Thanks for the nudge—you’re right! I’m in the process of updating the code with the latest from the Assistants API. Excited to get this out soon!
@romainhuet
-
New Assistants API Sample App with Next.js Released
By
–
Introducing a new sample app to help you get started with the Assistants API and @nextjs
! Great work by @ilanbigio and @karoliskosas
. Let us know what you need next—we can’t wait to see what you build! https://
github.com/openai/openai-
assistants-quickstart
… -
OpenAI Batch API Now Supports Embeddings and Vision Features
By
–
Another day, another ship! 🚢
— Romain Huet (@romainhuet) 30 avril 2024
The Batch API now supports a top-requested feature: batch embeddings! We’ve also added support for vision, increased rate limits, and made it easy to create batches directly from the dashboard. Don’t miss our new guide: https://t.co/bB2yOaarrN https://t.co/mTRbYLX1VRAnother day, another ship! The Batch API now supports a top-requested feature: batch embeddings! We’ve also added support for vision, increased rate limits, and made it easy to create batches directly from the dashboard. Don’t miss our new guide: https://
platform.openai.com/docs/guides/ba
tch
… -
Romain Huet Praises Stripe Sessions and Speaks on DX and AI
By
–
Congrats to the @Stripe team on a fantastic Sessions! The craftsmanship and attention to detail each year is always impressive, and seeing all the familiar faces made it feel just like coming home. Thanks for inviting me back to speak about DX and AI!
-
New Function Calling Behavior for Structured Responses
By
–
Addressing a common developer request, we’ve introduced a new function calling behavior to ensure the model always calls one of your specified functions—ideal for structured responses and agentic use cases.
-
Assistants API Updates: Expanded File Support and Better Control
By
–
Launching a series of updates to the Assistants API—now with support for up to 10,000 files for knowledge retrieval and more precise tool and token control. Excited to see what you build!
-
Batch API Launched: Lower Costs and Higher Rate Limits for Async Tasks
By
–
Developers managing large async AI tasks, this is for you! Our new Batch API is here to reduce costs and increase your rate limits:
-
Improving developer experience through better error messages
By
–
Building a delightful developer experience is all about the details, including error messages. Excited for us to make them even more helpful!
-
GPT-4 Turbo Vision et Whisper timestamps pour synchronisation multimodale
By
–
Thanks for sharing! We just launched GPT-4 Turbo with Vision, and we recently added word-level timestamps in Whisper for precise text-audio synchronization. We’re excited about multi-modality, and we’d love to hear if this fits your use case!
-
Cursor AI améliore le raisonnement avec GPT-4 Turbo
By
–
The awesome team at @cursor_ai shows improved reasoning on complex coding tasks with the new GPT-4 Turbo model: