
  model: 'text-davinci-edit-001',
  input: 'What day of the wek is it?',
  instruction: 'Fix the spelling mistakes',
});

console.log(response.choices[0].text); // "What day of the week is it?"

Specifying organization

If you belong to multiple organizations, you can specify an organization when constructing the client. Usage from these API requests will count against the specified organization's subscription quota.

const client = new OpenAIClient({
  token: 'YOUR_API_KEY',
  organization: 'org-dXiZKrWii8lND9WMvqr0UoKy',
});

Handling errors

When the API returns a non-success status code (4xx or 5xx response), a subclass of OpenAIError will be thrown:

try {
  await client.edit.create({
    model: 'text-davinci-edit-001',
    input: 'What day of the wek is it?',
    instruction: 'Fix the spelling mistakes',
  });
} catch (error) {
  if (err instanceof OpenAIError) {
    console.log(err.statusCode);
    console.log(err.body);
  }
}

Error codes are as followed:

File upload

The SDK supports uploading files using the built-in File and ReadStream classes.

import * as fs from "fs";
import { OpenAIClient } from '@fern-api/openai';

const { Configuration, OpenAIApi } = require("openai");

const client = new OpenAIClient({
  token: 'YOUR_API_KEY',
  organization: 'org-dXiZKrWii8lND9WMvqr0UoKy',
});

const response = await client.file.upload(
  fs.createReadStream("mydata.jsonl"),
  { purpose: "fine-tune" }
);

Streaming

The SDK supports streaming responses from certain endpoints:

• Create completion
• Create chat completion
• List fine tune events

To take advantage of this feature, pass stream: true with your request and a callback to handle the events.

await client.chat.createCompletion({
  model: "gpt-3.5-turbo",
  messages: [{ role: "user", content: "Who won the world series in 2015?" }],
  stream: true, // <---
}, (data) => {
  console.log("Received a new data chunk", data);
});

You can specify additional callbacks for handling errors and completion:

await client.chat.createCompletion({
  model: "gpt-3.5-turbo",
  messages: [{ role: "user", content: "Who won the world series in 2015?" }],
  stream: true,
}, (data) => {
  console.log("Received a new data chunk", data);
}, {
  onError: (error) => {
    console.log("Received error", error);
  },
  onFinish: () => {
    console.log("Finished!");
  },
});

Beta status

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning the package version to a specific version in your package.json file. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

On the other hand, contributions to the README are always very welcome!