Alex Rattray

Thank you for the feature request; we'll think this over.

The API doesn't accept a stream of `messages`; the request must be a single JSON payload. If you'd like to request that feature in the API, you may do so...

Interesting… can you share more about the motivating use-case for streaming request bodies?

Right, thank you, that makes sense. Sorry for misunderstanding at first. I'm not sure that we'll be able to do this in the short term but it does sound worthwhile.

Thanks @luisfarzati, I appreciate your willingness to do that – unfortunately, there's a very slim chance it'd be accepted at this time, since this library is generated and we'd want...

@pixelpax please raise that at https://help.openai.com/ – it's not an SDK issue.

@nilsreichardt FYI, the [upcoming v4](github.com/openai/openai-node/discussions/182) of this library has auto-retry with exponential backoff baked-in.

The API does distinguish, with a `type` field in the error response which can be `'tokens'`, `'request'`, or `'insufficient_quota'`. For example: ```ts { message: 'Rate limit reached for 10KTPM-200RPM in...

Thanks for reporting, we hope to fix this soon.

The workaround would be to pass an empty object, perhaps with an `as any` annotation