openai-node

Full Changelog: https://github.com/openai/openai-node/compare/v4.0.1...v4.1.0

Full Changelog: https://github.com/openai/openai-node/compare/v4.0.0...v4.0.1

Version 4 is a complete rewrite of the SDK, offering a huge set of improvements.

What's new

• Streaming support for completions and chat completions!
• Improved typescript types for responses & errors
• Support for ESM, CloudFlare Workers, Vercel edge functions, Deno, and more
• Better file upload API for Whisper, fine-tune files, & DALL·E images
• Improved error handling through automatic retries & error classes
• Improved latency through reusing TCP connections
• Simpler initialization logic

Getting started

npm install [email protected]

Migration guide

➡️ View the v3 to v4 migration guide

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

v4.0.0 Beta – Learn more

Add support for function calling in the Chat Completions API

Announcement: https://openai.com/blog/function-calling-and-other-api-updates
Documentation: https://platform.openai.com/docs/guides/gpt/function-calling

Added new ChatGPT and Whisper APIs.

Breaking changes in this release:

• The function signature of createCompletion(engineId, params) changed to createCompletion(params). The value previously passed in as the engineId argument should now be passed in as model in the params object (e.g. createCompletion({ model: "text-davinci-002, ... }))