Support for response streaming

[denniszielke]

This issue is for a: (mark with an x)

- [ ] bug report -> please search issues before submitting
- [x] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)

Minimal steps to reproduce

I want response streaming which is using ServerSide Events to ensure that long running LLM prompts return quickly. https://cookbook.openai.com/examples/how_to_stream_completions

Any log messages given by the failure

Expected/desired behavior

OS and Version?

Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)

Versions

Mention any other details that might be useful

---

Thanks! We'll be in touch soon.

[andredewes]

This solution does support streaming!