Never miss a release that matters
AI-powered summaries of every GitHub release.
AI Summaries
Changelogs condensed into clear, actionable insights.
Always Free
Track up to 5 packages at no cost, forever.
Weekly Digest
A curated summary of every release, delivered weekly.
TL;DR
This release expands the SDK to support Amazon Bedrock (cloud AI service) alongside OpenAI, giving you more model provider options.
New
- Support for Amazon Bedrock responses.
- Moderation data is now included with both chat and standard completions.
- Improved audit logging with workload identity.
Fixes Worth Knowing
- Resolved an issue with
text/planuploads, ensuring binary data is handled correctly. - Improved guidance for resolving issues with the underlying
undicinetworking library.
TL;DR
The latest updates add support for the new gpt-5-codex (code generation model) and improve performance with faster formatting.
New
- gpt-5-codex: Access to the new GPT-5 Codex model is now available.
Fixes Worth Knowing
- Realtime classes no longer incorrectly display a "beta" label.
- Formatting operations are now faster, improving overall response times.
TL;DR
The Node SDK now supports streaming responses in the background, improving application responsiveness when using the OpenAI API (artificial intelligence service).
Breaking
- The Assistants API is deprecated (remove usage of this feature).
New
- Streaming helpers are available for background responses, allowing for more efficient handling of large responses.
Fixes Worth Knowing
- Azure deployments now correctly support image editing endpoints.
- File content is now returned as binary data when retrieved from containers.
TL;DR
The OpenAI Node SDK is previewing version 4, introducing a new client architecture with improved flexibility and TypeScript support.
Breaking
- The client initialization has changed (requires updating your code to use the new constructor).
- Request options are now passed differently (update how you configure API calls).
TL;DR
The Node SDK now supports function calling (using GPT models to execute tools) in the Chat Completions API, enabling more dynamic and interactive applications.
New
- Function Calling: Chat Completions can now call external tools or functions based on user input, expanding the capabilities of GPT-based applications.
Before You Upgrade
Review the function calling documentation (https://platform.openai.com/docs/guides/gpt/function-calling) to understand how to define and use functions with the Chat Completions API.